Publications by authors named "Shijie Dang"
Purpose: This study aims to combine deep learning features with radiomics features for the computer-assisted preoperative assessment of meningioma consistency.
Methods: 202 patients with surgery and pathological diagnosis of meningiomas at our institution between December 2016 and December 2018 were retrospectively included in the study. The T2-fluid attenuated inversion recovery (T2-Flair) images were evaluated to classify meningioma as soft or hard by professional neurosurgeons based on Zada's consistency grading system.
Article Synopsis
- This study explored how effective convolutional neural networks and transformers are for detecting and accurately segmenting meningioma tumors in MRI scans.
- Using data from 523 patients, the researchers trained models with a majority of cases and tested them, achieving high accuracy rates (up to 97.3%) and consistent results with experienced radiologists.
- The findings suggest that the proposed deep learning approach could greatly enhance the efficiency of diagnosing and segmenting meningiomas, rivaling the performance of intermediate and senior radiologists.
Objectives: Although recent animal studies have highlighted the importance of cardiorespiratory coupling in the pathogenesis of hypertension, little research has assessed the cardiorespiratory coupling in humans at high risk of developing hypertension. The aim of this study was to investigate the cardiorespiratory coupling in healthy young individuals genetically predisposed to hypertension at both rest and mental stress conditions.
Methods: We studied 39 normotensive male participants [21 with (FH+) and 18 without (FH-) a family history of hypertension].