Genji Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Genji Bai has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
Jianye Jia
6 shared publicationsWei Zhou
Department of Radiology, The Affiliated Huai'an No. 1 People's Hospital of Nanjing Medical University, Huai'an, Jiangsu, China (H.Z., F.B., W.-T.G., W.Z.).
5 shared publications- Yating Wang
The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University
5 shared publications Qian Wang
The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University
4 shared publicationsYan Zhu
The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University
4 shared publicationsZiyan Liu
4 shared publications
Latest Publications
- 27 June 2026
- Published by Baishideng Publishing Group Inc. in World Journal of Gastrointestinal Surgery
- Vol. 18 (6)
Predictive value of portal venous phase computed tomography parameters for anastomotic stricture after D2 gastrectomy
BACKGROUND The most common complication in D2 gastrectomy for gastric cancer is the anastomotic stricture, with reported incidence between 3% and 15%. Appropriate tissue perfusion is essential at all time points during the inflammatory, proliferative, and remodeling phases of anastomotic healing. Portal venous phase computed tomography (CT), a study universally indicated for preoperative staging and postoperative re-evaluation, is an objective assessment of visceral hemodynamic status that may impact anastomotic healing. Yet the predictive value of preoperative CT portal venous parameters for risk of anastomotic stricture has not yet been investigated, and reliable preoperative stratification tools are urgently needed. Deep learning-based portal venous CT parameters have been particularly well-studied for liver cirrhosis and portal hypertension, but this is the first time they have been studied in predicting gastrointestinal anastomotic complications. AIM To prospectively explore the predictive power of preoperative enhanced CT portal venous phase quantitative parameters for anastomotic stricture after D2 gastrectomy for gastric cancer to establish a combined prediction model. METHODS Clinical data from 199 patients who underwent D2 gastrectomy for gastric cancer at our institution between January 2022 and June 2024 were retrospectively analyzed. Patients were categorized into stricture group (n = 23) and non-stricture group (n = 176) based on whether anastomotic stricture occurred within 12 months postoperatively. On preoperative enhanced CT portal venous phase images, main portal vein (PV) CT value (PV-HU), splenic vein CT value, hepatic parenchyma, and abdominal aorta were measured. Derived parameters including normalized PV-HU (nPV-HU) and PV-to-abdominal aorta CT value (aorta-HU) ratio were calculated. Multivariate logistic regression analysis was employed to identify independent predictive factors. Receiver operating characteristic curves were constructed to evaluate predictive performance, and a combined prediction model was developed. RESULTS The postoperative anastomotic stricture rate was 11.6% (23/199). The stricture group demonstrated significantly lower PV-HU, splenic vein CT value, PV-to-aorta-HU ratio, and nPV-HU compared to the non-stricture group (P < 0.05). Multivariate logistic regression analysis revealed that body mass index ≥ 25 kg/m2, diabetes mellitus, total gastrectomy, 25 mm stapler diameter, decreased nPV-HU, and decreased PV-to-aorta-HU ratio were independent risk factors for anastomotic stricture (P < 0.05). For predicting anastomotic stricture, nPV-HU yielded an area under the curve (AUC) of 0.812, with an optimal cutoff value of 42.5%, sensitivity of 78.3%, and specificity of 72.7%; PV-to-aorta-HU ratio yielded an AUC of 0.768, with an optimal cutoff value of 1.45, sensitivity of 73.9%, and specificity of 71.0%. The combined prediction model incorporating clinical factors and CT parameters achieved an AUC of 0.893, with sensitivity of 87.0%, specificity of 80.1%, and negative predictive value of 97.9%. CONCLUSION Preoperative enhanced CT portal venous phase quantitative parameters nPV-HU and PV-to-aorta-HU ratio can effectively predict the risk of anastomotic stricture following D2 gastrectomy for gastric cancer. The prediction model combining clinical risk factors demonstrates high diagnostic performance and provides a strong imaging-based rationale for preoperative risk stratification, potentially guiding personalized perioperative management strategies.
