Medical Image Segmentation using Squeeze-and-Expansion Transformers

Three-dimensional (3D) medical image segmentation is used to segment the target (a lesion or an organ) in 3D medical images. Through this process, 3D target information is obtained; hence, this technology is an important auxiliary tool for medical diagnosis. Although some methods have proved to be successful for two-dimensional (2D) image segmentation, their direct use in the 3D case has been unsatisfactory. To obtain more precise tumor segmentation results from 3D MR images, in this paper, we propose a method known as the 3D shape-weighted level set method (3D-SLSM). The proposed method first converts the LSM, which is superior with respect to 2D image segmentation, into a 3D algorithm that is suitable for overall calculations in 3D image models, and which improves the efficiency and accuracy of calculations. A 3D shape-weighted value is then added for each 3D-SLSM iterative process according to the changes in volume. Besides increasing the convergence rate and eliminating background noise, this shape-weighted value also brings the segmented contour closer to the actual tumor margins. To perform a quantitative analysis of 3D-SLSM and to examine its feasibility in clinical applications, we have divided our experiments into computer-simulated sequence images and actual breast MRI cases. Subsequently, we simultaneously compared various existing 3D segmentation methods. The experimental results demonstrated that 3D-SLSM exhibited precise segmentation results for both types of experimental images. In addition, 3D-SLSM showed better results for quantitative data compared with existing 3D segmentation methods.

We systematically evaluate a Deep Learning model in a 3D medical image segmentation task. With our model, we address the flaws of manual segmentation: high inter-rater contouring variability and time consumption of the contouring process. The main extension over the existing evaluations is the careful and detailed analysis that could be further generalized on other medical image segmentation tasks. Firstly, we analyze the changes in the inter-rater detection agreement. We show that the model reduces the number of detection disagreements by [Formula: see text] [Formula: see text]. Secondly, we show that the model improves the inter-rater contouring agreement from [Formula: see text] to [Formula: see text] surface Dice Score [Formula: see text]. Thirdly, we show that the model accelerates the delineation process between [Formula: see text] and [Formula: see text] times [Formula: see text]. Finally, we design the setup of the clinical experiment to either exclude or estimate the evaluation biases; thus, preserving the significance of the results. Besides the clinical evaluation, we also share intuitions and practical ideas for building an efficient DL-based model for 3D medical image segmentation.

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.

BackgroundMagnetic Resonance Imaging (MRI) is a cornerstone in diagnosing brain tumors. However, the complex nature of these tumors makes accurate segmentation in MRI images a demanding task.ObjectiveAccurate brain tumor segmentation remains a critical challenge in medical image analysis, with early detection crucial for improving patient outcomes.MethodsTo develop and evaluate a novel UNet-based architecture for improved brain tumor segmentation in MRI images. This paper presents a novel UNet-based architecture for improved brain tumor segmentation. The UNet model architecture incorporates Leaky ReLU activation, batch normalization, and regularization to enhance training and performance. The model consists of varying numbers of layers and kernel sizes to capture different levels of detail. To address the issue of class imbalance in medical image segmentation, we employ focused loss and generalized Dice (GDL) loss functions.ResultsThe proposed model was evaluated on the BraTS'2020 dataset, achieving an accuracy of 99.64% and Dice coefficients of 0.8984, 0.8431, and 0.8824 for necrotic core, edema, and enhancing tumor regions, respectively.ConclusionThese findings demonstrate the efficacy of our approach in accurately predicting tumors, which has the potential to enhance diagnostic systems and improve patient outcomes.

MA-SAM: Modality-agnostic SAM adaptation for 3D medical image segmentation

Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed for performance enhancement. However, the large size of 3D volume images poses a great computational challenge to traditional attention methods. In this paper, we propose a folded attention (FA) approach to improve the computational efficiency of traditional attention methods on 3D medical images. The main idea is that we apply tensor folding and unfolding operations to construct four small sub-affinity matrices to approximate the original affinity matrix. Through four consecutive sub-attention modules of FA, each element in the feature tensor can aggregate spatial-channel information from all other elements. Compared to traditional attention methods, with the moderate improvement of accuracy, FA can substantially reduce the computational complexity and GPU memory consumption. We demonstrate the superiority of our method on two challenging tasks for 3D MIR and MIS, which are quantitative susceptibility mapping and multiple sclerosis lesion segmentation.

