Goto Masaaki, Futamura Yasunori, Makishima Hirokazu, Saito Takashi, Sakamoto Noriaki, Iijima Tatsuo, Tamaki Yoshio, Okumura Toshiyuki, Sakurai Tetsuya, Sakurai Hideyuki
Department of Radiation Oncology & Proton Medical Research Center, Institute of Medicine, University of Tsukuba, 2-1-1 Amakubo, Tsubuka, Ibaraki 305-8576, Japan.
Department of Radiation Oncology, Japan Red Cross Medical Center, 4-1-22 Hiroo, Shibuya, Tokyo 150-8935, Japan.
J Radiat Res. 2025 Mar 24;66(2):144-156. doi: 10.1093/jrr/rraf004.
This study aims to create a deep learning-based classification model for cervical cancer biopsy before and during radiotherapy, visualize the results on whole slide images (WSIs), and explore the clinical significance of obtained features. This study included 95 patients with cervical cancer who received radiotherapy between April 2013 and December 2020. Hematoxylin-eosin stained biopsies were digitized to WSIs and divided into small tiles. Our model adopted the feature extractor of DenseNet121 and the classifier of the support vector machine. About 12 400 tiles were used for training the model and 6000 tiles for testing. The model performance was assessed on a per-tile and per-WSI basis. The resultant probability was defined as radiotherapy status probability (RSP) and its color map was visualized on WSIs. Survival analysis was performed to examine the clinical significance of the RSP. In the test set, the trained model had an area under the receiver operating characteristic curve of 0.76 per-tile and 0.95 per-WSI. In visualization, the model focused on viable tumor components and stroma in tumor biopsies. While survival analysis failed to show the prognostic impact of RSP during treatment, cases with low RSP at diagnosis had prolonged overall survival compared to those with high RSP (P = 0.045). In conclusion, we successfully developed a model to classify biopsies before and during radiotherapy and visualized the result on slide images. Low RSP cases before treatment had a better prognosis, suggesting that tumor morphologic features obtained using the model may be useful for predicting prognosis.
本研究旨在创建一种基于深度学习的宫颈癌放疗前及放疗期间活检分类模型，在全切片图像（WSIs）上可视化结果，并探索所获特征的临床意义。本研究纳入了95例在2013年4月至2020年12月期间接受放疗的宫颈癌患者。苏木精-伊红染色的活检标本被数字化为全切片图像并分割成小图块。我们的模型采用了DenseNet121的特征提取器和支持向量机分类器。约12400个图块用于训练模型，6000个图块用于测试。在每个图块和每张全切片图像基础上评估模型性能。所得概率被定义为放疗状态概率（RSP），其彩色图在全切片图像上可视化。进行生存分析以检验RSP的临床意义。在测试集中，训练后的模型在每个图块的受试者操作特征曲线下面积为0.76，在每张全切片图像上为0.95。在可视化过程中，模型聚焦于肿瘤活检中的存活肿瘤成分和间质。虽然生存分析未能显示治疗期间RSP的预后影响，但诊断时RSP低的病例与RSP高的病例相比总生存期延长（P = 0.045）。总之，我们成功开发了一种在放疗前及放疗期间对活检进行分类并在切片图像上可视化结果的模型。治疗前RSP低的病例预后较好，这表明使用该模型获得的肿瘤形态学特征可能有助于预测预后。
