Approach For Medical Image Segmentation Research Articles

Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation

The transition in medical image segmentation from fine-grained to coarse-grained annotation methods, notably scribble annotation, offers a practical and efficient preparation for deep learning applications. However, these methods often compromise segmentation precision and result in irregular contours. This study targets the enhancement of scribble-supervised segmentation to match the accuracy of fine-grained annotation. Capitalizing on the consistency of target shapes across unpaired datasets, this study introduces a shape-aware scribble-supervised learning framework (MaskMixAdv) addressing two critical tasks: (1) Pseudo label generation, where a mixup-based masking strategy enables image-level and feature-level data augmentation to enrich coarse-grained scribbles annotations. A dual-branch siamese network is proposed to generate fine-grained pseudo labels. (2) Pseudo label optimization, where a CNN-based discriminator is proposed to refine pseudo label contours by distinguishing them from external unpaired masks during model fine-tuning. MaskMixAdv works under constrained annotation conditions as a label-efficient learning approach for medical image segmentation. A case study on public cardiac MRI datasets demonstrated that the proposed MaskMixAdv outperformed the state-of-the-art methods and narrowed the performance gap between scribble-supervised and mask-supervised segmentation. This innovation cuts annotation time by at least 95%, with only a minor impact on Dice performance, specifically a 2.6% reduction. The experimental outcomes indicate that employing efficient and cost-effective scribble annotation can achieve high segmentation accuracy, significantly reducing the typical requirement for fine-grained annotations.

A flexible 2.5D medical image segmentation approach with in-slice and cross-slice attention

Deep learning has become the de facto method for medical image segmentation, with 3D segmentation models excelling in capturing complex 3D structures and 2D models offering high computational efficiency. However, segmenting 2.5D images, characterized by high in-plane resolution but lower through-plane resolution, presents significant challenges. While applying 2D models to individual slices of a 2.5D image is feasible, it fails to capture the spatial relationships between slices. On the other hand, 3D models face challenges such as resolution inconsistencies in 2.5D images, along with computational complexity and susceptibility to overfitting when trained with limited data. In this context, 2.5D models, which capture inter-slice correlations using only 2D neural networks, emerge as a promising solution due to their reduced computational demand and simplicity in implementation. In this paper, we introduce CSA-Net, a flexible 2.5D segmentation model capable of processing 2.5D images with an arbitrary number of slices. CSA-Net features an innovative Cross-Slice Attention (CSA) module that effectively captures 3D spatial information by learning long-range dependencies between the center slice (for segmentation) and its neighboring slices. Moreover, CSA-Net utilizes the self-attention mechanism to learn correlations among pixels within the center slice. We evaluated CSA-Net on three 2.5D segmentation tasks: (1) multi-class brain MR image segmentation, (2) binary prostate MR image segmentation, and (3) multi-class prostate MR image segmentation. CSA-Net outperformed leading 2D, 2.5D, and 3D segmentation methods across all three tasks, achieving average Dice coefficients and HD95 values of 0.897 and 1.40 mm for the brain dataset, 0.921 and 1.06 mm for the prostate dataset, and 0.659 and 2.70 mm for the ProstateX dataset, demonstrating its efficacy and superiority. Our code is publicly available at: https://github.com/mirthAI/CSA-Net.

UNETR++: Delving Into Efficient and Accurate 3D Medical Image Segmentation.

Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture long-range dependencies, compared to the local convolutional-based design. However, the self-attention operation has quadratic complexity which proves to be a computational bottleneck, especially in volumetric medical imaging, where the inputs are 3D with numerous slices. In this paper, we propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features using a pair of inter-dependent branches based on spatial and channel attention. Our spatial attention formulation is efficient and has linear complexity with respect to the input. To enable communication between spatial and channel-focused branches, we share the weights of query and key mapping functions that provide a complimentary benefit (paired attention), while also reducing the complexity. Our extensive evaluations on five benchmarks, Synapse, BTCV, ACDC, BraTS, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy. On Synapse, our UNETR++ sets a new state-of-the-art with a Dice Score of 87.2%, while significantly reducing parameters and FLOPs by over 71%, compared to the best method in the literature. Our code and models are available at: https://tinyurl.com/2p87x5xn.

