Image Segmentation Applications Research Articles

Applications of Artificial Intelligence for Pediatric Cancer Imaging.

Artificial intelligence (AI) is transforming medical imaging of adult patients. However, its utilization in pediatric oncology imaging remains constrained, in part due to the inherent data scarcity associated with childhood cancers. Pediatric cancers are rare, and imaging technologies are evolving rapidly, leading to insufficient data of a particular type to effectively train these algorithms. The small market size of pediatrics compared to adults could also contribute to this challenge, as market size is a driver of commercialization. This article provides an overview of the current state of AI applications for pediatric cancer imaging, including applications for medical image acquisition, processing, reconstruction, segmentation, diagnosis, staging, and treatment response monitoring. While current developments are promising, impediments due to diverse anatomies of growing children and nonstandardized imaging protocols have led to limited clinical translation thus far. Opportunities include leveraging reconstruction algorithms to achieve accelerated low-dose imaging and automating the generation of metric-based staging and treatment monitoring scores. Transfer-learning of adult-based AI models to pediatric cancers, multi-institutional data sharing, and ethical data privacy practices for pediatric patients with rare cancers will be keys to unlocking AI's full potential for clinical translation and improved outcomes for these young patients.

Review of Semi-Supervised Medical Image Segmentation based on the U-Net

Medical image segmentation is a core task in the field of medical image processing. It aims to separate areas of interest such as organs, tissues, and lesions from the background in medical images to facilitate further analysis, diagnosis, and treatment planning. Accurate image segmentation is crucial for improving the accuracy of disease diagnosis, assessing disease progression, and developing personalized treatment plans. However, fully supervised segmentation methods face the challenge of high annotation costs. With the emergence of the U-Net architecture, semi-supervised medical image segmentation based on U-Net is receiving increasing attention. This article reviews semi-supervised segmentation methods, the design concept and structure of the U-Net network, how it has been extended, and its application in semi-supervised medical image segmentation. The article also identifies the challenges faced by semi-supervised medical image segmentation techniques based on U-Net and speculates on possible future research directions. In conclusion, the article summarizes the potential of semi-supervised medical image segmentation technology based on U-Net as an accurate and efficient tool for medical diagnosis and treatment.

LCAMix: Local-and-contour aware grid mixing based data augmentation for medical image segmentation

Medical image segmentation often faces challenges related to overfitting, primarily due to the limited and complex training samples. This challenge often prompts the use of self-supervised learning and data augmentation. However, self-supervised learning requires well-defined hand-crafted tasks and multiple training stages. On the other hand, basic image augmentation techniques like cropping, rotation, and flipping, effective for natural scene images, have limited efficacy for medical images due to their isotropic nature.While regional dropout regularization data augmentation methods have proven effective in image recognition tasks, their application in image segmentation is not as extensively studied. Additionally, existing augmentation methods often operate on square regions, leading to the loss of crucial contour information. This is particularly problematic for medical image segmentation tasks dealing with regions of interest characterized by intricate shapes. In this work, we introduce LCAMix, a novel data augmentation approach designed for medical image segmentation. LCAMix operates by blending two images and their segmentation masks based on their superpixels, incorporating a local-and-contour-aware strategy. The training process on augmented images adopts two auxiliary pretext tasks: firstly, classifying local superpixels in augmented images using an adaptive focal margin, leveraging segmentation ground truth masks as prior knowledge; secondly, reconstructing the two source images using mixed superpixels as mutual masks, emphasizing spatial sensitivity. Our method stands out as a simple, one-stage, model-agnostic, and plug-and-play data augmentation solution applicable to various segmentation tasks. Notably, it requires no external data or additional models. Extensive experiments validate its superior performance across diverse medical segmentation datasets and tasks. The source codes are available at https://github.com/DanielaPlusPlus/DataAug4Medical.