Objective. Over the past years, convolutional neural networks based methods have dominated the field of medical image segmentation. But the main drawback of these methods is that they have difficulty representing long-range dependencies. Recently, the Transformer has demonstrated super performance in computer vision and has also been successfully applied to medical image segmentation because of the self-attention mechanism and long-range dependencies encoding on images. To the best of our knowledge, only a few works focus on cross-modalities of image segmentation using the Transformer. Hence, the main objective of this study was to design, propose and validate a deep learning method to extend the application of Transformer to multi-modality medical image segmentation. Approach. This paper proposes a novel automated multi-modal Transformer network termed AMTNet for 3D medical image segmentation. Especially, the network is a well-modeled U-shaped network architecture where many effective and significant changes have been made in the feature encoding, fusion, and decoding parts. The encoding part comprises 3D embedding, 3D multi-modal Transformer, and 3D Co-learn down-sampling blocks. Symmetrically, the 3D Transformer block, upsampling block, and 3D-expanding blocks are included in the decoding part. In addition, a Transformer-based adaptive channel interleaved Transformer feature fusion module is designed to fully fuse features of different modalities. Main results. We provide a comprehensive experimental analysis of the Prostate and BraTS2021 datasets. The results show that our method achieves an average DSC of 0.907 and 0.851 (0.734 for ET, 0.895 for TC, and 0.924 for WT) on these two datasets, respectively. These values show that AMTNet yielded significant improvements over the state-of-the-art segmentation networks. Significance. The proposed 3D segmentation network exploits complementary features of different modalities during the feature extraction process at multiple scales to increase the 3D feature representations and improve the segmentation efficiency. This powerful network enriches the research of the Transformer to multi-modal medical image segmentation.

TANet: Triple Attention Network for medical image segmentation

Medical image segmentation of tissue abnormalities, key organs, or blood vascular system is of great significance for any computerized diagnostic system. However, automatic segmentation in medical image analysis is a challenging task since it requires sophisticated knowledge of the target organ anatomy. This paper develops an end-to-end deep learning segmentation method called Contextual Multi-Scale Multi-Level Network (CMM-Net). The main idea is to fuse the global contextual features of multiple spatial scales at every contracting convolutional network level in the U-Net. Also, we re-exploit the dilated convolution module that enables an expansion of the receptive field with different rates depending on the size of feature maps throughout the networks. In addition, an augmented testing scheme referred to as Inversion Recovery (IR) which uses logical “OR” and “AND” operators is developed. The proposed segmentation network is evaluated on three medical imaging datasets, namely ISIC 2017 for skin lesions segmentation from dermoscopy images, DRIVE for retinal blood vessels segmentation from fundus images, and BraTS 2018 for brain gliomas segmentation from MR scans. The experimental results showed superior state-of-the-art performance with overall dice similarity coefficients of 85.78%, 80.27%, and 88.96% on the segmentation of skin lesions, retinal blood vessels, and brain tumors, respectively. The proposed CMM-Net is inherently general and could be efficiently applied as a robust tool for various medical image segmentations.

Segmentation of medical images has been the most demanding and growing area currently for analysis of medical images. Segmentation of polyp images is a huge challenge because of the variability of color depth and morphology in polyps throughout colonoscopy imaging. For segmentation, in this work, we have used a dataset of images of the gastrointestinal polyp. The algorithms used in this paper for segmentation of gastrointestinal polyp images depend on profound deep convolutional neural network architectures: FCN, Dual U-net with Resnet Encoder, U-net, and Unet_Resnet. To improve the performance, data augmentation is performed on the dataset. The efficiency of the algorithms is measured by using metrics such as Dice Similarity Coefficient (DSC) and Intersection Over Union (IOU). The algorithm Dual U-net with Resnet Encoder obtains a higher DSC of 0.87 and IOU of 0.80 and beats the other algorithms U-net, FCN, and Unet_Resnet in segmentation of gastrointestinal polyp images.

The fully convolutional networks (FCNs) have been widely applied in numerous medical image segmentation tasks. However, tissue regions usually have large variations of shape and scale, so the ability of neural networks to learn multi-scale features is important to the segmentation performance. In this paper, we improve the network for multi-scale feature fusion, in the medical image segmentation by introducing two feature fusion modules: i) global attention multi-scale feature fusion module (GMF); ii) local dense multi-scale feature fusion module (LMF). GMF aims to use global context information to guide the recalibration of low-level features from both spatial and channel aspects, so as to enhance the utilization of effective multi-scale features and suppress the noise of low-level features. LMF adopts bottom-up top-down structure to capture context information, to generate semantic features, and to fuse feature information at different scales. LMF can integrate local dense multi-scale context features layer by layer in the network, thus improving the ability of network to encode interdependent relationships among boundary pixels. Based on the above two modules, we propose a novel medical image segmentation framework (GLF-Net). We evaluated the proposed network and modules on challenging brain tumor segmentation and pancreas segmentation datasets, and very competitive performance has been achieved.