Medical image segmentation approach based on hybrid adaptive differential evolution and crayfish optimizer

Image segmentation plays a pivotal role in medical image analysis, particularly for accurately isolating tumors and lesions. Effective segmentation improves diagnostic precision and facilitates quantitative analysis, which is vital for medical professionals. However, traditional segmentation methods often struggle with multilevel thresholding due to the associated computational complexity. Therefore, determining the optimal threshold set is an NP-hard problem, highlighting the pressing need for efficient optimization strategies to overcome these challenges. This paper introduces a multi-threshold image segmentation (MTIS) method that integrates a hybrid approach combining Differential Evolution (DE) and the Crayfish Optimization Algorithm (COA), known as HADECO. Utilizing two-dimensional (2D) Kapur’s entropy and a 2D histogram, this method aims to enhance the efficiency and accuracy of subsequent image analysis and diagnosis. HADECO is a hybrid algorithm that combines DE and COA by exchanging information based on predefined rules, leveraging the strengths of both for superior optimization results. It employs Latin Hypercube Sampling (LHS) to generate a high-quality initial population. HADECO introduces an improved DE algorithm (IDE) with adaptive and dynamic adjustments to key DE parameters and new mutation strategies to enhance its search capability. In addition, it incorporates an adaptive COA (ACOA) with dynamic adjustments to the switching probability parameter, effectively balancing exploration and exploitation. To evaluate the effectiveness of HADECO, its performance is initially assessed using CEC’22 benchmark functions. HADECO is evaluated against several contemporary algorithms using the Wilcoxon signed rank test (WSRT) and the Friedman test (FT) to integrate the results. The findings highlight HADECO’s superior optimization abilities, demonstrated by its lowest average Friedman ranking of 1.08. Furthermore, the HADECO-based MTIS method is evaluated using MRI images for knee and CT scans for brain intracranial hemorrhage (ICH). Quantitative results in brain hemorrhage image segmentation show that the proposed method achieves a superior average peak signal-to-noise ratio (PSNR) and feature similarity index (FSIM) of 1.5 and 1.7 at the 6-level threshold. In knee image segmentation, it attains an average PSNR and FSIM of 1.3 and 1.2 at the 5-level threshold, demonstrating the method’s effectiveness in solving image segmentation problems.

DeepMedSegment A Deep Learning Approach for Medical Image Segmentation

Deep Med Segment introduces an innovative approach to medical image segmentation, utilizing deeplearning techniques. Its goal is to precisely identify regions of interest within medical images, which is crucial forclinical diagnosis and treatment planning. Unlike traditional methods that rely on manual feature engineering, DeepMed Segment learns directly from data, enhancing accuracy and adaptability. Deep Med Segment employs deepconvolutional neural networks (CNNs), tailored for the complexities of medical images. It can handle variousmodalities like MRI, CT, X-ray, and ultrasound, making it versatile across medical specialties. Training requiresannotated datasets, enabling the model to map images to segmentation masks through supervised learning. To ensurerobustness, Deep Med Segment utilizes data augmentation techniques during training, enhancing its ability togeneralize across different imaging conditions. Evaluation on diverse datasets demonstrates superior performancecompared to traditional methods, with metrics like Dice similarity coefficient used for accuracy assessment. Inexperiments, Deep Med Segment consistently outperforms existing techniques, promising significant advancements inmedical imaging analysis. Its accuracy, efficiency, and adaptability make it a valuable tool for clinical diagnosis andresearch, with potential to improve patient care and healthcare outcomes. In the realm of medical image analysis,DeepMedSegment emerges as a pioneering approach harnessing the power of deep learning for image segmentation.Segmentation of medical images plays a pivotal role in clinical diagnosis, treatment planning, and monitoring ofvarious diseases. DeepMedSegment aims to tackle this challenge by leveraging advanced deep learning techniques toaccurately delineate regions of interest within medical images.One of the key strengths of DeepMedSegment lies in its ability to adapt and generalize across different modalities andimaging techniques, including magnetic resonance imaging (MRI), computed tomography (CT), X-ray, ultrasound, andmore. This versatility makes DeepMedSegment a valuable tool for a wide range of medical imaging applications,spanning from neuroimaging and oncology to cardiology and musculoskeletal imaging.

