Deep learning radiomics for focal liver lesions diagnosis on long-range contrast-enhanced ultrasound and clinical factors

Quantitative Imaging in Medicine and Surgery

article

Li Liu¹  Chunlin Tang¹  Lu Li³  Ping Chen¹  Ying Tan¹  Xiaofei Hu⁴  Kaixuan Chen¹  Yongning Shang¹  Deng Liu¹  He Liu⁴  Hongjun Liu²  Fang Nie⁵  Jiawei Tian⁶  Mingchang Zhao³  Wen He⁷  Yanli Guo¹ 

[1] Department of Ultrasound, Southwest Hospital , Third Military Medical University ,(Army Medical University);Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging , Third Military Medical University ,(Army Medical University);CHISON Medical Technologies Co., LTD;Department of Radiology, Southwest Hospital , Third Military Medical University ,(Army Medical University);Department of Ultrasound , Lanzhou University Second Hospital;Department of Ultrasound , the Second Affiliated Hospital of Harbin Medical University;Department of Ultrasound, Beijing Tiantan Hospital , Capital Medical University

关键词: Deep learning (DL);    radiomics;    focal liver lesions (FLLs);    contrast-enhanced ultrasound (CEUS);    diagnosis;   

DOI  :  10.21037/qims-21-1004

学科分类：外科医学

来源: AME Publications

【 摘 要 】

Background: Routine clinical factors play an important role in the clinical diagnosis of focal liver lesions (FLLs); however, they are rarely used in computer-assisted diagnosis. Therefore, we developed a deep learning (DL) radiomics model, and investigated its effectiveness in diagnosing FLLs using long-range contrast-enhanced ultrasound (CEUS) cines and clinical factors. Methods: Herein, 303 patients with pathologically confirmed FLLs after surgery at three hospitals were retrospectively enrolled and divided into a training cohort (n=203), internal validation (IV) cohort (n=50) from one hospital with the ratio of 4:1, and external validation (EV) cohort (n=50) from the other two hospitals. Four DL radiomics models, namely Four Stream 3D convolutional neural network (FS3DU) (trained with CEUS cines only), FS3DU+A (trained with CEUS cines and alpha fetoprotein), FS3DU+H (trained with CEUS cines and hepatitis), and FS3DU+A+H (trained with CEUS cines, alpha fetoprotein, and hepatitis), were formed based on 3D convolutional neural networks (CNNs). They used approximately 20-s preoperative CEUS cines and/or clinical factors to extract spatiotemporal features for the classification of FLLs and the location of the region of interest. The area under curve of the receiver operating characteristic and diagnosis speed were calculated to evaluate the models in the IV and EV cohorts, and they were compared with those of two radiologists. Two-sided Delong tests were used to calculate the statistical differences between the models and radiologists. Results: FS3DU+A+H, which incorporated CEUS cines, hepatitis, and alpha fetoprotein, achieved the highest area under curve of 0.969 (95% CI: 0.901–1.000) and 0.957 (95% CI: 0.894–1.000) among radiologists and other models in IV and EV cohorts, respectively. A significant difference was observed when comparing FS3DU and radiologist 2 (all P<0.05). The diagnosis speed of all the models was the same (10.76 s per patient), and it was two times faster than those of the radiologists (radiologist 1: 23.74 and 27.75 s; radiologist 2: 25.95 and 29.50 s in IV and EV cohorts, respectively). Conclusions: The proposed DL radiomics demonstrated excellent performance on the benign and malignant diagnosis of FLLs by combining CEUS cines and clinical factors. It could help the individualized characterization of FLLs, and enhance the accuracy of diagnosis in the future.

【 授权许可】

All Rights reserved