Julia Ellbrant
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Julia Ellbrant has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Lisa Rydén
Lund University
10 shared publications - Pär-Ola Bendahl
Lund University
8 shared publications - Looket Dihge
Department of Clinical Sciences, Division of Surgery, Lund University, Lund, Sweden
7 shared publications - Mattias Ohlsson
Lund University 6 Department of Earth and Environmental Sciences Lund, Sweden
7 shared publications - Ida Skarping
Department of Clinical Physiology and Nuclear Medicine, Skåne University Hospital, Lund, Sweden
6 shared publications - Malin Hjärtström
Department of Clinical Sciences Lund, Anesthesiology and Intensive Care, Lund University, Lund, Sweden
4 shared publications
Latest Publications
- Open Access
- 22 June 2026
- Published by Springer Nature in Research Square
Residual cancer cells in re-excision after breast-conserving surgery: association to invasive lobular carcinoma and locoregional recurrence (ISRCTN12077301)
Background Invasive lobular carcinoma (ILC) is a risk factor for positive margins after breast-conserving surgery (BCS). This retrospective observational study examined whether the presence of residual cancer cells in re-excision is associated with ILC or locoregional recurrence. Methods Patients (aged > 18 years) who underwent BCS for invasive or in situ cancer at two sites (2015–2017) were included. Data were retrieved from medical records and the Swedish National Breast Cancer Register. The primary endpoint was residual cancer cells in first re-excision, and secondary endpoints were locoregional recurrence-free interval (LRFi), distant recurrence-free interval, and breast cancer-specific survival. Results In total, 770 patients were included, of whom 132 (17.1%) had positive margins; 130/132 underwent re-excision, and residual cancer cells were detected in 80 (61.5%). Residual cancer cells were weakly and not significantly associated with histological subtype (ILC versus invasive carcinoma of no special type (NST)), but associated with number of positive margins, mammographic lesion size, and pathological extent (all P < 0.05). After a median follow-up time of 7.0 years, locoregional recurrence was diagnosed in 34/721 patients (4.7%). There was no evidence of a difference in LRFi by margin status, residual cancer cells, or histological subtype (all P > 0.4). Molecular subtypes and adjuvant therapies were associated with the risk of locoregional recurrence. Conclusion The presence of residual cancer cells in the first re-excision is not associated with locoregional recurrence risk and only weakly associated with ILC. Number of margins involved and lesion size are predictive of residual cancer cells and might support surgical decision-making at re-excision.
- 22 June 2026
- Published by Springer Nature in Research Square
Open AccessResidual cancer cells in re-excision after breast-conserving surgery: association to invasive lobular carcinoma and locoregional recurrence (ISRCTN12077301)
Background Invasive lobular carcinoma (ILC) is a risk factor for positive margins after breast-conserving surgery (BCS). This retrospective observational study examined whether the presence of residual cancer cells in re-excision is associated with ILC or locoregional recurrence. Methods Patients (aged > 18 years) who underwent BCS for invasive or in situ cancer at two sites (2015–2017) were included. Data were retrieved from medical records and the Swedish National Breast Cancer Register. The primary endpoint was residual cancer cells in first re-excision, and secondary endpoints were locoregional recurrence-free interval (LRFi), distant recurrence-free interval, and breast cancer-specific survival. Results In total, 770 patients were included, of whom 132 (17.1%) had positive margins; 130/132 underwent re-excision, and residual cancer cells were detected in 80 (61.5%). Residual cancer cells were weakly and not significantly associated with histological subtype (ILC versus invasive carcinoma of no special type (NST)), but associated with number of positive margins, mammographic lesion size, and pathological extent (all P < 0.05). After a median follow-up time of 7.0 years, locoregional recurrence was diagnosed in 34/721 patients (4.7%). There was no evidence of a difference in LRFi by margin status, residual cancer cells, or histological subtype (all P > 0.4). Molecular subtypes and adjuvant therapies were associated with the risk of locoregional recurrence. Conclusion The presence of residual cancer cells in the first re-excision is not associated with locoregional recurrence risk and only weakly associated with ILC. Number of margins involved and lesion size are predictive of residual cancer cells and might support surgical decision-making at re-excision.
