Jingyan Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jingyan Xu has a total of 157 co-authors. Here are the top co-authors by number of shared publications:
Chong Jiang
Department of Nuclear Medicine, West China Hospital, Sichuan University, Chengdu, China
12 shared publicationsYue Teng
Department of Nuclear Medicine, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, China
10 shared publications- Bing Chen
Department of Hematology, Affiliated Hospital of Medical School, Nanjing Drum Tower Hospital, Nanjing University, Nanjing, People’s Republic of China
5 shared publications - Qinglong Guo
School of Basic Medicine and Clinical Pharmacy China Pharmaceutical University Nanjing Jiangsu China
5 shared publications - Zhengyang Zhou
Department of Radiology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China
5 shared publications - Chongyang Ding
Department of Nuclear Medicine, the First Affiliated Hospital of Nanjing Medical University, Jiangsu Province Hospital, Nanjing, China
4 shared publications
Latest Publications
- 11 July 2026
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 53 (11) , 6670-6683
FUO-PETMamba: a pet maximum-intensity-projection-based artificial intelligence framework for aetiological classification of fever of unknown origin with multicentre validation
Background Fever of unknown origin (FUO) remains diagnostically challenging because of heterogeneous causes, non-specific clinical manifestations, and overlapping imaging findings. We developed and validated FUO-PETMamba, a PET maximum-intensity-projection (MIP)-based artificial intelligence framework for AI-assisted aetiological classification of FUO. Methods This retrospective multicentre study included 681 patients with FUO who underwent baseline [18 F]FDG PET/CT, comprising one development cohort (n = 355) and two independent external validation cohorts (n = 195 and n = 131). FUO-PETMamba is a weakly supervised framework analysing PET MIP images generated from PET data. Model performance was assessed by discrimination, calibration, decision curve analysis (DCA). Attention-based visual explanations were generated using attention mechanisms and gradient-based activation mapping. A reader study assessed the potential assistive effect of model-predicted probabilities on physicians with different PET/CT experience. Results In the development cohort, FUO-PETMamba achieved AUCs of 0.838 for malignancy, 0.851 for infection, 0.914 for autoimmune disease, and 0.788 for miscellaneous causes. Corresponding AUCs were 0.809, 0.815, 0.805, and 0.849 in external validation cohort 1, and 0.808, 0.772, 0.701, and 0.927 in external validation cohort 2, respectively. Calibration and decision curve analysis suggested potential clinical benefit for the major aetiological categories, although performance varied across cohorts and classes. The miscellaneous category should be interpreted cautiously because of limited case numbers and low positive predictive value and F1 scores. In the reader study, AI assistance improved diagnostic accuracy for junior and intermediate physicians, whereas changes in senior-physician performance were variable. Post hoc attention-based visualisations highlighted clinically plausible hypermetabolic patterns and served as qualitative explanatory aids. Conclusions FUO-PETMamba provides a PET MIP-based AI-assisted diagnostic support framework for aetiological classification of FUO across multicentre cohorts and may help reduce experience-dependent diagnostic variability after prospective validation.
