Medical Segmentation Tasks Research Articles

FedATA: Adaptive attention aggregation for federated self-supervised medical image segmentation

Pre-trained on large-scale datasets has profoundly promoted the development of deep learning models in medical image analysis. For medical image segmentation, collecting a large number of labeled volumetric medical images from multiple institutions is an enormous challenge due to privacy concerns. Self-supervised learning with mask image modeling (MIM) can learn general representation without annotations. Integrating MIM into FL enables collaborative learning of an efficient pre-trained model from unlabeled data, followed by fine-tuning with limited annotations. However, setting pixels as reconstruction targets in traditional MIM fails to facilitate robust representation learning due to the medical image's complexity and distinct characteristics. On the other hand, the generalization of the aggregated model in FL is also impaired under the heterogeneous data distributions among institutions. To address these issues, we proposed a novel self-supervised federated learning, which combines masked self-distillation with adaptive attention federated learning. Such incorporation enjoys two vital benefits. First, masked self-distillation sets high-quality latent representations of masked tokens as the target, improving the descriptive capability of the learned presentation rather than reconstructing low-level pixels. Second, adaptive attention aggregation with Personalized federate learning effectively captures specific-related representation from the aggregated model, thus facilitating local fine-tuning performance for target tasks. We conducted comprehensive experiments on two medical segmentation tasks using a large-scale dataset consisting of volumetric medical images from multiple institutions, demonstrating superior performance compared to existing federated self-supervised learning approaches.

Necessity and impact of specialization of large foundation model for medical segmentation tasks.

Large foundation models, such as the Segment Anything Model (SAM), have shown remarkable performance in image segmentation tasks. However, the optimal approach to achieve true utility of these models for domain-specific applications, such as medical image segmentation, remains an open question. Recent studies have released a medical version of the foundation model MedSAM by training on vast medical data, who promised SOTA medical segmentation. Independent community inspection and dissection is needed. Foundation models are developed for general purposes. On the other hand, stable delivery of reliable performance is key to clinical utility. This study aims at elucidating the potential advantage and limitations of landing the foundation models in clinical use by assessing the performance of off-the-shelf medical foundation model MedSAM for the segmentation of anatomical structures in pelvic MR images. We also explore the simple remedies by evaluating the dependency on prompting scheme. Finally, we demonstrate the need and performance gain of further specialized fine-tuning. MedSAM and its lightweight version LiteMedSAM were evaluated out-of-the-box on a public MR dataset consisting of 589 pelvic images split 80:20 for training and testing. An nnU-Net model was trained from scratch to serve as a benchmark and to provide bounding box prompts for MedSAM. MedSAM was evaluated using different quality bounding boxes, those derived from ground truth labels, those derived from nnU-Net, and those derived from the former two but with 5-pixel isometric expansion. Lastly, LiteMedSAM was refined on the training set and reevaluated on this task. Out-of-the-box MedSAM and LiteMedSAM both performed poorly across the structure set, especially for disjoint or non-convex structures. Varying prompt with different bounding box inputs had minimal effect. For example, the mean Dice score and mean Hausdorff distances (in mm) for obturator internus using MedSAM and LiteMedSAM were {0.251±0.110, 0.101±0.079} and {34.142±5.196, 33.688±5.306}, respectively. Fine-tuning of LiteMedSAM led to significant performance gain, improving Dice score and Hausdorff distance for the obturator internus to 0.864±0.123 and 5.022±10.684, on par with nnU-Net with no significant difference in evaluation of most structures. All segmentation structures benefited significantly from specialized refinement, at varying improvement margin. While our study alludes to the potential of deep learning models like MedSAM and LiteMedSAM for medical segmentation, it highlights the need for specialized refinement and adjudication. Off-the-shelf use of such large foundation models is highly likely to be suboptimal, and specialized fine-tuning is often necessary to achieve clinical desired accuracy and stability.

DRFL: Dynamic-Recall Focal Loss for Image Classification and Segmentation

ABSTRACT The accuracy of neural networks heavily depends on numerous precisely annotated samples. But in actual datasets, the number of samples for each category varies greatly. In the dataset, some classes may have a large sample size, called majority classes, while others may have a small sample size, called minority classes. Training model with imbalanced data is often conducive to the majority classes, while unfair to minority classes. As a result, the outputs return good performance on majority classes and bad performance on minority classes. This article proposes a new loss function called dynamic-recall focal loss (DRFL), which can solve the problem of imbalanced data categories in image classification and medical segmentation tasks. The DRFL assigns different weight coefficient to the classes according to their dynamic recall based on focal loss. Experimental results have shown that the newly proposed loss function DRFL can effectively improve the classification and segmentation accuracy of two imbalanced datasets.

