Breast ultrasound (BUS) image segmentation is a critical procedure in the diagnosis and quantitative analysis of breast cancer. Most existing methods for BUS image segmentation do not effectively utilize the prior information extracted from the images. In addition, breast tumors have very blurred boundaries, various sizes and irregular shapes, and the images have a lot of noise. Thus, tumor segmentation remains a challenge. In this paper, we propose a BUS image segmentation method using a boundary-guided and region-aware network with global scale-adaptive (BGRA-GSA). Specifically, we first design a global scale-adaptive module (GSAM) to extract features of tumors of different sizes from multiple perspectives. GSAM encodes the features at the top of the network in both channel and spatial dimensions, which can effectively extract multi-scale context and provide global prior information. Moreover, we develop a boundary-guided module (BGM) for fully mining boundary information. BGM guides the decoder to learn the boundary context by explicitly enhancing the extracted boundary features. Simultaneously, we design a region-aware module (RAM) for realizing the cross-fusion of diverse layers of breast tumor diversity features, which can facilitate the network to improve the learning ability of contextual features of tumor regions. These modules enable our BGRA-GSA to capture and integrate rich global multi-scale context, multi-level fine-grained details, and semantic information to facilitate accurate breast tumor segmentation. Finally, the experimental results on three publicly available datasets show that our model achieves highly effective segmentation of breast tumors even with blurred boundaries, various sizes and shapes, and low contrast.

Optical coherence tomography angiography (OCTA) has been widely used in ophthalmology in recent years due to its noninvasive and high resolution. In OCTA images, two biomarkers are extremely important for clinical diagnosis, i.e., foveal avascular zone (FAZ) and retinal vessel (RV), and RV has an implicit constraint on FAZ in position. In previous studies, the segmentation of the two biomarkers is naturally separated, which undoubtedly leads to the omission of such constraints between them. In this article, we propose a joint segmentation framework ( Joint-Seg ), a single-encoder and dual-decoder architecture, through which simultaneous FAZ and RV extractions from en-face OCTA images can be achieved. Specifically, the OCTA image is encoded through joint encoding and provides FAZ- or RV-related information to separate decoding branches through a feature adaptive filter (FAF). In the FAZ segmentation branch, we propose a feature alignment decoder block (FADB) to recover image details, especially boundaries. While in the RV segmentation branch, a multiscale soft fusion module (MSFM) is designed to adapt to different vessel thicknesses. Finally, we evaluate the proposed Joint-Seg on the OCTA-500 dataset, and the experimental results show that our Joint-Seg outperforms the state-of-the-art methods on both FAZ and RV segmentations and has fewer floating point operations (FLOPs) and parameters. The generalization experiments on four other datasets, i.e., OCTAGON, sFAZ, OCTA-25K, and ROSE, also demonstrate the portability and scalability of the proposed Joint-Seg framework. In addition, the noise analysis further shows good robustness of the proposed method against noise.

For the study of various retinal diseases, an accurate quantitative analysis of the retinal layer is essential for assessing the severity of the disease and diagnosing the progression of the disease. Optical coherence tomography (OCT) images can clearly show each layer of the retinal structure and detect subtle early lesions, thus providing a gold standard for the diagnosis of retinal diseases. In this article, we propose a coarse-to-fine retinal layer boundary segmentation method based on the embedded residual recurrent network (ERR-Net) and the graph search (GS). Considering the integrity of information transmission and the dependence of features, we first design a novel end-to-end residual recurrent network to roughly segment the retinal layer boundaries. The proposed ERR-Net not only solves the gradient problem brought by the depth but also fully captures the global spatial structure of the image. Second, we employ a GS algorithm for boundary continuous to make the layer boundary segmentation results more accurate. Finally, we evaluate the effectiveness of the proposed method on three publicly available datasets and compare it with the state-of-the-art methods on each dataset. The quantitative results and visual effects show that the proposed method outperforms the state-of-the-art approaches in the segmentation of retinal layer boundaries in OCT images. Moreover, the results also show that the proposed method has good algorithm stability on three datasets with different sizes, characteristics, and segmentation difficulties.

