{"title":"探索髓母细胞瘤分子亚群和预后相关遗传特征的深度学习和混合方法。","authors":"Yanong Li, Hailong Liu, Yawei Liu, Jane Li, Hiro Hiromichi Suzuki, Yaou Liu, Jiang Tao, Xiaoguang Qiu","doi":"10.1186/s41016-025-00405-7","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Deep learning (DL) based on MRI of medulloblastoma enables risk stratification, potentially aiding in therapeutic decisions. This study aims to develop DL models that identify four medulloblastoma molecular subgroups and prognostic-related genetic signatures.</p><p><strong>Methods: </strong>This retrospective study enrolled 325 patients for model development and an independent external validation cohort of 124 patients, totaling 449 MB patients from 2 medical institutes. Consecutive patients with newly diagnosed MB at MRI (T1-weighted, T2-weighted, and contrast-enhanced T1-weighted) at two medical institutes between January 2015 and June 2023 were identified. Two-stage sequential DL models were designed-MB-CNN that first identifies wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. Further, prognostic-related genetic signatures using DL models (MB-CNN_TP53/MYC/Chr11) were developed to predict TP53 mutation, MYC amplification, and chromosome 11 loss status. A hybrid model combining MB-CNN and conventional data (clinical information and MRI features) was compared to a logistic regression model constructed only with conventional data. Four-classification tasks were evaluated with confusion matrices (accuracy) and two-classification tasks with ROC curves (area under the curve (AUC)).</p><p><strong>Results: </strong>The datasets comprised 449 patients (mean age ± SD at diagnosis, 13.55 years ± 2.33, 249 males). MB-CNN accurately classified MB subgroups in the external test dataset, achieving a median accuracy of 77.50% (range in 76.29% to 78.71%). MB-CNN_TP53/MYC/Chr11 models effectively predicted signatures (AUC of TP53 in SHH: 0.91, MYC amplification in Group 3: 0.87, chromosome 11 loss in Group 4: 0.89). The accuracy of the hybrid model outperformed the logistic regression model (82.20% vs. 59.14%, P = .009) and showed comparable performance to MB-CNN (82.20% vs. 77.50%, P = 0.105).</p><p><strong>Conclusion: </strong>MRI-based DL models allowed identification of the molecular medulloblastoma subgroups and prognostic-related genetic signatures.</p>","PeriodicalId":36700,"journal":{"name":"Chinese Neurosurgical Journal","volume":"11 1","pages":"19"},"PeriodicalIF":0.0000,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12434915/pdf/","citationCount":"0","resultStr":"{\"title\":\"Exploring deep learning and hybrid approaches in molecular subgrouping and prognostic-related genetic signatures of medulloblastoma.\",\"authors\":\"Yanong Li, Hailong Liu, Yawei Liu, Jane Li, Hiro Hiromichi Suzuki, Yaou Liu, Jiang Tao, Xiaoguang Qiu\",\"doi\":\"10.1186/s41016-025-00405-7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Deep learning (DL) based on MRI of medulloblastoma enables risk stratification, potentially aiding in therapeutic decisions. This study aims to develop DL models that identify four medulloblastoma molecular subgroups and prognostic-related genetic signatures.</p><p><strong>Methods: </strong>This retrospective study enrolled 325 patients for model development and an independent external validation cohort of 124 patients, totaling 449 MB patients from 2 medical institutes. Consecutive patients with newly diagnosed MB at MRI (T1-weighted, T2-weighted, and contrast-enhanced T1-weighted) at two medical institutes between January 2015 and June 2023 were identified. Two-stage sequential DL models were designed-MB-CNN that first identifies wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. Further, prognostic-related genetic signatures using DL models (MB-CNN_TP53/MYC/Chr11) were developed to predict TP53 mutation, MYC amplification, and chromosome 11 loss status. A hybrid model combining MB-CNN and conventional data (clinical information and MRI features) was compared to a logistic regression model constructed only with conventional data. Four-classification tasks were evaluated with confusion matrices (accuracy) and two-classification tasks with ROC curves (area under the curve (AUC)).