基于深度学习的经腹超声图像中胃肠道间质瘤自动分割与风险分层预测
研究回顾性收集245例GIST患者的980幅超声图像训练分割与分类网络,并前瞻性收集47例患者的188幅图像验证;SegNeXt-ResNet18模型在外部测试集的分割IoU、DSC分别为81.0%、89.5%,风险预测准确率86.7%、AUC 92.5%。
要点
- SegNeXt-ResNet18在经腹超声上可自动分割GIST并预测风险分层。
- 外部测试集分割DSC 89.5%、IoU 81.0%,风险预测AUC 92.5%。
- 内部测试集分割DSC 90.2%、IoU 82.1%,风险预测AUC 92.0%。
核心结论
- 两阶段SegNeXt-ResNet18模型可实现GIST自动分割和风险分层预测,分割与分类性能良好。
研究设计与样本
- 回顾性收集245例GIST患者的980幅超声图像,按6:2:2随机分为训练集、验证集和内部测试集;前瞻性收集47例GIST患者的188幅超声图像作为外部测试集。
诊断标准与关键数值
- 内部测试集:SegNeXt-ResNet18分割IoU 82.1%、DSC 90.2%、精确率91.7%、召回率88.8%;风险预测准确率87.4%、AUC 92.0%。
- 外部测试集:分割IoU 81.0%、DSC 89.5%、精确率92.8%、召回率86.4%;风险预测准确率86.7%、AUC 92.5%。
- 比较UNet、FCN、DeepLabV3+、Swin Transformer和SegNeXt五种分割网络及ResNet18分类网络,SegNeXt-ResNet18分割与分类性能最佳。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs).
METHODS: A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning-based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC).
RESULTS: Among the compared models, SegNeXt-ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively.
CONCLUSION: This two-stage SegNeXt-ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.
引用
- Zhuo M, Chen X, Guo J, et al. Deep Learning-Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging. J Ultrasound Med. 2024. PMID: 38822195. doi:10.1002/jum.16489
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。