PDE-UNet: A Modified UNet Architecture Applied to Medical Image Segmentation

Explainable multi-module semantic guided attention based network for medical image segmentation

Medical image segmentation is a critical application of computer vision in the analysis of medical images. Its primary objective is to isolate regions of interest in medical images from the background, thereby assisting clinicians in accurately identifying lesions, their sizes, locations, and their relationships with surrounding tissues. However, compared to natural images, medical images present unique challenges, such as low resolution, poor contrast, inconsistency, and scattered target regions. Furthermore, the accuracy and stability of segmentation results are subject to more stringent requirements. In recent years, with the widespread application of Convolutional Neural Networks (CNNs) in computer vision, deep learning-based methods for medical image segmentation have become a focal point of research. This paper categorizes, reviews, and summarizes the current representative methods and research status in the field of medical image segmentation. A comparative analysis of relevant experiments is presented, along with an introduction to commonly used public datasets, performance evaluation metrics, and loss functions in medical image segmentation. Finally, potential future research directions and development trends in this field are predicted and analyzed.

Introduction: Precise segmentation of the liver from computed tomography (CT) scans is an essential component in the diagnosis and treatment of liver diseases such as hepatocellular carcinoma. Manual segmentation can be time-consuming and subject to variability, spurring the application of automated systems based on deep learning. We introduce a 3D U-Net-based convolutional neural network for end-to-end segmentation of the liver from volumetric CT images. The model is trained and tested on the LiTS dataset using a standard preprocessing pipeline and an in-house composite loss function—AdvancedComboLoss—combining Dice Loss, Binary Cross-Entropy, and Focal Tversky Loss to balance class imbalance and boundary accuracy. The network handles entire 3D volumes with spatial context retained between anatomical planes and is trained on a GPU-enabled setup with the PyTorch environment. Objectives: To develop a highly accurate and computationally efficient 3D U-Net-based deep learning model for automated liver segmentation from volumetric CT scans, addressing challenges like class imbalance, anatomical variability, and low tissue contrast, using a custom loss function (AdvancedComboLoss) and a standardized preprocessing pipeline. Methods: The methodology adopted is volumetric liver segmentation from a specially designed 3D U-Net architecture specific to medical CT scans. The process entails preprocessing of raw CT scans into a common shape and intensity range and training a fully convolutional 3D neural network that learns the spatial relationships among all three anatomical planes. The model uses an encoder-decoder architecture with skip connections to maintain fine-grained structural information, allowing for accurate delineation of liver regions. A hybrid loss function—integrating Dice, Binary Cross-Entropy, and Focal Tversky losses—is used to direct the learning process to optimize overlap of regions, accuracy of classification, and class imbalance. Results: Experimental outcomes demonstrate that the model has a Dice score of 0.9604 and voxel-wise accuracy of 0.9979, indicating excellent performance in segmentation as well as strong agreement with expert annotations. The model presented in this paper presents a solid, scalable, and clinically valuable approach to automated liver segmentation with future potential to integrate into multi-stage liver and tumor analysis workflows. Conclusions: Herein, we built and tested a 3D U-Net deep learning architecture for unsupervised liver segmentation from abdominal CT volumes. Through utilization of volumetric convolutions as well as through a well-engineered composite loss function, the model was successful in capturing complicated liver anatomy as well as being able to hold high performance even on varied CT volumes. The power of the method is not just in its quantitative performance but also in its capability to generate anatomically consistent and visually plausible segmentations, making it extremely relevant to actual clinical workflows. Although there are some limitations—constrained batch size and absence of data augmentation—there is room for improvement, the findings affirm that deep learning can be an effective tool for automating key tasks in medical image analysis. As a whole, this paper adds a robust and effective segmentation model that would be potentially embedded in wider diagnostic workflows, ending up improving the accuracy, speed, and scalability of liver evaluation in clinical practice. In brief, this paper adds a high-fidelity, scalable, and computationally effective solution for computer-aided liver segmentation, pushing the application of artificial intelligence in clinical decision-making and medical image analysis.

Medical image segmentation, the process of precisely delineating regions of interest (e.g. organs, lesions, cells) within medical images, is a pivotal technique in medical image analysis. It finds widespread application in computer‐aided diagnosis, surgical planning, radiation therapy, and pathological analysis, thus playing a crucial role in enabling precision medicine and enhancing the quality of clinical care. Traditional medical image segmentation methods often rely on hand‐crafted features and rule‐based approaches, which struggle to handle the inherent complexity and variability of medical imagery, leading to limitations in segmentation accuracy and robustness. Recently, deep learning methodologies, driven by their powerful capabilities in automatic feature learning and non‐linear modelling, have overcome the limitations of traditional methods and achieved significant advancements in the field of medical image segmentation. This review provides a comprehensive overview and summary of recent progress in deep learning‐based medical image segmentation, with a particular focus on fully supervised learning paradigms leveraging convolutional neural networks, transformers, and the segment anything model. We delve into the underlying principles, network architectures, advantages, and limitations of these approaches. Furthermore, we systematically compare their performance across diverse imaging modalities, anatomical structures, and pathological targets. We also present a curated compilation of commonly used datasets, evaluation metrics, and loss functions relevant to medical image segmentation. Finally, we discuss future research directions and potential challenges, offering insights into the evolving landscape of this critical field.