- 27 June 2026
- Published by Baishideng Publishing Group Inc. in World Journal of Gastrointestinal Surgery
- Vol. 18 (6)
Predictive value of portal venous phase computed tomography parameters for anastomotic stricture after D2 gastrectomy
BACKGROUND The most common complication in D2 gastrectomy for gastric cancer is the anastomotic stricture, with reported incidence between 3% and 15%. Appropriate tissue perfusion is essential at all time points during the inflammatory, proliferative, and remodeling phases of anastomotic healing. Portal venous phase computed tomography (CT), a study universally indicated for preoperative staging and postoperative re-evaluation, is an objective assessment of visceral hemodynamic status that may impact anastomotic healing. Yet the predictive value of preoperative CT portal venous parameters for risk of anastomotic stricture has not yet been investigated, and reliable preoperative stratification tools are urgently needed. Deep learning-based portal venous CT parameters have been particularly well-studied for liver cirrhosis and portal hypertension, but this is the first time they have been studied in predicting gastrointestinal anastomotic complications. AIM To prospectively explore the predictive power of preoperative enhanced CT portal venous phase quantitative parameters for anastomotic stricture after D2 gastrectomy for gastric cancer to establish a combined prediction model. METHODS Clinical data from 199 patients who underwent D2 gastrectomy for gastric cancer at our institution between January 2022 and June 2024 were retrospectively analyzed. Patients were categorized into stricture group (n = 23) and non-stricture group (n = 176) based on whether anastomotic stricture occurred within 12 months postoperatively. On preoperative enhanced CT portal venous phase images, main portal vein (PV) CT value (PV-HU), splenic vein CT value, hepatic parenchyma, and abdominal aorta were measured. Derived parameters including normalized PV-HU (nPV-HU) and PV-to-abdominal aorta CT value (aorta-HU) ratio were calculated. Multivariate logistic regression analysis was employed to identify independent predictive factors. Receiver operating characteristic curves were constructed to evaluate predictive performance, and a combined prediction model was developed. RESULTS The postoperative anastomotic stricture rate was 11.6% (23/199). The stricture group demonstrated significantly lower PV-HU, splenic vein CT value, PV-to-aorta-HU ratio, and nPV-HU compared to the non-stricture group (P < 0.05). Multivariate logistic regression analysis revealed that body mass index ≥ 25 kg/m2, diabetes mellitus, total gastrectomy, 25 mm stapler diameter, decreased nPV-HU, and decreased PV-to-aorta-HU ratio were independent risk factors for anastomotic stricture (P < 0.05). For predicting anastomotic stricture, nPV-HU yielded an area under the curve (AUC) of 0.812, with an optimal cutoff value of 42.5%, sensitivity of 78.3%, and specificity of 72.7%; PV-to-aorta-HU ratio yielded an AUC of 0.768, with an optimal cutoff value of 1.45, sensitivity of 73.9%, and specificity of 71.0%. The combined prediction model incorporating clinical factors and CT parameters achieved an AUC of 0.893, with sensitivity of 87.0%, specificity of 80.1%, and negative predictive value of 97.9%. CONCLUSION Preoperative enhanced CT portal venous phase quantitative parameters nPV-HU and PV-to-aorta-HU ratio can effectively predict the risk of anastomotic stricture following D2 gastrectomy for gastric cancer. The prediction model combining clinical risk factors demonstrates high diagnostic performance and provides a strong imaging-based rationale for preoperative risk stratification, potentially guiding personalized perioperative management strategies.
