Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, 58 Zhongshan II Road, Guangzhou, 510080, People's Republic of China.
Medical AI Lab, School of Biomedical Engineering, Health Science Center, Shenzhen University, Block A2, Lihu Campus of Shenzhen University, 1066 Xueyuan Avenue, Shenzhen, 518000, People's Republic of China.
Eur Radiol. 2022 Dec;32(12):8692-8705. doi: 10.1007/s00330-022-08842-z. Epub 2022 May 26.
Accurate evaluation of bowel fibrosis in patients with Crohn's disease (CD) remains challenging. Computed tomography enterography (CTE)-based radiomics enables the assessment of bowel fibrosis; however, it has some deficiencies. We aimed to develop and validate a CTE-based deep learning model (DLM) for characterizing bowel fibrosis more efficiently.
We enrolled 312 bowel segments of 235 CD patients (median age, 33 years old) from three hospitals in this retrospective study. A training cohort and test cohort 1 were recruited from center 1, while test cohort 2 from centers 2 and 3. All patients performed CTE within 3 months before surgery. The histological fibrosis was semi-quantitatively assessed. A DLM was constructed in the training cohort based on a 3D deep convolutional neural network with 10-fold cross-validation, and external independent validation was conducted on the test cohorts. The radiomics model (RM) was developed with 4 selected radiomics features extracted from CTE images by using logistic regression. The evaluation of CTE images was performed by two radiologists. DeLong's test and a non-inferiority test were used to compare the models' performance.
DLM distinguished none-mild from moderate-severe bowel fibrosis with an area under the receiver operator characteristic curve (AUC) of 0.828 in the training cohort and 0.811, 0.808, and 0.839 in the total test cohort, test cohorts 1 and 2, respectively. In the total test cohort, DLM achieved better performance than two radiologists (*1 AUC = 0.579, *2 AUC = 0.646; both p < 0.05) and was not inferior to RM (AUC = 0.813, p < 0.05). The total processing time for DLM was much shorter than that of RM (p < 0.001).
DLM is better than radiologists in diagnosing intestinal fibrosis on CTE in patients with CD and not inferior to RM; furthermore, it is more time-saving compared to RM.
• Question Could computed tomography enterography (CTE)-based deep learning model (DLM) accurately distinguish intestinal fibrosis severity in patients with Crohn's disease (CD)? • Findings In this cross-sectional study that included 235 patients with CD, DLM achieved better performance than that of two radiologists' interpretation and was not inferior to RM with significant differences and much shorter processing time. • Meaning This DLM may accurately distinguish the degree of intestinal fibrosis in patients with CD and guide gastroenterologists to formulate individualized treatment strategies for those with bowel strictures.
准确评估克罗恩病（CD）患者的肠纤维化仍然具有挑战性。基于计算机断层肠造影术（CTE）的放射组学可用于评估肠纤维化，但存在一些局限性。本研究旨在开发和验证一种基于 CTE 的深度学习模型（DLM），以更有效地对肠纤维化进行特征描述。
本回顾性研究纳入了来自 3 家医院的 235 例 CD 患者的 312 个肠段（中位年龄 33 岁）。训练队列和 1 号测试队列来自中心 1，2 号和 3 号测试队列来自中心 2 和 3。所有患者在手术前 3 个月内均行 CTE 检查。对组织学纤维化进行半定量评估。在训练队列中，基于 3D 深度卷积神经网络进行 10 折交叉验证构建 DLM，并在测试队列中进行外部独立验证。通过使用逻辑回归从 CTE 图像中提取 4 个选定的放射组学特征来开发放射组学模型（RM）。两名放射科医生对 CTE 图像进行评估。使用 DeLong 检验和非劣效性检验比较模型性能。
DLM 在训练队列中区分无-轻度和中-重度肠纤维化的受试者工作特征曲线下面积（AUC）为 0.828，在总测试队列、测试队列 1、测试队列 2 中的 AUC 分别为 0.811、0.808 和 0.839。在总测试队列中，DLM 比两名放射科医生的表现更好（*1 AUC = 0.579，*2 AUC = 0.646；均 p < 0.05），与 RM 无差异（AUC = 0.813，p < 0.05）。与 RM 相比，DLM 的总处理时间明显更短（p < 0.001）。
DLM 在诊断 CD 患者 CTE 肠纤维化严重程度方面优于放射科医生，且不劣于 RM；此外，与 RM 相比，其耗时更短。
问题：基于计算机断层肠造影术（CTE）的深度学习模型（DLM）能否准确区分克罗恩病（CD）患者肠纤维化的严重程度？
发现：在这项包括 235 例 CD 患者的横断面研究中，与两名放射科医生的解释相比，DLM 具有更好的性能，与 RM 相比差异具有统计学意义，且处理时间更短。
意义：该 DLM 可准确区分 CD 患者肠纤维化的程度，有助于指导胃肠病学家为肠狭窄患者制定个体化治疗策略。
