Hao Yang

Many patients with ischaemia with non-obstructive coronary arteries (INOCA) have a poor prognosis. This study aims to explore the diagnostic value of left ventricular hypertrophy (LVH)-related ultrasound parameters in INOCA patients. The study group consisted of 258 patients with INOCA in this retrospective cross-sectional study, and these patients were free of obstructive coronary artery disease, previous revascularization, atrial fibrillation, ejection fraction < 50%, major distortions of left ventricular geometry, suspected non-ischaemic causes. Control individuals were matched 1:1 with study group according to age, sex, cardiovascular risk factors, and time of hospital stay. According to left ventricular mass index (LVMI) and relative wall thickness, left ventricular geometry was composed of concentric hypertrophy, eccentric hypertrophy, concentric remodeling and normal geometry. LVH-related parameters, left ventricular geometry, demographic characteristics, laboratory parameters and other echocardiographic indicators were compared between the two groups. Subgroup analysis was performed based on sex. LVMI in the study group was higher than that in the control group (86.86 ± 18.83 g/m² vs 82.25 ± 14.29 g/m², P = 0.008). The ratio of LVH was higher in the study group (20.16% vs 10.85%, P = 0.006). After subgroup analysis based on sex, LVMI differences (85.77 ± 18.30 g/m² vs 81.59 ± 14.64 g/m², P = 0.014) and the ratio of LVH differences (25.00% vs 14.77%, P = 0.027) still existed in females between the two groups. There was no difference in the constituent ratio of left ventricular geometry between the two groups (P = 0.157). Sex-based subgroup analysis showed no difference in the constituent ratio of left ventricular geometry between the two groups in females (P = 0.242). The degree of LVH in the study group was higher than that in the control group, suggesting that LVH may play an important role in the occurrence and development of INOCA. Moreover, LVH-related ultrasound parameters may be of higher diagnostic value for female INOCA patients than for male INOCA patients.

Background: Identifying cervical lymph node metastasis (LNM) in primary thyroid cancer preoperatively using ultrasound is challenging. Therefore, a non-invasive method is needed to assess LNM accurately. Purpose: To address this need, we developed the Primary Thyroid Cancer Lymph Node Metastasis Assessment System (PTC-MAS), a transfer learning-based and B-mode ultrasound images-based automatic assessment system for assessing LNM in primary thyroid cancer. Methods: The system has two parts: YOLO Thyroid Nodule Recognition System (YOLOS) for obtaining regions of interest (ROIs) of nodules, and LMM assessment system for building the LNM assessment system using transfer learning and majority voting with extracted ROIs as input. We retained the relative size features of nodules to improve the system’s performance. Results: We evaluated three transfer learning-based neural networks (DenseNet, ResNet, and GoogLeNet) and majority voting, which had the area under the curves (AUCs) of 0.802, 0.837, 0.823, and 0.858, respectively. Method III preserved relative size features and achieved higher AUCs than Method II, which fixed nodule size. YOLOS achieved high precision and sensitivity on a test set, indicating its potential for ROIs extraction. Conclusions: Our proposed PTC-MAS system effectively assesses primary thyroid cancer LNM based on preserving nodule relative size features. It has potential for guiding treatment modalities and avoiding inaccurate ultrasound results due to tracheal interference.