Capturing rich multi-scale features is essential to address complex variations in medical image segmentation. Multiple hybrid networks have been developed to integrate the complementary benefits of convolutional neural networks (CNN) and Transformers. However, existing methods may suffer from either huge computational cost required by the complicated networks or unsatisfied performance of lighter networks. How to give full play to the advantages of both convolution and self-attention and design networks that are both effective and efficient still remains an unsolved problem. In this work, we propose a robust lightweight multi-stage hybrid architecture, named Multi-stage Aggregation Transformer version 2 (MA-TransformerV2), to extract multi-scale features with progressive aggregations for accurate segmentation of highly variable medical images at a low computational cost. Specifically, lightweight Trans blocks and lightweight CNN blocks are parallelly introduced into the dual-branch encoder module in each stage, and then a vector quantization block is incorporated at the bottleneck to discretizes the features and discard the redundance. This design not only enhances the representation capabilities and computational efficiency of the model, but also makes the model interpretable. Extensive experimental results on public datasets show that our method outperforms state-of-the-art methods, including CNN-based, Transformer-based, advanced hybrid CNN-Transformer-based models, and several lightweight models, in terms of both segmentation accuracy and model capacity. Code will be made publicly available at https://github.com/zjmiaprojects/MATransformerV2.

Emerging evidence suggests that diminished skeletal muscle mass is associated with lower health-related quality of life (HRQOL) in individuals with cancer. There are no studies that we know of in the literature that use ultrasound system to evaluate muscle mass and its relationship with HRQOL. The aim of our study was to evaluate the relationship between HRQOL determined by the EuroQol-5D tool and muscle mass determined by an artificial intelligence-based ultrasound system at the rectus femoris (RF) level in outpatients with cancer. Anthropometric data by bioimpedance (BIA), muscle mass by ultrasound by an artificial intelligence-based at the RF level, biochemistry determination, dynamometry and HRQOL were measured. A total of 158 patients with cancer were included with a mean age of 70.6 ±9.8 years. The mean body mass index was 24.4 ± 4.1 kg/m² with a mean body weight of 63.9 ± 11.7 kg (38% females and 62% males). A total of 57 patients had a severe degree of malnutrition (36.1%). The distribution of the location of the tumors was 66 colon-rectum cancer (41.7%), 56 esophageal-stomach cancer (35.4%), 16 pancreatic cancer (10.1%), and 20.2% other locations. A positive correlation cross-sectional area (CSA), muscle thickness (MT), pennation angle, (BIA) parameters, and muscle strength was detected. Patients in the groups below the median for the visual scale and the EuroQol-5D index had lower CSA and MT, BIA, and muscle strength values. CSA (beta 4.25, 95% CI 2.03-6.47) remained in the multivariate model as dependent variable (visual scale) and muscle strength (beta 0.008, 95% CI 0.003-0.14) with EuroQol-5D index. Muscle strength and pennation angle by US were associated with better score in dimensions of mobility, self-care, and daily activities. CSA, MT, and pennation angle of RF determined by an artificial intelligence-based muscle ultrasound system in outpatients with cancer were related to HRQOL determined by EuroQol-5D.

Radiographic imaging is a non-invasive technique of considerable importance for evaluating tumor treatment response. However, redundancy in CT data and the lack of labeled data make it challenging to accurately assess the response of locally advanced rectal cancer (LARC) patients to neoadjuvant chemoradiotherapy (nCRT) using current imaging indicators. In this study, we propose a novel learning framework to automatically predict the response of LARC patients to nCRT. Specifically, we develop a deep learning network called the Expand Intensive Attention Network (EIA-Net), which enhances the network's feature extraction capability through cascaded 3D convolutions and coordinate attention. Instance-oriented collaborative self-supervised learning (IOC-SSL) is proposed to leverage unlabeled data for training, reducing the reliance on labeled data. In a dataset consisting of 1,575 volumes, the proposed method achieves an AUC score of 0.8562. The dataset includes two distinct parts: the self-supervised dataset containing 1,394 volumes and the supervised dataset comprising 195 volumes. Analysis of the lifetime predictions reveals that patients with pathological complete response (pCR) predicted by EIA-Net exhibit better overall survival (OS) compared to non-pCR patients with LARC. The retrospective study demonstrates that imaging-based pCR prediction for patients with low rectal cancer can assist clinicians in making informed decisions regarding the need for Miles operation, thereby improving the likelihood of anal preservation, with an AUC of 0.8222. These results underscore the potential of our method to enhance clinical decision-making, offering a promising tool for personalized treatment and improved patient outcomes in LARC management.

Medical image segmentation is crucial for computer-aided diagnosis and treatment planning, directly influencing clinical decision-making. To enhance segmentation accuracy, existing methods typically fuse local, global, and various other features. However, these methods often ignore the negative impact of noise on the results during the feature fusion process. In contrast, certain regions of the human visual system, such as the inferotemporal cortex and parietal cortex, effectively suppress irrelevant noise while integrating multiple features-a capability lacking in current methods. To address this gap, we propose MS-Net, a medical image segmentation network inspired by human visual perception. MS-Net incorporates a multi-feature compression (MFC) module that mimics the human visual system's processing of complex images, first learning various feature types and subsequently filtering out irrelevant ones. Additionally, MS-Net features a segmentation refinement (SR) module that emulates how physicians segment lesions. This module initially performs coarse segmentation to capture the lesion's approximate location and shape, followed by a refinement step to achieve precise boundary delineation. Experimental results demonstrate that MS-Net not only attains state-of-the-art segmentation performance across three public datasets but also significantly reduces the number of parameters compared to existing models. Code is available at https://github.com/guangguangLi/MS-Net.