- 11 July 2026
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 53 (11) , 6670-6683
FUO-PETMamba: a pet maximum-intensity-projection-based artificial intelligence framework for aetiological classification of fever of unknown origin with multicentre validation
Background Fever of unknown origin (FUO) remains diagnostically challenging because of heterogeneous causes, non-specific clinical manifestations, and overlapping imaging findings. We developed and validated FUO-PETMamba, a PET maximum-intensity-projection (MIP)-based artificial intelligence framework for AI-assisted aetiological classification of FUO. Methods This retrospective multicentre study included 681 patients with FUO who underwent baseline [18 F]FDG PET/CT, comprising one development cohort (n = 355) and two independent external validation cohorts (n = 195 and n = 131). FUO-PETMamba is a weakly supervised framework analysing PET MIP images generated from PET data. Model performance was assessed by discrimination, calibration, decision curve analysis (DCA). Attention-based visual explanations were generated using attention mechanisms and gradient-based activation mapping. A reader study assessed the potential assistive effect of model-predicted probabilities on physicians with different PET/CT experience. Results In the development cohort, FUO-PETMamba achieved AUCs of 0.838 for malignancy, 0.851 for infection, 0.914 for autoimmune disease, and 0.788 for miscellaneous causes. Corresponding AUCs were 0.809, 0.815, 0.805, and 0.849 in external validation cohort 1, and 0.808, 0.772, 0.701, and 0.927 in external validation cohort 2, respectively. Calibration and decision curve analysis suggested potential clinical benefit for the major aetiological categories, although performance varied across cohorts and classes. The miscellaneous category should be interpreted cautiously because of limited case numbers and low positive predictive value and F1 scores. In the reader study, AI assistance improved diagnostic accuracy for junior and intermediate physicians, whereas changes in senior-physician performance were variable. Post hoc attention-based visualisations highlighted clinically plausible hypermetabolic patterns and served as qualitative explanatory aids. Conclusions FUO-PETMamba provides a PET MIP-based AI-assisted diagnostic support framework for aetiological classification of FUO across multicentre cohorts and may help reduce experience-dependent diagnostic variability after prospective validation.
- 16 January 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 117
GEPNet: Granularity-edge perception feature learning network for 3D PET segmentation
- 16 January 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 117
GEPNet: Granularity-edge perception feature learning network for 3D PET segmentation
- Open Access
- 22 October 2025
- Published by Wiley in The FASEB Journal
- Vol. 39 (20) , e71167
Chidamide Accelerates the Death of Senescence‐Like Diffuse Large B‐Cell Lymphoma Cells With TP53 Mutation Induced by Doxorubicin
Diffuse large B‐cell lymphoma (DLBCL), a heterogeneous malignancy characterized by distinct genetic and clinical subtypes, remains a therapeutic challenge despite standard R‐CHOP chemotherapy. This study systematically investigated the synergistic anti‐tumor efficacy and mechanism of the histone deacetylase inhibitor chidamide (CHI) combined with doxorubicin (DOX) in DLBCL models. Through multimodal experimental approaches including CCK8 proliferation assays, senescence‐associated β‐galactosidase (SA‐β‐gal) staining analysis, comet assay for DNA damage quantification, and comprehensive western blotting for molecular mechanism elucidation, we identified a potent synergistic interaction between CHI and DOX. By constructing a xenograft tumor model, the synergistic effect of the two drugs and its mechanism in vivo were confirmed. Our research found that CHI showed cell cycle inhibition and apoptosis induction effects on DLBCL cells. When combined with DOX, both synergistically inhibited the proliferation of DLBCL cells and promoted death of DOX‐induced senescent cells. Preliminary mechanism studies revealed that CHI can reduce the level of mutant p53, inhibit cell senescence, and induce irreparable DNA damage in DOX‐induced senescent tumor cells, ultimately leading them into programmed apoptosis. Thus, the “One‐two punch” strategy increased the sensitivity of p53‐mutated DLBCL cells to CHI. In summary, our study demonstrates that CHI synergizes with DOX to suppress DLBCL and presents a promising strategy to augment the therapeutic efficacy of DOX.
- 22 October 2025
- Published by Wiley in The FASEB Journal
- Vol. 39 (20) , e71167
Open AccessChidamide Accelerates the Death of Senescence‐Like Diffuse Large B‐Cell Lymphoma Cells With TP53 Mutation Induced by Doxorubicin
Diffuse large B‐cell lymphoma (DLBCL), a heterogeneous malignancy characterized by distinct genetic and clinical subtypes, remains a therapeutic challenge despite standard R‐CHOP chemotherapy. This study systematically investigated the synergistic anti‐tumor efficacy and mechanism of the histone deacetylase inhibitor chidamide (CHI) combined with doxorubicin (DOX) in DLBCL models. Through multimodal experimental approaches including CCK8 proliferation assays, senescence‐associated β‐galactosidase (SA‐β‐gal) staining analysis, comet assay for DNA damage quantification, and comprehensive western blotting for molecular mechanism elucidation, we identified a potent synergistic interaction between CHI and DOX. By constructing a xenograft tumor model, the synergistic effect of the two drugs and its mechanism in vivo were confirmed. Our research found that CHI showed cell cycle inhibition and apoptosis induction effects on DLBCL cells. When combined with DOX, both synergistically inhibited the proliferation of DLBCL cells and promoted death of DOX‐induced senescent cells. Preliminary mechanism studies revealed that CHI can reduce the level of mutant p53, inhibit cell senescence, and induce irreparable DNA damage in DOX‐induced senescent tumor cells, ultimately leading them into programmed apoptosis. Thus, the “One‐two punch” strategy increased the sensitivity of p53‐mutated DLBCL cells to CHI. In summary, our study demonstrates that CHI synergizes with DOX to suppress DLBCL and presents a promising strategy to augment the therapeutic efficacy of DOX.
