机构：[1]Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200025, China.[2]School of Mathematical Sciences, Zhejiang University, Hangzhou 310013, China.[3]Zhejiang Qiushi Institute for Mathematical Medicine, Hangzhou 311121, China.[4]College of Mathematical Medicine, Zhejiang Normal University, Jinhua 321004, China.[5]Department of Ultrasound, Puyang People's Hospital, Puyang 457005, China.[6]Demetics Medical Technology, Hangzhou 310012, China.[7]Department of Ultrasound, Gansu Provincial Cancer Hospital, Lanzhou 730050, China.[8]Department of Ultrasound, Shanxi Provincial People's Hospital, Taiyuan 030012, China.[9]Department of Ultrasound, The First Affiliated Hospital, Zhengzhou University, Zhengzhou 450052, China.[10]Department of Ultrasound, Affiliated Hospital of Guizhou Medical University, Guiyang 550001, China.[11]Department of Ultrasound, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Kunming 650031, China.[12]Department of Ultrasound Diagnostics, Tangdu Hospital, Fourth Military Medical University, Xi'an 710038, China.[13]Department of Ultrasound, Affiliated Hospital of Yan'an University, School of Medicine, Yan'an University, Yan'an 716000, China.[14]Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China.江苏省人民医院[15]Department of Ultrasound, Traditional Chinese Medical Hospital of Xinjiang, Urumqi 830000, China.[16]Department of Ultrasound, Anyang Tumor Hospital, The Fourth Affiliated Hospital of Henan University of Science and Technology, Anyang 455000, China.
We present a Human Artificial Intelligence Hybrid (HAIbrid) integrating framework that reweights Thyroid Imaging Reporting and Data System (TIRADS) features and the malignancy score predicted by a convolutional neural network (CNN) for nodule malignancy stratification and diagnosis. We defined extra ultrasonographical features from color Doppler images to explore malignancy-relevant features. We proposed Gated Attentional Factorization Machine (GAFM) to identify second-order interacting features trained via a 10 fold distribution-balanced stratified cross-validation scheme on ultrasound images of 3002 nodules all finally characterized by postoperative pathology (1270 malignant ones), retrospectively collected from 131 hospitals. Our GAFM-HAIbrid model demonstrated significant improvements in Area Under the Curve (AUC) value (p-value < 10-5), reaching about 0.92 over the standalone CNN (~0.87) and senior radiologists (~0.86), and identified a second-order vascularity localization and morphological pattern which was overlooked if only first-order features were considered. We validated the advantages of the integration framework on an already-trained commercial CNN system and our findings using an extra set of ultrasound images of 500 nodules. Our HAIbrid framework allows natural integration to clinical workflow for thyroid nodule malignancy risk stratification and diagnosis, and the proposed GAFM-HAIbrid model may help identify novel diagnosis-relevant second-order features beyond ultrasonography.
基金：
National Natural Science Foundation of China, grant
numbers 12090020, 12090025 and 82071928 and in part by the Natural Science Foundation of Zhejiang
Province under Grant LSD19H180005.
语种：
外文
PubmedID：
中科院(CAS)分区：
出版当年[2022]版：
大类|2 区医学
小类|2 区肿瘤学
最新[2023]版：
大类|2 区医学
小类|3 区肿瘤学
第一作者：
第一作者机构：[1]Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200025, China.
共同第一作者：
通讯作者：
推荐引用方式(GB/T 7714)：
Jia Xiaohong,Ma Zehao,Kong Dexing,et al.Novel Human Artificial Intelligence Hybrid Framework Pinpoints Thyroid Nodule Malignancy and Identifies Overlooked Second-Order Ultrasonographic Features[J].Cancers.2022,14(18):doi:10.3390/cancers14184440.
医学