Mingyang Hou
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
Mingyang Hou has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Zhiyong Huang
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, 400044, China; Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University), Ministry of Education of China, Chongqing University, Chongqing, 400044, China
16 shared publications - Zhi Yu
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
15 shared publications - Yan Yan
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
13 shared publications - Yushi Liu
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China
12 shared publications - Xiaoyu Li
Bioengineering College, Chongqing University, Chongqing, China
8 shared publications - Jiahong Wang
The Second Medical Center, Health Management Institute, National Clinical Research Center for Geriatric Diseases, Chinese PLA General Hospital, Beijing, 100853, China
5 shared publications
Latest Publications
- 12 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Bridging teacher–student representation domains for manifold-aware knowledge distillation
- 12 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Bridging teacher–student representation domains for manifold-aware knowledge distillation
- Open Access
- 4 August 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e83889
Prediction of Blood Transfusion Need and Dose in Patients With Upper Gastrointestinal Bleeding: Retrospective Multicenter Prediction Model Study
Background: Transfusion thresholds in upper gastrointestinal bleeding are debated; hemoglobin cutoffs of 70‐80 g/L are widely cited yet inconsistently applied. Common risk scores offer limited individualized guidance and rarely provide calibrated, interpretable predictions for transfusion decisions. Objective: This study aimed to develop and validate a two-stage, clinically constrained gradient-boosting framework (Medically Constrained Gradient Boosting [MCGB]) that predicts transfusion need and estimates transfusion dose with quantified uncertainty and to implement a prototype recommendation system for clinical use. Methods: We analyzed a retrospective multicenter cohort of 849 adults with endoscopically confirmed upper gastrointestinal bleeding admitted to 3 hospitals in Chongqing, China (January 2019 to August 2025). Predictors available before the transfusion decision included demographics, first recorded vital signs, initial laboratory indices, and clinician-adjudicated etiology. Stage 1 used a calibrated classifier with prespecified monotonic constraints and stability-screened, clinically justified interactions. Stage 2 modeled transfusion dose via quantile predictions with conformal adjustment to generate 95% prediction intervals. Performance was assessed using a cross-site hold-out design. Overall, 2 hospitals were used as the development cohort, within which stratified 5-fold cross-validation was performed for model development, hyperparameter tuning, interaction screening, and calibration. The remaining hospital was held out as an independent test cohort for final evaluation. Hospital-wise alternating external testing was further conducted as a supplementary robustness analysis to assess performance stability across institutions. Classification performance was evaluated using discrimination metrics (area under the receiver operating characteristic curve and area under the precision-recall curve), calibration metrics, and decision-curve analysis; regression performance was evaluated using R ², mean absolute error, and prediction-interval coverage. A graphical user interface was implemented to enable clinicians to input patient data and obtain calibrated predictions of transfusion probability and corresponding dose recommendations. Results: MCGB achieved strong discrimination and good calibration across subgroups (area under the receiver operating characteristic curve=0.97 and area under the precision-recall curve=0.91). At a reference probability threshold of .50, sensitivity, specificity, and F 1 -scores were 0.99, 0.87, and 0.85, respectively, providing a representative operating point for comparison. For dose prediction among transfused patients, MCGB achieved R ² of 0.95 and mean absolute error 0.04; 95% prediction-interval coverage was 0.94, indicating accurate point estimates with reliable uncertainty quantification. The software prototype further demonstrated feasibility of real-time decision support at the bedside. Conclusions: MCGB provides calibrated, interpretable predictions of transfusion need and individualized dose in upper gastrointestinal bleeding and may support bedside decision-making and blood-bank planning, with a prototype interface demonstrating potential for clinical deployment. External validation in additional settings is warranted to confirm generalizability.