HSMix: Hard and soft mixing data augmentation for medical image segmentation

Due to the high cost of annotation or the rarity of some diseases, medical image segmentation is often limited by data scarcity and the resulting overfitting problem. Self-supervised learning and semi-supervised learning can mitigate the data scarcity challenge to some extent. However, both of these paradigms are complex and require either hand-crafted pretexts or well-defined pseudo-labels. In contrast, data augmentation represents a relatively simple and straightforward approach to addressing data scarcity issues. It has led to significant improvements in image recognition tasks. However, the effectiveness of local image editing augmentation techniques in the context of segmentation has been less explored. Additionally, traditional data augmentation methods for local image editing augmentation methods generally utilize square regions, which cause a loss of contour information.We propose HSMix, a novel approach to local image editing data augmentation involving hard and soft mixing for medical semantic segmentation. In our approach, a hard-augmented image is created by combining homogeneous regions (superpixels) from two source images. A soft mixing method further adjusts the brightness of these composed regions with brightness mixing based on locally aggregated pixel-wise saliency coefficients. The ground-truth segmentation masks of the two source images undergo the same mixing operations to generate the associated masks for the augmented images.Our method fully exploits both the prior contour and saliency information, thus preserving local semantic information in the augmented images while enriching the augmentation space with more diversity. Our method is a plug-and-play solution that is model agnostic and applicable to a range of medical imaging modalities. Extensive experimental evidence has demonstrated its effectiveness in a variety of medical segmentation tasks. The source code is available in https://github.com/DanielaPlusPlus/HSMix.

Prototype-Guided Graph Reasoning Network for Few-Shot Medical Image Segmentation.

Few-shot semantic segmentation (FSS) is of tremendous potential for data-scarce scenarios, particularly in medical segmentation tasks with merely a few labeled data. Most of the existing FSS methods typically distinguish query objects with the guidance of support prototypes. However, the variances in appearance and scale between support and query objects from the same anatomical class are often exceedingly considerable in practical clinical scenarios, thus resulting in undesirable query segmentation masks. To tackle the aforementioned challenge, we propose a novel prototype-guided graph reasoning network (PGRNet) to explicitly explore potential contextual relationships in structured query images. Specifically, a prototype-guided graph reasoning module is proposed to perform information interaction on the query graph under the guidance of support prototypes to fully exploit the structural properties of query images to overcome intra-class variances. Moreover, instead of fixed support prototypes, a dynamic prototype generation mechanism is devised to yield a collection of dynamic support prototypes by mining rich contextual information from support images to further boost the efficiency of information interaction between support and query branches. Equipped with the proposed two components, PGRNet can learn abundant contextual representations for query images and is therefore more resilient to object variations. We validate our method on three publicly available medical segmentation datasets, namely CHAOS-T2, MS-CMRSeg, and Synapse. Experiments indicate that the proposed PGRNet outperforms previous FSS methods by a considerable margin and establishes a new state-of-the-art performance.

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.

Super-resolution reconstruction for early cervical cancer magnetic resonance imaging based on deep learning

This study aims to develop a super-resolution (SR) algorithm tailored specifically for enhancing the image quality and resolution of early cervical cancer (CC) magnetic resonance imaging (MRI) images. The proposed method is subjected to both qualitative and quantitative analyses, thoroughly investigating its performance across various upscaling factors and assessing its impact on medical image segmentation tasks. The innovative SR algorithm employed for reconstructing early CC MRI images integrates complex architectures and deep convolutional kernels. Training is conducted on matched pairs of input images through a multi-input model. The research findings highlight the significant advantages of the proposed SR method on two distinct datasets at different upscaling factors. Specifically, at a 2× upscaling factor, the sagittal test set outperforms the state-of-the-art methods in the PSNR index evaluation, second only to the hybrid attention transformer, while the axial test set outperforms the state-of-the-art methods in both PSNR and SSIM index evaluation. At a 4× upscaling factor, both the sagittal test set and the axial test set achieve the best results in the evaluation of PNSR and SSIM indicators. This method not only effectively enhances image quality, but also exhibits superior performance in medical segmentation tasks, thereby providing a more reliable foundation for clinical diagnosis and image analysis.

