CSM-Net: Automatic joint segmentation of intima-media complex and lumen in carotid artery ultrasound images

Baran T, O’Connell A, Parker K. Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it popular among researchers. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the Dice coefficient, specificity, sensitivity, and F1 score values obtained were 0.93, 0.99, 0.94, and 0.94, respectively. In addition, McNemar's statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperformed all other models, resulting in improved breast lesion segmentation.

Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules

Ultrasound segmentation of thyroid nodules is a challenging task, which plays an vital role in the diagnosis of thyroid cancer. However, the following two factors limit the development of automatic thyroid nodule segmentation algorithms: (1) existing automatic nodule segmentation algorithms that directly apply semantic segmentation techniques can easily mistake non-thyroid areas as nodules, because of the lack of the thyroid gland region perception, the large number of similar areas in the ultrasonic images, and the inherently low contrast images; (2) the currently available dataset (i.e., DDTI) is small and collected from a single center, which violates the fact that thyroid ultrasound images are acquired from various devices in real-world situations. To overcome the lack of thyroid gland region prior knowledge, we design a thyroid region prior guided feature enhancement network (TRFE+) for accurate thyroid nodule segmentation. Specifically, (1) a novel multi-task learning framework that simultaneously learns the nodule size, gland position, and the nodule position is designed; (2) an adaptive gland region feature enhancement module is proposed to make full use of the thyroid gland prior knowledge; (3) a normalization approach with respect to the channel dimension is applied to alleviate the domain gap during the training process. To facilitate the development of thyroid nodule segmentation, we have contributed TN3K: an open-access dataset containing 3493 thyroid nodule images with high-quality nodule masks labeling from various devices and views. We perform a thorough evaluation based on the TN3K test set and DDTI to demonstrate the effectiveness of the proposed method. Code and data are available at https://github.com/haifangong/TRFE-Net-for-thyroid-nodule-segmentation.

HRU-Net: A Transfer Learning Method for Carotid Artery Plaque Segmentation in Ultrasound Images

Carotid artery stenotic plaque segmentation in ultrasound images is a crucial means for the analysis of plaque components and vulnerability. However, segmentation of severe stenotic plaques remains a challenging task because of the heterogeneities of inter-plaques and intra-plaques, and obscure boundaries of plaques. In this paper, we propose an automated HRU-Net transfer learning method for segmenting carotid plaques, using the limited images. The HRU-Net is based on the U-Net encoder−decoder paradigm, and cross-domain knowledge is transferred for plaque segmentation by fine-tuning the pretrained ResNet-50. Moreover, a cropped-blood-vessel image augmentation is customized for the plaque position constraint during training only. Moreover, hybrid atrous convolutions (HACs) are designed to derive diverse long-range dependences for refined plaque segmentation that are used on high-level semantic layers to exploit the implicit discrimination features. The experiments are performed on 115 images; Firstly, the 10-fold cross-validation, using 40 images with severe stenosis plaques, shows that the proposed method outperforms some of the state-of-the-art CNN-based methods on Dice, IoU, Acc, and modified Hausdorff distance (MHD) metrics; the improvements on metrics of Dice and MHD are statistically significant (p < 0.05). Furthermore, our HRU-Net transfer learning method shows fine generalization performance on 75 new images with varying degrees of plaque stenosis, and it may be used as an alternative for automatic noisy plaque segmentation in carotid ultrasound images clinically.