- 4 August 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e83889
Open AccessPrediction of Blood Transfusion Need and Dose in Patients With Upper Gastrointestinal Bleeding: Retrospective Multicenter Prediction Model Study
Background: Transfusion thresholds in upper gastrointestinal bleeding are debated; hemoglobin cutoffs of 70‐80 g/L are widely cited yet inconsistently applied. Common risk scores offer limited individualized guidance and rarely provide calibrated, interpretable predictions for transfusion decisions. Objective: This study aimed to develop and validate a two-stage, clinically constrained gradient-boosting framework (Medically Constrained Gradient Boosting [MCGB]) that predicts transfusion need and estimates transfusion dose with quantified uncertainty and to implement a prototype recommendation system for clinical use. Methods: We analyzed a retrospective multicenter cohort of 849 adults with endoscopically confirmed upper gastrointestinal bleeding admitted to 3 hospitals in Chongqing, China (January 2019 to August 2025). Predictors available before the transfusion decision included demographics, first recorded vital signs, initial laboratory indices, and clinician-adjudicated etiology. Stage 1 used a calibrated classifier with prespecified monotonic constraints and stability-screened, clinically justified interactions. Stage 2 modeled transfusion dose via quantile predictions with conformal adjustment to generate 95% prediction intervals. Performance was assessed using a cross-site hold-out design. Overall, 2 hospitals were used as the development cohort, within which stratified 5-fold cross-validation was performed for model development, hyperparameter tuning, interaction screening, and calibration. The remaining hospital was held out as an independent test cohort for final evaluation. Hospital-wise alternating external testing was further conducted as a supplementary robustness analysis to assess performance stability across institutions. Classification performance was evaluated using discrimination metrics (area under the receiver operating characteristic curve and area under the precision-recall curve), calibration metrics, and decision-curve analysis; regression performance was evaluated using R ², mean absolute error, and prediction-interval coverage. A graphical user interface was implemented to enable clinicians to input patient data and obtain calibrated predictions of transfusion probability and corresponding dose recommendations. Results: MCGB achieved strong discrimination and good calibration across subgroups (area under the receiver operating characteristic curve=0.97 and area under the precision-recall curve=0.91). At a reference probability threshold of .50, sensitivity, specificity, and F 1 -scores were 0.99, 0.87, and 0.85, respectively, providing a representative operating point for comparison. For dose prediction among transfused patients, MCGB achieved R ² of 0.95 and mean absolute error 0.04; 95% prediction-interval coverage was 0.94, indicating accurate point estimates with reliable uncertainty quantification. The software prototype further demonstrated feasibility of real-time decision support at the bedside. Conclusions: MCGB provides calibrated, interpretable predictions of transfusion need and individualized dose in upper gastrointestinal bleeding and may support bedside decision-making and blood-bank planning, with a prototype interface demonstrating potential for clinical deployment. External validation in additional settings is warranted to confirm generalizability.
- 25 June 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109293
Integrating visual and language cues via state space models for medical image segmentation
- 25 June 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109293
Integrating visual and language cues via state space models for medical image segmentation
- Open Access
- 7 April 2026
- Published by BMJ in BMJ Open Gastroenterology
- Vol. 13 (1) , e002212
Dyssynergia phenotypes in obstructed defecation: insights from Fecobionics assessment
Objective: Obstructed defecation syndrome (ODS) is a chronic constipation subtype. Conventional tests are limited by non-physiological conditions and poor correlation with symptoms. This study investigated anorectal dynamics and dyssynergia phenotypes in patients with ODS using Fecobionics. Methods: This study was designed as a prospective observational study including 10 control subjects and 25 patients with ODS. All measurements were performed according to a predefined protocol. All patients with ODS underwent clinical evaluation, anorectal manometry (ARM) and defecography. Fecobionics recorded anorectal pressures, sensation and expulsion performance. Expulsion dynamics were further analysed using preload–afterload diagrams to characterise dyssynergia subtypes. Results: Compared with the control group, the ODS group showed prolonged expulsion time (76 (23–120) vs 18.7 s (10.6–34), p<0.01), reduced effective propulsive force (P_delta) (26.2 (8.6–35.9) vs 48.2 cmH₂O (32.5–88.0), p<0.01), increased number of contractions (7 (4–14) vs 2.5 (1.3–3.8), p<0.01) and higher paradoxical contraction rates (71% (50–100) vs 0% (0–44), p<0.01). ARM during attempted evacuation (push) demonstrated lower anal relaxation rates in the ODS group (16% (12–37) vs 36% (27–44), p<0.03). Correlation analyses demonstrated that impaired Fecobionics metrics were associated with greater symptom burden. Three dyssynergia phenotypes were identified: multiple simultaneous contractions, insufficient or delayed anal relaxation and persistently elevated outlet pressure. Conclusion: Fecobionics enables integrated and physiologically relevant assessment of anorectal function and identifies distinct dyssynergia phenotypes in ODS, reflecting heterogeneous mechanisms of outlet obstruction with implications for individualised management. Study registration: ChiCTR2300078807.