- Open Access
- 6 January 2025
- Published by Springer Nature in Research Square
Enhancing the Prediction of Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Routine Full-Breast Mammograms
Background: With a trend toward de-escalation of axillary surgery in breast cancer, prediction models incorporating imaging modalities can help reassess the need for surgical axillary staging. Although mammography is routinely performed for breast cancer imaging, its potential in nodal staging remains underutilized. This study aims to employ advancements in deep learning (DL) to comprehensively evaluate the potential of routine mammograms for predicting lymph node metastasis (LNM) in preoperative clinical settings. Methods: This retrospective study included 1,265 cN0 T1-T2 breast cancer patients, comprising 368 node-positive and 897 node-negative cases, diagnosed from 2009-2017 at three Swedish institutions. Patients diagnosed in 2017 were assigned to the independent test set (n=123, site 2) and the external test set (n=103, site 3), while the remaining patients (n=1,039, site 1 and 2) were used for model development and double cross-validation. A neck module, in conjunction with a ResNet backbone pretrained on unlabeled mammograms, was developed to extract global information from full-breast or region-of-interest (ROI) mammograms by predicting five cancer outcomes. Clinicopathological characteristics were combined with the learned mammogram features to predict LNM collaboratively. The models were evaluated using area under the receiver operating characteristic (ROC) curve (AUC), calibration, and decision curve analysis. Results: Compared to models using only clinical variables, incorporating full-breast mammograms with preoperative clinical variables improved the ROC AUC from 0.690 ± 0.063 (SD) to 0.774 ± 0.057 in the independent test set and from 0.584 ± 0.068 to 0.637 ± 0.063 in the external test set. The combined model showed good calibration and, at sensitivity ≥ 90%, achieved a better net benefit, and a higher sentinel lymph node biopsy reduction rate of 41.7% in the independent test set. Full-breast mammograms showed comparable ability to tumor ROIs in predicting LNM. Conclusion: Our findings underscore that routine mammograms, particularly full-breast images, can enhance preoperative nodal status prediction. They may substitute key postoperative predictors such as pathological tumor size and multifocality, aiding patient stratification before surgery. Interestingly, the added predictive value of mammography was consistent across all sites, whereas the overall performance varied over time periods and sites, likely due to advancements in equipment and procedures.
- 6 January 2025
- Published by Springer Nature in Research Square
Open AccessEnhancing the Prediction of Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Routine Full-Breast Mammograms
Background: With a trend toward de-escalation of axillary surgery in breast cancer, prediction models incorporating imaging modalities can help reassess the need for surgical axillary staging. Although mammography is routinely performed for breast cancer imaging, its potential in nodal staging remains underutilized. This study aims to employ advancements in deep learning (DL) to comprehensively evaluate the potential of routine mammograms for predicting lymph node metastasis (LNM) in preoperative clinical settings. Methods: This retrospective study included 1,265 cN0 T1-T2 breast cancer patients, comprising 368 node-positive and 897 node-negative cases, diagnosed from 2009-2017 at three Swedish institutions. Patients diagnosed in 2017 were assigned to the independent test set (n=123, site 2) and the external test set (n=103, site 3), while the remaining patients (n=1,039, site 1 and 2) were used for model development and double cross-validation. A neck module, in conjunction with a ResNet backbone pretrained on unlabeled mammograms, was developed to extract global information from full-breast or region-of-interest (ROI) mammograms by predicting five cancer outcomes. Clinicopathological characteristics were combined with the learned mammogram features to predict LNM collaboratively. The models were evaluated using area under the receiver operating characteristic (ROC) curve (AUC), calibration, and decision curve analysis. Results: Compared to models using only clinical variables, incorporating full-breast mammograms with preoperative clinical variables improved the ROC AUC from 0.690 ± 0.063 (SD) to 0.774 ± 0.057 in the independent test set and from 0.584 ± 0.068 to 0.637 ± 0.063 in the external test set. The combined model showed good calibration and, at sensitivity ≥ 90%, achieved a better net benefit, and a higher sentinel lymph node biopsy reduction rate of 41.7% in the independent test set. Full-breast mammograms showed comparable ability to tumor ROIs in predicting LNM. Conclusion: Our findings underscore that routine mammograms, particularly full-breast images, can enhance preoperative nodal status prediction. They may substitute key postoperative predictors such as pathological tumor size and multifocality, aiding patient stratification before surgery. Interestingly, the added predictive value of mammography was consistent across all sites, whereas the overall performance varied over time periods and sites, likely due to advancements in equipment and procedures.
- Open Access
- 4 September 2024
- Published by Springer Nature
Lobular breast cancer and breast-conserving surgery – risk of reoperations, residual cancer cells and local recurrence
- 4 September 2024
- Published by Springer Nature
Open AccessLobular breast cancer and breast-conserving surgery – risk of reoperations, residual cancer cells and local recurrence
- Open Access
- 8 May 2024
- Published by Oxford University Press (OUP) in BJS Open
- Vol. 8 (3)
Health-related quality of life by type of breast surgery in women with primary breast cancer: prospective longitudinal cohort study
Health-related quality of life and patient-related outcome measures for patients with cancer have gained increased interest over the last decade. However, few prospective studies with longitudinal data evaluated health-related quality of life in patients with breast cancer. This study aimed to investigate how health-related quality of life changed from the time of diagnosis to 1 year after breast cancer surgery for the main surgical techniques. This prospective longitudinal single-centre study included patients with primary breast cancer diagnosed in 2019–2020 who underwent surgery. Patients completed a health-related quality of life questionnaire (Breast-Q) at baseline. One year after surgery, they completed the Breast-Q a second time, the EORTC (European Organization for Research and Treatment of Cancer) quality of life questionnaire-C30 and the quality of life questionnaire-BR23. Analysis of variance and Kruskal–Wallis tests were used to evaluate the differences in health-related quality of life between surgical groups. Analysis of covariance with robust standard errors was used to adjust for confounders. In total, 340 patients were included in the study; 160 patients received oncoplastic partial mastectomy, 112 received partial mastectomy, 42 received mastectomy and 26 had mastectomy with immediate reconstruction. Patients that had partial mastectomy or oncoplastic partial mastectomy were more satisfied with their breasts (P < 0.001), had a better body image (P = 0.006) and higher sexual functioning scores (P = 0.027) than patients who had a mastectomy with/without reconstruction. The oncoplastic and mastectomy with reconstruction groups had more breast symptoms than other groups (P < 0.001), and the mastectomy group had the least symptoms from the chest area. Partial mastectomy and oncoplastic partial mastectomy have the best outcomes in terms of breast satisfaction, body image and sexual functioning. This highlights the importance of preserving the breast when feasible and underscores that breast reconstruction is not equal to breast conservation. Registration number: NCT04227613 (http://www.clinicaltrials.gov).