Artemisinin optimization based on malaria therapy: Algorithm and applications to medical image segmentation

This study proposes an efficient metaheuristic algorithm called the Artemisinin Optimization (AO) algorithm. This algorithm draws inspiration from the process of artemisinin medicine therapy for malaria, which involves the comprehensive eradication of malarial parasites within the human body. AO comprises three optimization stages: a comprehensive eliminations phase simulating global exploration, a local clearance phase for local exploitation, and a post-consolidation phase to enhance the algorithm's ability to escape local optima. In the experimental, this paper conducts a qualitative analysis experiment on the AO, explaining its characteristics in searching for the optimal solution. Subsequently, AO is then tested on the classical IEEE CEC 2014, and the latest IEEE CEC 2022 benchmark function sets to assess its adaptability. Comparative analyses are conducted against eight well-established algorithms and eight high-performance improved algorithms. Statistical analyses of convergence curves and qualitative metrics revealed AO's robust competitiveness. Lastly, the AO is incorporated into breast cancer pathology image segmentation applications. Using 15 authentic medical images at six threshold levels, AO's segmentation performance is compared against eight distinguished algorithms. Experimental results demonstrated AO's superiority in terms of image segmentation accuracy, Feature Similarity Index (FSIM), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) over the contrast algorithms. These results emphasize AO's efficiency and its potential in real-world optimization applications. The source codes22https://github.com/aliasgharheidaricom/Artemisinin-Optimizer-using-Malaria-Therapy-Algorithm-and-Applications-to-Medical-Image-Segmentation. of this paper are available in https://aliasgharheidari.com/AO.html and other public websites33https://ch.mathworks.com/matlabcentral/fileexchange/165791-artemisinin-optimization-ao-based-on-malaria-therapy..

Adversarial attacks and adversarial training for burn image segmentation based on deep learning.

Deep learning has been widely applied in the fields of image classification and segmentation, while adversarial attacks can impact the model's results in image segmentation and classification. Especially in medical images, due to constraints from factors like shooting angles, environmental lighting, and diverse photography devices, medical images typically contain various forms of noise. In order to address the impact of these physically meaningful disturbances on existing deep learning models in the application of burn image segmentation, we simulate attack methods inspired by natural phenomena and propose an adversarial training approach specifically designed for burn image segmentation. The method is tested on our burn dataset. Through the defensive training using our approach, the segmentation accuracy of adversarial samples, initially at 54%, is elevated to 82.19%, exhibiting a 1.97% improvement compared to conventional adversarial training methods, while substantially reducing the training time. Ablation experiments validate the effectiveness of individual losses, and we assess and compare training results with different adversarial samples using various metrics.

The improved strategy of BOA algorithm and its application in multi-threshold image segmentation

In response to the low efficiency and poor quality of current seed optimization algorithms for multi-threshold image segmentation, this paper proposes the utilization of the normal distribution in the cluster distribution mathematical model, the Levy flight mechanism, and the differential evolution algorithm to address the deficiencies of the seed optimization algorithm. The main innovation lies in applying the BBO algorithm to image multi threshold segmentation, providing a new perspective and method for image segmentation tasks. The second significant progress is the combination of Levy flight dynamics and differential evolution algorithm (DEA) to improve the BBO algorithm, thereby enhancing its performance and image segmentation quality. Therefore, a multi-threshold image segmentation model based on the optimized seed optimization algorithm is developed. The experimental results showed that on the function f1, the iteration of the improved seed optimization algorithm was 53, the Generational Distance value was 0.0020, the Inverted Generational Distance value was 0.098, and the Spacing value was 0.051. Compared with the other two algorithms, the improved seed optimization algorithm has better image segmentation performance and clearer image segmentation details. In summary, compared with existing multi-threshold image segmentation methods, the proposed multi-threshold image segmentation model based on the improved seed optimization algorithm has a better image segmentation effect and higher efficiency, can significantly improve the quality of image segmentation, has positive significance for the development of image processing technology, and also provides references for the improvement and application of optimization algorithms.