- Open Access
- 28 March 2025
- Published by Springer Nature in Journal of Cancer Research and Clinical Oncology
- Vol. 151 (3) , 1-11
18F-FDG PET radiomics score construction by automatic machine learning for treatment response prediction in elderly patients with diffuse large B-cell lymphoma: a multicenter study
Purpose To explore the development and validation of automated machine learning (AutoML) models for 18F-FDG PET imaging-based radiomics signatures to predict treatment response in elderly patients with diffuse large B-cell lymphoma (DLBCL). Methods A retrospective analysis was conducted on 175 elderly (≥ 60 years) DLBCL patients diagnosed between March 2015 and March 2023 at two medical centers, with a total of 1010 lesions. The baseline PET imaging-based radiomics features of the training cohort were processed using AutoML model AutoGluon to generate a radiomics score (radscore) and predict treatment response at the lesion and patient levels. Furthermore, a multivariable logistic analysis was used to design and evaluate a multivariable model in the training and validation cohorts. Results ROC curve analysis showed that the radscore generated by AutoML exhibited higher accuracy in predicting treatment response at the lesion level compared to metabolic parameters (SUVmax, MTV, and TLG) in both the training group (AUC: 0.791, 0.542, 0.667, 0.651, respectively) and the validation group (AUC: 0.712, 0.616, 0.639, 0.657, respectively). Multivariable logistic analysis indicated that NCCN-IPI (OR = 5.427, 95% CI: 1.163–25.317), BCL-2 (OR = 3.714, 95% CI: 1.406–9.816), TMTV (OR = 4.324, 95% CI: 1.095–17.067), and avg-radscore (OR = 3.176, 95% CI: 1.313-7. 686) were independent predictors of treatment response. The multivariable model comprising NCCN-IPI, BCL-2, TMTV, and avg-radscore outperformed conventional models and clinical-pathological models in predicting treatment response. (P<0.05). Conclusion The radscore generated by AutoML can predict the treatment response of elderly DLBCL patients, potentially aiding in clinical decision-making.
- 28 March 2025
- Published by Springer Nature in Journal of Cancer Research and Clinical Oncology
- Vol. 151 (3) , 1-11
Open Access18F-FDG PET radiomics score construction by automatic machine learning for treatment response prediction in elderly patients with diffuse large B-cell lymphoma: a multicenter study
Purpose To explore the development and validation of automated machine learning (AutoML) models for 18F-FDG PET imaging-based radiomics signatures to predict treatment response in elderly patients with diffuse large B-cell lymphoma (DLBCL). Methods A retrospective analysis was conducted on 175 elderly (≥ 60 years) DLBCL patients diagnosed between March 2015 and March 2023 at two medical centers, with a total of 1010 lesions. The baseline PET imaging-based radiomics features of the training cohort were processed using AutoML model AutoGluon to generate a radiomics score (radscore) and predict treatment response at the lesion and patient levels. Furthermore, a multivariable logistic analysis was used to design and evaluate a multivariable model in the training and validation cohorts. Results ROC curve analysis showed that the radscore generated by AutoML exhibited higher accuracy in predicting treatment response at the lesion level compared to metabolic parameters (SUVmax, MTV, and TLG) in both the training group (AUC: 0.791, 0.542, 0.667, 0.651, respectively) and the validation group (AUC: 0.712, 0.616, 0.639, 0.657, respectively). Multivariable logistic analysis indicated that NCCN-IPI (OR = 5.427, 95% CI: 1.163–25.317), BCL-2 (OR = 3.714, 95% CI: 1.406–9.816), TMTV (OR = 4.324, 95% CI: 1.095–17.067), and avg-radscore (OR = 3.176, 95% CI: 1.313-7. 686) were independent predictors of treatment response. The multivariable model comprising NCCN-IPI, BCL-2, TMTV, and avg-radscore outperformed conventional models and clinical-pathological models in predicting treatment response. (P<0.05). Conclusion The radscore generated by AutoML can predict the treatment response of elderly DLBCL patients, potentially aiding in clinical decision-making.