- 8 May 2024
- Published by Oxford University Press (OUP) in BJS Open
- Vol. 8 (3)
Open AccessHealth-related quality of life by type of breast surgery in women with primary breast cancer: prospective longitudinal cohort study
Health-related quality of life and patient-related outcome measures for patients with cancer have gained increased interest over the last decade. However, few prospective studies with longitudinal data evaluated health-related quality of life in patients with breast cancer. This study aimed to investigate how health-related quality of life changed from the time of diagnosis to 1 year after breast cancer surgery for the main surgical techniques. This prospective longitudinal single-centre study included patients with primary breast cancer diagnosed in 2019–2020 who underwent surgery. Patients completed a health-related quality of life questionnaire (Breast-Q) at baseline. One year after surgery, they completed the Breast-Q a second time, the EORTC (European Organization for Research and Treatment of Cancer) quality of life questionnaire-C30 and the quality of life questionnaire-BR23. Analysis of variance and Kruskal–Wallis tests were used to evaluate the differences in health-related quality of life between surgical groups. Analysis of covariance with robust standard errors was used to adjust for confounders. In total, 340 patients were included in the study; 160 patients received oncoplastic partial mastectomy, 112 received partial mastectomy, 42 received mastectomy and 26 had mastectomy with immediate reconstruction. Patients that had partial mastectomy or oncoplastic partial mastectomy were more satisfied with their breasts (P < 0.001), had a better body image (P = 0.006) and higher sexual functioning scores (P = 0.027) than patients who had a mastectomy with/without reconstruction. The oncoplastic and mastectomy with reconstruction groups had more breast symptoms than other groups (P < 0.001), and the mastectomy group had the least symptoms from the chest area. Partial mastectomy and oncoplastic partial mastectomy have the best outcomes in terms of breast satisfaction, body image and sexual functioning. This highlights the importance of preserving the breast when feasible and underscores that breast reconstruction is not equal to breast conservation. Registration number: NCT04227613 (http://www.clinicaltrials.gov).
- Open Access
- 16 January 2024
- Published by Springer Nature in BMC Cancer
- Vol. 24 (1) , 1-14
Retrospective validation study of an artificial neural network-based preoperative decision-support tool for noninvasive lymph node staging (NILS) in women with primary breast cancer (ISRCTN14341750)
Background: Surgical sentinel lymph node biopsy (SLNB) is routinely used to reliably stage axillary lymph nodes in early breast cancer (BC). However, SLNB may be associated with postoperative arm morbidities. For most patients with BC undergoing SLNB, the findings are benign, and the procedure is currently questioned. A decision-support tool for the prediction of benign sentinel lymph nodes based on preoperatively available data has been developed using artificial neural network modelling. Methods: This was a retrospective geographical and temporal validation study of the noninvasive lymph node staging (NILS) model, based on preoperatively available data from 586 women consecutively diagnosed with primary BC at two sites. Ten preoperative clinicopathological characteristics from each patient were entered into the web-based calculator, and the probability of benign lymph nodes was predicted. The performance of the NILS model was assessed in terms of discrimination with the area under the receiver operating characteristic curve (AUC) and calibration, that is, comparison of the observed and predicted event rates of benign axillary nodal status (N0) using calibration slope and intercept. The primary endpoint was axillary nodal status (discrimination, benign [N0] vs. metastatic axillary nodal status [N+]) determined by the NILS model compared to nodal status by definitive pathology. Results: The mean age of the women in the cohort was 65 years, and most of them (93%) had luminal cancers. Approximately three-fourths of the patients had no metastases in SLNB (N0 74% and 73%, respectively). The AUC for the predicted probabilities for the whole cohort was 0.6741 (95% confidence interval: 0.6255–0.7227). More than one in four patients (n = 151, 26%) were identified as candidates for SLNB omission when applying the predefined cut-off for lymph node-negative status from the development cohort. The NILS model showed the best calibration in patients with a predicted high probability of healthy axilla. Conclusion: The performance of the NILS model was satisfactory. In approximately every fourth patient, SLNB could potentially be omitted. Considering the shift from postoperatively to preoperatively available predictors in this validation study, we have demonstrated the robustness of the NILS model. The clinical usability of the web interface will be evaluated before its clinical implementation. Trial registration: Registered in the ISRCTN registry with study ID ISRCTN14341750. Date of registration 23/11/2018.