A Dual-Stage Semi-Supervised Pre-Training Approach for Medical Image Segmentation

Deep neural networks have played a vital role in developing automated methods for addressing medical image segmentation. However, their reliance on labeled data impedes the practicability. Semi-supervised learning is gaining attention for its intrinsic ability to extract valuable information from labeled and unlabeled data with improved performance. Recently, consistency regularization methods have gained interest due to their efficient learning procedures. They are, however, confined to data or network-level perturbations, negating the benefit of having both forms in a single framework. In light of this, we ask an intriguing but unexplored question: can we have both network-level and data-level perturbation in the semi-supervised framework? To this end, we present a holistic approach that integrates data-level perturbation in the model pre-training stage, followed by implicit network-level perturbation in the fine-tuning stage. Furthermore, we incorporate networks with manifold learning paradigms throughout the training to facilitate the formation of robust data representations by ensuring local and global semantic affinities adhering to the theory of consensus. Notably, this may be the first attempt in the semi-supervised medical image segmentation archetype to use data and network-level perturbation with a model pre-training strategy. We extensively validated the efficacy of the proposed framework on three benchmark datasets, namely the Automated Cardiac Diagnosis Challenge, ISIC-2018, and Left Atrial Segmentation Challenge datasets, subjected to severely low-sampled labeled data. Notably, in ACDC (4%), ISIC-2018 (5%), and LA (6%) labeled cases, the proposed method outperforms the second-best method by 2.95%, 1.31%, and 0.71% in the Dice Similarity Metric.

An effective U-net model for diagnosing Covid-19 infection

Coronavirus disease 2019 (COVID-19) has become a pandemic all over the world and has spread rapidly. To distinguish between infected and non-infected areas, there is a critical need for segmentation methods that can identify infected areas from Chest Computed Tomography (CT) scans. In recent years, deep learning has become the most widely used approach for medical image segmentation, including the identification of infected areas in Chest CT scans. We propose an encoder-decoder based on the U-NET architecture for segmenting the MedSeg dataset, which contains lung CT scans. To study the effect of input dimensions on the model's output results, we gave CT images with dimensions of 224 × 224, 256 × 256, and 512 × 512 as inputs to the model. The results showed that 224 × 224 achieved higher results compared to 256 × 256 and 512 × 512, with a dicecoef of 81.36, accuracy of 87.65, sensitivity of 84.71, and specificity of 88.35. Additionally, the 224 × 224 input based on the proposed model achieved the highest number of correct answers compared to previous U-net methods. The proposed model can be applied as an effective screening tool to help primary service staff better refer suspected patients to specialists.

A Deep Learning Approach for Medical Image Segmentation Integrating Magnetic Resonance Imaging to Enhance Brain Tumor Recognition

A Deep Learning Approach for Medical Image Segmentation Integrating Magnetic Resonance Imaging to Enhance Brain Tumor Recognition

InterTeach: A Novel Approach for Semi-Supervised Medical Image Segmentation Using Cooperative Teacher-Student Networks

InterTeach: A Novel Approach for Semi-Supervised Medical Image Segmentation Using Cooperative Teacher-Student Networks

MAXFormer: Enhanced transformer for medical image segmentation with multi-attention and multi-scale features fusion

