RESUMEN
OBJECTIVE: To assess the accuracy of an artificial intelligence (AI) software (BoneMetrics, Gleamer) in performing automated measurements on weight-bearing forefoot and lateral foot radiographs. METHODS: Consecutive forefoot and lateral foot radiographs were retrospectively collected from three imaging institutions. Two senior musculoskeletal radiologists independently annotated key points to measure the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs and the talus-first metatarsal, medial arch, and calcaneus inclination angles on lateral foot radiographs. The ground truth was defined as the mean of their measurements. Statistical analysis included mean absolute error (MAE), bias assessed with Bland-Altman analysis between the ground truth and AI prediction, and intraclass coefficient (ICC) between the manual ratings. RESULTS: Eighty forefoot radiographs were included (53 ± 17 years, 50 women), and 26 were excluded. Ninety-seven lateral foot radiographs were included (51 ± 20 years, 46 women), and 21 were excluded. MAE for the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs were respectively 1.2° (95% CI [1; 1.4], bias = - 0.04°, ICC = 0.98), 0.7° (95% CI [0.6; 0.9], bias = - 0.19°, ICC = 0.91) and 0.9° (95% CI [0.7; 1.1], bias = 0.44°, ICC = 0.96). MAE for the talus-first, medial arch, and calcaneal inclination angles on the lateral foot radiographs were respectively 3.9° (95% CI [3.4; 4.5], bias = 0.61° ICC = 0.88), 1.5° (95% CI [1.2; 1.8], bias = - 0.18°, ICC = 0.95) and 1° (95% CI [0.8; 1.2], bias = 0.74°, ICC = 0.99). Bias and MAE between the ground truth and the AI prediction were low across all measurements. ICC between the two manual ratings was excellent, except for the talus-first metatarsal angle. CONCLUSION: AI demonstrated potential for accurate and automated measurements on weight-bearing forefoot and lateral foot radiographs.
RESUMEN
PURPOSE: To appraise the performances of an AI trained to detect and localize skeletal lesions and compare them to the routine radiological interpretation. METHODS: We retrospectively collected all radiographic examinations with the associated radiologists' reports performed after a traumatic injury of the limbs and pelvis during 3 consecutive months (January to March 2017) in a private imaging group of 14 centers. Each examination was analyzed by an AI (BoneView, Gleamer) and its results were compared to those of the radiologists' reports. In case of discrepancy, the examination was reviewed by a senior skeletal radiologist to settle on the presence of fractures, dislocations, elbow effusions, and focal bone lesions (FBL). The lesion-wise sensitivity of the AI and the radiologists' reports was compared for each lesion type. This study received IRB approval (CRM-2106-177). RESULTS: A total of 4774 exams were included in the study. Lesion-wise sensitivity was 73.7% for the radiologists' reports vs. 98.1% for the AI (+24.4 points) for fracture detection, 63.3% vs. 89.9% (+26.6 points) for dislocation detection, 84.7% vs. 91.5% (+6.8 points) for elbow effusion detection, and 16.1% vs. 98.1% (+82 points) for FBL detection. The specificity of the radiologists' reports was always 100% whereas AI specificity was 88%, 99.1%, 99.8%, 95.6% for fractures, dislocations, elbow effusions, and FBL respectively. The NPV was measured at 99.5% for fractures, 99.8% for dislocations, and 99.9% for elbow effusions and FBL. CONCLUSION: AI has the potential to prevent diagnosis errors by detecting lesions that were initially missed in the radiologists' reports.