- 30 January 2025
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 52 (7) , 2384-2396
An explainable transformer model integrating PET and tabular data for histologic grading and prognosis of follicular lymphoma: a multi-institutional digital biopsy study
Background Pathological grade is a critical determinant of clinical outcomes and decision-making of follicular lymphoma (FL). This study aimed to develop a deep learning model as a digital biopsy for the non-invasive identification of FL grade. Methods This study retrospectively included 513 FL patients from five independent hospital centers, randomly divided into training, internal validation, and external validation cohorts. A multimodal fusion Transformer model was developed integrating 3D PET tumor images with tabular data to predict FL grade. Additionally, the model is equipped with explainable modules, including Gradient-weighted Class Activation Mapping (Grad-CAM) for PET images, SHapley Additive exPlanations analysis for tabular data, and the calculation of predictive contribution ratios for both modalities, to enhance clinical interpretability and reliability. The predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) and accuracy, and its prognostic value was also assessed. Results The Transformer model demonstrated high accuracy in grading FL, with AUCs of 0.964–0.985 and accuracies of 90.2-96.7% in the training cohort, and similar performance in the validation cohorts (AUCs: 0.936–0.971, accuracies: 86.4-97.0%). Ablation studies confirmed that the fusion model outperformed single-modality models (AUCs: 0.974 − 0.956, accuracies: 89.8%-85.8%). Interpretability analysis revealed that PET images contributed 81-89% of the predictive value. Grad-CAM highlighted the tumor and peri-tumor regions. The model also effectively stratified patients by survival risk (P < 0.05), highlighting its prognostic value. Conclusions Our study developed an explainable multimodal fusion Transformer model for accurate grading and prognosis of FL, with the potential to aid clinical decision-making. Graphical Abstract
- 30 January 2025
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 52 (7) , 2384-2396
An explainable transformer model integrating PET and tabular data for histologic grading and prognosis of follicular lymphoma: a multi-institutional digital biopsy study
Background Pathological grade is a critical determinant of clinical outcomes and decision-making of follicular lymphoma (FL). This study aimed to develop a deep learning model as a digital biopsy for the non-invasive identification of FL grade. Methods This study retrospectively included 513 FL patients from five independent hospital centers, randomly divided into training, internal validation, and external validation cohorts. A multimodal fusion Transformer model was developed integrating 3D PET tumor images with tabular data to predict FL grade. Additionally, the model is equipped with explainable modules, including Gradient-weighted Class Activation Mapping (Grad-CAM) for PET images, SHapley Additive exPlanations analysis for tabular data, and the calculation of predictive contribution ratios for both modalities, to enhance clinical interpretability and reliability. The predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) and accuracy, and its prognostic value was also assessed. Results The Transformer model demonstrated high accuracy in grading FL, with AUCs of 0.964–0.985 and accuracies of 90.2-96.7% in the training cohort, and similar performance in the validation cohorts (AUCs: 0.936–0.971, accuracies: 86.4-97.0%). Ablation studies confirmed that the fusion model outperformed single-modality models (AUCs: 0.974 − 0.956, accuracies: 89.8%-85.8%). Interpretability analysis revealed that PET images contributed 81-89% of the predictive value. Grad-CAM highlighted the tumor and peri-tumor regions. The model also effectively stratified patients by survival risk (P < 0.05), highlighting its prognostic value. Conclusions Our study developed an explainable multimodal fusion Transformer model for accurate grading and prognosis of FL, with the potential to aid clinical decision-making. Graphical Abstract
- 17 October 2024
- Published by Taylor & Francis in Future Oncology
- Vol. 20 (38) , 3107-3117
The clinical utility of plasma circulating tumor DNA in the diagnosis and disease surveillance in non-diffuse large B-cell non-Hodgkin lymphomas
Aim: Advances in circulating tumor DNA (ctDNA) analysis for diffuse large B-cell lymphoma (DLBCL) have prompted the evaluation of its utility in other non-Hodgkin lymphomas (NHLs), leading to significant insights into its potential applications.