- Open Access
- 27 February 2026
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 25
Transformer-Based Deep Learning Model Using MRI-Derived Microvascular Atlas for Predicting Lymphovascular Invasion in Breast Cancer Patients
Introduction: Lymphovascular invasion (LVI), an aggressive pathological manifestation of breast cancer, is closely associated with increased risk of distant metastasis and poor prognosis. This study proposes a novel modeling strategy that integrates MRI-derived microvascular atlas parameters with the TwinsSVT deep learning architecture to enable noninvasive prediction of LVI status in breast cancer patients and to explore its biological interpretability. Materials and Methods: A total of 436 breast cancer patients from two medical centers, all pathologically confirmed postoperatively, were retrospectively enrolled. All patients underwent high-resolution multi-b-value diffusion-weighted imaging (DWI) prior to surgery. From the MRI data, four types of microvascular simulation parameter maps were reconstructed within tumor regions: apparent diffusion coefficient (ADC), mean flow velocity (v_m), velocity dispersion (v_s), and angiographic branching index (ANB), aiming to characterize intratumoral microcirculation and vascular structural complexity. These functional parametric maps were individually input into separate encoder branches of the TwinsSVT model to extract multi-scale spatial features. A multi-layer Transformer fusion module was then employed to capture structural interactions across modalities, thereby constructing a multi-parametric fusion model. Model performance was evaluated using metrics including area under the curve (AUC) and F1 score. Results: Compared with single-parameter models, the multi-parametric fusion model demonstrated significantly improved predictive performance, with AUCs of 0.881 (95% CI: 0.781-0.982) and 0.859 (95% CI: 0.764-0.953) in internal and external validation cohorts, respectively. Grad-CAM visualizations revealed that the model predominantly focused on tumor margins and regions of high vascular density, suggesting a strong correlation between the model's attention and actual pathological structures. Conclusion: The deep learning model constructed based on MRI-derived microvascular simulation atlases enables noninvasive preoperative prediction of LVI status in breast cancer patients. By effectively capturing structural information and offering biological interpretability, the model holds promise as a robust imaging-based tool for precision subtyping and clinical decision support.
- 27 February 2026
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 25
Open AccessTransformer-Based Deep Learning Model Using MRI-Derived Microvascular Atlas for Predicting Lymphovascular Invasion in Breast Cancer Patients
Introduction: Lymphovascular invasion (LVI), an aggressive pathological manifestation of breast cancer, is closely associated with increased risk of distant metastasis and poor prognosis. This study proposes a novel modeling strategy that integrates MRI-derived microvascular atlas parameters with the TwinsSVT deep learning architecture to enable noninvasive prediction of LVI status in breast cancer patients and to explore its biological interpretability. Materials and Methods: A total of 436 breast cancer patients from two medical centers, all pathologically confirmed postoperatively, were retrospectively enrolled. All patients underwent high-resolution multi-b-value diffusion-weighted imaging (DWI) prior to surgery. From the MRI data, four types of microvascular simulation parameter maps were reconstructed within tumor regions: apparent diffusion coefficient (ADC), mean flow velocity (v_m), velocity dispersion (v_s), and angiographic branching index (ANB), aiming to characterize intratumoral microcirculation and vascular structural complexity. These functional parametric maps were individually input into separate encoder branches of the TwinsSVT model to extract multi-scale spatial features. A multi-layer Transformer fusion module was then employed to capture structural interactions across modalities, thereby constructing a multi-parametric fusion model. Model performance was evaluated using metrics including area under the curve (AUC) and F1 score. Results: Compared with single-parameter models, the multi-parametric fusion model demonstrated significantly improved predictive performance, with AUCs of 0.881 (95% CI: 0.781-0.982) and 0.859 (95% CI: 0.764-0.953) in internal and external validation cohorts, respectively. Grad-CAM visualizations revealed that the model predominantly focused on tumor margins and regions of high vascular density, suggesting a strong correlation between the model's attention and actual pathological structures. Conclusion: The deep learning model constructed based on MRI-derived microvascular simulation atlases enables noninvasive preoperative prediction of LVI status in breast cancer patients. By effectively capturing structural information and offering biological interpretability, the model holds promise as a robust imaging-based tool for precision subtyping and clinical decision support.
