Yasaka Koichiro, Kawamura Motohide, Sonoda Yuki, Kubo Takatoshi, Kiryu Shigeru, Abe Osamu
Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan.
Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan.
Jpn J Radiol. 2025 May;43(5):779-786. doi: 10.1007/s11604-024-01718-w. Epub 2024 Dec 13.
This study aimed to develop a large multimodality model (LMM) that can detect breast and esophageal carcinomas on chest contrast-enhanced CT.
In this retrospective study, CT images of 401 (age, 62.9 ± 12.9 years; 169 males), 51 (age, 65.5 ± 11.6 years; 23 males), and 120 (age, 64.6 ± 14.2 years; 60 males) patients were used in the training, validation, and test phases. The numbers of CT images with breast carcinoma, esophageal carcinoma, and no lesion were 927, 2180, and 2087; 80, 233, and 270; and 184, 246, and 6919 for the training, validation, and test datasets, respectively. The LMM was fine-tuned using CT images as input and text data ("suspicious of breast carcinoma"/ "suspicious of esophageal carcinoma"/ "no lesion") as reference data on a desktop computer equipped with a single graphic processing unit. Because of the random nature of the training process, supervised learning was performed 10 times. The performance of the best performing model on the validation dataset was further tested using the time-independent test dataset. The detection performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC).
The sensitivities of the fine-tuned LMM for detecting breast and esophageal carcinomas in the test dataset were 0.929 and 0.951, respectively. The diagnostic performance of the fine-tuned LMM for detecting breast and esophageal carcinomas was high, with AUCs of 0.890 (95%CI 0.871-0.909) and 0.880 (95%CI 0.865-0.894), respectively.
The fine-tuned LMM could detect both breast and esophageal carcinomas on chest contrast-enhanced CT with high diagnostic performance. Usefulness of large multimodality models in chest cancer imaging has not been assessed so far. The fine-tuned large multimodality model could detect breast and esophageal carcinomas with high diagnostic performance (area under the receiver operating characteristic curve of 0.890 and 0.880, respectively).
本研究旨在开发一种大型多模态模型（LMM），该模型能够在胸部增强CT上检测乳腺癌和食管癌。
在这项回顾性研究中，401例患者（年龄62.9±12.9岁；男性169例）、51例患者（年龄65.5±11.6岁；男性23例）和120例患者（年龄64.6±14.2岁；男性60例）的CT图像分别用于训练、验证和测试阶段。训练、验证和测试数据集中，含有乳腺癌、食管癌及无病变的CT图像数量分别为927、2180和2087；80、233和270；以及184、246和6919。以CT图像作为输入，文本数据（“怀疑乳腺癌”/“怀疑食管癌”/“无病变”）作为参考数据，在配备单个图形处理单元的台式计算机上对LMM进行微调。由于训练过程的随机性，进行了10次监督学习。使用与时间无关的测试数据集进一步测试在验证数据集上表现最佳的模型的性能。通过计算受试者操作特征曲线（AUC）下的面积来评估检测性能。
在测试数据集中，微调后的LMM检测乳腺癌和食管癌的灵敏度分别为0.929和0.951。微调后的LMM检测乳腺癌和食管癌的诊断性能较高，AUC分别为0.890（95%CI 0.871 - 0.909）和0.880（95%CI 0.865 - 0.894）。
微调后的LMM能够在胸部增强CT上检测乳腺癌和食管癌，且诊断性能较高。迄今为止，尚未评估大型多模态模型在胸部癌症成像中的实用性。微调后的大型多模态模型能够以较高的诊断性能检测乳腺癌和食管癌（受试者操作特征曲线下面积分别为0.890和0.880）。
