Meilin Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Meilin Zhu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Longlin Yin
Department of Radiology, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications Fang Han
1 shared publicationJiahao Gao
1 shared publication- Jiawen Zhang
Department of Radiology, Huashan hospital, Fudan University, Shanghai, China
1 shared publication - Li Liu
Department of Radiology, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Maoheng Tian
Department of Radiology, Affiliated Hospital of Southwest Medical University, Luzhou 646000, China
1 shared publication
Latest Publications
- Open Access
- 1 June 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (6) , 5752-5768
A three-classification machine learning model for non-invasive prediction of molecular subtypes in diffuse glioma: a two-center study
Background: Determining the molecular status of gliomas is crucial for evaluating treatment efficacy and prognosis. However, this process currently requires the invasive and cumbersome method of histological analysis. We aimed to develop and validate a non-invasive three-classification machine learning (ML) model to predict the three molecular subtypes of adult-type diffuse gliomas according to the 2021 World Health Organization classification of tumors of the central nervous system 5th edition (WHO CNS 5). Methods: This retrospective study included a total of 306 glioma patients, among whom 258 were from Center 1 (Huashan Hospital; 180 for the training and 78 for the internal validation set) and 48 were from Center 2 (The First Affiliated Hospital of Anhui Medical University; external validation set). Conventional magnetic resonance imaging (MRI) features of tumors were assessed, and the radiomics and Swin Transformer-based deep learning (RSTD) features were respectively extracted from tumor segmentation on axial three-dimensional contrast-enhanced T1-weighted (3D T1C) and T2-fluid-attenuated inversion recovery (T2-FLAIR) sequences. Three types of prediction models: conventional MRI (CM) model, RSTD model, and combined model were respectively trained using six ML classifiers [k-nearest neighbor (kNN), light gradient-boosting machine (LightGBM), random forest (RF), support vector machine (SVM), stochastic gradient descent (SGD), and extreme gradient boosting (XGBoost)] to identify the three major molecular subtypes of adult-type diffuse gliomas. The performance of the models was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, accuracy, precision, and F1-score. Results: XGBoost classifier was chosen as our algorithm for model construction due to its superior performance in the training and internal validation cohorts. The combined model, which incorporates CM features, RSTD features, as well as demographic features, achieved best performance in the internal [micro-AUC (0.905) and macro-AUC (0.878)] and external validation sets [micro-AUC (0.911) and macro-AUC (0.891)]. The SHapley Additive explanations (SHAP) and gradient-weighted class activation mapping (Grad-CAM) were used to explain the model. Conclusions: Our study constructed a three-classification ML model that combined CM features, RSTD features, and demographic characteristics, achieved promising performance in predicting molecular subtypes of diffuse glioma. The combined model provided a non-invasive, timely, and accurate diagnostic approach prior to patient treatment to assist clinical decision-making.
- 1 June 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (6) , 5752-5768
Open AccessA three-classification machine learning model for non-invasive prediction of molecular subtypes in diffuse glioma: a two-center study
Background: Determining the molecular status of gliomas is crucial for evaluating treatment efficacy and prognosis. However, this process currently requires the invasive and cumbersome method of histological analysis. We aimed to develop and validate a non-invasive three-classification machine learning (ML) model to predict the three molecular subtypes of adult-type diffuse gliomas according to the 2021 World Health Organization classification of tumors of the central nervous system 5th edition (WHO CNS 5). Methods: This retrospective study included a total of 306 glioma patients, among whom 258 were from Center 1 (Huashan Hospital; 180 for the training and 78 for the internal validation set) and 48 were from Center 2 (The First Affiliated Hospital of Anhui Medical University; external validation set). Conventional magnetic resonance imaging (MRI) features of tumors were assessed, and the radiomics and Swin Transformer-based deep learning (RSTD) features were respectively extracted from tumor segmentation on axial three-dimensional contrast-enhanced T1-weighted (3D T1C) and T2-fluid-attenuated inversion recovery (T2-FLAIR) sequences. Three types of prediction models: conventional MRI (CM) model, RSTD model, and combined model were respectively trained using six ML classifiers [k-nearest neighbor (kNN), light gradient-boosting machine (LightGBM), random forest (RF), support vector machine (SVM), stochastic gradient descent (SGD), and extreme gradient boosting (XGBoost)] to identify the three major molecular subtypes of adult-type diffuse gliomas. The performance of the models was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, accuracy, precision, and F1-score. Results: XGBoost classifier was chosen as our algorithm for model construction due to its superior performance in the training and internal validation cohorts. The combined model, which incorporates CM features, RSTD features, as well as demographic features, achieved best performance in the internal [micro-AUC (0.905) and macro-AUC (0.878)] and external validation sets [micro-AUC (0.911) and macro-AUC (0.891)]. The SHapley Additive explanations (SHAP) and gradient-weighted class activation mapping (Grad-CAM) were used to explain the model. Conclusions: Our study constructed a three-classification ML model that combined CM features, RSTD features, and demographic characteristics, achieved promising performance in predicting molecular subtypes of diffuse glioma. The combined model provided a non-invasive, timely, and accurate diagnostic approach prior to patient treatment to assist clinical decision-making.