- 16 January 2024
- Published by Springer Nature in BMC Cancer
- Vol. 24 (1) , 1-14
Open AccessRetrospective validation study of an artificial neural network-based preoperative decision-support tool for noninvasive lymph node staging (NILS) in women with primary breast cancer (ISRCTN14341750)
Background: Surgical sentinel lymph node biopsy (SLNB) is routinely used to reliably stage axillary lymph nodes in early breast cancer (BC). However, SLNB may be associated with postoperative arm morbidities. For most patients with BC undergoing SLNB, the findings are benign, and the procedure is currently questioned. A decision-support tool for the prediction of benign sentinel lymph nodes based on preoperatively available data has been developed using artificial neural network modelling. Methods: This was a retrospective geographical and temporal validation study of the noninvasive lymph node staging (NILS) model, based on preoperatively available data from 586 women consecutively diagnosed with primary BC at two sites. Ten preoperative clinicopathological characteristics from each patient were entered into the web-based calculator, and the probability of benign lymph nodes was predicted. The performance of the NILS model was assessed in terms of discrimination with the area under the receiver operating characteristic curve (AUC) and calibration, that is, comparison of the observed and predicted event rates of benign axillary nodal status (N0) using calibration slope and intercept. The primary endpoint was axillary nodal status (discrimination, benign [N0] vs. metastatic axillary nodal status [N+]) determined by the NILS model compared to nodal status by definitive pathology. Results: The mean age of the women in the cohort was 65 years, and most of them (93%) had luminal cancers. Approximately three-fourths of the patients had no metastases in SLNB (N0 74% and 73%, respectively). The AUC for the predicted probabilities for the whole cohort was 0.6741 (95% confidence interval: 0.6255–0.7227). More than one in four patients (n = 151, 26%) were identified as candidates for SLNB omission when applying the predefined cut-off for lymph node-negative status from the development cohort. The NILS model showed the best calibration in patients with a predicted high probability of healthy axilla. Conclusion: The performance of the NILS model was satisfactory. In approximately every fourth patient, SLNB could potentially be omitted. Considering the shift from postoperatively to preoperatively available predictors in this validation study, we have demonstrated the robustness of the NILS model. The clinical usability of the web interface will be evaluated before its clinical implementation. Trial registration: Registered in the ISRCTN registry with study ID ISRCTN14341750. Date of registration 23/11/2018.
- Open Access
- 20 November 2023
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 9 (1) , e46474
Noninvasive Staging of Lymph Node Status in Breast Cancer Using Machine Learning: External Validation and Further Model Development
Background: Most patients diagnosed with breast cancer present with a node-negative disease. Sentinel lymph node biopsy (SLNB) is routinely used for axillary staging, leaving patients with healthy axillary lymph nodes without therapeutic effects but at risk of morbidities from the intervention. Numerous studies have developed nodal status prediction models for noninvasive axillary staging using postoperative data or imaging features that are not part of the diagnostic workup. Lymphovascular invasion (LVI) is a top-ranked predictor of nodal metastasis; however, its preoperative assessment is challenging. Objective: This paper aimed to externally validate a multilayer perceptron (MLP) model for noninvasive lymph node staging (NILS) in a large population-based cohort (n=18,633) and develop a new MLP in the same cohort. Data were extracted from the Swedish National Quality Register for Breast Cancer (NKBC, 2014-2017), comprising only routinely and preoperatively available documented clinicopathological variables. A secondary aim was to develop and validate an LVI MLP for imputation of missing LVI status to increase the preoperative feasibility of the original NILS model. Methods: Three nonoverlapping cohorts were used for model development and validation. A total of 4 MLPs for nodal status and 1 LVI MLP were developed using 11 to 12 routinely available predictors. Three nodal status models were used to account for the different availabilities of LVI status in the cohorts and external validation in NKBC. The fourth nodal status model was developed for 80% (14,906/18,663) of NKBC cases and validated in the remaining 20% (3727/18,663). Three alternatives for imputation of LVI status were compared. The discriminatory capacity was evaluated using the validation area under the receiver operating characteristics curve (AUC) in 3 of the nodal status models. The clinical feasibility of the models was evaluated using calibration and decision curve analyses. Results: External validation of the original NILS model was performed in NKBC (AUC 0.699, 95% CI 0.690-0.708) with good calibration and the potential of sparing 16% of patients with node-negative disease from SLNB. The LVI model was externally validated (AUC 0.747, 95% CI 0.694-0.799) with good calibration but did not improve the discriminatory performance of the nodal status models. A new nodal status model was developed in NKBC without information on LVI (AUC 0.709, 95% CI: 0.688-0.729), with excellent calibration in the holdout internal validation cohort, resulting in the potential omission of 24% of patients from unnecessary SLNBs. Conclusions: The NILS model was externally validated in NKBC, where the imputation of LVI status did not improve the model’s discriminatory performance. A new nodal status model demonstrated the feasibility of using register data comprising only the variables available in the preoperative setting for NILS using machine learning. Future steps include ongoing preoperative validation of the NILS model and extending the model with, for example, mammography images.
