RESUMO
BACKGROUND: Artificial intelligence (AI) shows promising potential to enhance human decision-making as synergistic augmented intelligence (AuI), but requires critical evaluation for skin cancer screening in a real-world setting. OBJECTIVES: To investigate the perspectives of patients and dermatologists after skin cancer screening by human, artificial and augmented intelligence. METHODS: A prospective comparative cohort study conducted at the University Hospital Basel included 205 patients (at high-risk of developing melanoma, with resected or advanced disease) and 8 dermatologists. Patients underwent skin cancer screening by a dermatologist with subsequent 2D and 3D total-body photography (TBP). Any suspicious and all melanocytic skin lesions ≥3 mm were imaged with digital dermoscopes and classified by corresponding convolutional neural networks (CNNs). Excisions were performed based on dermatologist's melanoma suspicion, study-defined elevated CNN risk-scores and/or melanoma suspicion by AuI. Subsequently, all patients and dermatologists were surveyed about their experience using questionnaires, including quantification of patient's safety sense following different examinations (subjective safety score (SSS): 0-10). RESULTS: Most patients believed AI could improve diagnostic performance (95.5%, n = 192/201). In total, 83.4% preferred AuI-based skin cancer screening compared to examination by AI or dermatologist alone (3D-TBP: 61.3%; 2D-TBP: 22.1%, n = 199). Regarding SSS, AuI induced a significantly higher feeling of safety than AI (mean-SSS (mSSS): 9.5 vs. 7.7, p < 0.0001) or dermatologist screening alone (mSSS: 9.5 vs. 9.1, p = 0.001). Most dermatologists expressed high trust in AI examination results (3D-TBP: 90.2%; 2D-TBP: 96.1%, n = 205). In 68.3% of the examinations, dermatologists felt that diagnostic accuracy improved through additional AI-assessment (n = 140/205). Especially beginners (<2 years' dermoscopic experience; 61.8%, n = 94/152) felt AI facilitated their clinical work compared to experts (>5 years' dermoscopic experience; 20.9%, n = 9/43). Contrarily, in divergent risk assessments, only 1.5% of dermatologists trusted a benign CNN-classification more than personal malignancy suspicion (n = 3/205). CONCLUSIONS: While patients already prefer AuI with 3D-TBP for melanoma recognition, dermatologists continue to rely largely on their own decision-making despite high confidence in AI-results. TRIAL REGISTRATION: ClinicalTrials.gov (NCT04605822).
RESUMO
OBJECTIVE: To assess the diagnostic performance of quantitative and qualitative image parameters in cone-beam computed tomography (CBCT) for diagnosis of bisphosphonate-related osteonecrosis of the jaw (BRONJ). MATERIALS AND METHODS: A BRONJ (22 patients, mean age 70.0 years) group was age and gender matched to a healthy control group (22 patients, mean age 68.0 years). On CBCT images two independent readers performed quantitative bone density value (BDV) measurements with region and volume-of-interest (ROI and VOI) based approaches and qualitative scoring of BRONJ-associated necrosis, sclerosis and periosteal thickening (1 = not present to 5 = definitely present). Intraoperative and clinical findings served as standard of reference. Interreader agreements and diagnostic performance were assessed by intraclass correlation coefficients (ICC), kappa-statistics and receiver-operating characteristic (ROC) analysis. RESULTS: Twenty-three regions in 22 patients were affected by BRONJ. ICC values for mean BDV VOI and mean BDV ROI were 0.864 and 0.968, respectively (p < 0.001). The area under the curve (AUC) for mean BDV VOI and mean BDV ROI was 0.58/0.83 with a sensitivity of 57/83% and specificity of 61/77% for diagnosis of BRONJ, respectively. Kappa values for presence of necrosis, sclerosis and periosteal thickening were 0.575, 0.617 and 0.885, respectively. AUC values for qualitative parameters ranged between 0.90-0.96 with sensitivity of 96% and specificities between 79-96% at respective cutoff scores. CONCLUSIONS: BRONJ can be effectively diagnosed with CBCT. Qualitative image parameters yield a higher diagnostic performance than quantitative parameters, and ROI-based attenuation measurements were more accurate than VOI-based measurements.