Objective:To develop and validate machine learning-based radiomics models using preoperative CT images for individualized prediction of mitotic index (MI) in patients with gastrointestinal stromal tumors (GIST).Methods:The study was a case-control study. The data of 348 GIST patients confirmed by pathology were retrospectively collected from two independent medical centers: the Affiliated Hospital of Qingdao University (center 1) and Shandong Provincial Hospital Affiliated to Shandong First Medical University (center 2), covering the period from January 2013 to June 2018. Patients from center 1 were divided into a training cohort (176 cases) and an internal validation cohort (75 cases) at a ratio of 7∶3 using random sampling. Patients from center 2 served as an independent external validation cohort (97 cases). The primary endpoint was MI, categorized into high MI (145 cases) and low MI (203 cases) groups. Radiomic features were extracted from the portal venous phase images of preoperative contrast-enhanced CT scans. Five machine learning algorithms, including logistic regression, support vector machine, random forest, decision tree, and extreme gradient boosting (XGBoost),were employed to construct MI prediction models. The optimal model was identified using receiver operating characteristic curves. An individualized prediction model was developed by integrating the the optimal machine learning model combined with selected independent clinical factors, and the importance of features was visualized using Shapley Additive Explanation (SHAP) analysis. Patients were followed up, and Kaplan-Meier curves along with log-rank tests were used to evaluate recurrence-free survival (RFS) differences between the predicted high MI and low MI groups.Results:Among the five constructed machine learning models, the XGBoost model demonstrated the best predictive performance, with area under the curve (AUC) of 0.809 (95% CI 0.738-0.872), 0.693 (95% CI 0.571-0.809), and 0.718 (95% CI 0.605-0.822) in the training cohort, internal validation cohort, and external validation cohort, respectively. An individualized prediction model combining the XGBoost model with independent clinical factors (tumor location and tumor size) was developed. The model achieved AUC of 0.843 (95% CI 0.785-0.899), 0.791 (95% CI 0.680-0.894), and 0.777 (95% CI 0.678-0.861) in the training cohort, internal validation cohort, and external validation cohort, respectively. SHAP analysis indicated that radiomic features had the highest predictive impact. In both the training cohort and internal validation cohort, the RFS of patients predicted to be in the high MI group was lower than that of the low MI group, with statistically significant differences ( χ2=14.58, 9.52, both P<0.001). However, there was no statistically significant difference in RFS in the external validation set ( χ2=6.18, P=0.080). Conclusions:The optimal XGBoost model based on radiomic features extracted from preoperative portal venous phase CT images, when combined with clinical factors, can effectively predict the MI of GIST patients.

Objective:To develop an artificial intelligence (AI)-based automatic scoring model for magnetic resonance imaging-detected extramural vascular invasion (AI-mrEMVI) and evaluate its performance and prognostic value in patients with rectal cancer.Methods:In this multicenter retrospective cohort study, a total of 2 501 rectal cancer patients from seven centers between November 2012 and December 2020 were included and divided into completely independent training ( n=1 830) and validation ( n=671) cohorts. A nnUNet-based AI-mrEMVI scoring model was constructed. Manual mrEMVI scores assigned by two radiologists served as the reference standard for accessing the accuracy of the AI-mrEMVI scoring. Kaplan-Meier survival analysis and Cox regression were used to evaluate the prognostic stratification ability of the AI-mrEMVI scores. The concordance index (C-index) was calculated to evaluate prognostic performance. Results:In the validation cohort, the manual mrEMVI scores were 0-2 in 425 patients (63.3%), 3 in 89 (13.4%), and 4 in 157 (23.4%). The AI-mrEMVI model identified 0-2 in 375 patients (55.9%), 3 in 95 (14.2%), and 4 in 201 (30.0%), with an overall accuracy of 81.1% (544/671, 95% CI 77.9%-84.0%). The 3-year disease-free survival (DFS) rates for patients with AI-mrEMVI scores of 0-2, 3, and 4 were 85.2%, 70.0%, and 58.2%, respectively, and the 5-year overall survival (OS) rates were 87.2%, 81.6%, and 62.6%, respectively (DFS: χ2=48.74, P<0.001; OS: χ2=30.04, P<0.001). Multivariable Cox regression showed that for DFS, AI-mrEMVI scores of 3 and 4 were associated with hazard ratios ( HR) of 1.75 (95% CI 1.11-2.77, P=0.016) and 2.65 (95% CI 1.86-3.78, P<0.001), respectively. For OS, an AI-mrEMVI score of 4 was associated with an HR of 2.56 (95% CI 1.62-4.03, P<0.001). The C-index values of the AI-mrEMVI scoring model for predicting DFS and OS were 0.647 (95% CI 0.608-0.686) and 0.650 (95% CI 0.598-0.702), respectively. Conclusion:The proposed AI-mrEMVI automatic scoring model demonstrated high diagnostic accuracy and performed favorably in predicting DFS and OS prognostic risk in patients with rectal cancer.