- Open Access
- 23 February 2026
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 25
The Predictive Value of Extracellular Volume Fraction Derived from Enhanced CT Combined with Systemic Immune-Inflammation Index for Tumor Budding in Rectal Cancer
Introduction: To explore the value of enhanced computed tomography (CT) -derived extracellular volume (ECV) combined with systemic immune-inflammation index (SII) in predicting tumor budding (TB) grading of rectal cancer. Materials and Methods: The clinical and imaging data of 177 rectal cancer patients were retrospectively analyzed, and we divided them into a low-grade and medium-high group according to pathological TB count. ECV and SII values between the two groups were compared. Intra-class correlation coefficient (ICC) was used to detect the consistency of measurements among observers. Binary logistic regression was used to analyze the correlations between variables and TB grading of rectal cancer. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic efficiency of statistically significant parameters and their combination. Area under the curve (AUC), its 95% confidence interval, and the corresponding Youden index, sensitivity, and specificity were calculated. Results: Among the 177 rectal cancer patients, 108 were low-grade and 69 were medium-high grade. ECV values measured by two physicians showed good consistency (ICC = 0.98). ECV value of low-grade (21.76% ± 4.89%) was lower than that of medium-high grade TB group (27.91% ± 4.77%) (P < .001). SII value was lower in low-grade group (492.14 ± 239.56) than in medium-high grade TB group (825.02 ± 529.38). In the multivariate analysis, ECV value [odds ratio (OR): 1.339 (95% CI: 1.194-1.502)] and SII value [OR: 1.004 (95% CI: 1.002-1.005)] were independent risk factors for predicting TB grading. In the training set, AUCs of ECV, SII, and their combination in evaluating TB grading of rectal cancer were 0.838 (95% CI: 0.760-0.905), 0.755 (95% CI: 0.663-0.829), and 0.889 (95% CI: 0.832-0.943), respectively. In the test set, the corresponding AUCs were 0.741 (95% CI: 0.626-0.870), 0.716 (95% CI: 0.554-0.849), and 0.815 (95% CI: 0.711-0.913). Decision curve analysis (DCA) showed that the combination had higher clinical value than using ECV or SII alone. Conclusion: The combination of ECV and SII can non-invasively evaluate TB grading of rectal cancer before surgery, potentially providing a reference for preoperative risk stratification as a decision-support tool.
- 23 February 2026
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 25
Open AccessThe Predictive Value of Extracellular Volume Fraction Derived from Enhanced CT Combined with Systemic Immune-Inflammation Index for Tumor Budding in Rectal Cancer
Introduction: To explore the value of enhanced computed tomography (CT) -derived extracellular volume (ECV) combined with systemic immune-inflammation index (SII) in predicting tumor budding (TB) grading of rectal cancer. Materials and Methods: The clinical and imaging data of 177 rectal cancer patients were retrospectively analyzed, and we divided them into a low-grade and medium-high group according to pathological TB count. ECV and SII values between the two groups were compared. Intra-class correlation coefficient (ICC) was used to detect the consistency of measurements among observers. Binary logistic regression was used to analyze the correlations between variables and TB grading of rectal cancer. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic efficiency of statistically significant parameters and their combination. Area under the curve (AUC), its 95% confidence interval, and the corresponding Youden index, sensitivity, and specificity were calculated. Results: Among the 177 rectal cancer patients, 108 were low-grade and 69 were medium-high grade. ECV values measured by two physicians showed good consistency (ICC = 0.98). ECV value of low-grade (21.76% ± 4.89%) was lower than that of medium-high grade TB group (27.91% ± 4.77%) (P < .001). SII value was lower in low-grade group (492.14 ± 239.56) than in medium-high grade TB group (825.02 ± 529.38). In the multivariate analysis, ECV value [odds ratio (OR): 1.339 (95% CI: 1.194-1.502)] and SII value [OR: 1.004 (95% CI: 1.002-1.005)] were independent risk factors for predicting TB grading. In the training set, AUCs of ECV, SII, and their combination in evaluating TB grading of rectal cancer were 0.838 (95% CI: 0.760-0.905), 0.755 (95% CI: 0.663-0.829), and 0.889 (95% CI: 0.832-0.943), respectively. In the test set, the corresponding AUCs were 0.741 (95% CI: 0.626-0.870), 0.716 (95% CI: 0.554-0.849), and 0.815 (95% CI: 0.711-0.913). Decision curve analysis (DCA) showed that the combination had higher clinical value than using ECV or SII alone. Conclusion: The combination of ECV and SII can non-invasively evaluate TB grading of rectal cancer before surgery, potentially providing a reference for preoperative risk stratification as a decision-support tool.