Federated Learning (FL) has emerged as a promising approach for collaborative medical image analysis while preserving data privacy, making it particularly suitable for radiomics tasks. This paper presents a systematic meta-analysis of recent surveys on Federated Learning in Medical Imaging (FL-MI), published in reputable venues over the past five years. We adopt the PRISMA methodology, categorizing and analyzing the existing body of research in FL-MI. Our analysis identifies common trends, challenges, and emerging strategies for implementing FL in medical imaging, including handling data heterogeneity, privacy concerns, and model performance in non-IID settings. The paper also highlights the most widely used datasets and a comparison of adopted machine learning models. Moreover, we examine FL frameworks in FL-MI applications, such as tumor detection, organ segmentation, and disease classification. We identify several research gaps, including the need for more robust privacy protection. Our findings provide a comprehensive overview of the current state of FL-MI and offer valuable directions for future research and development in this rapidly evolving field.

Breast cancer poses a major health concern for women globally. Effective segmentation of breast tumors for ultrasound images is crucial for early diagnosis and treatment. Conventional convolutional neural networks have shown promising results in this domain but face challenges due to image complexities and are computationally expensive, limiting their practical application in real-time clinical settings. We propose Eff-AResUNet-GL, a segmentation model using EfficienetNet-B3 as the encoder. This design integrates attention gates in skip connections to focus on significant features and residual blocks in the decoder to retain details and reduce gradient loss. Additionally, guided loss functions are applied at each decoder layer to generate better features, subsequently improving segmentation accuracy. Experimental results on BUSIS and Dataset B demonstrate that Eff-AResUNet-GL achieves superior performance and computational efficiency compared to state-of-the-art models, showing robustness in handling complex breast ultrasound images. Eff-AResUNet-GL offers a practical, high-performing solution for breast tumor segmentation, demonstrating potential clinical through improved segmentation accuracy and efficiency.

Accurate cardiac MRI segmentation is vital for detailed cardiac analysis, yet the manual process is labor-intensive and prone to variability. Despite advancements in MRI technology, there remains a significant need for automated methods that can reliably and efficiently segment cardiac structures. This paper introduces HALSR-Net, a novel multi-level segmentation architecture designed to improve the accuracy and reproducibility of cardiac segmentation from Cine-MRI acquisitions, focusing on the left ventricle (LV). The methodology consists of two main phases: first, the extraction of the region of interest (ROI) using a regression model that accurately predicts the location of a bounding box around the LV; second, the semantic segmentation step based on HALSR-Net architecture. This architecture incorporates a Hybrid Attention Pooling Module (HAPM) that merges attention and pooling mechanisms to enhance feature extraction and capture contextual information. Additionally, a reconstruction module leverages latent space features to further improve segmentation accuracy. Experiments conducted on an in-house clinical dataset and two public datasets (ACDC and LVQuan19) demonstrate that HALSR-Net outperforms state-of-the-art architectures, achieving up to 98% accuracy and F1-score for the segmentation of the LV cavity and myocardium. The proposed approach effectively addresses the limitations of existing methods, offering a more accurate and robust solution for cardiac MRI segmentation, thereby likely to improve cardiac function analysis and patient care.

Self-supervised learning has shown potential in enhancing deep learning methods, yet its application in brain magnetic resonance imaging (MRI) analysis remains underexplored. This study seeks to leverage large-scale, unlabeled public brain MRI datasets to improve the performance of deep learning models in various downstream tasks for the development of clinical decision support systems. To enhance training efficiency, data filtering methods based on image entropy and slice positions were developed, condensing a combined dataset of approximately 2 million images from fastMRI-brain, OASIS-3, IXI, and BraTS21 into a more focused set of 250 K images enriched with brain features. The Momentum Contrast (MoCo) v3 algorithm was then employed to learn these image features, resulting in robustly pretrained models specifically tailored to brain MRI. The pretrained models were subsequently evaluated in tumor classification, lesion detection, hippocampal segmentation, and image reconstruction tasks. The results demonstrate that our brain MRI-oriented pretraining outperformed both ImageNet pretraining and pretraining on larger multi-organ, multi-modality medical datasets, achieving a ∼2.8 % increase in 4-class tumor classification accuracy, a ∼0.9 % improvement in tumor detection mean average precision, a ∼3.6 % gain in adult hippocampal segmentation Dice score, and a ∼0.1 PSNR improvement in reconstruction at 2-fold acceleration. This study underscores the potential of self-supervised learning for brain MRI using large-scale, tailored datasets derived from public sources.

Assessing collateral circulation is essential in determining the best treatment for ischemic stroke patients as good collaterals lead to different treatment options, i.e., thrombectomy, whereas poor collaterals can adversely affect the treatment by leading to excess bleeding and eventually death. To reduce inter- and intra-rater variability and save time in radiologist assessments, computer-aided methods, mainly using deep neural networks, have gained popularity. The current literature demonstrates effectiveness when using balanced and extensive datasets in deep learning; however, such data sets are scarce for stroke, and the number of data samples for poor collateral cases is often limited compared to those for good collaterals. We propose a novel approach called CASCADE-FSL to distinguish poor collaterals effectively. Using a small, unbalanced data set, we employ a few-shot learning approach for training using a 2D ResNet-50 as a backbone and designating good and intermediate cases as two normal classes. We identify poor collaterals as anomalies in comparison to the normal classes. Our novel approach achieves an overall accuracy, sensitivity, and specificity of 0.88, 0.88, and 0.89, respectively, demonstrating its effectiveness in addressing the imbalanced dataset challenge and accurately identifying poor collateral circulation cases.