Convolutional neural networks(CNN), especially U-shaped networks, have become the mainstream approach for medical image segmentation. However, due to the intrinsic locality of convolutional operations, CNN has inherent limitations in capturing long-range dependencies. Although Transformer-based methods have demonstrated remarkable performance in computer vision by modeling long-range dependencies, their high computational complexity and reliance on large-scale pre-training present challenges, particularly for higher-resolution medical images. In this paper, we introduce MAXFormer, a U-shaped hierarchical network that effectively leverages global context within individual samples and relationships between different samples. Our Transformer module reformulates the self-attention mechanism into two parts: local–global attention and external attention. The local–global attention provides an efficient alternative to self-attention with linear complexity, employing a parallel architecture that allows local–global spatial interactions. The local attention branch captures high-frequency local information, while the global attention branch captures low-frequency global information. Furthermore, we have designed the Refined Fused Connection module to effectively merge feature outputs from each encoder block with the decoder output, mitigating spatial detail loss due to downsampling. Extensive experiments on two different medical image segmentation datasets show that our proposed method outperforms other state-of-the-art methods without requiring pre-training weights. Code will be available at https://github.com/zhiwei-liang/MAXFormer.

A Comprehensive Review of Various Approach for Medical Image Segmentation and Disease Prediction

A Comprehensive Review of Various Approach for Medical Image Segmentation and Disease Prediction

A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning

In recent years, there have been several solutions to medical image segmentation, such as U-shaped structure, transformer-based network, and multi-scale feature learning method. However, their network parameters and real-time performance are often neglected and cannot segment boundary regions well. The main reason is that such networks have deep encoders, a large number of channels, and excessive attention to local information rather than global information, which is crucial to the accuracy of image segmentation. Therefore, we propose a novel multi-branch medical image segmentation network MBSNet. We first design two branches using a parallel residual mixer (PRM) module and dilate convolution block to capture the local and global information of the image. At the same time, a SE-Block and a new spatial attention module enhance the output features. Considering the different output features of the two branches, we adopt a cross-fusion method to effectively combine and complement the features between different layers. MBSNet was tested on five datasets ISIC2018, Kvasir, BUSI, COVID-19, and LGG. The combined results show that MBSNet is lighter, faster, and more accurate. Specifically, for a 320 times 320 input, MBSNet’s FLOPs is 10.68G, with an F1-Score of 85.29% on the Kvasir test dataset, well above 78.73% for UNet++ with FLOPs of 216.55G. We also use the multi-criteria decision making method TOPSIS based on F1-Score, IOU and Geometric-Mean (G-mean) for overall analysis. The proposed MBSNet model performs better than other competitive methods. Code is available at https://github.com/YuLionel/MBSNet.

Multi-threshold image segmentation based on an improved differential evolution: Case study of thyroid papillary carcinoma

The scholarly world has demonstrated an immense enthusiasm for medical image segmentation due to its intricate nature and critical role in medical diagnosis and treatment systems. Multi-threshold image segmentation (MTIS) is a popular technique for this purpose, due to its simplicity and straightforwardness. This paper presents an improved Differential Evolution (DE) algorithm called AGDE, which is based on MTIS and was used to evaluate its high capability at IEEE CEC 2017. Comparisons with classical and advanced algorithms were conducted as part of the experiments. An AGDE-based multi-threshold image segmentation method utilizing a non-local mean 2D histogram in combination with Rényi's entropy was applied to segment images from the Berkeley Segmentation Datasets 500 (BSDS500) and microscopic images of thyroid papillary carcinoma (TPC). The experimental results showed that the proposed image segmentation method outperformed its competitors, making it a promising approach for medical image segmentation.

