A Coarse-Fine Collaborative Learning Model for Three Vessel Segmentation in Fetal Cardiac Ultrasound Images.

Congenital heart disease (CHD) is the most frequent birth defect and a leading cause of infant mortality, emphasizing the crucial need for its early diagnosis. Ultrasound is the primary imaging modality for prenatal CHD screening. As a complement to the four-chamber view, the three-vessel view (3VV) plays a vital role in detecting anomalies in the great vessels. However, the interpretation of fetal cardiac ultrasound images is subjective and relies heavily on operator experience, leading to variability in CHD detection rates, particularly in resource-constrained regions. In this study, we propose an automated method for segmenting the pulmonary artery, ascending aorta, and superior vena cava in the 3VV using a novel deep learning network named CoFi-Net. Our network incorporates a coarse-fine collaborative strategy with two parallel branches dedicated to simultaneous global localization and fine segmentation of the vessels. The coarse branch employs a partial decoder to leverage high-level semantic features, enabling global localization of objects and suppression of irrelevant structures. The fine branch utilizes attention-parameterized skip connections to improve feature representations and improve boundary information. The outputs of the two branches are fused to generate accurate vessel segmentations. Extensive experiments conducted on a collected dataset demonstrate the superiority of CoFi-Net compared to state-of-the-art segmentation models for 3VV segmentation, indicating its great potential for enhancing CHD diagnostic efficiency in clinical practice. Furthermore, CoFi-Net outperforms other deep learning models in breast lesion segmentation on a public breast ultrasound dataset, despite not being specifically designed for this task, demonstrating its potential and robustness for various segmentation tasks.

A deep learning framework for identifying and segmenting three vessels in fetal heart ultrasound images.

BACKGROUND: Congenital heart disease (CHD) is one of the most common birth defects in the world. It is the leading cause of infant mortality, necessitating an early diagnosis for timely intervention. Prenatal screening using ultrasound is the primary method for CHD detection. However, its effectiveness is heavily reliant on the expertise of physicians, leading to subjective interpretations and potential underdiagnosis. Therefore, a method for automatic analysis of fetal cardiac ultrasound images is highly desired to assist an objective and effective CHD diagnosis. METHOD: In this study, we propose a deep learning-based framework for the identification and segmentation of the three vessels-the pulmonary artery, aorta, and superior vena cava-in the ultrasound three vessel view (3VV) of the fetal heart. In the first stage of the framework, the object detection model Yolov5 is employed to identify the three vessels and localize the Region of Interest (ROI) within the original full-sized ultrasound images. Subsequently, a modified Deeplabv3 equipped with our novel AMFF (Attentional Multi-scale Feature Fusion) module is applied in the second stage to segment the three vessels within the cropped ROI images. RESULTS: We evaluated our method with a dataset consisting of 511 fetal heart 3VV images. Compared to existing models, our framework exhibits superior performance in the segmentation of all the three vessels, demonstrating the Dice coefficients of 85.55%, 89.12%, and 77.54% for PA, Ao and SVC respectively. CONCLUSIONS: Our experimental results show that our proposed framework can automatically and accurately detect and segment the three vessels in fetal heart 3VV images. This method has the potential to assist sonographers in enhancing the precision of vessel assessment during fetal heart examinations.

A deep learning-based approach for rectus abdominis segmentation and distance measurement in ultrasonography.

Introduction: Diastasis recti abdominis (DRA) is a common condition in postpartum women. Measuring the distance between separated rectus abdominis (RA) in ultrasound images is a reliable method for the diagnosis of this disease. In clinical practice, the RA distance in multiple ultrasound images of a patient is measured by experienced sonographers, which is time-consuming, labor-intensive, and highly dependent on experience of operators. Therefore, an objective and fully automatic technique is highly desired to improve the DRA diagnostic efficiency. This study aimed to demonstrate the deep learning-based methods on the performance of RA segmentation and distance measurement in ultrasound images. Methods: A total of 675 RA ultrasound images were collected from 94 postpartum women, and were split into training (448 images), validation (86 images), and test (141 images) datasets. Three segmentation models including U-Net, UNet++ and Res-UNet were evaluated on their performance of RA segmentation and distance measurement. Results: Res-UNet model outperformed the other two models with the highest Dice score (85.93% ± 0.26%), the highest MIoU score (76.00% ± 0.39%) and the lowest Hausdorff distance (21.80 ± 0.76 mm). The average physical distance between RAs measured from the segmentation masks generated by Res-UNet and that measured by experienced sonographers was only 3.44 ± 0.16 mm. In addition, these two measurements were highly correlated with each other (r = 0.944), with no systematic difference. Conclusion: Deep learning model Res-UNet has good reliability in RA segmentation and distance measurement in ultrasound images, with great potential in the clinical diagnosis of DRA.