SuMRak: a multi-tool solution for preclinical brain MRI data analysis.

Magnetic resonance imaging (MRI) is invaluable for understanding brain disorders, but data complexity poses a challenge in experimental research. In this study, we introduce suMRak, a MATLAB application designed for efficient preclinical brain MRI analysis. SuMRak integrates brain segmentation, volumetry, image registration, and parameter map generation into a unified interface, thereby reducing the number of separate tools that researchers may require for straightforward data handling. All functionalities of suMRak are implemented using the MATLAB App Designer and the MATLAB-integrated Python engine. A total of six helper applications were developed alongside the main suMRak interface to allow for a cohesive and streamlined workflow. The brain segmentation strategy was validated by comparing suMRak against manual segmentation and ITK-SNAP, a popular open-source application for biomedical image segmentation. When compared with the manual segmentation of coronal mouse brain slices, suMRak achieved a high Sørensen-Dice similarity coefficient (0.98 ± 0.01), approaching manual accuracy. Additionally, suMRak exhibited significant improvement (p = 0.03) when compared to ITK-SNAP, particularly for caudally located brain slices. Furthermore, suMRak was capable of effectively analyzing preclinical MRI data obtained in our own studies. Most notably, the results of brain perfusion map registration to T2-weighted images were shown, improving the topographic connection to anatomical areas and enabling further data analysis to better account for the inherent spatial distortions of echoplanar imaging. SuMRak offers efficient MRI data processing of preclinical brain images, enabling researchers' consistency and precision. Notably, the accelerated brain segmentation, achieved through K-means clustering and morphological operations, significantly reduces processing time and allows for easier handling of larger datasets.

Liver tumor segmentation method based on U-Net architecture: a review

Liver cancer is a disease with a high incidence and high probability of deterioration, and for the rapid diagnosis of liver disease, CT scans must be used to segment the liver tumors. For the past few years, with the rapid development of deep learning, many deep learning methods for liver tumor segmentation using abdominal computed tomography (CT) images have appeared, and the clinical application of these methods is of important significance for computer-aided diagnosis of liver tumors. The U-Net, with its unique U-shape network structure, exhibits excellent performance in medical image segmentation field and has been extensively utilized in various medical image segmentation applications. In this paper, we summarize the researches of U-Net and its improved networks in CT image segmentation of liver tumors by deep learning methods and classify various U-Net-based convolutional neural networks (CNNs) into 2D (two-dimensional), 3D (three-dimensional), and 2.5D (2.5-dimensional). In this paper, 2D, 3D, and 2.5D convolutional neural networks are summarized. In addition, this paper summarizes the advantages and disadvantages as well as the improvement methods of each type of network, which provides a useful reference for the studies of deep learning based on liver tumor segmentation field. Finally, this paper envisions future research trends for deep learning segmentation methods in the context of liver tumors.

A deep learning-based framework (Co-ReTr) for auto-segmentation of non-small cell-lung cancer in computed tomography images.

