Fujita Hiroaki, Wakiya Taiichi, Ishido Keinosuke, Kimura Norihisa, Nagase Hayato, Kanda Taishu, Matsuzaka Masashi, Sasaki Yoshihiro, Hakamada Kenichi
Department of Gastroenterological Surgery Hirosaki University Graduate School of Medicine Hirosaki Japan.
Department of Medical Informatics Hirosaki University Hospital Hirosaki Japan.
Ann Gastroenterol Surg. 2022 Jun 11;6(6):823-832. doi: 10.1002/ags3.12589. eCollection 2022 Nov.
The differential diagnosis between gallbladder cancer (GBC) and xanthogranulomatous cholecystitis (XGC) remains quite challenging, and can possibly lead to improper surgery. This study aimed to distinguish between XGC and GBC by combining computed tomography (CT) images and deep learning (DL) to maximize the therapeutic success of surgery.
We collected a dataset, including preoperative CT images, from 28 cases of GBC and 21 XGC patients undergoing surgery at our facility. It was subdivided into training and validation (n = 40), and test (n = 9) datasets. We built a CT patch-based discriminating model using a residual convolutional neural network and employed 5-fold cross-validation. The discriminating performance of the model was analyzed in the test dataset.
Of the 40 patients in the training dataset, GBC and XGC were observed in 21 (52.5%), and 19 (47.5%) patients, respectively. A total of 61 126 patches were extracted from the 40 patients. In the validation dataset, the average sensitivity, specificity, and accuracy were 98.8%, 98.0%, and 98.5%, respectively. Furthermore, the area under the receiver operating characteristic curve (AUC) was 0.9985. In the test dataset, which included 11 738 patches, the discriminating accuracy for GBC patients after neoadjuvant chemotherapy (NAC) (n = 3) was insufficient (61.8%). However, the discriminating model demonstrated high accuracy (98.2%) and AUC (0.9893) for cases other than those receiving NAC.
Our CT-based DL model exhibited high discriminating performance in patients with GBC and XGC. Our study proposes a novel concept for selecting the appropriate procedure and avoiding unnecessary invasive measures.
胆囊癌（GBC）与黄色肉芽肿性胆囊炎（XGC）的鉴别诊断仍然颇具挑战性，且可能导致手术不当。本研究旨在通过结合计算机断层扫描（CT）图像和深度学习（DL）来区分XGC和GBC，以最大限度地提高手术治疗成功率。
我们收集了来自我院28例接受手术的GBC患者和21例XGC患者的数据集，包括术前CT图像。该数据集被细分为训练集和验证集（n = 40）以及测试集（n = 9）。我们使用残差卷积神经网络构建了基于CT图像块的鉴别模型，并采用5折交叉验证。在测试集中分析该模型的鉴别性能。
在训练数据集中的40例患者中，分别观察到21例（52.5%）GBC患者和19例（47.5%）XGC患者。从这40例患者中总共提取了61126个图像块。在验证集中，平均灵敏度、特异性和准确率分别为98.8%、98.0%和98.5%。此外，受试者操作特征曲线（AUC）下的面积为0.9985。在包含11738个图像块的测试集中，新辅助化疗（NAC）后GBC患者（n = 3）的鉴别准确率不足（61.8%）。然而，对于未接受NAC的病例，鉴别模型显示出高准确率（98.2%）和AUC（0.9893）。
我们基于CT的DL模型在GBC和XGC患者中表现出高鉴别性能。我们的研究提出了一个选择合适手术程序并避免不必要侵入性措施的新概念。