- 7 April 2026
- Published by BMJ in BMJ Open Gastroenterology
- Vol. 13 (1) , e002212
Open AccessDyssynergia phenotypes in obstructed defecation: insights from Fecobionics assessment
Objective: Obstructed defecation syndrome (ODS) is a chronic constipation subtype. Conventional tests are limited by non-physiological conditions and poor correlation with symptoms. This study investigated anorectal dynamics and dyssynergia phenotypes in patients with ODS using Fecobionics. Methods: This study was designed as a prospective observational study including 10 control subjects and 25 patients with ODS. All measurements were performed according to a predefined protocol. All patients with ODS underwent clinical evaluation, anorectal manometry (ARM) and defecography. Fecobionics recorded anorectal pressures, sensation and expulsion performance. Expulsion dynamics were further analysed using preload–afterload diagrams to characterise dyssynergia subtypes. Results: Compared with the control group, the ODS group showed prolonged expulsion time (76 (23–120) vs 18.7 s (10.6–34), p<0.01), reduced effective propulsive force (P_delta) (26.2 (8.6–35.9) vs 48.2 cmH₂O (32.5–88.0), p<0.01), increased number of contractions (7 (4–14) vs 2.5 (1.3–3.8), p<0.01) and higher paradoxical contraction rates (71% (50–100) vs 0% (0–44), p<0.01). ARM during attempted evacuation (push) demonstrated lower anal relaxation rates in the ODS group (16% (12–37) vs 36% (27–44), p<0.03). Correlation analyses demonstrated that impaired Fecobionics metrics were associated with greater symptom burden. Three dyssynergia phenotypes were identified: multiple simultaneous contractions, insufficient or delayed anal relaxation and persistently elevated outlet pressure. Conclusion: Fecobionics enables integrated and physiologically relevant assessment of anorectal function and identifies distinct dyssynergia phenotypes in ODS, reflecting heterogeneous mechanisms of outlet obstruction with implications for individualised management. Study registration: ChiCTR2300078807.