- Open Access
- 27 July 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (15) , 2497
The Diagnostic Performance of Tumor Stage on MRI for Predicting Prostate Cancer-Positive Surgical Margins: A Systematic Review and Meta-Analysis
Purpose: Surgical margin status in radical prostatectomy (RP) specimens is an established predictive indicator for determining biochemical prostate cancer recurrence and disease progression. Predicting positive surgical margins (PSMs) is of utmost importance. We sought to perform a meta-analysis evaluating the diagnostic utility of a high clinical tumor stage (≥3) on magnetic resonance imaging (MRI) for predicting PSMs. Method: A systematic search of the PubMed, Embase databases, and Cochrane Library was performed, covering the interval from 1 January 2000 to 31 December 2022, to identify relevant studies. The Quality Assessment of Diagnostic Accuracy Studies 2 method was used to evaluate the studies’ quality. A hierarchical summary receiver operating characteristic plot was created depicting sensitivity and specificity data. Analyses of subgroups and meta-regression were used to investigate heterogeneity. Results: This meta-analysis comprised 13 studies with 3924 individuals in total. The pooled sensitivity and specificity values were 0.40 (95% CI, 0.32–0.49) and 0.75 (95% CI, 0.69–0.80), respectively, with an area under the receiver operating characteristic curve of 0.63 (95% CI, 0.59–0.67). The Higgins I2 statistics indicated moderate heterogeneity in sensitivity (I2 = 75.59%) and substantial heterogeneity in specificity (I2 = 86.77%). Area, prevalence of high Gleason scores (≥7), laparoscopic or robot-assisted techniques, field strength, functional technology, endorectal coil usage, and number of radiologists were significant factors responsible for heterogeneity (p ≤ 0.01). Conclusions: T stage on MRI has moderate diagnostic accuracy for predicting PSMs. When determining the treatment modality, clinicians should consider the factors contributing to heterogeneity for this purpose.
- 27 July 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (15) , 2497
Open AccessThe Diagnostic Performance of Tumor Stage on MRI for Predicting Prostate Cancer-Positive Surgical Margins: A Systematic Review and Meta-Analysis
Purpose: Surgical margin status in radical prostatectomy (RP) specimens is an established predictive indicator for determining biochemical prostate cancer recurrence and disease progression. Predicting positive surgical margins (PSMs) is of utmost importance. We sought to perform a meta-analysis evaluating the diagnostic utility of a high clinical tumor stage (≥3) on magnetic resonance imaging (MRI) for predicting PSMs. Method: A systematic search of the PubMed, Embase databases, and Cochrane Library was performed, covering the interval from 1 January 2000 to 31 December 2022, to identify relevant studies. The Quality Assessment of Diagnostic Accuracy Studies 2 method was used to evaluate the studies’ quality. A hierarchical summary receiver operating characteristic plot was created depicting sensitivity and specificity data. Analyses of subgroups and meta-regression were used to investigate heterogeneity. Results: This meta-analysis comprised 13 studies with 3924 individuals in total. The pooled sensitivity and specificity values were 0.40 (95% CI, 0.32–0.49) and 0.75 (95% CI, 0.69–0.80), respectively, with an area under the receiver operating characteristic curve of 0.63 (95% CI, 0.59–0.67). The Higgins I2 statistics indicated moderate heterogeneity in sensitivity (I2 = 75.59%) and substantial heterogeneity in specificity (I2 = 86.77%). Area, prevalence of high Gleason scores (≥7), laparoscopic or robot-assisted techniques, field strength, functional technology, endorectal coil usage, and number of radiologists were significant factors responsible for heterogeneity (p ≤ 0.01). Conclusions: T stage on MRI has moderate diagnostic accuracy for predicting PSMs. When determining the treatment modality, clinicians should consider the factors contributing to heterogeneity for this purpose.