Deep learning-based auto-segmentation algorithms can improve clinical workflow by defining accurate regions of interest while reducing manual labor. Over the past decade, convolutional neural networks (CNNs) have become prominent in medical image segmentation applications. However, CNNs have limitations in learning long-range spatial dependencies due to the locality of the convolutional layers. Transformers were introduced to address this challenge. In transformers with self-attention mechanism, even the first layer of information processing makes connections between distant image locations. Our paper presents a novel framework that bridges these two unique techniques, CNNs and transformers, to segment the gross tumor volume (GTV) accurately and efficiently in computed tomography (CT) images of non-small cell-lung cancer (NSCLC) patients. Under this framework, input of multiple resolution images was used with multi-depth backbones to retain the benefits of high-resolution and low-resolution images in the deep learning architecture. Furthermore, a deformable transformer was utilized to learn the long-range dependency on the extracted features. To reduce computational complexity and to efficiently process multi-scale, multi-depth, high-resolution 3D images, this transformer pays attention to small key positions, which were identified by a self-attention mechanism. We evaluated the performance of the proposed framework on a NSCLC dataset which contains 563 training images and 113 test images. Our novel deep learning algorithm was benchmarked against five other similar deep learning models. The experimental results indicate that our proposed framework outperforms other CNN-based, transformer-based, and hybrid methods in terms of Dice score (0.92) and Hausdorff Distance (1.33). Therefore, our proposed model could potentially improve the efficiency of auto-segmentation of early-stage NSCLC during the clinical workflow. This type of framework may potentially facilitate online adaptive radiotherapy, where an efficient auto-segmentation workflow is required. Our deep learning framework, based on CNN and transformer, performs auto-segmentation efficiently and could potentially assist clinical radiotherapy workflow.

Optimisation of automatic optical inspection on THT-PCB based on image segmentation and GLCM

ABSTRACT Application Automatic Optical Inspection (AOI) is comprehensive in producing electronic circuits in the industry as an essential part of product assurance. Previous research created an AOI model for THT-PCB, which did not require complicated processing, and computers in vocational schools were able to process this model very well. However, this model cannot detect disturbed solder defects at solder joints. This study proposes optimising the AOI system to assist teachers in checking workpieces in soldering practicum, which significantly affects the industry’s need for students’ soldering skills. A Region of Interest (ROI) obtained by applying Image segmentation and log-polar transformation to the model. Then feature extraction had applied to the ROI using the Gray Level Cooccurrence Matrix (GLCM). The model verification shows an improved ability for disturbed soldering defects detection, which was not previously available on models. Accuracy and precision measurement for disturbed soldering defect detection by a correlation matrix gives a result of the accuracy of 91.75% and 90.20% precision. The fastest computation time measured on disturbed soldering defects detection is 800 milliseconds, while the total computing time is 2.8 seconds.

Designing Deep Learning Models on FPGA with Multiple Heterogeneous Engines

Deep learning models are becoming more complex and heterogeneous with new layer types to improve their accuracy. This brings a considerable challenge to the designers of accelerators of deep neural networks. There have been several architectures and design flows to map deep learning models on hardware, but they are limited to a particular model and/or layer types. Also, the architectures generated by these tools target, in general, high-performance devices, not appropriate for embedded computing. This article proposes a multi-engine architecture and a design flow to implement deep learning models on FPGA. The hardware design uses high-level synthesis to allow design space exploration. The architecture is scalable and therefore applicable to any density FPGAs. The architecture and design flow were applied to the development of a hardware/software system for image classification with ResNet50, object detection with YOLOv3-Tiny, and image segmentation with DeepLabV3+. The system was tested in a low-density Zynq UltraScale+ ZU3EG FPGA to show its scalability. The results show that the proposed multi-engine architecture generates efficient accelerators. An accelerator of ResNet50 with a 4-bit quantization achieves 67 FPS, and the object detector with YOLOv3-Tiny with a throughput of 36 FPS and the image segmentation application achieves 1.4 FPS.

ASCAEO: accelerated sine cosine algorithm hybridized with equilibrium optimizer with application in image segmentation using multilevel thresholding

ASCAEO: accelerated sine cosine algorithm hybridized with equilibrium optimizer with application in image segmentation using multilevel thresholding

Development and implementation of a stand-level satellite-based forest inventory for Canada