- 11 March 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 111, 104037
Eliminating domain-related confounding factors in cross-domain one-shot medical image segmentation via causal inference
- 11 March 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 111, 104037
Eliminating domain-related confounding factors in cross-domain one-shot medical image segmentation via causal inference
- 21 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
Enhancing Radiography-Report foundation model via Multi-View masked contrastive learning
- 21 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
Enhancing Radiography-Report foundation model via Multi-View masked contrastive learning
- 26 December 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 335
BACFormer: A robust boundary-aware transformer for medical image segmentation
- 26 December 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 335
BACFormer: A robust boundary-aware transformer for medical image segmentation
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 5301-5314
Overcoming Limitations in One-Shot Semantic Segmentation via Adaptive Visual-Text Guided Prototype Relationship Optimization
The scarcity of high-quality annotated data in medical imaging significantly constrains the performance of deep learning-based segmentation models. While few-shot medical image segmentation (FSMIS) has emerged as a promising solution, existing methods exhibit critical limitations when handling scenarios with inter-class similarity between foreground-background regions and intra-class heterogeneity within foreground objects. Current prototype-based approaches focus primarily on the holistic extraction of the prototype from support images, failing to distinguish subtle anatomical variations and complex feature representations effectively. The AVT-ProNet features three innovative components: 1) An Adaptive Visual-Text Prototype Generation (AVPG) module leveraging CLIP’s cross-modal guide capabilities through adaptive prompting strategies; 2) a graph-based multiregion prototyping relationship optimization (GMPRO) module establishing structural relationships between decomposed subregion prototypes via graph neural networks; 3) a foreground-background prototyping contrast learning (FBPCL) strategy implementing dual-space optimization through inter-class separation and intra-class compactness. The synergistic integration of multi-modal guidance, structural relationship modeling, and contrastive prototype refinement enables our framework to overcome existing limitations in FSMIS. Comprehensive evaluations across multiple clinical scenarios (CHAOS, SABS, and CMR datasets under diverse training configurations) demonstrate superior performance over state-of-the-art approaches, including PANet, CAT-Net, DMAP, and recent PAMI baselines, Source code is available at https://github.com/394481125/AVT-ProNet.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 5301-5314
Overcoming Limitations in One-Shot Semantic Segmentation via Adaptive Visual-Text Guided Prototype Relationship Optimization
The scarcity of high-quality annotated data in medical imaging significantly constrains the performance of deep learning-based segmentation models. While few-shot medical image segmentation (FSMIS) has emerged as a promising solution, existing methods exhibit critical limitations when handling scenarios with inter-class similarity between foreground-background regions and intra-class heterogeneity within foreground objects. Current prototype-based approaches focus primarily on the holistic extraction of the prototype from support images, failing to distinguish subtle anatomical variations and complex feature representations effectively. The AVT-ProNet features three innovative components: 1) An Adaptive Visual-Text Prototype Generation (AVPG) module leveraging CLIP’s cross-modal guide capabilities through adaptive prompting strategies; 2) a graph-based multiregion prototyping relationship optimization (GMPRO) module establishing structural relationships between decomposed subregion prototypes via graph neural networks; 3) a foreground-background prototyping contrast learning (FBPCL) strategy implementing dual-space optimization through inter-class separation and intra-class compactness. The synergistic integration of multi-modal guidance, structural relationship modeling, and contrastive prototype refinement enables our framework to overcome existing limitations in FSMIS. Comprehensive evaluations across multiple clinical scenarios (CHAOS, SABS, and CMR datasets under diverse training configurations) demonstrate superior performance over state-of-the-art approaches, including PANet, CAT-Net, DMAP, and recent PAMI baselines, Source code is available at https://github.com/394481125/AVT-ProNet.
