Artificial intelligence vs. radiologist: accuracy of wrist fracture detection on radiographs.

OBJECTIVE: To compare the performances of artificial intelligence (AI) to those of radiologists in wrist fracture detection on radiographs. METHODS: This retrospective study included 637 patients (1917 radiographs) with wrist trauma between January 2017 and December 2019. The AI software used was a deep neuronal network algorithm. Ground truth was established by three senior musculoskeletal radiologists who compared the initial radiology reports (IRR) made by non-specialized radiologists, the results of AI, and the combination of AI and IRR (IR+AI) RESULTS: A total of 318 fractures were reported by the senior radiologists in 247 patients. Sensitivity of AI (83%; 95% CI: 78-87%) was significantly greater than that of IRR (76%; 95% CI: 70-81%) (p < 0.001). Specificities were similar for AI (96%; 95% CI: 93-97%) and for IRR (96%; 95% CI: 94-98%) (p = 0.80). The combination of AI+IRR had a significantly greater sensitivity (88%; 95% CI: 84-92%) compared to AI and IRR (p < 0.001) and a lower specificity (92%; 95% CI: 89-95%) (p < 0.001). The sensitivity for scaphoid fracture detection was acceptable for AI (84%) and IRR (80%) but poor for the detection of other carpal bones fracture (41% for AI and 26% for IRR). CONCLUSIONS: Performance of AI in wrist fracture detection on radiographs is better than that of non-specialized radiologists. The combination of AI and radiologist's analysis yields best performances. KEY POINTS: • Artificial intelligence has better performances for wrist fracture detection compared to non-expert radiologists in daily practice. • Performance of artificial intelligence greatly differs depending on the anatomical area. • Sensitivity of artificial intelligence for the detection of carpal bones fractures is 56%.

First stellar photons for an integrated optics discrete beam combiner at the William Herschel Telescope.

We present the first on-sky results of a four-telescope integrated optics discrete beam combiner (DBC) tested at the 4.2 m William Herschel Telescope. The device consists of a four-input pupil remapper followed by a DBC and a 23-output reformatter. The whole device was written monolithically in a single alumino-borosilicate substrate using ultrafast laser inscription. The device was operated at astronomical H-band (1.6 µm), and a deformable mirror along with a microlens array was used to inject stellar photons into the device. We report the measured visibility amplitudes and closure phases obtained on Vega and Altair that are retrieved using the calibrated transfer matrix of the device. While the coherence function can be reconstructed, the on-sky results show significant dispersion from the expected values. Based on the analysis of comparable simulations, we find that such dispersion is largely caused by the limited signal-to-noise ratio of our observations. This constitutes a first step toward an improved validation of the DBC as a possible beam combination scheme for long-baseline interferometry.

Wave-front reconstruction from multidirectional phase derivatives generated by multilateral shearing interferometers.

To increase the accuracy of wave-front evaluation, we propose to exploit the natural capability of multiple lateral shearing interferometers to measure simultaneously more than two orthogonal phase derivatives. We also describe a method, based on Fourier-transform analysis, that uses this multiple information to reconstruct the wave-front under study.