- Open Access
- 1 June 2025
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 24
Predicting the Efficacy of Neoadjuvant Chemotherapy Combined with Immunotherapy for Esophageal Squamous Cell Carcinoma via Enhanced CT Radiomics Combined with Clinical Features
Introduction: To evaluate the predictive efficacy of enhanced Computed Tomograph(CT) radiomics combined with clinical features for assessing treatment response to neoadjuvant chemotherapy plus immunotherapy in esophageal squamous cell carcinoma (ESCC) patients. Methods: We retrospectively analyzed 189 pathologically confirmed esophageal squamous cell carcinoma patients (treated between January 2020 and October 2024) who underwent neoadjuvant chemoimmunotherapy. Patients were stratified into remission and non-remission groups based on pathological response and randomly divided into training (n = 114) and testing (n = 75) sets (6:4 ratio). Clinical predictors were identified using logistic regression to construct a clinical model. Radiomic features were extracted from manually delineated tumor regions on contrast-enhanced CT scans, and a radiomics model was developed. A combined model integrating clinical variables and radiomics probabilities was then built and presented as a nomogram. Model performance was assessed using receiver operating characteristic (ROC) curves (AUC, Area Under the Curve) comparison via Delong test), calibration curves, and decision curve analysis (DCA). Results: Multivariable analysis identified treatment cycle number as a significant clinical predictor. Ten radiomic features were selected for the final model. In the training set, the clinical model achieved an AUC of 0.705 (95% CI 0.607-0.802), while the radiomics and combined models showed superior performance with AUCs of 0.905 (95% CI 0.843-0.967) and 0.914 (95% CI 0.857-0.970), respectively. Similar trends were observed in the testing set, where the combined model (AUC 0.859, 95% CI 0.768-0.950) outperformed both the radiomics (AUC 0.815) and clinical (AUC 0.644) models. Conclusion: The enhanced CT radiomics model has better predictive efficacy for remission with neoadjuvant chemotherapy combined with immunotherapy in esophageal squamous cell carcinoma patients, and the combined model has greater predictive value.
