Detection and subtyping of hepatic echinococcosis from plain CT images with deep learning: a retrospective, multicentre study

Background Hepatic echinococcosis is a severe endemic disease in some underdeveloped rural areas worldwide. Qualified physicians are in short supply in such areas, resulting in low rates of accurate diagnosis of this condition. In this study, we aimed to develop and evaluate an artificial intelligence (AI) system for automated detection and subtyping of hepatic echinococcosis using plain CT images with the goal of providing interpretable assistance to radiologists and clinicians.Methods We developed EDAM, an echinococcosis diagnostic AI system, to provide accurate and generalisable CT analysis for distinguishing hepatic echinococcosis from hepatic cysts and normal controls (no liver lesions), as well as subtyping hepatic echinococcosis as alveolar or cystic echinococcosis. EDAM includes a slice-level prediction model for lesion classification and segmentation and a patient-level diagnostic model for patient classification. We collected a plain CT database (n=700: 395 cystic echinococcosis, 122 alveolar echinococcosis, 130 hepatic cysts, and 53 normal controls) for developing EDAM, and two additional independent cohorts (n=156) for external validation of its performance and generalisation ability. We compared the performance of EDAM with 52 experienced radiologists in diagnosing and subtyping hepatic echinococcosis.Findings EDAM showed reliable performance in patient-level diagnosis on both the internal testing data (overall area under the receiver operating characteristic curve [AUC]: 0 center dot 974 [95% CI 0 center dot 936-0 center dot 994]; accuracy: 0 center dot 952 [0 center dot 939-0 center dot 965] for cystic echinococcosis, 0 center dot 981 [0 center dot 973-0 center dot 989] for alveolar echinococcosis; sensitivity: 0 center dot 966 [0 center dot 951-0 center dot 979] for cystic echinococcosis, 0 center dot 944 [0 center dot 908-0 center dot 970] for alveolar echinococcosis) and the external testing set (overall AUC: 0 center dot 953 [95% CI 0 center dot 840-0 center dot 973]; accuracy: 0 center dot 929 [0 center dot 915-0 center dot 947] for cystic echinococcosis, 0 center dot 936 [0 center dot 919-0 center dot 950] for alveolar echinococcosis; sensitivity: 0 center dot 913 [0 center dot 879-0 center dot 944] for cystic echinococcosis, 0 center dot 868 [0 center dot 841-0 center dot 897] for alveolar echinococcosis). The sensitivity of EDAM was robust across images from different CT manufacturers. EDAM outperformed most of the enrolled radiologists in detecting both alveolar echinococcosis and cystic echinococcosis.Interpretation EDAM is a clinically applicable AI system that can provide patient-level diagnoses with interpretable results. The accuracy and generalisation ability of EDAM demonstrates its potential for clinical use, especially in underdeveloped areas.