Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer

Yihuang Hu; Juan Li; Zhuokai Zhuang; Bin Xu; Dabiao Wang; Huichuan Yu; Lanlan Li

doi:10.1016/j.heliyon.2023.e13094

Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer

Heliyon. 2023 Jan 25;9(2):e13094. doi: 10.1016/j.heliyon.2023.e13094. eCollection 2023 Feb.

Authors

Yihuang Hu¹, Juan Li², Zhuokai Zhuang^{3

4}, Bin Xu¹, Dabiao Wang⁵, Huichuan Yu⁶, Lanlan Li¹

Affiliations

¹ Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350108, China.
² Department of Endoscopic Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510655, China.
³ Guangdong Institute of Gastroenterology, Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Disease, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510655, China.
⁴ Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510655, China.
⁵ College of Chemical and Engineering, Fuzhou University, Fuzhou, 350108, China.
⁶ Guangdong Institute of Gastroenterology, Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Disease, The Sixth Affiliated Hospital, Sun Yat-sen University, 26 Yuancun Erheng Road, Guangzhou, Guangdong, 510655, China.

Abstract

Neoadjuvant systemic treatment before surgery is a prevalent regimen in the patients with advanced-stage or high-risk tumor, which has shaped the treatment strategies and cancer survival in the past decades. However, some patients present with poor response to the neoadjuvant treatment. Therefore, it is of great significance to develop tools to help distinguish the patients that could achieve pathological complete response before surgery to avoid inappropriate treatment. Here, this study demonstrated a multi-task deep learning tool called DeepInteg. In the DeepInteg framework, the segmentation module was constructed based on the CE-Net with a context extractor to achieve end-to-end delineation of region of interest (ROI) from radiological images, then the features of segmented Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images of each case were fused and input to the classification module based on a convolution neural network for treatment outcome prediction. The dataset with 1700 MRI and CT slices collected from the prospectively randomized clinical trial (NCT01211210) on systemic treatment for rectal cancer was used to develop and systematically optimize DeepInteg. As a result, DeepInteg achieved automatic segmentation of tumoral ROI with Dices of 0.766 and 0.719 and mIoUs of 0.788 and 0.756 in CT and MRI images, respectively. In addition, DeepInteg achieved AUC of 0.833, accuracy of 0.826 and specificity of 0.856 in the prediction for pathological complete response after treatment, which showed better performance compared with the model based on CT or MRI alone. This study provide a robust framework to develop disease-specific tools for automatic delineation of ROI and clinical outcome prediction. The well-trained DeepInteg could be readily applied in clinic to predict pathological complete response after neoadjuvant therapy in rectal cancer patients.

Keywords: CT; Deep learning; MRI; Neoadjuvant therapy; Rectal cancer.