Institutional Repository of Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
| A multi-scale, multi-region and attention mechanism-based deep learning framework for prediction of grading in hepatocellular carcinoma | |
Wei, Jingwei1,2 ; Ji, Qian3; Gao, Yu4,5; Yang, Xiaozhen6; Guo, Donghui7; Gu, Dongsheng1,2; Yuan, Chunwang6; Tian, Jie1,2,8,9; Ding, Dawei4,5
| |
| Source Publication | MEDICAL PHYSICS
 |
| ISSN | 0094-2405 |
| 2022-12-10 | |
| Pages | 13 |
| Corresponding Author | Yuan, Chunwang(yuancw@ccmu.edu.cn) ; Tian, Jie(tian@ieee.org) ; Ding, Dawei(dingdawei@ustb.edu.cn) |
| Abstract | BackgroundHistopathological grading is a significant risk factor for postsurgical recurrence in hepatocellular carcinoma (HCC). Preoperative knowledge of histopathological grading could provide instructive guidance for individualized treatment decision-making in HCC management. PurposeThis study aims to develop and validate a newly proposed deep learning model to predict histopathological grading in HCC with improved accuracy. MethodsIn this dual-centre study, we retrospectively enrolled 384 HCC patients with complete clinical, pathological and radiological data. Aiming to synthesize radiological information derived from both tumour parenchyma and peritumoral microenvironment regions, a modelling strategy based on a multi-scale and multi-region dense connected convolutional neural network (MSMR-DenseCNNs) was proposed to predict histopathological grading using preoperative contrast enhanced computed tomography (CT) images. Multi-scale inputs were defined as three-scale enlargement of an original minimum bounding box in width and height by given pixels, which correspondingly contained more peritumoral analysis areas with the enlargement. Multi-region inputs were defined as three regions of interest (ROIs) including a squared ROI, a precisely delineated tumour ROI, and a peritumoral tissue ROI. The DenseCNN structure was designed to consist of a shallow feature extraction layer, dense block module, and transition and attention module. The proposed MSMR-DenseCNN was pretrained by the ImageNet dataset to capture basic graphic characteristics from the images and was retrained by the collected retrospective CT images. The predictive ability of the MSMR-DenseCNN models on triphasic images was compared with a conventional radiomics model, radiological model and clinical model. ResultsMSMR-DenseCNN applied to the delayed phase (DP) achieved the highest area under the curve (AUC) of 0.867 in the validation cohort for grading prediction, outperforming those on the arterial phase (AP) and portal venous phase (PVP). Fusion of the results on triphasic images did not increase the predictive ability, which underscored the role of DP for grading prediction. Compared with a single-scale and single-region network, the DP-phase based MSMR-DenseCNN model remarkably raised sensitivity from 67.4% to 75.5% with comparable specificity of 78.6%. MSMR-DenseCNN on DP defeated conventional radiomics, radiological and clinical models, where the AUCs were correspondingly 0.765, 0.695 and 0.612 in the validation cohort. ConclusionsThe MSMR-DenseCNN modelling strategy increased the accuracy for preoperative prediction of grading in HCC, and enlightens similar radiological analysis pipelines in a variety of clinical scenarios in HCC management. |
| Keyword | computed tomography deep learning hepatocellular carcinoma histopathological grading radiomics |
| DOI | 10.1002/mp.16127 |
| WOS Keyword | CANCER |
| Indexed By | SCI |
| Language | 英语 |
| Funding Project | National Key Research and Development Program of China[2017YFA0700401] ; National Key Research and Development Program of China[2021YFC2500402] ; National Key Research and Development Program of China[2022YFC2503700] ; National Key Research and Development Program of China[2022YFC2503705] ; Ministry of Science and Technology of China[2017YFA0205200] ; National Natural Science Foundation of China[82001917] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[82090052] ; National Natural Science Foundation of China[82090051] ; National Natural Science Foundation of China[82093219055] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[92159202] ; National Natural Science Foundation of China[81527805] ; National Natural Science Foundation of China[U22A2023] ; National Natural Science Foundation of China[U22A20343] ; Beijing Natural Science Foundation[L192061] |
| Funding Organization | National Key Research and Development Program of China ; Ministry of Science and Technology of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation |
| WOS Research Area | Radiology, Nuclear Medicine & Medical Imaging |
| WOS Subject | Radiology, Nuclear Medicine & Medical Imaging |
| WOS ID | WOS:000896883400001 |
| Publisher | WILEY |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/51321 |
| Collection | 中国科学院分子影像重点实验室 |
| Corresponding Author | Yuan, Chunwang; Tian, Jie; Ding, Dawei |
| Affiliation | 1.Chinese Acad Sci, Inst Automat, Key Lab Mol Imaging, Beijing 100190, Peoples R China 2.Beijing Key Lab Mol Imaging, Beijing, Peoples R China 3.Tianjin First Cent Hosp, Oriental Organ Transplant Ctr, Tianjin, Peoples R China 4.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 5.Univ Sci & Technol Beijing, Key Lab Knowledge Automat Ind Proc, Minist Educ, Beijing, Peoples R China 6.Capital Med Univ, Beijing Youan Hosp, Ctr Intervent Oncol & Liver Dis, Beijing 100069, Peoples R China 7.Zhejiang Shuren Univ, Shulan Int Med Coll, Shulan Hangzhou Hosp, Hangzhou, Zhejiang, Peoples R China 8.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med, Beijing, Peoples R China 9.Xidian Univ, Engn Res Ctr Mol & Neuro Imaging, Sch Life Sci & Technol, Minist Educ, Xian, Shaanxi, Peoples R China |
| First Author Affilication | Institute of Automation, Chinese Academy of Sciences |
| Corresponding Author Affilication | Institute of Automation, Chinese Academy of Sciences |
| Recommended Citation GB/T 7714 | Wei, Jingwei,Ji, Qian,Gao, Yu,et al. A multi-scale, multi-region and attention mechanism-based deep learning framework for prediction of grading in hepatocellular carcinoma[J]. MEDICAL PHYSICS,2022:13. |
| APA | Wei, Jingwei.,Ji, Qian.,Gao, Yu.,Yang, Xiaozhen.,Guo, Donghui.,...&Ding, Dawei.(2022).A multi-scale, multi-region and attention mechanism-based deep learning framework for prediction of grading in hepatocellular carcinoma.MEDICAL PHYSICS,13. |
| MLA | Wei, Jingwei,et al."A multi-scale, multi-region and attention mechanism-based deep learning framework for prediction of grading in hepatocellular carcinoma".MEDICAL PHYSICS (2022):13. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment