Artificial intelligence to diagnose meniscus tears on MRI.

PURPOSE: The purpose of this study was to build and evaluate a high-performance algorithm to detect and characterize the presence of a meniscus tear on magnetic resonance imaging examination (MRI) of the knee. MATERIAL AND METHODS: An algorithm was trained on a dataset of 1123 MR images of the knee. We separated the main task into three sub-tasks: first to detect the position of both horns, second to detect the presence of a tear, and last to determine the orientation of the tear. An algorithm based on fast-region convolutional neural network (CNN) and faster-region CNN, was developed to classify the tasks. The algorithm was thus used on a test dataset composed of 700 images for external validation. The performance metric was based on area under the curve (AUC) analysis for each task and a final weighted AUC encompassing the three tasks was calculated. RESULTS: The use of our algorithm yielded an AUC of 0.92 for the detection of the position of the two meniscal horns, of 0.94 for the presence of a meniscal tear and of 083 for determining the orientation of the tear, resulting in a final weighted AUC of 0.90. CONCLUSION: We demonstrate that our algorithm based on fast-region CNN is able to detect meniscal tears and is a first step towards developing more end-to-end artificial intelligence-powered diagnostic tools.

Electron cooling and debye-waller effect in photoexcited bismuth.

By means of first principles calculations, we compute the effective electron-phonon coupling constant G(0) governing the electron cooling in photoexcited bismuth. G(0) strongly increases as a function of electron temperature, which can be traced back to the semimetallic nature of bismuth. We also use a thermodynamical model to compute the time evolution of both electron and lattice temperatures following laser excitation. Thereby, we simulate the time evolution of (1 -1 0), (-2 1 1) and (2 -2 0) Bragg peak intensities measured by Sciaini et al. [Nature (London) 458, 56 (2009)] in femtosecond electron diffraction experiments. The effect of the electron temperature on the Debye-Waller factors through the softening of all optical modes across the whole Brillouin zone turns out to be crucial to reproduce the time evolution of these Bragg peak intensities.

Entropy driven atomic motion in laser-excited bismuth.

We introduce a thermodynamical model based on the two-temperature approach in order to fully understand the dynamics of the coherent A(1g) phonon in laser-excited bismuth. Using this model, we simulate the time evolution of (111) Bragg peak intensities measured by Fritz et al. [Science 315, 633 (2007)] in femtosecond x-ray diffraction experiments performed on a bismuth film for different laser fluences. The agreement between theoretical and experimental results is striking not only because we use fluences very close to the experimental ones but also because most of the model parameters are obtained from ab initio calculations performed for different electron temperatures.