- 20 November 2023
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 9 (1) , e46474
Open AccessNoninvasive Staging of Lymph Node Status in Breast Cancer Using Machine Learning: External Validation and Further Model Development
Background: Most patients diagnosed with breast cancer present with a node-negative disease. Sentinel lymph node biopsy (SLNB) is routinely used for axillary staging, leaving patients with healthy axillary lymph nodes without therapeutic effects but at risk of morbidities from the intervention. Numerous studies have developed nodal status prediction models for noninvasive axillary staging using postoperative data or imaging features that are not part of the diagnostic workup. Lymphovascular invasion (LVI) is a top-ranked predictor of nodal metastasis; however, its preoperative assessment is challenging. Objective: This paper aimed to externally validate a multilayer perceptron (MLP) model for noninvasive lymph node staging (NILS) in a large population-based cohort (n=18,633) and develop a new MLP in the same cohort. Data were extracted from the Swedish National Quality Register for Breast Cancer (NKBC, 2014-2017), comprising only routinely and preoperatively available documented clinicopathological variables. A secondary aim was to develop and validate an LVI MLP for imputation of missing LVI status to increase the preoperative feasibility of the original NILS model. Methods: Three nonoverlapping cohorts were used for model development and validation. A total of 4 MLPs for nodal status and 1 LVI MLP were developed using 11 to 12 routinely available predictors. Three nodal status models were used to account for the different availabilities of LVI status in the cohorts and external validation in NKBC. The fourth nodal status model was developed for 80% (14,906/18,663) of NKBC cases and validated in the remaining 20% (3727/18,663). Three alternatives for imputation of LVI status were compared. The discriminatory capacity was evaluated using the validation area under the receiver operating characteristics curve (AUC) in 3 of the nodal status models. The clinical feasibility of the models was evaluated using calibration and decision curve analyses. Results: External validation of the original NILS model was performed in NKBC (AUC 0.699, 95% CI 0.690-0.708) with good calibration and the potential of sparing 16% of patients with node-negative disease from SLNB. The LVI model was externally validated (AUC 0.747, 95% CI 0.694-0.799) with good calibration but did not improve the discriminatory performance of the nodal status models. A new nodal status model was developed in NKBC without information on LVI (AUC 0.709, 95% CI: 0.688-0.729), with excellent calibration in the holdout internal validation cohort, resulting in the potential omission of 24% of patients from unnecessary SLNBs. Conclusions: The NILS model was externally validated in NKBC, where the imputation of LVI status did not improve the model’s discriminatory performance. A new nodal status model demonstrated the feasibility of using register data comprising only the variables available in the preoperative setting for NILS using machine learning. Future steps include ongoing preoperative validation of the NILS model and extending the model with, for example, mammography images.
- Open Access
- 15 February 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Noninvasive Staging of Lymph Node Status in Breast Cancer Using Machine Learning: External Validation and Further Model Development (Preprint)
BACKGROUND Most patients diagnosed with breast cancer present with a node-negative disease. Sentinel lymph node biopsy (SLNB) is routinely used for axillary staging, leaving patients with healthy axillary lymph nodes without therapeutic effects but at risk of morbidities from the intervention. Numerous studies have developed nodal status prediction models for noninvasive axillary staging using postoperative data or imaging features that are not part of the diagnostic workup. Lymphovascular invasion (LVI) is a top-ranked predictor of nodal metastasis; however, its preoperative assessment is challenging. OBJECTIVE This paper aimed to externally validate a multilayer perceptron (MLP) model for noninvasive lymph node staging (NILS) in a large population-based cohort (n=18,633) and develop a new MLP in the same cohort. Data were extracted from the Swedish National Quality Register for Breast Cancer (NKBC, 2014-2017), comprising only routinely and preoperatively available documented clinicopathological variables. A secondary aim was to develop and validate an LVI MLP for imputation of missing LVI status to increase the preoperative feasibility of the original NILS model. METHODS Three nonoverlapping cohorts were used for model development and validation. A total of 4 MLPs for nodal status and 1 LVI MLP were developed using 11 to 12 routinely available predictors. Three nodal status models were used to account for the different availabilities of LVI status in the cohorts and external validation in NKBC. The fourth nodal status model was developed for 80% (14,906/18,663) of NKBC cases and validated in the remaining 20% (3727/18,663). Three alternatives for imputation of LVI status were compared. The discriminatory capacity was evaluated using the validation area under the receiver operating characteristics curve (AUC) in 3 of the nodal status models. The clinical feasibility of the models was evaluated using calibration and decision curve analyses. RESULTS External validation of the original NILS model was performed in NKBC (AUC 0.699, 95% CI 0.690-0.708) with good calibration and the potential of sparing 16% of patients with node-negative disease from SLNB. The LVI model was externally validated (AUC 0.747, 95% CI 0.694-0.799) with good calibration but did not improve the discriminatory performance of the nodal status models. A new nodal status model was developed in NKBC without information on LVI (AUC 0.709, 95% CI: 0.688-0.729), with excellent calibration in the holdout internal validation cohort, resulting in the potential omission of 24% of patients from unnecessary SLNBs. CONCLUSIONS The NILS model was externally validated in NKBC, where the imputation of LVI status did not improve the model’s discriminatory performance. A new nodal status model demonstrated the feasibility of using register data comprising only the variables available in the preoperative setting for NILS using machine learning. Future steps include ongoing preoperative validation of the NILS model and extending the model with, for example, mammography images.
