Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer
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, i...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023003018 |
| _version_ | 1811161877150957568 |
|---|---|
| author | Yihuang Hu Juan Li Zhuokai Zhuang Bin Xu Dabiao Wang Huichuan Yu Lanlan Li |
| author_facet | Yihuang Hu Juan Li Zhuokai Zhuang Bin Xu Dabiao Wang Huichuan Yu Lanlan Li |
| author_sort | Yihuang Hu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-10T06:21:05Z |
| format | Article |
| id | doaj.art-df2d310b8fd54699a574fe41f86674ca |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-10T06:21:05Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-df2d310b8fd54699a574fe41f86674ca2023-03-02T05:00:03ZengElsevierHeliyon2405-84402023-02-0192e13094Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancerYihuang Hu0Juan Li1Zhuokai Zhuang2Bin Xu3Dabiao Wang4Huichuan Yu5Lanlan Li6Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350108, ChinaDepartment of Endoscopic Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510655, ChinaGuangdong 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; Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, 510655, ChinaFujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350108, ChinaCollege of Chemical and Engineering, Fuzhou University, Fuzhou, 350108, China; Corresponding author.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; Corresponding author.Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350108, China; Corresponding author.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.http://www.sciencedirect.com/science/article/pii/S2405844023003018Deep learningMRICTNeoadjuvant therapyRectal cancer |
| spellingShingle | Yihuang Hu Juan Li Zhuokai Zhuang Bin Xu Dabiao Wang Huichuan Yu Lanlan Li Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer Heliyon Deep learning MRI CT Neoadjuvant therapy Rectal cancer |
| title | Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer |
| title_full | Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer |
| title_fullStr | Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer |
| title_full_unstemmed | Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer |
| title_short | Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer |
| title_sort | automatic treatment outcome prediction with deepinteg based on multimodal radiological images in rectal cancer |
| topic | Deep learning MRI CT Neoadjuvant therapy Rectal cancer |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023003018 |
| work_keys_str_mv | AT yihuanghu automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer AT juanli automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer AT zhuokaizhuang automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer AT binxu automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer AT dabiaowang automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer AT huichuanyu automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer AT lanlanli automatictreatmentoutcomepredictionwithdeepintegbasedonmultimodalradiologicalimagesinrectalcancer |