IU-Net: a hybrid structured network with a novel feature fusion approach for medical image segmentation

In recent years, convolutional neural networks (CNNs) have made great achievements in the field of medical image segmentation, especially full convolutional neural networks based on U-shaped structures and skip connections. However, limited by the inherent limitations of convolution, CNNs-based methods usually exhibit limitations in modeling long-range dependencies and are unable to extract large amounts of global contextual information, which deprives neural networks of the ability to adapt to different visual modalities. In this paper, we propose our own model, which is called iU-Net bacause its structure closely resembles the combination of i and U. iU-Net is a multiple encoder-decoder structure combining Swin Transformer and CNN. We use a hierarchical Swin Transformer structure with shifted windows as the primary encoder and convolution as the secondary encoder to complement the context information extracted by the primary encoder. To sufficiently fuse the feature information extracted from multiple encoders, we design a feature fusion module (W-FFM) based on wave function representation. Besides, a three branch up sampling method(Tri-Upsample) has developed to replace the patch expand in the Swin Transformer, which can effectively avoid the Checkerboard Artifacts caused by the patch expand. On the skin lesion region segmentation task, the segmentation performance of iU-Net is optimal, with Dice and Iou reaching 90.12% and 83.06%, respectively. To verify the generalization of iU-Net, we used the model trained on ISIC2018 dataset to test on PH2 dataset, and achieved 93.80% Dice and 88.74% IoU. On the lung feild segmentation task, the iU-Net achieved optimal results on IoU and Precision, reaching 98.54% and 94.35% respectively. Extensive experiments demonstrate the segmentation performance and generalization ability of iU-Net.

Modified Histogram Equalization for Improved CNN Medical Image Segmentation

This research aims to improve the performance of convolutional neural network (CNN) in medical image segmentation that will detect specific parts of the body's anatomical structures. Medical images have drawbacks, such as the image's variability, quality, and complexity. We developed image preprocessing scenarios using Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and the hybrid approaches (HE-CLAHE and CLAHE-HE). We propose CNN with image enhancement for image segmentation and evaluate its performance on Lung CT-Scan and Chest X-ray datasets, which totaled 267 and 3616 images, respectively, and had ground truth. The experimental results indicate that the optimal cumulative distribution function (CDF) value of HE is 0 to 39, and the clip limit of CLAHE is 0.01. CNN produces the best segmentation with the addition of the CLAHE-HE approach. This method can increase the accuracy by 1.23 percentage points (training) and 3.22 percentage points (testing) for Lung CT-Scan images. Meanwhile, for Chest X-ray images, the training and testing accuracy increased by 1.58 and 0.96 percentage points. In addition, the proposed medical image segmentation approach using the CNN method with CLAHE-HE obtained the values of comparative coefficients DSC (dice similarity coefficient), and SSIM (structural similarity index measurement) of only about 0.92 and 0.97, respectively.

Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency.

Despite that Convolutional Neural Networks (CNNs) have achieved promising performance in many medical image segmentation tasks, they rely on a large set of labeled images for training, which is expensive and time-consuming to acquire. Semi-supervised learning has shown the potential to alleviate this challenge by learning from a large set of unlabeled images and limited labeled samples. In this work, we present a simple yet efficient consistency regularization approach for semi-supervised medical image segmentation, called Uncertainty Rectified Pyramid Consistency (URPC). Inspired by the pyramid feature network, we chose a pyramid-prediction network that obtains a set of segmentation predictions at different scales. For semi-supervised learning, URPC learns from unlabeled data by minimizing the discrepancy between each of the pyramid predictions and their average. We further present multi-scale uncertainty rectification to boost the pyramid consistency regularization, where the rectification seeks to temper the consistency loss at outlier pixels that may have substantially different predictions than the average, potentially due to upsampling errors or lack of enough labeled data. Experiments on two public datasets and an in-house clinical dataset showed that: 1) URPC can achieve large performance improvement by utilizing unlabeled data and 2) Compared with five existing semi-supervised methods, URPC achieved better or comparable results with a simpler pipeline. Furthermore, we build a semi-supervised medical image segmentation codebase to boost research on this topic: https://github.com/HiLab-git/SSL4MIS.