Medical imaging large-scale models demonstrate broad application prospects in the field of tumor diagnosis and treatment.Their powerful high-dimensional feature extraction and data analysis capabilities have brought revolutionary breakthroughs to precision oncology,driving the transformation of diagnostic and therapeutic paradigms.However,current research in this field still faces numerous challenges and technical bot-tlenecks.Based on the research background of artificial intelligence(AI)large-scale models,this article sys-tematically reviews the current research status of medical imaging large-scale models from three key dimensions:the construction of large-scale medical imaging datasets,optimization of large-scale model algorithms,and com-putational resource requirements.Furthermore,it elaborates on the application scenarios of these models in pre-cision oncology and provides a forward-looking perspective on their future development.The aim is to offer prac-tical guidance for advancing precision diagnosis and treatment of tumors.

Objective To evaluate the diagnostic value of dual-layer spectral CT(DLCT)virtual non-contrast(VNC)imaging combined with iodine maps in differentiating early post-endovascular therapy(EVT)intracranial hemorrhage from contrast extravasation.Methods Retrospective analysis of 97 patients who underwent DLCT immediately after EVT was conducted.Taking 24-hour follow-up CT/MRI as the gold standard,patients were divided into hemorrhage and non-hemorrhage groups,and their clinical data were compared.VNC CT values and iodine concentration(IC)were measured.Spearman's rank correlation was used to analyze the relationship between VNC CT and IC values,and ROC curve analysis using R software to evaluate the diagnostic performance of VNC,iodine maps,and their combination.Results Among 97 patients,51(52.6%)showed no intracranial hyperdense lesions,while 46(47.4%)with abnormal densities were analyzed.Using 24-hour postoperative CT/MRI as reference stan-dard,among the 46 patients ultimately included in the analysis,38 cases(82.6%)were non-hemorrhagic and 8 cases(17.4%)hemorrhagic.No significant differences existed in age,sex,or treatment methods(all P>0.05).VNC CT values and IC showed significantly negative correlation(r=-0.537,P<0.01).ROC analysis revealed AUCs of 0.917(95%CI:0.786～0.999)for VNC,0.878(95%CI:0.719～0.999)for IC,and 0.919(95%CI:0.812～0.999)for the combination of the two(P<0.05 for combined vs.individual methods).Optimal thresholds were 53.6 HU for VNC and 0.605 mg/ml for IC.Based on the final analysis of 46 enrolled patients,the sensitivity of VNC,iodine map,and their combination in differentiating early cerebral hemorrhage from contrast extravasation was 88.9%,94.3%,and 91.4%,respectively;the specificity 94.3%,77.8%,and 88.9%,respectively;and the accuracy 90.9%,90.9%,and 93.2%,respectively.Conclusion The DLCT VNC-iodine map combination significantly im-proves differentiation between post-EVT hemorrhage and contrast extravasation,and it is recommended for routine clinical application.

Medical imaging large-scale models demonstrate broad application prospects in the field of tumor diagnosis and treatment.Their powerful high-dimensional feature extraction and data analysis capabilities have brought revolutionary breakthroughs to precision oncology,driving the transformation of diagnostic and therapeutic paradigms.However,current research in this field still faces numerous challenges and technical bot-tlenecks.Based on the research background of artificial intelligence(AI)large-scale models,this article sys-tematically reviews the current research status of medical imaging large-scale models from three key dimensions:the construction of large-scale medical imaging datasets,optimization of large-scale model algorithms,and com-putational resource requirements.Furthermore,it elaborates on the application scenarios of these models in pre-cision oncology and provides a forward-looking perspective on their future development.The aim is to offer prac-tical guidance for advancing precision diagnosis and treatment of tumors.