Abstract Satellite data are increasingly used to provide information to support forest monitoring and reporting at varying levels of detail and for a range of attributes and spatial extents. Forests are dynamic environments and benefit from regular assessments to capture status and changes both locally and over large areas. Satellite data can provide products relevant to forest science and management on a regular basis (e.g. annually) for land cover, disturbance (i.e. date, extent, severity, and type), forest recovery (e.g. quantification of return of trees following disturbance), and forest structure (e.g. volume, biomass, canopy cover, stand height), with products generated over large areas in a systematic, transparent, and repeatable fashion. While pixel-based outcomes are typical based upon satellite data inputs, many end users continue to require polygon-based forest inventory information. To meet this information need and have a spatial context for forest inventory attributes such as tree species assemblages, we present a new work-flow to produce a novel spatially explicit, stand-level satellite-based forest inventory (SBFI) in Canada applying image segmentation approaches to generate spatially unique forest stands (polygons), which are the fundamental spatial unit of management-level inventories. Thus, SBFI offers spatial context to aggregate and generalize other pixel-based forest data sets. Canada has developed a National Terrestrial Ecosystem Monitoring System (NTEMS) that utilizes medium spatial resolution imagery, chiefly from Landsat, to annually characterize Canada’s forests at a pixel level from 1984 until present. These NTEMS datasets are used to populate SBFI polygons with information regarding status (e.g. current land cover type, dominant tree species, or total biomass) as well as information on dynamics (e.g. has this polygon been subject to change, when, by what, and if so, how is the forest recovering). Here, we outline the information drivers for forest monitoring, present a set of products aimed at meeting these information needs, and follow to demonstrate the SBFI concept over the 650-Mha extent of Canada’s forest-dominated ecosystems. In so doing, the entirety of Canada’s forest ecosystems (managed and unmanaged) were mapped using the same data, attributes, and temporal representation. Moreover, the use of polygons allows for the generation of attributes such as tree species composition, and total biomass and wood volume in a stand-scale format familiar to landscape managers and suitable for strategic planning. The data, methods, and outcomes presented here are portable to other regions and input data sources, and the national SBFI outcomes for Canada are available via open access.

MRI Intracranial Neoplasm Localization Using Convolution Neural Network Based Residual Block ResUnet: A Systematic Approach

Analysis of intracranial neoplasm using multimodal MR images requires accurate and automatic segmentation. However, manually classifying tumors with similar structures or appearances in magnetic resonance imaging (MRI) with similar anatomy or appearances is more challenging, requiring experience to detect brain tumors. Precise segmentation of brain tumors gives clinicians with a foundation for surgical planning and treatment. Due to its capacity to segment brain tumor images automatically, Deep Neural Networks (DNN) have been widely used in image segmentation applications. To classify, segment and marking the occurrence of the brain tumor area accurately, we present custom Deep Convolution Neural Network (CNN) based Residual block U-Net (RB-ResUnet) architecture. Our technique is tested on publicly available Kaggle datasets utilizing quantitative metrics. Comparative results demonstrate that the custom CNN-based RB-ResUnet model can more reliably identify tumor locations and give accurate segmentation masks to tumor locations that are defined by bounding boxes. The findings of the experiment reveal that our proposed model RB-ResUnet can effectively aid in the identification, toxicological evaluation of the brain tumor and has clinical research as well as practical application.

SC-UneXt: Nested UNeXt Architecture based on Medical Image Segmentation

UNet and its various variants are commonly used methods in medical image segmentation tasks; however, many network parameters, complex calculations, and slow usage are problems that need to be overcome. These problems hinder the specific application of fast image segmentation in real-time tasks. At the same time, the lesion area has problems such as small size, irregular shape, and blurred edges, which makes the network feature extraction difficult and the segmentation accuracy needs to be improved. At the same time, medical image segmentation provides a variety of effective methods for the accuracy and robustness of organ segmentation, lesion detection, and classification. Medical images have fixed structures, simple semantics, and diverse details, so integrating rich multi-scale features can improve segmentation accuracy. Given that the density of diseased tissue may be comparable to that of surrounding normal tissue, both global and local information are crucial to segmentation results. To this end, we propose an image segmentation method (SC -UNe X t) based on edge feature extraction and multi-scale feature fusion of convolutional multi-layer perceptron (MLP). The network is a deeply supervised encoder-decoder network, in which the encoder and decoder pass through a series of nested, multiple jump paths to reduce the semantic gap between the feature maps of the encoder and decoder sub-networks.; Multi - scale feature fusion is introduced based on the UNe Finally, we evaluate our model approach on the LIDC dataset public dataset. Experiments have proven the effectiveness of this method. Our model's similarity coefficient and intersection ratio reached 86.44% and 90.86% respectively. Compared with UNet and UNe X t, the network proposed in this article has improved in accuracy, intersection ratio of real values and predicted values, similarity coefficient, and segmentation effect.