C+Ref-UNet: A Novel Approach for Medical Image Segmentation Based on Multi-Scale Connected UNet and CBAM

C+Ref-UNet: A Novel Approach for Medical Image Segmentation Based on Multi-Scale Connected UNet and CBAM

Hybrid Segmentation Approach for Different Medical Image Modalities

The segmentation process requires separating the image region into sub-regions of similar properties. Each sub-region has a group of pixels having the same characteristics, such as texture or intensity. This paper suggests an efficient hybrid segmentation approach for different medical image modalities based on particle swarm optimization (PSO) and improved fast fuzzy C-means clustering (IFFCM) algorithms. An extensive comparative study on different medical images is presented between the proposed approach and other different previous segmentation techniques. The existing medical image segmentation techniques incorporate clustering, thresholding, graph-based, edge-based, active contour, region-based, and watershed algorithms. This paper extensively analyzes and summarizes the comparative investigation of these techniques. Finally, a prediction of the improvement involves the combination of these techniques is suggested. The obtained results demonstrate that the proposed hybrid medical image segmentation approach provides superior outcomes in terms of the examined evaluation metrics compared to the preceding segmentation techniques.

Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization

An accurate whole heart segmentation (WHS) on medical images, including computed tomography (CT) and magnetic resonance (MR) images, plays a crucial role in many clinical applications, such as cardiovascular disease diagnosis, pre-surgical planning, and intraoperative treatment. Manual whole-heart segmentation is a time-consuming process, prone to subjectivity and error. Therefore, there is a need to develop a quick, automatic, and accurate whole heart segmentation systems. Nowadays, convolutional neural networks (CNNs) emerged as a robust approach for medical image segmentation. In this paper, we first introduce a novel connectivity structure of residual unit that we refer to as a feature merge residual unit (FM-Pre-ResNet). The proposed connectivity allows the creation of distinctly deep models without an increase in the number of parameters compared to the pre-activation residual units. Second, we propose a three-dimensional (3D) encoder–decoder based architecture that successfully incorporates FM-Pre-ResNet units and variational autoencoder (VAE). In an encoding stage, FM-Pre-ResNet units are used for learning a low-dimensional representation of the input. After that, the variational autoencoder (VAE) reconstructs the input image from the low-dimensional latent space to provide a strong regularization of all model weights, simultaneously preventing overfitting on the training data. Finally, the decoding stage creates the final whole heart segmentation. We evaluate our method on the 40 test subjects of the MICCAI Multi-Modality Whole Heart Segmentation (MM-WHS) Challenge. The average dice values of whole heart segmentation are 90.39% (CT images) and 89.50% (MRI images), which are both highly comparable to the state-of-the-art.

An accurate Cluster chaotic optimization approach for digital medical image segmentation

Image segmentation is a crucial stage in digital image processing used to obtain a more straightforward representation of images. Although classic bi-level segmentation is a relatively simple task, it only suffices to analyze rather simple images. More complex real-life scenarios such as medical imaging processing usually require multi-level segmentation to differentiate between the many regions of interest present in the original images. Traditional histogram-based approaches for multi-level segmentation tend to perform suboptimally, with the best performing being computationally expensive. This difficult compromise between performance and computational cost has led to the proposal of new approaches mixing a variety of optimization algorithms and statistical criteria. Despite the success of these new approaches, there is still room for improvement. It is under these circumstances that evolutionary algorithms like the cluster chaotic optimization (CCO) become relevant. The CCO takes advantage of the classification procedures of clustering techniques and the randomness of chaotic sequences for encouraging the search strategy. This paper proposes a novel method based on the CCO algorithm named minimum cross-entropy multi-level segmentation CCO (CEMS-CCO). The CEMS-CCO employs the cross-entropy as its fitness function and the CCO capabilities to deal with multimodal functions to search for the optimal solution to the multi-level segmentation problem. The CEMS-CCO shows competitive results for medical images multi-level segmentation regarding different quality metrics. Furthermore, its robustness and effectiveness are tested through the analysis of well-known benchmark images. Statistical analysis of the experimental results shows that the proposed CEMS-CCO technique outperforms state-of-the-art algorithms.