Added value of an artificial intelligence solution for fracture detection in the radiologist's daily trauma emergencies workflow.

PURPOSE: The main objective of this study was to compare radiologists' performance without and with artificial intelligence (AI) assistance for the detection of bone fractures from trauma emergencies. MATERIALS AND METHODS: Five hundred consecutive patients (232 women, 268 men) with a mean age of 37 ± 28 (SD) years (age range: 0.25-99 years) were retrospectively included. Three radiologists independently interpreted radiographs without then with AI assistance after a 1-month minimum washout period. The ground truth was determined by consensus reading between musculoskeletal radiologists and AI results. Patient-wise sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for fracture detection and reading time were compared between unassisted and AI-assisted readings of radiologists. Their performances were also assessed by receiver operating characteristic (ROC) curves. RESULTS: AI improved the patient-wise sensitivity of radiologists for fracture detection by 20% (95% confidence interval [CI]: 14-26), P< 0.001) and their specificity by 0.6% (95% CI: -0.9-1.5; P = 0.47). It increased the PPV by 2.9% (95% CI: 0.4-5.4; P = 0.08) and the NPV by 10% (95% CI: 6.8-13.3; P < 0.001). Thanks to AI, the area under the ROC curve for fracture detection of readers increased respectively by 10.6%, 10.2% and 9.9%. Their mean reading time per patient decreased by respectively 10, 16 and 12 s (P < 0.001). CONCLUSIONS: AI-assisted radiologists work better and faster compared to unassisted radiologists. AI is of great aid to radiologists in daily trauma emergencies, and could reduce the cost of missed fractures.

CT-guided microwave ablation of osteoid osteoma: Long-term outcome in 28 patients.

PURPOSE: The purpose of this study was to assess the long-term efficacy of CT-guided microwave ablation (MWA) in the treatment of osteoid osteoma. Secondary objectives were to assess early outcome and side-effects of MWA. MATERIALS AND METHODS: Twenty-eight consecutive patients (18 men, 10 women) with a median age of 19.5 years (IQR: 16, 25.5) with a total of 28 non-spinal osteoid osteoma treated by CT-guided MWA were retrospectively included. The ablations were performed with a median power and duration of 60 Watt and 1 min 30 s, respectively. Pain referred to osteoid osteoma was assessed at predefined time points using a 0-10 numeric rating scale. At one month, contrast-enhanced follow-up MRI was performed to evaluate the nidus vascularization and the volume of necrosis induced by MWA. Clinical success was defined by the absence of osteoid osteoma-related pain, and technical success was defined by the presence of necrosis of the nidus on the one-month post-MWA MRI. RESULTS: Long term success rate was 93% (26/28) after a follow-up of 55.5 months (IQR: 25.75, 74.5) and technical success rate was 96 % (25/26). One late failure was observed after a patient had been declared cured at one month but the formal proof of a late recurrence of osteoid osteoma could not be brought. Three minor complications were reported including mild reversible superficial radial nerve injury with a skin burn (grade 2) in one patient and moderate skin burn only in two patients. CONCLUSION: Our results suggest that CT-guided MWA is an effective option for a minimally-invasive treatment of osteoid osteoma with a low rate of complication and no late recurrence.

Tumors and pseudotumors of the soft tissues: Imaging semiology and strategy.

The aims of this educational review are to learn the semiological basis of soft-tissue lesions and, with the help of diagnostic algorithms, to apply the current recommendations for the management of soft-tissue tumors. Pseudotumors must first be identified and excluded. Among primary tumors, the search for macroscopic fat content on MRI is decisive; since it restricts the diagnostic range to adipocytic tumors. Key imaging features of non-adipocytic tumors are highlighted. When a deep soft-tissue mass is found, therapeutic abstention or simple monitoring is only appropriate when there is diagnostic certainty: This is only the case for typical pseudotumors, typical benign tumors, and fat tumors without atypical criteria. In all other cases, histological evidence is required. If there is any suspicion of soft-tissue sarcoma or any undetermined lesion, the patient should be referred to a sarcoma referral center before biopsy.