A Recycling Training Strategy for Medical Image Segmentation with Diffusion Denoising Models

Denoising diffusion models have found applications in image segmentation by generating segmented masks conditioned on images. Existing studies predominantly focus on adjusting model architecture or improving inference, such as test-time sampling strategies. In this work, we focus on improving the training strategy and propose a novel recycling method. During each training step, a segmentation mask is first predicted given an image and a random noise. This predicted mask, which replaces the conventional ground truth mask, is used for denoising task during training. This approach can be interpreted as aligning the training strategy with inference by eliminating the dependence on ground truth masks for generating noisy samples. Our proposed method significantly outperforms standard diffusion training, self-conditioning, and existing recycling strategies across multiple medical imaging data sets: muscle ultrasound, abdominal CT, prostate MR, and brain MR. This holds for two widely adopted sampling strategies: denoising diffusion probabilistic model and denoising diffusion implicit model. Importantly, existing diffusion models often display a declining or unstable performance during inference, whereas our novel recycling consistently enhances or maintains performance. We show for the first time that, under a fair comparison with the same network architectures and computing budget, the proposed recycling-based diffusion models achieved on-par performance with non-diffusion-based supervised training. Furthermore, by ensembling the proposed diffusion model and the non-diffusion counterpart, significant improvements to the non-diffusion models have been observed across all applications, demonstrating the value of this novel training method. This paper summarizes these quantitative results and discusses their values, with a fully reproducible JAX-based implementation, released at <a href='https://github.com/mathpluscode/ImgX-DiffSeg'>https://github.com/mathpluscode/ImgX-DiffSeg</a>

Improved kernel density peaks clustering for plant image segmentation applications

Abstract In order to better solve the shortcomings of the k-means clustering method and density peaks clustering (DPC) method in agricultural image segmentation, this work proposes a method to divide points in a high-dimensional space, and a clustering method is obtained to divide crops and soil. In the process of assigning points in the DPC method, if a point is divided incorrectly, a series of points may be assigned to a cluster that is not related to it. In response to this problem, this study uses the decision graph to select the centroids, and uses Gaussian kernel to map the data to the high-dimensional space, each centroid searches for the most relevant points in the high-dimensional space until a temporary boundary point is found to stop the first assignment strategy, and then the points that are not clustered are assigned to the correct cluster to complete the clustering. The experimental results show that the proposed method has a better clustering effect through experiments on multiple artificial datasets and UCI datasets, compared with other clustering methods, and finally applied to plant image segmentation.

Enhancing Alzheimer Disease Segmentation through Adaptively Regularized Weighted Kernel-Based Clustering