- 15 February 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessNoninvasive Staging of Lymph Node Status in Breast Cancer Using Machine Learning: External Validation and Further Model Development (Preprint)
BACKGROUND Most patients diagnosed with breast cancer present with a node-negative disease. Sentinel lymph node biopsy (SLNB) is routinely used for axillary staging, leaving patients with healthy axillary lymph nodes without therapeutic effects but at risk of morbidities from the intervention. Numerous studies have developed nodal status prediction models for noninvasive axillary staging using postoperative data or imaging features that are not part of the diagnostic workup. Lymphovascular invasion (LVI) is a top-ranked predictor of nodal metastasis; however, its preoperative assessment is challenging. OBJECTIVE This paper aimed to externally validate a multilayer perceptron (MLP) model for noninvasive lymph node staging (NILS) in a large population-based cohort (n=18,633) and develop a new MLP in the same cohort. Data were extracted from the Swedish National Quality Register for Breast Cancer (NKBC, 2014-2017), comprising only routinely and preoperatively available documented clinicopathological variables. A secondary aim was to develop and validate an LVI MLP for imputation of missing LVI status to increase the preoperative feasibility of the original NILS model. METHODS Three nonoverlapping cohorts were used for model development and validation. A total of 4 MLPs for nodal status and 1 LVI MLP were developed using 11 to 12 routinely available predictors. Three nodal status models were used to account for the different availabilities of LVI status in the cohorts and external validation in NKBC. The fourth nodal status model was developed for 80% (14,906/18,663) of NKBC cases and validated in the remaining 20% (3727/18,663). Three alternatives for imputation of LVI status were compared. The discriminatory capacity was evaluated using the validation area under the receiver operating characteristics curve (AUC) in 3 of the nodal status models. The clinical feasibility of the models was evaluated using calibration and decision curve analyses. RESULTS External validation of the original NILS model was performed in NKBC (AUC 0.699, 95% CI 0.690-0.708) with good calibration and the potential of sparing 16% of patients with node-negative disease from SLNB. The LVI model was externally validated (AUC 0.747, 95% CI 0.694-0.799) with good calibration but did not improve the discriminatory performance of the nodal status models. A new nodal status model was developed in NKBC without information on LVI (AUC 0.709, 95% CI: 0.688-0.729), with excellent calibration in the holdout internal validation cohort, resulting in the potential omission of 24% of patients from unnecessary SLNBs. CONCLUSIONS The NILS model was externally validated in NKBC, where the imputation of LVI status did not improve the model’s discriminatory performance. A new nodal status model demonstrated the feasibility of using register data comprising only the variables available in the preoperative setting for NILS using machine learning. Future steps include ongoing preoperative validation of the NILS model and extending the model with, for example, mammography images.
- Open Access
- 14 February 2023
- Published by Cold Spring Harbor Laboratory in medRxiv
Noninvasive Staging of Lymph Node Status (NILS) in Breast Cancer using Machine Learning: External Validation and Further Model Development
Background Most patients diagnosed with breast cancer present with node-negative disease. Sentinel lymph node biopsy (SLNB) is routinely used to stage the axilla, leaving patients with healthy axillary lymph nodes without therapeutic effects but at risk of morbidities from the intervention. Numerous studies have developed nodal (N) status prediction models for noninvasive axillary staging using postoperative data or imaging features that are not part of the diagnostic workup. Lymphovascular invasion (LVI) is a top-ranked predictor of N metastasis; however, it is challenging to assess preoperatively. Objective To externally validate a multilayer perceptron (MLP) model for noninvasive lymph node staging (NILS) in a large population-based register cohort (n=18 633) while developing a new N MLP in the same cohort. Data were extracted from the Swedish National Quality Register for Breast Cancer (NKBC), 2014–2017, comprising only routinely and preoperatively available documented clinicopathological variables. Furthermore, we aimed to develop and validate an LVI MLP to predict missing values of LVI status to increase the preoperative feasibility of the original NILS model. Methods Three non-overlapping cohorts were used for model development and validation. Four N MLPs and one LVI MLP were developed using 11–12 routinely available predictors. Three N models were used to account for the different availabilities of LVI status in the cohorts and external validation in NKBC. The fourth N model was developed for 80% of NKBC cases (n=14 906) and validated in the remaining 20% (n=3727). Three alternatives for imputing missing values of the LVI status were compared using the LVI model. The discriminatory capacity was evaluated by validation area under the receiver operating characteristics curve (AUC) in three of the N models. The clinical feasibility of the models was evaluated using calibration and decision curve analyses. Results External validation of the original NILS model was performed in NKBC (AUC 0.699, 95% CI: 0.690-0.708) with good calibration and the potential of sparing 16% of patients with node-negative disease from SLNB. The LVI model was externally validated (AUC 0.747, 95% CI: 0.694-0.799) with good calibration but did not improve the discriminatory performance of the N models. The new N model was developed in NKBC without information on LVI (AUC 0.709, 95% CI: 0.688-0.729) with excellent calibration in the hold-out internal validation cohort, resulting in the potential omission of 24% of patients from unnecessary SLNB. Conclusions The NILS model was externally validated in NKBC, where the imputation of LVI status did not improve the model’s discriminatory performance. A new N model demonstrated the feasibility of using register data comprising only the variables available in the preoperative setting for NILS using machine learning. Future steps include ongoing preoperative validation of the NILS model and extending the model with, for example, mammography images. Trial Registration Registered in the ISRCTN registry with study ID ISRCTN14341750. Date of registration 23/11/2018.
