Imaging examinations are integral to the diagnosis and treatment of cancer. Nevertheless, the intricate nature of medical images frequently necessitates that physicians follow time-consuming and potentially fallible diagnostic procedures. In response to these challenges, deep learning-based image segmentation technology has emerged as a potent instrument for aiding physicians in navigating diagnostic complexities by extracting pivotal information from extensive sets of medical images. Nonetheless, the majority of existing models prioritize overall high accuracy, often overlooking the sensitivity to local salient features and the precision of segmentation boundaries. This oversight limits the full realization of the practical utility of deep learning models in clinical settings. This study introduces a novel pathological image segmentation method, termed TransRNetFuse, which incorporates stepwise feature aggregation and a residual fully convolutional network architecture. The objective of this method is to address the issues associated with the extraction of local key features and the accurate delineation of boundaries in medical image segmentation. The proposed model achieves enhanced overall performance by merging a fully convolutional network branch with a Transformer branch and utilizing residual blocks along with dense U-net skip connections. It prevents attentional dispersion by emphasizing local features, and further employs an automatic augmentation strategy to identify the optimal data augmentation scheme, which is particularly advantageous for small-sample datasets. Furthermore, this paper introduces an edge enhancement loss function to enhance the model's sensitivity to tumor boundaries. A dataset comprising 2164 pathological images, provided by Hunan Medical University General Hospital, was utilized for model training. The experimental results indicate that the proposed method outperforms existing techniques, such as MedT, in terms of both accuracy and edge precision, thereby demonstrating its significant potential for application in the medical field. Code: https://github.com/GFF1228/-TransRNetFuse.git.

The analysis and interpretation of cytopathological images are crucial in modern medical diagnostics. However, manually locating and identifying relevant cells from the vast amount of image data can be a daunting task. This challenge is particularly pronounced in developing countries where there may be a shortage of medical expertise to handle such tasks. The challenge of acquiring large amounts of high-quality labelled data remains, many researchers have begun to use semi-supervised learning methods to learn from unlabeled data. Although current semi-supervised learning models partially solve the issue of limited labelled data, they are inefficient in exploiting unlabeled samples. To address this, we introduce a new AI-assisted semi-supervised scheme, the Reliable-Unlabeled Semi-Supervised Segmentation (RU3S) model. This model integrates the ResUNet-SE-ASPP-Attention (RSAA) model, which includes the Squeeze-and-Excitation (SE) network, Atrous Spatial Pyramid Pooling (ASPP) structure, Attention module, and ResUNet architecture. Our model leverages unlabeled data effectively, improving accuracy significantly. A novel confidence filtering strategy is introduced to make better use of unlabeled samples, addressing the scarcity of labelled data. Experimental results show a 2.0% improvement in mIoU accuracy over the current state-of-the-art semi-supervised segmentation model ST, demonstrating our approach’s effectiveness in solving this medical problem.

Liver cancer is a malignant tumor with high incidence and mortality rates. Computed tomography is a key imaging modality for clinical diagnosis but faces challenges such as subtle intra-class variations and the inefficiency of manual interpretation. Traditional diagnostic approaches often lack generalizability and effective feature extraction, increasing the risk of misdiagnosis. While deep learning models like ResUNet have improved diagnostic performance, issues such as information loss and inaccurate tumor boundary segmentation persist. To address these challenges, this study proposes NMD-FusionNet, a deep learning-based framework for liver cancer image segmentation and diagnosis. The framework includes a three-stage pipeline: first, a refined non-local means filtering algorithm is employed for pre-screening, discarding over 80% of non-diagnostic images using adaptive thresholding; second, a multimodal image fusion method integrates multi-phase, multi-source liver cancer image data through multi-scale decomposition and precise fusion rules to reduce noise and motion artifacts; third, a dual-path DconnNet segmentation network is constructed, incorporating a directional excitation module in the encoder and a spatial awareness unit in the decoder, guided by a boundary-constrained loss function to enhance segmentation accuracy. Evaluated on over 2,000 liver cancer images from the Second People's Hospital of Huaihua, NMD-FusionNet achieves a tumor segmentation Intersection over Union (IoU) of 83.9%, representing an 8.7% improvement over ResUNet and demonstrating superior sensitivity. This work provides a reliable computer-aided diagnostic tool for radiologists and shows strong potential for clinical application, particularly in resource-limited healthcare settings.

Diagnosing diseases heavily relies on cell pathology images, but the extensive data in each manual identification of relevant cells labor-intensive, especially in regions with a scarcity of qualified healthcare professionals. This study aims to develop an intelligent system to enhance the diagnostic accuracy of cytopathology images by addressing image noise and segmentation issues, thereby improving the efficiency of medical professionals in disease diagnosis. We introduced an innovative system combining a self-supervised algorithm, SDN, for image denoising with data enhancement and image segmentation using the UPerMVit model. The UPerMVit model’s novel attention mechanisms and modular architecture provide higher accuracy and lower computational complexity than traditional methods. The proposed system effectively reduces image noise and accurately segments annotated images, highlighting cellular structures relevant to medical staff. This enhances diagnostic accuracy and aids in the accurate identification of pathological cells. Our intelligent system offers a reliable tool for medical professionals, improving diagnostic efficiency and accuracy in cytopathologic image analysis. It provides significant technical support in regions lacking adequate medical expertise.

Precise liver tumor segmentation is essential for reliable clinical decision-making, particularly for treatment planning and quantitative assessment. To improve segmentation robustness under heterogeneous image quality and complex tumor appearance, we propose QCSeg-Net, a quality-controlled, coarse-to-fine framework consisting of tumor-presence classification (FALC-Net), image quality screening (IQS-Net), and refined segmentation via RGA-TransUNet. The framework first removes tumor-free slices to reduce redundant computation, then filters degraded images to ensure consistent input quality, and finally performs fine-grained segmentation using multi-scale receptive-field aggregation and a residual-guided Transformer module. Experiments on a liver tumor CT dataset from the Hunan University of Medicine General Hospital demonstrate that QCSeg-Net achieves a 2.09% improvement in IoU over advanced baseline models, while also exhibiting higher stability on small-volume and low-contrast tumors. These results highlight the potential of QCSeg-Net for intelligent auxiliary diagnosis of liver tumors in clinical applications. Code: https://github.com/luo-ming-hao/QCSeg-Net.