一步式算法用于肺癌组织学亚型的快速定位与多分类
本研究收集417例小细胞肺癌、肺腺癌或肺鳞癌患者的治疗前增强CT图像,由放射科医师手动勾画肿瘤体积,按约8:2随机分为训练集和测试集,训练自研深度学习模型同时实现肿瘤病灶快速追踪与组织学亚型分类,并用1921张测试图像评估性能。结果显示小细胞肺癌、腺癌、鳞癌的预测准确率分别为0.83、0.75、0.67,加权F1平均值为0.75,AUC分别为0.87、0.84、0.76,单张胸部CT图像切片同时完成定位与分类仅需0.24秒。
要点
- 小细胞肺癌、腺癌、鳞癌的预测准确率分别为0.83、0.75、0.67。
- 腺癌F1分数0.78最佳,优于小细胞肺癌0.77和鳞癌0.66。
- 小细胞肺癌、腺癌、鳞癌的AUC分别为0.87、0.84、0.76。
核心结论
- 新开发的多任务算法提供了一种基于卷积神经网络的深度学习方法,可在一步中自动快速追踪肿瘤病灶并分类相应的组织学亚型。
研究设计与样本
- 研究收集417例诊断为小细胞肺癌、肺腺癌或肺鳞癌患者的治疗前增强CT图像,由受过训练的放射科医师使用ITK-SNAP软件手动勾画肿瘤体积。
关键影像表现/征象
- 热图可视化展示了所提出模型提取的用于分类肺癌亚型的肿瘤特征。
诊断标准与关键数值
- 小细胞肺癌预测准确率0.83、F1分数0.77、AUC 0.87。
- 肺腺癌预测准确率0.75、F1分数0.78、AUC 0.84。
- 肺鳞癌预测准确率0.67、F1分数0.66、AUC 0.76。
- 加权F1平均值为0.75。
- 每类患者按约8:2随机分为训练集和测试集,训练集25042张CT图像,测试集1921张图像。
临床应用与阅片要点
- 该模型在单张胸部CT图像切片上同时实现肿瘤定位与组织学分类仅需0.24秒。
局限性
- 原文未报告局限性。
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
BACKGROUNDS: Accumulated evidence has proven that computer-derived features from computed tomography (CT) through radiomics and deep learning technologies can identify extensive characteristics of pulmonary malignancies, such as nodules detection and malignant lesion discrimination. However, there are few studies on whether CT images can reflect histological subtypes of lung cancer through computer-derived features.
METHODS: Contrast-enhanced CT images prior treatment from 417 patients diagnosed with small cell lung cancer (SCLC), lung adenocarcinoma (ADC), or lung squamous cell carcinoma (SCC) were collected. ITK-SNAP software was used by trained radiologists for the manual delineation of tumor volume. Patients of each category (SCLC, ADC, SCC) were then randomly split into training datasets and test datasets in an approximately ratio of 8:2. After image pre-processing and augmentation, 25,042 CT images from the training datasets were used to train our self-developed deep learning model for fast-tracking tumor lesions and classifying corresponding histological subtypes simultaneously. The performance of the network was evaluated by accuracy, F1-score and weighted F1-average using 1,921 testing images based on parameters generated during training.
RESULTS: The prediction accuracy of SCLC, ADC, and SCC were 0.83, 0.75 and 0.67, respectively. The weighted F1-average was 0.75. ADC obtained the best F1-score of 0.78, which was outperformed SCLC (0.77) and SCC (0.66). The corresponding AUC values of SCLC, ADC, and SCC were 0.87, 0.84, and 0.76, respectively. Only 0.24 s were required to simultaneously achieve functions of tumor localization and histological classification on a thoracic CT image slice. The heat map visualization illustrated the extracted tumor features to classify subtypes of lung cancer by the proposed model.
CONCLUSIONS: The newly developed multi-task algorithm provides a CNN-based DL approach in lung cancer for automatically fast-tracking tumor lesions and classifying corresponding histological subtypes in one-step.
引用
- Qi, Deng, Sun, et al. One-step algorithm for fast-track localization and multi-category classification of histological subtypes in lung cancer. Eur J Radiol. 2022. PMID: 35901600. doi:10.1016/j.ejrad.2022.110443
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。