- 17 October 2024
- Published by Taylor & Francis in Future Oncology
- Vol. 20 (38) , 3107-3117
The clinical utility of plasma circulating tumor DNA in the diagnosis and disease surveillance in non-diffuse large B-cell non-Hodgkin lymphomas
Aim: Advances in circulating tumor DNA (ctDNA) analysis for diffuse large B-cell lymphoma (DLBCL) have prompted the evaluation of its utility in other non-Hodgkin lymphomas (NHLs), leading to significant insights into its potential applications.
- Open Access
- 1 August 2024
- Published by Wiley in Cancer Medicine
- Vol. 13 (16) , e70178
Clinicopathological characteristics, prognostic factors, and outcomes of elderly patients with lymphoma‐associated hemophagocytic lymphohistiocytosis: A multicenter analysis
Background: Lymphoma is the most common secondary cause of hemophagocytic lymphohistiocytosis (HLH) in adults. Lymphoma‐associated HLH (LA‐HLH) in the elderly population is not rare, however, little has been reported regarding clinicopathological characteristics, prognostic factors, and outcomes of LA‐HLH in the elderly population.Methods: We retrospectively analyzed a multicenter cohort of elderly patients with LA‐HLH. Clinicopathological features and treatment information were collected. The impacts of baseline characteristics and treatments on survival outcomes were analyzed.Results: A total of 173 elderly patients with LA‐HLH were included. Compared with young patients, elderly patients showed different clinical and laboratory features. Regarding lymphoma subtypes, B‐cell lymphoma was more common in elderly patients (elderly 61.3% vs. young 32.3%, p < 0.001) while T/NK‐cell lymphoma was more common in young patients (65.3% vs. 35.3%, p < 0.001). The median survival of elderly patients with LA‐HLH was only 92 days. The prior use of HLH therapy or etoposide‐containing HLH therapy was not associated with improved overall survival. T/NK‐cell subtype, a lower platelet count (≤53 × 109/L), a lower albumin level (≤32.1 g/L), a higher LDH level (>1407 U/L), and a higher creatinine level (>96.8 μmol/L) were independent predictors of decreased overall survival and 60‐day survival. A prognostic index was established and demonstrated to be robust in predicting the overall survival and 60‐day survival of elderly patients with LA‐HLH.Conclusions: LA‐HLH in elderly patients displayed heterogeneous clinicopathological features and survival outcomes. Treatments need to be optimized to improve the outcomes of elderly patients with LA‐HLH.