- Open Access
- 10 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Medically-Constrained Gradient Boosting for Predicting Blood Transfusion Need and Dose in Upper Gastrointestinal Bleeding (Preprint)
BACKGROUND Transfusion thresholds in upper gastrointestinal bleeding (UGIB) are debated; hemoglobin cutoffs of 70–80 g/L are widely cited yet inconsistently applied. Common risk scores offer limited individualized guidance and rarely provide calibrated, interpretable predictions for transfusion decisions. OBJECTIVE To develop and validate a two-stage, clinically constrained gradient-boosting framework (Medically-Constrained Gradient Boosting, MGCB) that predicts transfusion need and estimates transfusion dose with quantified uncertainty, and to implement a prototype recommendation system for clinical use. METHODS We analyzed a retrospective multicenter cohort of 849 adults with endoscopically confirmed UGIB admitted to three hospitals in Chongqing, China (January 2019–August 2025). Predictors available before the transfusion decision included demographics, first recorded vital signs, initial laboratory indices, and clinician-adjudicated etiology. Stage 1 used a calibrated classifier with prespecified monotonic constraints and stability-screened, clinically justified interactions. Stage 2 modeled transfusion dose via quantile predictions with conformal adjustment to generate 95% prediction intervals. Performance was assessed using stratified five-fold cross-validation with discrimination (AUROC, AUPRC), calibration metrics and decision-curve analysis; regression performance included R², mean absolute error (MAE), and prediction-interval coverage. A graphical user interface was implemented to allow clinician input of patient data and to return calibrated transfusion probabilities and dose recommendations. RESULTS MGCB achieved strong discrimination and good calibration across subgroups (AUROC 0.97; AUPRC 0.91). At a probability threshold of 0.50, sensitivity, specificity, and F1 score were 0.99, 0.87, and 0.85, respectively. For dose prediction among transfused patients, MGCB achieved R² 0.95 and MAE 0.04; 95% prediction-interval coverage was 0.94, indicating accurate point estimates with reliable uncertainty quantification. The software prototype further demonstrated feasibility of real-time decision support at the bedside. CONCLUSIONS MGCB provides calibrated, interpretable predictions of transfusion need and individualized dose in UGIB and may support bedside decision-making and blood-bank planning, with a prototype interface demonstrating potential for clinical deployment. External validation in additional settings is warranted to confirm generalizability. CLINICALTRIAL Not applicable. This study does not involve a registered clinical trial or systematic review.
- 10 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessMedically-Constrained Gradient Boosting for Predicting Blood Transfusion Need and Dose in Upper Gastrointestinal Bleeding (Preprint)
BACKGROUND Transfusion thresholds in upper gastrointestinal bleeding (UGIB) are debated; hemoglobin cutoffs of 70–80 g/L are widely cited yet inconsistently applied. Common risk scores offer limited individualized guidance and rarely provide calibrated, interpretable predictions for transfusion decisions. OBJECTIVE To develop and validate a two-stage, clinically constrained gradient-boosting framework (Medically-Constrained Gradient Boosting, MGCB) that predicts transfusion need and estimates transfusion dose with quantified uncertainty, and to implement a prototype recommendation system for clinical use. METHODS We analyzed a retrospective multicenter cohort of 849 adults with endoscopically confirmed UGIB admitted to three hospitals in Chongqing, China (January 2019–August 2025). Predictors available before the transfusion decision included demographics, first recorded vital signs, initial laboratory indices, and clinician-adjudicated etiology. Stage 1 used a calibrated classifier with prespecified monotonic constraints and stability-screened, clinically justified interactions. Stage 2 modeled transfusion dose via quantile predictions with conformal adjustment to generate 95% prediction intervals. Performance was assessed using stratified five-fold cross-validation with discrimination (AUROC, AUPRC), calibration metrics and decision-curve analysis; regression performance included R², mean absolute error (MAE), and prediction-interval coverage. A graphical user interface was implemented to allow clinician input of patient data and to return calibrated transfusion probabilities and dose recommendations. RESULTS MGCB achieved strong discrimination and good calibration across subgroups (AUROC 0.97; AUPRC 0.91). At a probability threshold of 0.50, sensitivity, specificity, and F1 score were 0.99, 0.87, and 0.85, respectively. For dose prediction among transfused patients, MGCB achieved R² 0.95 and MAE 0.04; 95% prediction-interval coverage was 0.94, indicating accurate point estimates with reliable uncertainty quantification. The software prototype further demonstrated feasibility of real-time decision support at the bedside. CONCLUSIONS MGCB provides calibrated, interpretable predictions of transfusion need and individualized dose in UGIB and may support bedside decision-making and blood-bank planning, with a prototype interface demonstrating potential for clinical deployment. External validation in additional settings is warranted to confirm generalizability. CLINICALTRIAL Not applicable. This study does not involve a registered clinical trial or systematic review.