Objective To evaluate the diagnostic value of dual-layer spectral CT(DLCT)virtual non-contrast(VNC)imaging combined with iodine maps in differentiating early post-endovascular therapy(EVT)intracranial hemorrhage from contrast extravasation.Methods Retrospective analysis of 97 patients who underwent DLCT immediately after EVT was conducted.Taking 24-hour follow-up CT/MRI as the gold standard,patients were divided into hemorrhage and non-hemorrhage groups,and their clinical data were compared.VNC CT values and iodine concentration(IC)were measured.Spearman's rank correlation was used to analyze the relationship between VNC CT and IC values,and ROC curve analysis using R software to evaluate the diagnostic performance of VNC,iodine maps,and their combination.Results Among 97 patients,51(52.6%)showed no intracranial hyperdense lesions,while 46(47.4%)with abnormal densities were analyzed.Using 24-hour postoperative CT/MRI as reference stan-dard,among the 46 patients ultimately included in the analysis,38 cases(82.6%)were non-hemorrhagic and 8 cases(17.4%)hemorrhagic.No significant differences existed in age,sex,or treatment methods(all P>0.05).VNC CT values and IC showed significantly negative correlation(r=-0.537,P<0.01).ROC analysis revealed AUCs of 0.917(95%CI:0.786～0.999)for VNC,0.878(95%CI:0.719～0.999)for IC,and 0.919(95%CI:0.812～0.999)for the combination of the two(P<0.05 for combined vs.individual methods).Optimal thresholds were 53.6 HU for VNC and 0.605 mg/ml for IC.Based on the final analysis of 46 enrolled patients,the sensitivity of VNC,iodine map,and their combination in differentiating early cerebral hemorrhage from contrast extravasation was 88.9%,94.3%,and 91.4%,respectively;the specificity 94.3%,77.8%,and 88.9%,respectively;and the accuracy 90.9%,90.9%,and 93.2%,respectively.Conclusion The DLCT VNC-iodine map combination significantly im-proves differentiation between post-EVT hemorrhage and contrast extravasation,and it is recommended for routine clinical application.

Objective:To develop and validate machine learning-based radiomics models using preoperative CT images for individualized prediction of mitotic index (MI) in patients with gastrointestinal stromal tumors (GIST).Methods:The study was a case-control study. The data of 348 GIST patients confirmed by pathology were retrospectively collected from two independent medical centers: the Affiliated Hospital of Qingdao University (center 1) and Shandong Provincial Hospital Affiliated to Shandong First Medical University (center 2), covering the period from January 2013 to June 2018. Patients from center 1 were divided into a training cohort (176 cases) and an internal validation cohort (75 cases) at a ratio of 7∶3 using random sampling. Patients from center 2 served as an independent external validation cohort (97 cases). The primary endpoint was MI, categorized into high MI (145 cases) and low MI (203 cases) groups. Radiomic features were extracted from the portal venous phase images of preoperative contrast-enhanced CT scans. Five machine learning algorithms, including logistic regression, support vector machine, random forest, decision tree, and extreme gradient boosting (XGBoost),were employed to construct MI prediction models. The optimal model was identified using receiver operating characteristic curves. An individualized prediction model was developed by integrating the the optimal machine learning model combined with selected independent clinical factors, and the importance of features was visualized using Shapley Additive Explanation (SHAP) analysis. Patients were followed up, and Kaplan-Meier curves along with log-rank tests were used to evaluate recurrence-free survival (RFS) differences between the predicted high MI and low MI groups.Results:Among the five constructed machine learning models, the XGBoost model demonstrated the best predictive performance, with area under the curve (AUC) of 0.809 (95% CI 0.738-0.872), 0.693 (95% CI 0.571-0.809), and 0.718 (95% CI 0.605-0.822) in the training cohort, internal validation cohort, and external validation cohort, respectively. An individualized prediction model combining the XGBoost model with independent clinical factors (tumor location and tumor size) was developed. The model achieved AUC of 0.843 (95% CI 0.785-0.899), 0.791 (95% CI 0.680-0.894), and 0.777 (95% CI 0.678-0.861) in the training cohort, internal validation cohort, and external validation cohort, respectively. SHAP analysis indicated that radiomic features had the highest predictive impact. In both the training cohort and internal validation cohort, the RFS of patients predicted to be in the high MI group was lower than that of the low MI group, with statistically significant differences ( χ2=14.58, 9.52, both P<0.001). However, there was no statistically significant difference in RFS in the external validation set ( χ2=6.18, P=0.080). Conclusions:The optimal XGBoost model based on radiomic features extracted from preoperative portal venous phase CT images, when combined with clinical factors, can effectively predict the MI of GIST patients.