</p><p><strong>Results: </strong>The datasets comprised 449 patients (mean age ± SD at diagnosis, 13.55 years ± 2.33, 249 males). MB-CNN accurately classified MB subgroups in the external test dataset, achieving a median accuracy of 77.50% (range in 76.29% to 78.71%). MB-CNN_TP53/MYC/Chr11 models effectively predicted signatures (AUC of TP53 in SHH: 0.91, MYC amplification in Group 3: 0.87, chromosome 11 loss in Group 4: 0.89). The accuracy of the hybrid model outperformed the logistic regression model (82.20% vs. 59.14%, P = .009) and showed comparable performance to MB-CNN (82.20% vs. 77.50%, P = 0.105).</p><p><strong>Conclusion: </strong>MRI-based DL models allowed identification of the molecular medulloblastoma subgroups and prognostic-related genetic signatures.</p>\",\"PeriodicalId\":36700,\"journal\":{\"name\":\"Chinese Neurosurgical Journal\",\"volume\":\"11 1\",\"pages\":\"19\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12434915/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Chinese Neurosurgical Journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s41016-025-00405-7\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chinese Neurosurgical Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s41016-025-00405-7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0
摘要
背景：基于髓母细胞瘤MRI的深度学习（DL）可以进行风险分层，可能有助于治疗决策。本研究旨在建立识别髓母细胞瘤分子亚群和预后相关遗传特征的DL模型。方法：本回顾性研究纳入了来自2个医疗机构的325例患者进行模型开发和124例患者的独立外部验证队列，共计449例MB患者。在2015年1月至2023年6月期间，两家医疗机构的MRI （t1加权、t2加权和对比增强t1加权）连续确诊为MB患者。设计了两阶段序列深度学习模型- mb - cnn，首先识别无翼（WNT）、音猬（SHH）、组3和组4。此外，使用DL模型（MB-CNN_TP53/MYC/Chr11）开发了与预后相关的遗传特征，以预测TP53突变、MYC扩增和11号染色体丢失状态。将MB-CNN与常规数据（临床信息和MRI特征）相结合的混合模型与仅使用常规数据构建的逻辑回归模型进行比较。用混淆矩阵（准确率）评价四类任务，用ROC曲线（曲线下面积（AUC））评价两类任务。结果：数据集包括449例患者（诊断时平均年龄±SD， 13.55岁±2.33岁，男性249例）。MB- cnn对外部测试数据集中的MB子组进行了准确分类，准确率中位数达到77.50%（范围在76.29% ~ 78.71%之间）。MB-CNN_TP53/MYC/Chr11模型有效地预测了特征（SHH中TP53的AUC: 0.91，第3组MYC扩增：0.87，第4组11号染色体缺失：0.89）。混合模型的准确率优于logistic回归模型(82.20% vs. 59.14%, P =。009)，表现出与MB-CNN相当的性能（82.20%对77.50%,P = 0.105）。结论：基于mri的DL模型可以识别成神经管细胞瘤分子亚群和预后相关的遗传特征。
Exploring deep learning and hybrid approaches in molecular subgrouping and prognostic-related genetic signatures of medulloblastoma.
Background: Deep learning (DL) based on MRI of medulloblastoma enables risk stratification, potentially aiding in therapeutic decisions. This study aims to develop DL models that identify four medulloblastoma molecular subgroups and prognostic-related genetic signatures.
Methods: This retrospective study enrolled 325 patients for model development and an independent external validation cohort of 124 patients, totaling 449 MB patients from 2 medical institutes. Consecutive patients with newly diagnosed MB at MRI (T1-weighted, T2-weighted, and contrast-enhanced T1-weighted) at two medical institutes between January 2015 and June 2023 were identified. Two-stage sequential DL models were designed-MB-CNN that first identifies wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. Further, prognostic-related genetic signatures using DL models (MB-CNN_TP53/MYC/Chr11) were developed to predict TP53 mutation, MYC amplification, and chromosome 11 loss status. A hybrid model combining MB-CNN and conventional data (clinical information and MRI features) was compared to a logistic regression model constructed only with conventional data. Four-classification tasks were evaluated with confusion matrices (accuracy) and two-classification tasks with ROC curves (area under the curve (AUC)).
Results: The datasets comprised 449 patients (mean age ± SD at diagnosis, 13.55 years ± 2.33, 249 males). MB-CNN accurately classified MB subgroups in the external test dataset, achieving a median accuracy of 77.50% (range in 76.29% to 78.71%). MB-CNN_TP53/MYC/Chr11 models effectively predicted signatures (AUC of TP53 in SHH: 0.91, MYC amplification in Group 3: 0.87, chromosome 11 loss in Group 4: 0.89). The accuracy of the hybrid model outperformed the logistic regression model (82.20% vs. 59.14%, P = .009) and showed comparable performance to MB-CNN (82.20% vs. 77.50%, P = 0.105).
Conclusion: MRI-based DL models allowed identification of the molecular medulloblastoma subgroups and prognostic-related genetic signatures.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
