Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis.

PURPOSE: Fracture detection is one of the most commonly used and studied aspects of artificial intelligence (AI) in medicine. In this systematic review and meta-analysis, we aimed to summarize available literature and data regarding AI performance in fracture detection on plain radiographs and various factors affecting it. METHODS: We systematically reviewed studies evaluating AI algorithms in detecting bone fractures in plain radiographs, combined their performance using meta-analysis (a bivariate regression approach), and compared it with that of clinicians. We also analyzed the factors potentially affecting algorithm performance using meta-regression. RESULTS: Our analysis included 100 studies. In 83 studies with confusion matrices, AI algorithms showed a sensitivity of 91.43% and a specificity of 92.12% (Area under the summary receiver operator curve = 0.968). After adjustment and false discovery rate correction, tibia/fibula (excluding ankle) fractures were associated with higher (7.0%, p=0.004) AI sensitivity, while more recent publications (5.5%, p=0.003) and Xception architecture (6.6%, p<0.001) were associated with higher specificity. Clinicians and AI showed similar specificity in fracture identification, although AI leaned to higher sensitivity (7.6%, p=0.07). Radiologists, on the other hand, were more specific than AI overall and in several subgroups, and more sensitive to hip fractures before FDR correction. CONCLUSIONS: Currently available AI aids could result in a significant improvement in care where radiologists are not readily available. Moreover, identifying factors affecting algorithm performance could guide AI development teams in their process of optimizing their products.

Qualitative and quantitative DECT pulmonary angiography in COVID-19 pneumonia and pulmonary embolism.

AIM: To assess differences in qualitative and quantitative parameters of pulmonary perfusion from dual-energy computed tomography (CT) pulmonary angiography (DECT-PA) in patients with COVID-19 pneumonia with and without pulmonary embolism (PE). MATERIALS AND METHODS: This retrospective institutional review board-approved study included 74 patients (mean age 61±18 years, male:female 34:40) with COVID-19 pneumonia in two countries (one with 68 patients, and the other with six patients) who underwent DECT-PA on either dual-source (DS) or single-source (SS) multidetector CT machines. Images from DS-DECT-PA were processed to obtain virtual mono-energetic 40 keV (Mono40), material decomposition iodine (MDI) images and quantitative perfusion statistics (QPS). Two thoracic radiologists determined CT severity scores based on type and extent of pulmonary opacities, assessed presence of PE, and pulmonary parenchymal perfusion on MDI images. The QPS were calculated from the CT Lung Isolation prototype (Siemens). The correlated clinical outcomes included duration of hospital stay, intubation, SpO2 and death. The significance of association was determined by receiver operating characteristics and analysis of variance. RESULTS: One-fifth (20.2%, 15/74 patients) had pulmonary arterial filling defects; most filling defects were occlusive (28/44) located in the segmental and sub-segmental arteries. The parenchymal opacities were more extensive and denser (CT severity score 24±4) in patients with arterial filling defects than without filling defects (20±8; p=0.028). Ground-glass opacities demonstrated increased iodine distribution; mixed and consolidative opacities had reduced iodine on DS-DECT-PA but increased or heterogeneous iodine content on SS-DECT-PA. QPS were significantly lower in patients with low SpO2 (p=0.003), intubation (p=0.006), and pulmonary arterial filling defects (p=0.007). CONCLUSION: DECT-PA QPS correlated with clinical outcomes in COVID-19 patients.

Optimization of Z-axis automatic exposure control for multidetector row CT evaluation of neck and comparison with fixed tube current technique for image quality and radiation dose.

BACKGROUND AND PURPOSE: Z-axis automatic exposure control (AEC) technique automatically adjusts tube current based on size of body region scanned. The purpose of the current study was to compare diagnostic acceptability, noise, and radiation exposure of multidetector row CT (MDCT) of neck performed with z-axis AEC and with fixed current. MATERIALS AND METHODS: Two study groups of 26 patients each underwent MDCT of neck using z-axis AEC with 8 noise index (NI), 150-440 mA, and 10 NI, 75-440 mA, respectively. A control group consisting of another 26 patients underwent MDCT of neck with fixed-current technique (300 mA). Objective noise and mean tube current-time products (mA . s) were recorded. Two radiologists evaluated images for diagnostic acceptability and subjective noise on a 5-point scale. RESULTS: All CT examinations of study and control groups were diagnostically acceptable, though objective noise was significantly more with z-axis AEC (shoulder: NI 8, 20.6 +/- 6.2 HU; NI 10, 22.2 +/- 4.6 HU) than with fixed current (16.2 +/- 6 HU) (P = .01). There was no significant difference between AEC and fixed current in diagnostic acceptability and subjective noise (P = .22-.42). AEC resulted in significant radiation dose reduction (NI 8, 186.3 +/- 20.5 mA . s; NI 10, 158.1 +/- 21.2 mA x s), compared with fixed current (235 +/- 21.8 mA x s). CONCLUSION: Z-axis AEC resulted in similar subjective noise and diagnostic acceptability, with radiation dose reduction of 21% for NI of 8 and 33% for NI of 10, respectively, for MDCT evaluation of neck, compared with those of fixed current technique.

State-of-the-art imaging of pancreatic neoplasms.

Pancreatic imaging with multidetector CT allows multiphase acquisition of thin slices in a single breath-hold and is especially valuable in obtaining isotropic three-dimensional reformations that improves our ability to provide accurate pre-operative vascular mapping. Advanced MR technology allows faster imaging of pancreas, thus facilitating MR cholangiopancreatography. Use of tissue-specific MR contrast agents, endoscopic ultrasound and PET in pancreatic imaging has evolved considerably. This review article discusses the role of CT, MR, endoscopic ultrasound and PET imaging in pancreas.

The role of early flap coverage in the management of open fractures of both bones of the leg.

Sixty patients with type III injuries (open fractures) of the tibia were treated in a prospective fashion by combined orthopaedic and plastic surgical schemes based on the principles of early radical cleaning, a second-look operation, and early coverage of soft tissue defects with an appropriate local or distant flap. Stabilization of fractures was achieved by external fixation in most cases and patients were allowed to walk within 4-8 weeks (partial weight bearing). Bony union was achieved in 23.4 weeks. The mean hospital stay was 3.5 weeks. Limb salvage was achieved in all cases and there were no major complications.