BMCS-Net: A Bi-directional multi-scale cascaded segmentation network based on transformer-guided feature Aggregation for medical images

convolutional neural networks (CNNs) show great potential in medical image segmentation tasks, and can provide reliable basis for disease diagnosis and clinical research. However, CNNs exhibit general limitations on modeling explicit long-range relation, and existing cures, resorting to building deep encoders along with aggressive downsampling operations, leads to loss of localized details. Transformer has naturally excellent ability to model the global features and long-range correlations of the input information, which is strongly complementary to the inductive bias of CNNs. In this paper, a novel Bi-directional Multi-scale Cascaded Segmentation Network, BMCS-Net, is proposed to improve the performance of medical segmentation tasks by aggregating these features obtained from Transformers and CNNs branches. Specifically, a novel feature integration technique, termed as Two-stream Cascaded Feature Aggregation (TCFA) module, is designed to fuse features in two-stream branches, and solve the problem of gradual dilution of global information in the network. Besides, a Multi-Scale Expansion-Aware (MSEA) module based on the convolution of feature perception and expansion is introduced to capture context information, and further compensate for the loss of details. Extensive experiments demonstrated that BMCS-Net has an excellent performance on both skin and Polyp segmentation datasets.

Exploring Generalizable Distillation for Efficient Medical Image Segmentation.

Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook the generalizability of the cross-domain medical segmentation tasks. In this paper, we propose Generalizable Knowledge Distillation (GKD), a novel framework for enhancing the performance of lightweight networks on cross-domain medical segmentation by generalizable knowledge distillation from powerful teacher networks. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Based on the domain-invariant vectors in MSAN, we propose two generalizable distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). In DCGD, two implicit contrastive graphs are designed to model the intra-coupling and inter-coupling semantic correlations. Then, in DICD, the domain-invariant semantic vectors are reconstructed from two networks (i.e., teacher and student) with a crossover manner to achieve simultaneous generalization of lightweight networks, hierarchically. Moreover, a metric named Fréchet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver, Retinal Vessel and Colonoscopy segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization ability on lightweight networks.

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.

Deep Segmentation Techniques for Breast Cancer Diagnosis

Background: This research goes into in deep learning technologies within the realm of medical imaging, with a specific focus on the detection of anomalies in medical pathology, emphasizing breast cancer. It underscores the critical importance of segmentation techniques in identifying diseases and addresses the challenges of scarce labelled data in Whole Slide Images. Additionally, the paper provides a review, cataloguing 61 deep learning architectures identified during the study. Objectives: The aim of this study is to present and assess a novel quantitative approach utilizing specific deep learning architectures, namely the Feature Pyramid Net-work and the Linknet model, both of which integrate a ResNet34 layer encoder to enhance performance. The paper also seeks to examine the efficiency of a semi-supervised training regimen using a dual model architecture, consisting of ‘Teacher’ and ‘Student’ models, in addressing the issue of limited labelled datasets. Methods: Employing a semi-supervised training methodology, this research enables the ‘Student’ model to learn from the ‘Teacher’ model’s outputs. The study methodically evaluates the models’ stability, accuracy, and segmentation capabilities, employing metrics such as the Dice Coefficient and the Jaccard Index for comprehensive assessment. Results: The investigation reveals that the Linknet model exhibits good performance, achieving an accuracy rate of 94% in the detection of breast cancer tissues utilizing a 21-seed parameter for the initialization of model weights. It further excels in generating annotations for the ‘Student’ model, which then achieves a 91% accuracy with minimal computational demands. Conversely, the Feature Pyramid Network model demonstrates a slightly lower accuracy of 93% in the Teacher model but exhibits improved and more consistent results in the ‘Student’ model, reaching 95% accuracy with a 42-seed parameter. Conclusions: This study underscores the efficacy and potential of the Feature Pyra-mid Network and Linknet models in the domain of medical image analysis, particularly in the detection of breast cancer, and suggests their broader applicability in various medical segmentation tasks related to other pathology disorders. Furthermore, the research enhances the understanding of the pivotal role that deep learning technologies play in advancing diagnostic methods within the field of medical imaging.

Use of superpixels for improvement of inter-rater and intra-rater reliability during annotation of medical images

In the context of automatic medical image segmentation based on statistical learning, raters’ variability of ground truth segmentations in training datasets is a widely recognized issue. Indeed, the reference information is provided by experts but bias due to their knowledge may affect the quality of the ground truth data, thus hindering creation of robust and reliable datasets employed in segmentation, classification or detection tasks. In such a framework, automatic medical image segmentation would significantly benefit from utilizing some form of presegmentation during training data preparation process, which could lower the impact of experts’ knowledge and reduce time-consuming labeling efforts. The present manuscript proposes a superpixels-driven procedure for annotating medical images. Three different superpixeling methods with two different number of superpixels were evaluated on three different medical segmentation tasks and compared with manual annotations. Within the superpixels-based annotation procedure medical experts interactively select superpixels of interest, apply manual corrections, when necessary, and then the accuracy of the annotations, the time needed to prepare them, and the number of manual corrections are assessed. In this study, it is proven that the proposed procedure reduces inter- and intra-rater variability leading to more reliable annotations datasets which, in turn, may be beneficial for the development of more robust classification or segmentation models. In addition, the proposed approach reduces time needed to prepare the annotations.