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging-related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations.

LCP-Net: A local context-perception deep neural network for medical image segmentation

DSEU-net: A novel deep supervision SEU-net for medical ultrasound image segmentation

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

Image segmentation is the fundamental step in medical image analysis. Segmentation is a procedure to separate similar portions of images showing resemblance in different features such as color, intensity, or texture. Grayscale images are mostly used for the segmentation of medical images. Tumors are commonly stated as the abnormal growth of tissues and the brain tumor is a diseased part in the body tissues that is an abnormal mass in which the growth rate of cells is irrepressible. The mortality rate of people has raised over the past years due to brain tumors, hence this area has gained the attention of researchers. Automatic detection of brain tumors is a challenging task because it involves pathology, functional physics of MRI along with intensity and shapes analysis of MR image. After all, tumor shape, size, location, and intensity vary for each infected case. In this work, a novel hybrid approach is implemented by combing watershed segmentation, level set segmentation and K means clustering. First, the image is preprocessed by removing the skull. Watershed segmentation is applied to this preprocessed image. Level set segmentation is applied to the previous step. Finally, k means clustering is applied as the final step to detect tumor parts accurately. This Hybrid approach is compared with other four techniques such as Threshold segmentation, K means clustering, Watershed segmentation, and Level set-based segmentation methods. Statistical and Visual analysis is performed. It is found that the hybrid approach has better specificity, accuracy, and precision among all four techniques. Further, it is able to detect tumors more accurately. This research could help clinicians in surgical planning, treatment planning and accurately segmenting the tumor part with the most accurate method.

Medical image processing and analysis operations, particularly segmentation, can benefit a great deal from prior information encoded to capture variations over a population in form, shape, anatomic layout, and image appearance of objects. Model/atlas-based methods are extant in medical image segmentation. Although multi-atlas/ multi-model methods have shown improved accuracy for image segmentation, if the atlases/models do not cover representatively the distinct groups, then the methods may not be generalizable to new populations. In a previous study, we have given an answer to address the following problem at image level: How many models/ atlases are needed for optimally encoding prior information to address the differing body habitus factor in a population? However, the number of models for different objects may be different, and at the image level, it may not be possible to infer the number of models needed for each object. So, the modified question to which we are now seeking an answer to in this paper is: How many models/ atlases are needed for optimally encoding prior information to address the differing body habitus factor for each object in a body region? To answer this question, we modified our method in the previous study for seeking the optimum grouping for a given population of images but focusing on the individual objects. We present our results on head and neck computed tomography (CT) scans of 298 patients.

Machine learning techniques such as deep learning methods have produced promising results in medical images analysis. This work proposes a user-friendly system that utilizes deep learning techniques for detecting and diagnosing diseases using medical images. This includes the design of CAD-based project that can reduce human factor-related errors while performing manual screening of medical images. The system accepts medical images as input and performs segmentation of the images. Segmentation process analyzes and identifies the region of interest (ROI) of diseases from medical images. Analyzing and segmentation of medical images has assisted in the diagnosis and monitoring of some diseases. Diseases such as skin cancer, age-related fovea degeneration, diabetic retinopathy, glaucoma, hypertension, arteriosclerosis, and choroidal neovascularization can be effectively managed by the analysis of skin lesion and retinal vessels images. The proposed system was evaluated on diseases such as diabetic retinopathy from retina images and skin cancer from dermoscopic images.

