A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation
Purpose: This study aimed to build a deep learning system using enhanced computed tomography (CT) portal-phase images for predicting colorectal cancer patients’ preoperative staging and RAS gene mutation status. Methods: The contrast-enhanced CT image dataset comprises the CT portal-phase images fro...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/18/4497 |
| _version_ | 1797580888925536256 |
|---|---|
| author | Na Lu Xiao Guan Jianguo Zhu Yuan Li Jianping Zhang |
| author_facet | Na Lu Xiao Guan Jianguo Zhu Yuan Li Jianping Zhang |
| author_sort | Na Lu |
| collection | DOAJ |
| description | Purpose: This study aimed to build a deep learning system using enhanced computed tomography (CT) portal-phase images for predicting colorectal cancer patients’ preoperative staging and RAS gene mutation status. Methods: The contrast-enhanced CT image dataset comprises the CT portal-phase images from a retrospective cohort of 231 colorectal cancer patients. The deep learning system was developed via migration learning for colorectal cancer detection, staging, and RAS gene mutation status prediction. This study used pre-trained Yolov7, vision transformer (VIT), swin transformer (SWT), EfficientNetV2, and ConvNeXt. 4620, and contrast-enhanced CT images and annotated tumor bounding boxes were included in the tumor identification and staging dataset. A total of 19,700 contrast-enhanced CT images comprise the RAS gene mutation status prediction dataset. Results: In the validation cohort, the Yolov7-based detection model detected and staged tumors with a mean accuracy precision (IoU = 0.5) (mAP_0.5) of 0.98. The area under the receiver operating characteristic curve (AUC) in the test set and validation set for the VIT-based prediction model in predicting the mutation status of the RAS genes was 0.9591 and 0.9554, respectively. The detection network and prediction network of the deep learning system demonstrated great performance in explaining contrast-enhanced CT images. Conclusion: In this study, a deep learning system was created based on the foundation of contrast-enhanced CT portal-phase imaging to preoperatively predict the stage and RAS mutation status of colorectal cancer patients. This system will help clinicians choose the best treatment option to increase colorectal cancer patients’ chances of survival and quality of life. |
| first_indexed | 2024-03-10T22:57:27Z |
| format | Article |
| id | doaj.art-93e1c29313f14e3ab237275877aab214 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T22:57:27Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-93e1c29313f14e3ab237275877aab2142023-11-19T09:54:39ZengMDPI AGCancers2072-66942023-09-011518449710.3390/cancers15184497A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS MutationNa Lu0Xiao Guan1Jianguo Zhu2Yuan Li3Jianping Zhang4Department of General Surgery, The Second Affiliated Hospital of Nanjing Medical University, No. 121, Jiangjiayuan Road, Nanjing 210011, ChinaDepartment of General Surgery, The Second Affiliated Hospital of Nanjing Medical University, No. 121, Jiangjiayuan Road, Nanjing 210011, ChinaDepartment of Radiology, The Second Affiliated Hospital of Nanjing Medical University, Nanjing 210011, ChinaKey Laboratory of Modern Toxicology, Ministry of Education, School of Public Health, Nanjing Medical University, Nanjing 211166, ChinaDepartment of General Surgery, The Second Affiliated Hospital of Nanjing Medical University, No. 121, Jiangjiayuan Road, Nanjing 210011, ChinaPurpose: This study aimed to build a deep learning system using enhanced computed tomography (CT) portal-phase images for predicting colorectal cancer patients’ preoperative staging and RAS gene mutation status. Methods: The contrast-enhanced CT image dataset comprises the CT portal-phase images from a retrospective cohort of 231 colorectal cancer patients. The deep learning system was developed via migration learning for colorectal cancer detection, staging, and RAS gene mutation status prediction. This study used pre-trained Yolov7, vision transformer (VIT), swin transformer (SWT), EfficientNetV2, and ConvNeXt. 4620, and contrast-enhanced CT images and annotated tumor bounding boxes were included in the tumor identification and staging dataset. A total of 19,700 contrast-enhanced CT images comprise the RAS gene mutation status prediction dataset. Results: In the validation cohort, the Yolov7-based detection model detected and staged tumors with a mean accuracy precision (IoU = 0.5) (mAP_0.5) of 0.98. The area under the receiver operating characteristic curve (AUC) in the test set and validation set for the VIT-based prediction model in predicting the mutation status of the RAS genes was 0.9591 and 0.9554, respectively. The detection network and prediction network of the deep learning system demonstrated great performance in explaining contrast-enhanced CT images. Conclusion: In this study, a deep learning system was created based on the foundation of contrast-enhanced CT portal-phase imaging to preoperatively predict the stage and RAS mutation status of colorectal cancer patients. This system will help clinicians choose the best treatment option to increase colorectal cancer patients’ chances of survival and quality of life.https://www.mdpi.com/2072-6694/15/18/4497colorectal cancerstageRAS statusdeep learningconvolutional neural networkstransformer |
| spellingShingle | Na Lu Xiao Guan Jianguo Zhu Yuan Li Jianping Zhang A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation Cancers colorectal cancer stage RAS status deep learning convolutional neural networks transformer |
| title | A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation |
| title_full | A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation |
| title_fullStr | A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation |
| title_full_unstemmed | A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation |
| title_short | A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation |
| title_sort | contrast enhanced ct based deep learning system for preoperative prediction of colorectal cancer staging and ras mutation |
| topic | colorectal cancer stage RAS status deep learning convolutional neural networks transformer |
| url | https://www.mdpi.com/2072-6694/15/18/4497 |
| work_keys_str_mv | AT nalu acontrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT xiaoguan acontrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT jianguozhu acontrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT yuanli acontrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT jianpingzhang acontrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT nalu contrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT xiaoguan contrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT jianguozhu contrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT yuanli contrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation AT jianpingzhang contrastenhancedctbaseddeeplearningsystemforpreoperativepredictionofcolorectalcancerstagingandrasmutation |