Ultrasound imaging is one of the most widely used medical imaging techniques for visualizing human tissue due to its economical, convenient, practical, and safe advantages. Automatic segmentation of regions of interest in ultrasound images is of great significance in improving the clinical efficiency of ultrasound images and the accuracy of disease diagnosis. However, this task has been challenging due to speckle noise, low contrast, and blurred boundaries in ultrasound images. To address these problems, this paper proposes an interactive two-stream network based on detail screening and compensation called DSC-Net for ultrasound image segmentation. Unlike previous ultrasound image segmentation methods, our DSC-Net combines the Transformer and Convolutional Neural Network to perform accurate ultrasound image segmentation. Specifically, DSC-Net utilizes a Transformer Stream to obtain multi-scale detailed features and a Convolutional Neural Network Stream to extract body features with less noise. Then, the body features guide multi-scale detailed features to filter out noise through the Detail Screening Module. The filtered detail features are applied to Detail Compensation Module to supplement rich details for the Convolutional Neural Network Stream. With such interactions, DSC-Net ensures that more noise-free details are extracted. Extensive experiments on three datasets, including two publicly available datasets and one private dataset, demonstrate that the proposed DSC-Net achieves higher performance and superior robustness than state-of-the-art ultrasound image segmentation methods. Our code is publicly available at https://github.com/MLMIP/DSC-Net.

With the advent of the era of big data, it is troublesome to accurately predict the associations between lncRNAs and diseases based on traditional biological experiments due to its time-consuming and subjective. In this paper, we propose a novel deep learning method for predicting lncRNA-disease associations using multi-feature coding and attention convolutional neural network (MCA-Net). We first calculate six similarity features to extract different types of lncRNA and disease feature information. Second, a multi-feature coding method is proposed to construct the feature vectors of lncRNA-disease association samples by integrating the six similarity features. Furthermore, an attention convolutional neural network is developed to identify lncRNA-disease associations under 10-fold cross-validation. Finally, we evaluate the performance of MCA-Net from different perspectives including the effects of the model parameters, distinct deep learning models, and the necessity of attention mechanism. We also compare MCA-Net with several state-of-the-art methods on three publicly available datasets, i.e., LncRNADisease, Lnc2Cancer, and LncRNADisease2.0. The results show that our MCA-Net outperforms the state-of-the-art methods on all three dataset. Besides, case studies on breast cancer and lung cancer further verify that MCA-Net is effective and accurate for the lncRNA-disease association prediction.

The goal of few-shot class incremental learning (FSCIL) is to learn new concepts from a limited number of novel samples while preserving the knowledge of previously learned classes. The mainstream FSCIL framework begins with training in the base session, after which the feature extractor is frozen to accommodate novel classes. We observed that traditional base-session training approaches often lead to overfitting on challenging samples, which can lead to reduced robustness in the decision boundaries and exacerbate the forgetting phenomenon when introducing incremental data. To address this issue, we proposed the progressive learning strategy (PGLS). First, inspired by curriculum learning, we developed a covariance noise perturbation approach based on the statistical information as a difficulty measure for assessing sample robustness. We then reweighted the samples based on their robustness, initially concentrating on enhancing model stability by prioritizing robust samples and subsequently leveraging weakly robust samples to improve generalization. Second, we predefined forward compatibility for various virtual class augmentation models. Within base class training, we employed a curriculum learning strategy that progressively introduced fewer to more virtual classes in order to mitigate any adverse effects on model performance. This strategy enhances the adaptability of base classes to novel ones and alleviates forgetting problems. Finally, extensive experiments conducted on the CUB200, CIFAR100, and miniImageNet datasets demonstrate the significant advantages of our proposed method over state-of-the-art models.