- 1 August 2024
- Published by Wiley in Cancer Medicine
- Vol. 13 (16) , e70178
Open AccessClinicopathological characteristics, prognostic factors, and outcomes of elderly patients with lymphoma‐associated hemophagocytic lymphohistiocytosis: A multicenter analysis
Background: Lymphoma is the most common secondary cause of hemophagocytic lymphohistiocytosis (HLH) in adults. Lymphoma‐associated HLH (LA‐HLH) in the elderly population is not rare, however, little has been reported regarding clinicopathological characteristics, prognostic factors, and outcomes of LA‐HLH in the elderly population.Methods: We retrospectively analyzed a multicenter cohort of elderly patients with LA‐HLH. Clinicopathological features and treatment information were collected. The impacts of baseline characteristics and treatments on survival outcomes were analyzed.Results: A total of 173 elderly patients with LA‐HLH were included. Compared with young patients, elderly patients showed different clinical and laboratory features. Regarding lymphoma subtypes, B‐cell lymphoma was more common in elderly patients (elderly 61.3% vs. young 32.3%, p < 0.001) while T/NK‐cell lymphoma was more common in young patients (65.3% vs. 35.3%, p < 0.001). The median survival of elderly patients with LA‐HLH was only 92 days. The prior use of HLH therapy or etoposide‐containing HLH therapy was not associated with improved overall survival. T/NK‐cell subtype, a lower platelet count (≤53 × 109/L), a lower albumin level (≤32.1 g/L), a higher LDH level (>1407 U/L), and a higher creatinine level (>96.8 μmol/L) were independent predictors of decreased overall survival and 60‐day survival. A prognostic index was established and demonstrated to be robust in predicting the overall survival and 60‐day survival of elderly patients with LA‐HLH.Conclusions: LA‐HLH in elderly patients displayed heterogeneous clinicopathological features and survival outcomes. Treatments need to be optimized to improve the outcomes of elderly patients with LA‐HLH.
- Open Access
- 12 December 2023
- Published by Springer Nature in Research Square
[18F]FDG PET radiomics score generated by cross-combination approach for treatment response and prognosis prediction in primary gastrointestinal diffuse large B-cell lymphoma patients
Objectives We investigated the value of using a machine learning cross-combination approach to construct a PET radiomics score (RadScore) for predicting the early treatment response and prognosis of patients with primary gastrointestinal diffuse large B-cell lymphoma (PGI-DLBCL) treated with the R-CHOP-like regimen. Methods We conducted a retrospective analysis on 108 PGI-DLBCL patients diagnosed between November 2016 and December 2021. Seven machine learning models were used to generate 49 feature selection-classification candidates, and the optimal candidate was selected to create RadScore. Logistic regression identified risk factors, and a radiomics nomogram combining RadScore with selected risk factors was constructed. The model was evaluated using calibration curves and decision curve analysis (DCA). Results A total of 111 radiomics features were extracted, and 19 features with strong predictive performance were used to generate RadScore. Logistic regression analysis in the training cohort identified elevated lactate dehydrogenase (LDH) level, intestinal involvement, and total lesion glycolysis (TLG) as independent risk factors for predicting early treatment response. The multi-parameter model incorporating RadScore, clinical risk factors, and metabolic factors showed good performance (training cohort AUC: 0.860; validation cohort AUC: 0.902). The RadScore is capable of effectively stratifying patients' progression-free survival (PFS) and overall survival (OS). Conclusions The machine learning-based RadScore can predict the survival of PGI-DLBCL patients. When combined with clinical risk factors and metabolic factors, it forms a combinatorial model suitable for predicting early treatment response to R-CHOP-like chemotherapy regimens.
- 12 December 2023
- Published by Springer Nature in Research Square
Open Access[18F]FDG PET radiomics score generated by cross-combination approach for treatment response and prognosis prediction in primary gastrointestinal diffuse large B-cell lymphoma patients
Objectives We investigated the value of using a machine learning cross-combination approach to construct a PET radiomics score (RadScore) for predicting the early treatment response and prognosis of patients with primary gastrointestinal diffuse large B-cell lymphoma (PGI-DLBCL) treated with the R-CHOP-like regimen. Methods We conducted a retrospective analysis on 108 PGI-DLBCL patients diagnosed between November 2016 and December 2021. Seven machine learning models were used to generate 49 feature selection-classification candidates, and the optimal candidate was selected to create RadScore. Logistic regression identified risk factors, and a radiomics nomogram combining RadScore with selected risk factors was constructed. The model was evaluated using calibration curves and decision curve analysis (DCA). Results A total of 111 radiomics features were extracted, and 19 features with strong predictive performance were used to generate RadScore. Logistic regression analysis in the training cohort identified elevated lactate dehydrogenase (LDH) level, intestinal involvement, and total lesion glycolysis (TLG) as independent risk factors for predicting early treatment response. The multi-parameter model incorporating RadScore, clinical risk factors, and metabolic factors showed good performance (training cohort AUC: 0.860; validation cohort AUC: 0.902). The RadScore is capable of effectively stratifying patients' progression-free survival (PFS) and overall survival (OS). Conclusions The machine learning-based RadScore can predict the survival of PGI-DLBCL patients. When combined with clinical risk factors and metabolic factors, it forms a combinatorial model suitable for predicting early treatment response to R-CHOP-like chemotherapy regimens.