- 1 June 2025
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 24
Open AccessPredicting the Efficacy of Neoadjuvant Chemotherapy Combined with Immunotherapy for Esophageal Squamous Cell Carcinoma via Enhanced CT Radiomics Combined with Clinical Features
Introduction: To evaluate the predictive efficacy of enhanced Computed Tomograph(CT) radiomics combined with clinical features for assessing treatment response to neoadjuvant chemotherapy plus immunotherapy in esophageal squamous cell carcinoma (ESCC) patients. Methods: We retrospectively analyzed 189 pathologically confirmed esophageal squamous cell carcinoma patients (treated between January 2020 and October 2024) who underwent neoadjuvant chemoimmunotherapy. Patients were stratified into remission and non-remission groups based on pathological response and randomly divided into training (n = 114) and testing (n = 75) sets (6:4 ratio). Clinical predictors were identified using logistic regression to construct a clinical model. Radiomic features were extracted from manually delineated tumor regions on contrast-enhanced CT scans, and a radiomics model was developed. A combined model integrating clinical variables and radiomics probabilities was then built and presented as a nomogram. Model performance was assessed using receiver operating characteristic (ROC) curves (AUC, Area Under the Curve) comparison via Delong test), calibration curves, and decision curve analysis (DCA). Results: Multivariable analysis identified treatment cycle number as a significant clinical predictor. Ten radiomic features were selected for the final model. In the training set, the clinical model achieved an AUC of 0.705 (95% CI 0.607-0.802), while the radiomics and combined models showed superior performance with AUCs of 0.905 (95% CI 0.843-0.967) and 0.914 (95% CI 0.857-0.970), respectively. Similar trends were observed in the testing set, where the combined model (AUC 0.859, 95% CI 0.768-0.950) outperformed both the radiomics (AUC 0.815) and clinical (AUC 0.644) models. Conclusion: The enhanced CT radiomics model has better predictive efficacy for remission with neoadjuvant chemotherapy combined with immunotherapy in esophageal squamous cell carcinoma patients, and the combined model has greater predictive value.
- 10 March 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (7) , 3858-3869
Dual-Modality Virtual Biopsy System Integrating MRI and MG for Noninvasive Predicting HER2 Status in Breast Cancer
- 10 March 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (7) , 3858-3869
Dual-Modality Virtual Biopsy System Integrating MRI and MG for Noninvasive Predicting HER2 Status in Breast Cancer
- 10 February 2024
- Published by Springer Nature in European Radiology
- Vol. 34 (9) , 6121-6131
Multi-modality radiomics model predicts axillary lymph node metastasis of breast cancer using MRI and mammography
Objectives We aimed to develop a multi-modality model to predict axillary lymph node (ALN) metastasis by combining clinical predictors with radiomic features from magnetic resonance imaging (MRI) and mammography (MMG) in breast cancer. This model might potentially eliminate unnecessary axillary surgery in cases without ALN metastasis, thereby minimizing surgery-related complications. Methods We retrospectively enrolled 485 breast cancer patients from two hospitals and extracted radiomics features from tumor and lymph node regions on MRI and MMG images. After feature selection, three random forest models were built using the retained features, respectively. Significant clinical factors were integrated with these radiomics models to construct a multi-modality model. The multi-modality model was compared to radiologists’ diagnoses on axillary ultrasound and MRI. It was also used to assist radiologists in making a secondary diagnosis on MRI. Results The multi-modality model showed superior performance with AUCs of 0.964 in the training cohort, 0.916 in the internal validation cohort, and 0.892 in the external validation cohort. It surpassed single-modality models and radiologists’ ALN diagnosis on MRI and axillary ultrasound in all validation cohorts. Additionally, the multi-modality model improved radiologists’ MRI-based ALN diagnostic ability, increasing the average accuracy from 70.70 to 78.16% for radiologist A and from 75.42 to 81.38% for radiologist B. Conclusion The multi-modality model can predict ALN metastasis of breast cancer accurately. Moreover, the artificial intelligence (AI) model also assisted the radiologists to improve their diagnostic ability on MRI. Clinical relevance statement The multi-modality model based on both MRI and mammography images allows preoperative prediction of axillary lymph node metastasis in breast cancer patients. With the assistance of the model, the diagnostic efficacy of radiologists can be further improved. Key Points • We developed a novel multi-modality model that combines MRI and mammography radiomics with clinical factors to accurately predict axillary lymph node (ALN) metastasis, which has not been previously reported. • Our multi-modality model outperformed both the radiologists’ ALN diagnosis based on MRI and axillary ultrasound, as well as single-modality radiomics models based on MRI or mammography. • The multi-modality model can serve as a potential decision support tool to improve the radiologists’ ALN diagnosis on MRI.