- 14 February 2023
- Published by Cold Spring Harbor Laboratory in medRxiv
Open AccessNoninvasive Staging of Lymph Node Status (NILS) in Breast Cancer using Machine Learning: External Validation and Further Model Development
Background Most patients diagnosed with breast cancer present with node-negative disease. Sentinel lymph node biopsy (SLNB) is routinely used to stage the axilla, leaving patients with healthy axillary lymph nodes without therapeutic effects but at risk of morbidities from the intervention. Numerous studies have developed nodal (N) status prediction models for noninvasive axillary staging using postoperative data or imaging features that are not part of the diagnostic workup. Lymphovascular invasion (LVI) is a top-ranked predictor of N metastasis; however, it is challenging to assess preoperatively. Objective To externally validate a multilayer perceptron (MLP) model for noninvasive lymph node staging (NILS) in a large population-based register cohort (n=18 633) while developing a new N MLP in the same cohort. Data were extracted from the Swedish National Quality Register for Breast Cancer (NKBC), 2014–2017, comprising only routinely and preoperatively available documented clinicopathological variables. Furthermore, we aimed to develop and validate an LVI MLP to predict missing values of LVI status to increase the preoperative feasibility of the original NILS model. Methods Three non-overlapping cohorts were used for model development and validation. Four N MLPs and one LVI MLP were developed using 11–12 routinely available predictors. Three N models were used to account for the different availabilities of LVI status in the cohorts and external validation in NKBC. The fourth N model was developed for 80% of NKBC cases (n=14 906) and validated in the remaining 20% (n=3727). Three alternatives for imputing missing values of the LVI status were compared using the LVI model. The discriminatory capacity was evaluated by validation area under the receiver operating characteristics curve (AUC) in three of the N models. The clinical feasibility of the models was evaluated using calibration and decision curve analyses. Results External validation of the original NILS model was performed in NKBC (AUC 0.699, 95% CI: 0.690-0.708) with good calibration and the potential of sparing 16% of patients with node-negative disease from SLNB. The LVI model was externally validated (AUC 0.747, 95% CI: 0.694-0.799) with good calibration but did not improve the discriminatory performance of the N models. The new N model was developed in NKBC without information on LVI (AUC 0.709, 95% CI: 0.688-0.729) with excellent calibration in the hold-out internal validation cohort, resulting in the potential omission of 24% of patients from unnecessary SLNB. Conclusions The NILS model was externally validated in NKBC, where the imputation of LVI status did not improve the model’s discriminatory performance. A new N model demonstrated the feasibility of using register data comprising only the variables available in the preoperative setting for NILS using machine learning. Future steps include ongoing preoperative validation of the NILS model and extending the model with, for example, mammography images. Trial Registration Registered in the ISRCTN registry with study ID ISRCTN14341750. Date of registration 23/11/2018.
- Open Access
- 24 February 2022
- Published by MDPI AG in Diagnostics
- Vol. 12 (3) , 582
The NILS Study Protocol: A Retrospective Validation Study of an Artificial Neural Network Based Preoperative Decision-Making Tool for Noninvasive Lymph Node Staging in Women with Primary Breast Cancer (ISRCTN14341750)
Newly diagnosed breast cancer (BC) patients with clinical T1–T2 N0 disease undergo sentinel-lymph-node (SLN) biopsy, although most of them have a benign SLN. The pilot noninvasive lymph node staging (NILS) artificial neural network (ANN) model to predict nodal status was published in 2019, showing the potential to identify patients with a low risk of SLN metastasis. The aim of this study is to assess the performance measures of the model after a web-based implementation for the prediction of a healthy SLN in clinically N0 BC patients. This retrospective study was designed to validate the NILS prediction model for SLN status using preoperatively available clinicopathological and radiological data. The model results in an estimated probability of a healthy SLN for each study participant. Our primary endpoint is to report on the performance of the NILS prediction model to distinguish between healthy and metastatic SLNs (N0 vs. N+) and compare the observed and predicted event rates of benign SLNs. After validation, the prediction model may assist medical professionals and BC patients in shared decision making on omitting SLN biopsies in patients predicted to be node-negative by the NILS model. This study was prospectively registered in the ISRCTN registry (identification number: 14341750).