Objective:To develop an artificial intelligence (AI)-based automatic scoring model for magnetic resonance imaging-detected extramural vascular invasion (AI-mrEMVI) and evaluate its performance and prognostic value in patients with rectal cancer.Methods:In this multicenter retrospective cohort study, a total of 2 501 rectal cancer patients from seven centers between November 2012 and December 2020 were included and divided into completely independent training ( n=1 830) and validation ( n=671) cohorts. A nnUNet-based AI-mrEMVI scoring model was constructed. Manual mrEMVI scores assigned by two radiologists served as the reference standard for accessing the accuracy of the AI-mrEMVI scoring. Kaplan-Meier survival analysis and Cox regression were used to evaluate the prognostic stratification ability of the AI-mrEMVI scores. The concordance index (C-index) was calculated to evaluate prognostic performance. Results:In the validation cohort, the manual mrEMVI scores were 0-2 in 425 patients (63.3%), 3 in 89 (13.4%), and 4 in 157 (23.4%). The AI-mrEMVI model identified 0-2 in 375 patients (55.9%), 3 in 95 (14.2%), and 4 in 201 (30.0%), with an overall accuracy of 81.1% (544/671, 95% CI 77.9%-84.0%). The 3-year disease-free survival (DFS) rates for patients with AI-mrEMVI scores of 0-2, 3, and 4 were 85.2%, 70.0%, and 58.2%, respectively, and the 5-year overall survival (OS) rates were 87.2%, 81.6%, and 62.6%, respectively (DFS: χ2=48.74, P<0.001; OS: χ2=30.04, P<0.001). Multivariable Cox regression showed that for DFS, AI-mrEMVI scores of 3 and 4 were associated with hazard ratios ( HR) of 1.75 (95% CI 1.11-2.77, P=0.016) and 2.65 (95% CI 1.86-3.78, P<0.001), respectively. For OS, an AI-mrEMVI score of 4 was associated with an HR of 2.56 (95% CI 1.62-4.03, P<0.001). The C-index values of the AI-mrEMVI scoring model for predicting DFS and OS were 0.647 (95% CI 0.608-0.686) and 0.650 (95% CI 0.598-0.702), respectively. Conclusion:The proposed AI-mrEMVI automatic scoring model demonstrated high diagnostic accuracy and performed favorably in predicting DFS and OS prognostic risk in patients with rectal cancer.

Cardiovascular disease is the leading cause of death among Chinese residents, and non-invasive imaging technology has important value in the diagnosis and treatment of cardiovascular disease. Cardiac magnetic resonance (CMR) can characterize cardiac pathophysiological information from multiple dimensions, including cardiac structure, function, tissue characteristics, and microstructure, through multi parameter and multi sequence " one-stop" imaging. This article will focus on new technologies such as CMRT1 mapping, feature tracking, and diffusion tensor imaging, and explain their applications and progress in the diagnosis, efficacy monitoring, and prognosis prediction of various myocardial lesions such as non ischemic heart disease and ischemic heart disease.

In recent years, digital radiography (DR) system is widely used in China, and digital X-ray radiography is one of the most common examinations for bone and joint. Optimizing the osteoarthrographic technique, standardizing osteoarthrogram, and summarizing the requirements for radiation protection, will further enhance the clinical application value of digital X-ray imaging in bone and joint examination. Referring to domestic and foreign literatures, and combining the clinical situation of Guangdong-Hong Kong-Macao Greater Bay Area, the experts recruited by the Guangdong-Hong Kong-Macao Greater Bay Area Imaging Technology Alliance reach a consensus on the technique and protection specifications for bone and joint examination to guide and standardize the work related to X-ray examination of bone and joint in the medical imaging department of medical institutions at all levels in the Greater Bay Area.