- 10 February 2024
- Published by Springer Nature in European Radiology
- Vol. 34 (9) , 6121-6131
Multi-modality radiomics model predicts axillary lymph node metastasis of breast cancer using MRI and mammography
Objectives We aimed to develop a multi-modality model to predict axillary lymph node (ALN) metastasis by combining clinical predictors with radiomic features from magnetic resonance imaging (MRI) and mammography (MMG) in breast cancer. This model might potentially eliminate unnecessary axillary surgery in cases without ALN metastasis, thereby minimizing surgery-related complications. Methods We retrospectively enrolled 485 breast cancer patients from two hospitals and extracted radiomics features from tumor and lymph node regions on MRI and MMG images. After feature selection, three random forest models were built using the retained features, respectively. Significant clinical factors were integrated with these radiomics models to construct a multi-modality model. The multi-modality model was compared to radiologists’ diagnoses on axillary ultrasound and MRI. It was also used to assist radiologists in making a secondary diagnosis on MRI. Results The multi-modality model showed superior performance with AUCs of 0.964 in the training cohort, 0.916 in the internal validation cohort, and 0.892 in the external validation cohort. It surpassed single-modality models and radiologists’ ALN diagnosis on MRI and axillary ultrasound in all validation cohorts. Additionally, the multi-modality model improved radiologists’ MRI-based ALN diagnostic ability, increasing the average accuracy from 70.70 to 78.16% for radiologist A and from 75.42 to 81.38% for radiologist B. Conclusion The multi-modality model can predict ALN metastasis of breast cancer accurately. Moreover, the artificial intelligence (AI) model also assisted the radiologists to improve their diagnostic ability on MRI. Clinical relevance statement The multi-modality model based on both MRI and mammography images allows preoperative prediction of axillary lymph node metastasis in breast cancer patients. With the assistance of the model, the diagnostic efficacy of radiologists can be further improved. Key Points • We developed a novel multi-modality model that combines MRI and mammography radiomics with clinical factors to accurately predict axillary lymph node (ALN) metastasis, which has not been previously reported. • Our multi-modality model outperformed both the radiologists’ ALN diagnosis based on MRI and axillary ultrasound, as well as single-modality radiomics models based on MRI or mammography. • The multi-modality model can serve as a potential decision support tool to improve the radiologists’ ALN diagnosis on MRI.
- 9 January 2024
- Published by Elsevier in Academic Radiology
- Vol. 31 (7) , 2807-2817
Consensus Clustering Analysis Based on Enhanced-CT Radiomic Features: Esophageal Squamous Cell Carcinoma patients’ 3-Year Progression-Free Survival
- 9 January 2024
- Published by Elsevier in Academic Radiology
- Vol. 31 (7) , 2807-2817
Consensus Clustering Analysis Based on Enhanced-CT Radiomic Features: Esophageal Squamous Cell Carcinoma patients’ 3-Year Progression-Free Survival
- Open Access
- 19 October 2023
- Published by Elsevier in Asian Journal of Surgery
- Vol. 47 (1) , 600-601
Application of imaging techniques to distinguish between mucinous and non-mucinous lung adenocarcinoma
- 19 October 2023
- Published by Elsevier in Asian Journal of Surgery
- Vol. 47 (1) , 600-601
Open AccessApplication of imaging techniques to distinguish between mucinous and non-mucinous lung adenocarcinoma
- 3 May 2023
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 59 (1) , 122-131
Associating Peritoneal Metastasis With T2‐Weighted MRI Images in Epithelial Ovarian Cancer Using Deep Learning and Radiomics: A Multicenter Study