Medical image segmentation is a fundamental task in medical image analysis, playing a crucial role in disease diagnosis, treatment planning, and clinical decision-making. Accurate segmentation of anatomical structures, such as blood vessels, organs, and lesions, is essential for reliable medical interpretations. However, existing segmentation models often face challenges in effectively capturing both local and global features within medical images. Traditional convolutional neural networks (CNNs) excel at extracting fine-grained local features but struggle to model long-range dependencies due to their limited receptive fields. Conversely, transformer-based models can capture global contextual relationships but often fail to preserve detailed local structures, leading to suboptimal segmentation performance. The purpose of this study is to develop SEFormer, a novel hybrid network that integrates SENet, ResNet, and Transformer to enhance medical image segmentation. SEFormer aims to effectively capture both local and global features, addressing the limitations of traditional CNNs and transformer-based models.SENet is incorporated to recalibrate feature maps by adaptively emphasizing informative features, thereby compensating for the global representation limitations of CNNs. Meanwhile, the ResNet backbone ensures deep feature extraction while maintaining computational efficiency. Additionally, the Transformer module is introduced to capture long-range dependencies and enhance contextual awareness, complementing the local feature extraction capabilities of CNNs. This hybrid approach allows SEFormer to balance fine-grained spatial details with broader contextual information, leading to more precise segmentation results.Furthermore, to mitigate information loss during feature extraction and ensure a more complete and hierarchical representation of image information, we introduce a feature pyramid structure inspired by multi-scale image pyramid models. By progressively increasing the receptive field across different scales and employing skip connections, SEFormer effectively fuses multi-scale local and global features at each stage of the pyramid. This hierarchical fusion mechanism ensures a richer and more robust feature representation, which is particularly beneficial for segmenting complex medical structures such as blood vessels. We evaluate SEFormer on the CHASE_DB1 dataset, a widely used benchmark for retinal vessel segmentation. Experimental results demonstrate that SEFormer outperforms existing state-of-the-art segmentation methods, achieving a 3.25% improvement in segmentation accuracy. Additionally, we conduct ablation studies to verify the contributions of different components within SEFormer. The results show that incorporating SENet enhances feature recalibration and channel attention, while the Transformer module significantly improves global context awareness. The feature pyramid structure further contributes to performance gains by ensuring a multi-scale representation of vascular structures. Compared to conventional CNN-based methods, our approach achieves better segmentation accuracy with improved robustness to variations in vessel thickness, noise, and image contrast. Furthermore, SEFormer maintains computational efficiency, making it suitable for real-world clinical applications where both accuracy and processing speed are critical. SEFormer provides an efficient and accurate approach for medical image segmentation by leveraging the complementary strengths of CNNs, SENet, and Transformers while integrating a feature pyramid structure to maximize feature representation. Future research directions include extending SEFormer to other medical imaging modalities, such as CT and MRI scans, as well as exploring further optimization techniques to reduce computational costs while maintaining high segmentation performance. Additionally, integrating SEFormer with active learning frameworks could further improve segmentation performance by leveraging expert-annotated data more efficiently.

Multilevel thresholding for segmentation of medical brain images using real coded genetic algorithm

In response to the issues of single-scale information loss and large model parameter size during the sampling process in U-Net and its variants for medical image segmentation, this paper proposes a multi-scale medical image segmentation method based on pixel encoding and spatial attention. Firstly, by redesigning the input strategy of the Transformer structure, a pixel encoding module is introduced to enable the model to extract global semantic information from multi-scale image features, obtaining richer feature information. Additionally, deformable convolutions are incorporated into the Transformer module to accelerate convergence speed and improve module performance. Secondly, a spatial attention module with residual connections is introduced to allow the model to focus on the foreground information of the fused feature maps. Finally, through ablation experiments, the network is lightweighted to enhance segmentation accuracy and accelerate model convergence. The proposed algorithm achieves satisfactory results on the Synapse dataset, an official public dataset for multi-organ segmentation provided by the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), with Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) scores of 77.65 and 18.34, respectively. The experimental results demonstrate that the proposed algorithm can enhance multi-organ segmentation performance, potentially filling the gap in multi-scale medical image segmentation algorithms, and providing assistance for professional physicians in diagnosis.

The global incidence and mortality rates of pancreatic cancer have been on the rise in recent decades. At the same time, pancreatic cancer occupies a leading position among malignant neoplasms, which are often first detected at advanced stages, which significantly worsens the prognosis for patients. In this regard, it is important to create automated systems capable of accurately segmenting and diagnosing pancreatic tumors at an early stage. A diagnostic model based on U-Net is proposed and evaluated, aimed at improving the accuracy of automatic segmentation of medical images for segmentation of the pancreas and identification of malignant changes in computed tomography (CT) images. The diagnostic model of the algorithm was based on the U-Net architecture, and image texture indices were used as control features. The neural network algorithm was trained using CT data from 310 patients with pancreatic neoplasms. Segmentation datasets from 280 pancreatic cancer studies from an open source, Memorial Sloan Kettering Cancer Center, was used to segment medical images and train the algorithm. Manual segmentation of medical images obtained at Regional Clinical Hospital of the Kaliningrad was performed using specialized three-dimensional (3D) Slicer software: CT images of 30 patients with pancreatic neoplasms. Diagnoses in the patient group were confirmed by morphological diagnostics, including examination of biopsy samples and/or surgical material. Four types of indicators were used to quantify segmentation results: Dice similarity coefficient (DSC), accuracy, sensitivity, and specificity. The diagnostic model achieved an accuracy of 88% in the classification of pancreatic cancer, and the DSC segmentation accuracy factor was 70%, demonstrating sensitivity of 98% and specificity of 98%. The results obtained emphasize the effectiveness of CT image analysis for the diagnosis of pancreatic malignancies using a neural network algorithm that uses textural features of medical images. In the course of the work, a number of limitations were identified: obtaining false positive results during segmentation, a limited number of medical images and clinical data that may affect the representativeness of the developed diagnostic model. Nevertheless, the results show the prospects for integrating artificial intelligence (AI) technologies into clinical practice, which can significantly improve diagnostic efficiency. The use of neural network algorithms based on the textural features of medical images has significant potential in the field of clinical decision support systems. Despite certain limitations in the course of work, the using textural features for training neural networks will increase the accuracy of diagnosis of pancreatic malignancies and will play an important role in determining patient management strategies and monitoring the effectiveness of prescribed treatment methods. It is necessary to further study additional textural characteristics, utilize 3D models, and include more clinical data to improve the accuracy of the diagnostic model when differentiating malignant tumors from healthy tissues.