- Open Access
- 28 November 2023
- Published by American Society of Hematology in Blood
- Vol. 142 (Supplement) , 4478
PET Radiomics Score Generated By Cross-Combination Approach for Treatment Response and Prognosis Prediction in Primary Gastrointestinal Diffuse Large B-Cell Lymphoma Patients
Background: Current risk stratification for primary gastrointestinal diffuse large B-cell lymphoma(PGI-DLBCL) relies on mainly on clinical factors. Radiomics score (RadScore) associated with survival outcomes have been developed for other cancer types, however few studies have thus far examined the role of radiomics in PGI-DLBCL. Objective: In this study, we investigated the value of PET RadScore constructed using a machine learning cross-combination approach in predicting the early treatment response and prognosis of patients with primary gastrointestinal diffuse large B-cell lymphoma (PGI-DLBCL) treated with the R-CHOP-like regimen. Methods: A retrospective analysis was conducted on 108 PGI-DLBCL patients diagnosed through histopathological examination at two independent medical centers from March 2011 to March 2023, with 86 patients in the training cohort and 22 patients in the validation cohort. Seven different machine learning models were used to generate 49 feature selection-classification candidates, and the optimal candidate was selected based on the area under curve of ROC to establish RadScore. Risk factors were identified through logistic regression, and a radiomics nomogram was constructed by combining RadScore with the selected risk factors. The model was evaluated through calibration curves and decision curve analysis (DCA) using the training cohort and validation cohort. Results:A total of 111 radiomics features were extracted, and 19 features with strong predictive performance were selected to generate RadScore. The results suggest that RadScore can stratify patient prognosis.The logistic regression analysis results in the training cohort showed that elevated lactate dehydrogenase (LDH) level (OR=3.53, 95%CI: 1.21-10.31, p=0.021), intestinal involvement (OR=3.04, 95%CI: 1.04-8.88, p=0.042), and total lesion glycolysis (TLG) (OR=6.73, 95%CI: 2.23-20.29, p<0.001) were independent risk factors for predicting early treatment response. A multi-parameter model incorporating clinical risk factors, metabolic factors, and RadScore was constructed (training cohort AUC: 0.834; validation cohort AUC: 0.902), and the performance of the model was evaluated. Conclusion:The RadScore, constructed based on a cross-combination approach using machine learning, can predict the survival of PGI-DLBCL patients. When RadScore is combined with clinical risk factors and metabolic factors, it forms a combinatorial model suitable for predicting early treatment response to R-CHOP-like chemotherapy regimens. Larger studies will be needed to validate these results. Keywords : Primary gastrointestinal diffuse large B-cell lymphoma · [18F]FDG PET/CT · Early treatment response · Prognosis · Machine learning No relevant conflicts of interest to declare.
