Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography.

We demonstrate an adaptation of deep learning for label-free imaging of the micro-scale lymphatic vessels and aqueous veins in the eye using optical coherence tomography (OCT). The proposed deep learning-based OCT lymphangiography (DL-OCTL) method was trained, validated and tested, using OCT scans (23 volumetric scans comprising 19,736 B-scans) from 11 fresh ex vivo porcine eyes with the corresponding vessel labels generated by a conventional OCT lymphangiography (OCTL) method based on thresholding with attenuation compensation. Compared to conventional OCTL, the DL-OCTL method demonstrates comparable results for imaging lymphatics and aqueous veins in the eye, with an Intersection over Union value of 0.79 ± 0.071 (mean ± standard deviation). In addition, DL-OCTL mitigates the imaging artifacts in conventional OCTL where the OCT signal modelling was corrupted by the tissue heterogeneity, provides ~ 10 times faster processing based on a rough comparison and does not require OCT-related knowledge for correct implementation as in conventional OCTL. With these favorable features, DL-OCTL promises to improve the practicality of OCTL for label-free imaging of lymphatics and aqueous veins for preclinical and clinical imaging applications.

A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images.

Background and objective Thyroid image segmentation is an indispensable part in computer-aided diagnosis systems and medical image diagnoses of thyroid diseases. There have been dozens of studies on thyroid gland segmentation and thyroid nodule segmentation in ultrasound images. The aim of this work is to categorize and review the thyroid gland segmentation and thyroid nodule segmentation methods in medical ultrasound. Methods This work proposes a categorization approach of thyroid gland segmentation and thyroid nodule segmentation methods according to the theoretical bases of segmentation methods. The segmentation methods are categorized into four groups, including contour and shape based methods, region based methods, machine and deep learning methods and hybrid methods. The representative articles are reviewed with detailed descriptions of methods and analyses of correlations between methods. The evaluation metrics for the reviewed segmentation methods are named uniformly in this work. The segmentation performance results using the uniformly named evaluation metrics are compared. Results After careful investigation, 28 representative papers are selected for comprehensive analyses and comparisons in this review. The dominant thyroid gland segmentation methods are machine and deep learning methods. The training of massive data makes these models have better segmentation performance and robustness. But deep learning models usually require plenty of marked training data and long training time. For thyroid nodule segmentation, the most common methods are contour and shape based methods, which have good segmentation performance. However, most of them are tested on small datasets. Conclusions Based on the comprehensive consideration of application scenario, image features, method practicability and segmentation performance, the appropriate segmentation method for specific situation can be selected. Furthermore, several limitations of current thyroid ultrasound image segmentation methods are presented, which may be overcome in future studies, such as the segmentation of pathological or abnormal thyroid glands, identification of the specific nodular diseases, and the standard thyroid ultrasound image datasets.