Background: The preoperative diagnosis of peritoneal metastasis (PM) in epithelial ovarian cancer (EOC) is challenging and can impact clinical decision‐making.Purpose: To investigate the performance of T2‐weighted (T2W) MRI‐based deep learning (DL) and radiomics methods for PM evaluation in EOC patients.Study Type: Retrospective.Population: Four hundred seventy‐nine patients from five centers, including one training set (N = 297 [mean, 54.87 years]), one internal validation set (N = 75 [mean, 56.67 years]), and two external validation sets (N = 53 [mean, 55.58 years] and N = 54 [mean, 58.22 years]).Field Strength/Sequence: 1.5 or 3 T/fat‐suppression T2W fast or turbo spin‐echo sequence.Assessment: ResNet‐50 was used as the architecture of DL. The largest orthogonal slices of the tumor area, radiomics features, and clinical characteristics were used to construct the DL, radiomics, and clinical models, respectively. The three models were combined using decision‐level fusion to create an ensemble model. Diagnostic performances of radiologists and radiology residents with and without model assistance were evaluated.Statistical Tests: Receiver operating characteristic analysis was used to assess the performances of models. The McNemar test was used to compare sensitivity and specificity. A two‐tailed P < 0.05 was considered significant.Results: The ensemble model had the best AUCs, outperforming the DL model (0.844 vs. 0.743, internal validation set; 0.859 vs. 0.737, external validation set I) and clinical model (0.872 vs. 0.730, external validation set II). After model assistance, all readers had significantly improved sensitivity, especially for those with less experience (junior radiologist1, from 0.639 to 0.820; junior radiologist2, from 0.689 to 0.803; resident1, from 0.623 to 0.803; resident2, from 0.541 to 0.738). One resident also had significantly improved specificity (from 0.633 to 0.789).Data Conclusions: T2W MRI‐based DL and radiomics approaches have the potential to preoperatively predict PM in EOC patients and assist in clinical decision‐making.Evidence Level: 4Technical Efficacy: Stage 2
- 3 May 2023
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 59 (1) , 122-131
Associating Peritoneal Metastasis With T2‐Weighted MRI Images in Epithelial Ovarian Cancer Using Deep Learning and Radiomics: A Multicenter Study
Background: The preoperative diagnosis of peritoneal metastasis (PM) in epithelial ovarian cancer (EOC) is challenging and can impact clinical decision‐making.Purpose: To investigate the performance of T2‐weighted (T2W) MRI‐based deep learning (DL) and radiomics methods for PM evaluation in EOC patients.Study Type: Retrospective.Population: Four hundred seventy‐nine patients from five centers, including one training set (N = 297 [mean, 54.87 years]), one internal validation set (N = 75 [mean, 56.67 years]), and two external validation sets (N = 53 [mean, 55.58 years] and N = 54 [mean, 58.22 years]).Field Strength/Sequence: 1.5 or 3 T/fat‐suppression T2W fast or turbo spin‐echo sequence.Assessment: ResNet‐50 was used as the architecture of DL. The largest orthogonal slices of the tumor area, radiomics features, and clinical characteristics were used to construct the DL, radiomics, and clinical models, respectively. The three models were combined using decision‐level fusion to create an ensemble model. Diagnostic performances of radiologists and radiology residents with and without model assistance were evaluated.Statistical Tests: Receiver operating characteristic analysis was used to assess the performances of models. The McNemar test was used to compare sensitivity and specificity. A two‐tailed P < 0.05 was considered significant.Results: The ensemble model had the best AUCs, outperforming the DL model (0.844 vs. 0.743, internal validation set; 0.859 vs. 0.737, external validation set I) and clinical model (0.872 vs. 0.730, external validation set II). After model assistance, all readers had significantly improved sensitivity, especially for those with less experience (junior radiologist1, from 0.639 to 0.820; junior radiologist2, from 0.689 to 0.803; resident1, from 0.623 to 0.803; resident2, from 0.541 to 0.738). One resident also had significantly improved specificity (from 0.633 to 0.789).Data Conclusions: T2W MRI‐based DL and radiomics approaches have the potential to preoperatively predict PM in EOC patients and assist in clinical decision‐making.Evidence Level: 4Technical Efficacy: Stage 2