- 28 November 2023
- Published by American Society of Hematology in Blood
- Vol. 142 (Supplement) , 4478
Open AccessPET Radiomics Score Generated By Cross-Combination Approach for Treatment Response and Prognosis Prediction in Primary Gastrointestinal Diffuse Large B-Cell Lymphoma Patients
Background: Current risk stratification for primary gastrointestinal diffuse large B-cell lymphoma(PGI-DLBCL) relies on mainly on clinical factors. Radiomics score (RadScore) associated with survival outcomes have been developed for other cancer types, however few studies have thus far examined the role of radiomics in PGI-DLBCL. Objective: In this study, we investigated the value of PET RadScore constructed using a machine learning cross-combination approach in predicting the early treatment response and prognosis of patients with primary gastrointestinal diffuse large B-cell lymphoma (PGI-DLBCL) treated with the R-CHOP-like regimen. Methods: A retrospective analysis was conducted on 108 PGI-DLBCL patients diagnosed through histopathological examination at two independent medical centers from March 2011 to March 2023, with 86 patients in the training cohort and 22 patients in the validation cohort. Seven different machine learning models were used to generate 49 feature selection-classification candidates, and the optimal candidate was selected based on the area under curve of ROC to establish RadScore. Risk factors were identified through logistic regression, and a radiomics nomogram was constructed by combining RadScore with the selected risk factors. The model was evaluated through calibration curves and decision curve analysis (DCA) using the training cohort and validation cohort. Results:A total of 111 radiomics features were extracted, and 19 features with strong predictive performance were selected to generate RadScore. The results suggest that RadScore can stratify patient prognosis.The logistic regression analysis results in the training cohort showed that elevated lactate dehydrogenase (LDH) level (OR=3.53, 95%CI: 1.21-10.31, p=0.021), intestinal involvement (OR=3.04, 95%CI: 1.04-8.88, p=0.042), and total lesion glycolysis (TLG) (OR=6.73, 95%CI: 2.23-20.29, p<0.001) were independent risk factors for predicting early treatment response. A multi-parameter model incorporating clinical risk factors, metabolic factors, and RadScore was constructed (training cohort AUC: 0.834; validation cohort AUC: 0.902), and the performance of the model was evaluated. Conclusion:The RadScore, constructed based on a cross-combination approach using machine learning, can predict the survival of PGI-DLBCL patients. When RadScore is combined with clinical risk factors and metabolic factors, it forms a combinatorial model suitable for predicting early treatment response to R-CHOP-like chemotherapy regimens. Larger studies will be needed to validate these results. Keywords : Primary gastrointestinal diffuse large B-cell lymphoma · [18F]FDG PET/CT · Early treatment response · Prognosis · Machine learning No relevant conflicts of interest to declare.
- 9 November 2023
- Published by Springer Nature in Apoptosis
- Vol. 29 (1-2) , 66-85
New prospects of cancer therapy based on pyroptosis and pyroptosis inducers
Pyroptosis is a gasdermin-mediated programmed cell death (PCD) pathway. It differs from apoptosis because of the secretion of inflammatory molecules. Pyroptosis is closely associated with various malignant tumors. Recent studies have demonstrated that pyroptosis can either inhibit or promote the development of malignant tumors, depending on the cell type (immune or cancer cells) and duration and severity of the process. This review summarizes the molecular mechanisms of pyroptosis, its relationship with malignancies, and focuses on current pyroptosis inducers and their significance in cancer treatment. The molecules involved in the pyroptosis signaling pathway could serve as therapeutic targets for the development of novel drugs for cancer therapy. In addition, we analyzed the potential of combining pyroptosis with conventional anticancer techniques as a promising strategy for cancer treatment.
- 9 November 2023
- Published by Springer Nature in Apoptosis
- Vol. 29 (1-2) , 66-85
New prospects of cancer therapy based on pyroptosis and pyroptosis inducers
Pyroptosis is a gasdermin-mediated programmed cell death (PCD) pathway. It differs from apoptosis because of the secretion of inflammatory molecules. Pyroptosis is closely associated with various malignant tumors. Recent studies have demonstrated that pyroptosis can either inhibit or promote the development of malignant tumors, depending on the cell type (immune or cancer cells) and duration and severity of the process. This review summarizes the molecular mechanisms of pyroptosis, its relationship with malignancies, and focuses on current pyroptosis inducers and their significance in cancer treatment. The molecules involved in the pyroptosis signaling pathway could serve as therapeutic targets for the development of novel drugs for cancer therapy. In addition, we analyzed the potential of combining pyroptosis with conventional anticancer techniques as a promising strategy for cancer treatment.