Enhancing medical image segmentation with a multi-transformer U-Net.

Various segmentation networks based on Swin Transformer have shown promise in medical segmentation tasks. Nonetheless, challenges such as lower accuracy and slower training convergence have persisted. To tackle these issues, we introduce a novel approach that combines the Swin Transformer and Deformable Transformer to enhance overall model performance. We leverage the Swin Transformer's window attention mechanism to capture local feature information and employ the Deformable Transformer to adjust sampling positions dynamically, accelerating model convergence and aligning it more closely with object shapes and sizes. By amalgamating both Transformer modules and incorporating additional skip connections to minimize information loss, our proposed model excels at rapidly and accurately segmenting CT or X-ray lung images. Experimental results demonstrate the remarkable, showcasing the significant prowess of our model. It surpasses the performance of the standalone Swin Transformer's Swin Unet and converges more rapidly under identical conditions, yielding accuracy improvements of 0.7% (resulting in 88.18%) and 2.7% (resulting in 98.01%) on the COVID-19 CT scan lesion segmentation dataset and Chest X-ray Masks and Labels dataset, respectively. This advancement has the potential to aid medical practitioners in early diagnosis and treatment decision-making.

Calibrate the Inter-Observer Segmentation Uncertainty via Diagnosis-First Principle.

Many of the tissues/lesions in the medical images may be ambiguous. Therefore, medical segmentation is typically annotated by a group of clinical experts to mitigate personal bias. A common solution to fuse different annotations is the majority vote, e.g., taking the average of multiple labels. However, such a strategy ignores the difference between the grader expertness. Inspired by the observation that medical image segmentation is usually used to assist the disease diagnosis in clinical practice, we propose the diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis-First segmentation Framework (DiFF) is proposed. Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis-First Ground-truth (DF-GT). Then, the Take and Give Model (T&G Model) to segment DF-GT from the raw image is proposed. With the T&G Model, DiFF can learn the segmentation with the calibrated uncertainty that facilitate the disease diagnosis. We verify the effectiveness of DiFF on three different medical segmentation tasks: optic-disc/optic-cup (OD/OC) segmentation on fundus images, thyroid nodule segmentation on ultrasound images, and skin lesion segmentation on dermoscopic images. Experimental results show that the proposed DiFF can effectively calibrate the segmentation uncertainty, and thus significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods.

Simultaneous Hip Implant Segmentation and Gruen Landmarks Detection.

The assessment of implant status and complications of Total Hip Replacement (THR) relies mainly on the clinical evaluation of the X-ray images to analyse the implant and the surrounding rigid structures. Current clinical practise depends on the manual identification of important landmarks to define the implant boundary and to analyse many features in arthroplasty X-ray images, which is time-consuming and could be prone to human error. Semantic segmentation based on the Convolutional Neural Network (CNN) has demonstrated successful results in many medical segmentation tasks. However, these networks cannot define explicit properties that lead to inaccurate segmentation, especially with the limited size of image datasets. Our work integrates clinical knowledge with CNN to segment the implant and detect important features simultaneously. This is instrumental in the diagnosis of complications of arthroplasty, particularly for loose implant and implant-closed bone fractures, where the location of the fracture in relation to the implant must be accurately determined. In this work, we define the points of interest using Gruen zones that represent the interface of the implant with the surrounding bone to build a Statistical Shape Model (SSM). We propose a multitask CNN that combines regression of pose and shape parameters constructed from the SSM and semantic segmentation of the implant. This integrated approach has improved the estimation of implant shape, from 74% to 80% dice score, making segmentation realistic and allowing automatic detection of Gruen zones. To train and evaluate our method, we generated a dataset of annotated hip arthroplasty X-ray images that will be made available.

Accurate Lung Nodule Segmentation With Detailed Representation Transfer and Soft Mask Supervision.