Image segmentation is important in image analysis because it helps to locate objects and boundaries within a picture. This study offers Adaptively Regularized Weighted Kernel-Based Clustering (ARWKC), a unique segmentation technique built exclusively for recovering brain tissue from medical pictures. The proposed approach incorporates adaptive regularization and weighted kernel-based clustering techniques to increase the accuracy and resilience of brain tissue segmentation. The picture is initially preprocessed with the ARWKC method to improve its quality and eliminate any noise or artifacts. The adaptive regularization method is then utilized to effectively deal with the visual variation of brain tissue in clinical images. This adaptive regularization contributes to more accurate and consistent segmentation outcomes. The weighted kernel-based clustering method is then used to find and group pixels with comparable properties, with a focus on brain tissue areas. This clustering approach employs a weighted kernel function that takes into account both geographical closeness and pixel intensities, allowing the algorithm to capture local picture features and improve segmentation accuracy. Extensive experiments were conducted on a collection of medical images to evaluate the efficacy of the ARWKC algorithm. The well-known k-means clustering method, often used in image segmentation applications, was utilized as a benchmark for comparison. In terms of accuracy and resilience for brain tissue segmentation, the experimental findings showed that the ARWKC method surpasses the k-means clustering approach.

Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers.

Convolutional neural networks (CNNs) have a proven track record in medical image segmentation. Recently, Vision Transformers were introduced and are gaining popularity for many computer vision applications, including object detection, classification, and segmentation. Machine learning algorithms such as CNNs or Transformers are subject to an inductive bias, which can have a significant impact on the performance of machine learning models. This is especially relevant for medical image segmentation applications where limited training data are available, and a model's inductive bias should help it to generalize well. In this work, we quantitatively assess the performance of two CNN-based networks (U-Net and U-Net-CBAM) and three popular Transformer-based segmentation network architectures (UNETR, TransBTS, and VT-UNet) in the context of HNC lesion segmentation in volumetric [F-18] fluorodeoxyglucose (FDG) PET scans. For performance assessment, 272 FDG PET-CT scans of a clinical trial (ACRIN 6685) were utilized, which includes a total of 650 lesions (primary: 272 and secondary: 378). The image data used are highly diverse and representative for clinical use. For performance analysis, several error metrics were utilized. The achieved Dice coefficient ranged from 0.833 to 0.809 with the best performance being achieved by CNN-based approaches. U-Net-CBAM, which utilizes spatial and channel attention, showed several advantages for smaller lesions compared to the standard U-Net. Furthermore, our results provide some insight regarding the image features relevant for this specific segmentation application. In addition, results highlight the need to utilize primary as well as secondary lesions to derive clinically relevant segmentation performance estimates avoiding biases.

A NOVEL CARDIAC IMAGE SEGMENTATION METHOD USING AN OPTIMIZED 3D U-NET MODEL

Medical image segmentation holds significant importance for doctors, patients, and the entire health care industry. For doctors, it provides more accurate information about cardiac structures, aiding in improving diagnoses and treatment decisions. For patients, segmentation techniques enable personalized medical care, enhancing treatment outcomes and satisfaction. The entire health care sector benefits from the advancement of this technology, driving the development of medical science and contributing to better health care quality and patient well-being. Additionally, segmentation plays a crucial role in research and education, facilitating the accumulation and dissemination of medical knowledge. In summary, the application of medical image segmentation has profound implications for progress in the medical field and patient welfare. In recent years, with technological advancements and innovative algorithms, medical image quality has greatly improved, with higher resolution and reduced noise and artifacts. Simultaneously, the application of deep learning techniques has made the automatic analysis and diagnosis of medical images more precise and efficient. However, due to the complex structures and diversity often present in medical images, models tend to have limited generalization across different datasets, leading to unstable segmentation performance. Considering the excellent image segmentation performance of the three-dimensional (3D) U-Net model, this study introduces an improved spatial attention mechanism on the basis of the 3D U-Net model to enhance its segmentation performance. The spatial attention mechanism enhances the model’s feature extraction capabilities. The enhanced network can capture dependencies among features across both channel and spatial dimensions in the entire global scope. Additionally, it can strengthen any two correlated features within the input feature vector, thereby enhancing the model’s representational capacity. Through detailed experimental validation, the effectiveness of the proposed model is thoroughly demonstrated. Its superiority in performance and computational efficiency positions it as a significant breakthrough in the medical image segmentation field, providing a strong foundation for future research and clinical practice in medical image processing.