- 24 February 2022
- Published by MDPI AG in Diagnostics
- Vol. 12 (3) , 582
Open AccessThe NILS Study Protocol: A Retrospective Validation Study of an Artificial Neural Network Based Preoperative Decision-Making Tool for Noninvasive Lymph Node Staging in Women with Primary Breast Cancer (ISRCTN14341750)
Newly diagnosed breast cancer (BC) patients with clinical T1–T2 N0 disease undergo sentinel-lymph-node (SLN) biopsy, although most of them have a benign SLN. The pilot noninvasive lymph node staging (NILS) artificial neural network (ANN) model to predict nodal status was published in 2019, showing the potential to identify patients with a low risk of SLN metastasis. The aim of this study is to assess the performance measures of the model after a web-based implementation for the prediction of a healthy SLN in clinically N0 BC patients. This retrospective study was designed to validate the NILS prediction model for SLN status using preoperatively available clinicopathological and radiological data. The model results in an estimated probability of a healthy SLN for each study participant. Our primary endpoint is to report on the performance of the NILS prediction model to distinguish between healthy and metastatic SLNs (N0 vs. N+) and compare the observed and predicted event rates of benign SLNs. After validation, the prediction model may assist medical professionals and BC patients in shared decision making on omitting SLN biopsies in patients predicted to be node-negative by the NILS model. This study was prospectively registered in the ISRCTN registry (identification number: 14341750).
- Open Access
The NILS study protocol - a retrospective validation study of a preoperative decision-making tool for non-invasive lymph node staging in women with primary breast cancer [ISRCTN14341750]
Background Routine preoperative axillary ultrasonography has proven insufficient for detecting low-burden nodal metastatic deposits. For the majority of newly diagnosed breast cancer patients presenting with clinical T1-T2 N0 disease, the standard axillary staging by sentinel lymph node biopsy is not therapeutic. The pilot non-invasive lymph node staging (NILS) artificial neural network (ANN) model to predict nodal status was published in 2019. The aim of the current study is to assess the performance measures of the model for the prediction of healthy lymph nodes in clinically N0 breast cancer patients at two breast cancer centers in Sweden. Methods This bicenter, observational, retrospective study has been designed to validate the NILS prediction model for nodal status using preoperatively collected clinicopathological and radiological data. A web-based implementation of the nodal status classifier has been developed and will be used in this study, resulting in an estimated probability of healthy lymph nodes for each study participant. Our primary endpoint is to report on the performance of the NILS prediction model to distinguish between healthy and metastatic lymph nodes (discrimination, N0 vs. N+) and compare the observed and predicted event rates of benign axillary nodal status (calibration). Discussion Internationally, there are numerous artificial intelligence projects involving non-invasive identification of N0 breast cancer. Here, we present a robust validation study based on external cohorts of our ANN model. Although validation is necessary to show generalizability, it is often overlooked. If the accuracy and discrimination reach a satisfactory level, our prediction tool can be implemented to assist medical professionals and breast cancer patients in shared decision-making on omitting sentinel node biopsy in patients predicted to be node-negative. In future, this may potentially save healthcare resources and reduce costs and adverse side effects. In addition, our study might prompt future studies of nodal metastases of malignancies in other organs, and thus might have implications beyond breast cancer. Trial registration This study has been prospectively registered in the ISRCTN registry, identification number: 14341750
Open AccessThe NILS study protocol - a retrospective validation study of a preoperative decision-making tool for non-invasive lymph node staging in women with primary breast cancer [ISRCTN14341750]
Background Routine preoperative axillary ultrasonography has proven insufficient for detecting low-burden nodal metastatic deposits. For the majority of newly diagnosed breast cancer patients presenting with clinical T1-T2 N0 disease, the standard axillary staging by sentinel lymph node biopsy is not therapeutic. The pilot non-invasive lymph node staging (NILS) artificial neural network (ANN) model to predict nodal status was published in 2019. The aim of the current study is to assess the performance measures of the model for the prediction of healthy lymph nodes in clinically N0 breast cancer patients at two breast cancer centers in Sweden. Methods This bicenter, observational, retrospective study has been designed to validate the NILS prediction model for nodal status using preoperatively collected clinicopathological and radiological data. A web-based implementation of the nodal status classifier has been developed and will be used in this study, resulting in an estimated probability of healthy lymph nodes for each study participant. Our primary endpoint is to report on the performance of the NILS prediction model to distinguish between healthy and metastatic lymph nodes (discrimination, N0 vs. N+) and compare the observed and predicted event rates of benign axillary nodal status (calibration). Discussion Internationally, there are numerous artificial intelligence projects involving non-invasive identification of N0 breast cancer. Here, we present a robust validation study based on external cohorts of our ANN model. Although validation is necessary to show generalizability, it is often overlooked. If the accuracy and discrimination reach a satisfactory level, our prediction tool can be implemented to assist medical professionals and breast cancer patients in shared decision-making on omitting sentinel node biopsy in patients predicted to be node-negative. In future, this may potentially save healthcare resources and reduce costs and adverse side effects. In addition, our study might prompt future studies of nodal metastases of malignancies in other organs, and thus might have implications beyond breast cancer. Trial registration This study has been prospectively registered in the ISRCTN registry, identification number: 14341750