Accurate lung lesion segmentation from computed tomography (CT) images is crucial to the analysis and diagnosis of lung diseases, such as COVID-19 and lung cancer. However, the smallness and variety of lung nodules and the lack of high-quality labeling make the accurate lung nodule segmentation difficult. To address these issues, we first introduce a novel segmentation mask named "soft mask", which has richer and more accurate edge details description and better visualization, and develop a universal automatic soft mask annotation pipeline to deal with different datasets correspondingly. Then, a novel network with detailed representation transfer and soft mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results. Our DSNet contains a special detailed representation transfer module (DRTM) for reconstructing the detailed representation to alleviate the small size of lung nodules images and an adversarial training framework with soft mask for further improving the accuracy of segmentation. Extensive experiments validate that our DSNet outperforms other state-of-the-art methods for accurate lung nodule segmentation, and has strong generalization ability in other accurate medical segmentation tasks with competitive results. Besides, we provide a new challenging lung nodules segmentation dataset for further studies (https://drive.google.com/file/d/15NNkvDTb_0Ku0IoPsNMHezJR TH1Oi1wm/view?usp=sharing).

UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation.

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks. Our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively. Code, pre-trained models, and use case pipeline are available at: https://github.com/MASILab/UNesT.

GLRP: Global and local contrastive learning based on relative position for medical image segmentation on cardiac MRI

AbstractContrastive learning, as an unsupervised technique, is widely employed in image segmentation to enhance segmentation performance even when working with small labeled datasets. However, generating positive and negative data pairs for medical image segmentation poses a challenge due to the presence of similar tissues and organs across different slices in datasets. To tackle this issue, we propose a novel contrastive learning strategy that leverages the relative position differences between image slices. Additionally, we combine global and local features to address this problem effectively. In order to enhance segmentation accuracy and reduce isolated mis‐segmented regions, we employ a two‐dimensional fully connected conditional random field for iterative optimization of the segmentation results. With only 10 labeled samples, our proposed method is able to achieve average dice scores of 0.876 and 0.899 on the public and private dataset heart segmentation tasks, surpassing the PCL method's 0.801 and 0.852. Experimental results on both public and private MRI datasets demonstrate that our proposed method yields significant improvements in medical segmentation tasks with limited annotated samples, outperforming existing semi‐supervised and self‐supervised techniques.

A global-frequency-domain network for medical image segmentation

The UNet series networks have been a leader in the field of medical image segmentation since their introduction. However, encoder and decoder structures of the traditional UNet series network are complex, with a large number of parameters and floating-point operations. This requires a large amount of data as support for model training, but most medical datasets only contain limited numbers of samples. To address this issue, we propose a global frequency domain UNet (GFUNet), a novel architecture for fast medical image segmentation. Inspired by recent modified Multi-Layer Perceptron(MLP)-like models, we combine Fourier Transform with UNet structure to achieve more efficient and effective encoding and decoding processes. Meanwhile, A dual-domain encoding module is designed to improve the performance of the encoder and decoder by fully used frequency domain feature. Furthermore, due to the excellent property of the Fourier Transform and its optimization, our network greatly reduces the number of parameters compared to other UNets. We evaluate GFUNet on several medical segmentation tasks, achieving improved segmentation performance compared to state-of-the-art network architectures for medical image segmentation. Compared to the original UNet, the results show that we reduce the number of parameters by 46 times, reduce computational complexity by 114 times, and improved the considerable dice score.

DPCTN: Dual path context-aware transformer network for medical image segmentation

Accurate segmentation of lesions in medical images is a key step to assist clinicians in diagnosis and analysis. Most studies combine the Transformer model with CNN at a single scale or use the highest-level feature tensor extracted by CNN as input to Transformer without fully exploiting Transformer’s potential. In addition, for the problems of structural boundary blurring, heterogeneous textures, etc., in medical images, most existing methods pay attention to using contour information to solve this problem but simply fuse the contour information and ignore the potential relationship between the regions and the contours. We propose the DPCTN network based on the traditional encoding–decoding structure, consisting of the CNN, Transformer dual backbone networks and parallel attention mechanisms, to achieve accurate segmentation in medical image lesions. Local and global multiscale feature information is extracted by CNN and Transformer. The Transformer block of channel cross fusion can implement multiscale information fusion of the high-level local features and reduce the impact of the redundant information. The dual backbone feature fusion module effectively couples the local and global high-level feature information. The decoder refines and enriches the boundary and regional features, layer by layer, to achieve effective supervision of the boundary and region. Considering the possible dimension collapse in the attention mechanism, a novel three branch transposed self-attention module is designed to reduce the information loss caused by feature pooling. To verify the effectiveness of our proposed method, subjective and objective comparative experiments and ablation experiments were performed on four medical segmentation tasks, polyps, skin lesions, glands and breast tumors. A large number of experimental results show that our method is superior to the current state-of-the-art method, reduces the standard deviation and is more robust. Source code is released at https://github.com/sd-spf/DPCTN.