Preoperative and Prognostic Prediction of Microvascular Invasion in Hepatocellular Carcinoma: A Review Based on Artificial Intelligence.

Microvascular invasion of hepatocellular carcinoma is an important factor affecting tumor recurrence after liver resection and liver transplantation. There are many ways to classify microvascular invasion, however, an international consensus is urgently needed. Recently, artificial intelligence has emerged as an important tool for improving the clinical management of hepatocellular carcinoma. Many studies about microvascular invasion currently focus on preoperative and prognosis prediction of microvascular invasion using artificial intelligence. In this paper, we review the definition and staging of microvascular invasion, especially the diagnosis of it by using artificial intelligence. In preoperative prediction, deep learning based on multimodal data modeling of radiomics-screened features, clinical features, and medical images is currently the most effective means. In prognostic prediction, pathology is the gold standard, and the techniques used should more effectively utilize the global features of the pathology images.

Nondestructive evaluation of thickness variations for elastic plates by high-overtone bulk acoustic resonance.

Based on the resonant frequency spectra of a high-overtone bulk acoustic resonance, a model for nondestructive evaluation of the elastic plate thickness is given. The simulations demonstrate that the thickness deviations of the elastic plates are sensitive to two parameters: the parallel resonance frequencies and the spacing of parallel resonance frequencies (SPRF). At the normal and transition regions of the SPRF curves, the parallel resonance frequencies periodically linearly decrease with the increase of thickness deviations, which is applicable for evaluating the thickness deviations of the plates.

Effects of shapes and symmetries of scatterers on acoustic dual-negative refraction.

The potential operating conditions of acoustic dual-negative refraction (ADNR) are investigated by band structure theory for scatterers with different shapes and symmetries. Specifically, two types of lattices (triangular and honeycomb) and four different shapes of scatterers (circle, hexagon, square and triangle) are considered. Based on the generation mechanism of the ADNR effect, which is dependent on the frequency of the incident wave at the overlapping second and third Bloch bands, the optimum operating frequencies of ADNR with different crystal structures are given. The calculations demonstrate that the ADNR effect can be generated at the normalized frequency from 0.8 to 1.05.

Broadband acoustic concentrator with multilayered alternative homogeneous materials.

A two-dimensional cylindrical acoustic concentrator is designed with multilayered alternative homogeneous materials, which can focus acoustic field and enhance acoustic energy in a given area. The frequency response analysis of the acoustic concentrator demonstrates that the acoustic energy can be concentrated within the device over a wide frequency band. Meanwhile, there are contradictory relations between the acoustic concentrating performances in the inner region and the scattering properties in the outer region of these concentrators. When the contradictory relations satisfy compromise balance, the concentration ratio can reach at least 70%.