Contrastive learning, a successful form of representational learning, has shown promising results in pretraining deep learning (DL) models for downstream tasks. When working with limited annotation data, as in medical image segmentation tasks, learning domain-specific local representations can further improve the performance of DL models. In this work, we extend the contrastive learning framework to utilize domain-specific contrast information from unlabeled Magnetic Resonance (MR) images to improve the performance of downstream MR image segmentation tasks in the presence of limited labeled data. The contrast in MR images is controlled by underlying tissue properties (e.g., T1 or T2) and image acquisition parameters. We hypothesize that learning to discriminate local representations based on underlying tissue properties should improve subsequent segmentation tasks on MR images. We propose a novel constrained contrastive learning (CCL) strategy that uses tissue-specific information via a constraint map to define positive and negative local neighborhoods for contrastive learning, embedding this information in the representational space during pretraining. For a given MR contrast image, the proposed strategy uses local signal characteristics (constraint map) across a set of related multi-contrast MR images as a surrogate for underlying tissue information. We demonstrate the utility of the approach for downstream: (1) multi-organ segmentation tasks in T2-weighted images where a DL model learns T2 information with constraint maps from a set of 2D multi-echo T2-weighted images (n=101) and (2) tumor segmentation tasks in multi-parametric images from the public brain tumor segmentation (BraTS) (n=80) dataset where DL models learn T1 and T2 information from multi-parametric BraTS images. Performance is evaluated on downstream multi-label segmentation tasks with limited data in (1) T2-weighted images of the abdomen from an in-house Radial-T2 (Train/Test=30/20), (2) public Cartesian-T2 (Train/Test=6/12) dataset, and (3) multi-parametric MR images from the public brain tumor segmentation dataset (BraTS) (Train/Test=40/50). The performance of the proposed CCL strategy is compared to state-of-the-art self-supervised contrastive learning techniques. In each task, a model is also trained using all available labeled data for supervised baseline performance. The proposed CCL strategy consistently yielded improved Dice scores, Precision, and Recall metrics, and reduced HD95 values across all segmentation tasks. We also observed performance comparable to the baseline with reduced annotation effort. The t-SNE visualization of features for T2-weighted images demonstrates its ability to embed T2 information in the representational space. On the BraTS dataset, we also observed that using an appropriate multi-contrast space to learn T1+T2, T1, or T2 information during pretraining further improved the performance of tumor segmentation tasks. Learning to embed tissue-specific information that controls MR image contrast with the proposed constrained contrastive learning improved the performance of DL models on subsequent segmentation tasks compared to conventional self-supervised contrastive learning techniques. The use of such domain-specific local representations could help understand, improve performance, and mitigate the scarcity of labeled data in MR image segmentation tasks.

Many current and state-of-the-art deep learning models for accurate image segmentation are based on the U-Net architecture, a convolutional neural network designed for biomedical applications. Despite its widespread adoption in the medical imaging community, U-Net has two major limitations. First, due to its deep structure and the large number of filters used, the number of parameters and Floating-Point Operations Per Second (FLOPS) are high. This results in high computational complexity and demands a large memory size, making real-time implementation and deployment of U-Net models challenging. Second, the base U-Net model only uses a single type of kernel (i.e., 3×3) throughout the network for all convolution operations. Feature extraction using a single spatial extent throughout the network is suitable if the size, location, and shape of the salient regions remain static in all the images of a dataset, which is not necessarily the case in medical imaging. To address these two limitations, we propose an Efficient Multi-Encoder-Decoder based UNet (EMED-UNet), a novel architecture for efficient medical image segmentation. We evaluated our network on four medical imaging datasets: Montgomery County, Shenzhen CXR, COVID-19 CT LS, and BraTS (Brain Tumor Segmentation) dataset. EMED-UNet outperforms the U-Net and its variants in terms of accuracy, with around 77% reduction in parameters, a 60% reduction in FLOPS, and a 79.2% reduction in memory usage (all as compared to U-Net). The results demonstrate that EMED-UNet is a lightweight and accurate model for image segmentation that substantially improves upon the U-Net base model and is more feasible to deploy, given its decreased computational cost.

Polyp segmentation with distraction separation

Lesion detection or segmentation on 3D medical image (e.g., MRI, CT-PET or hybrid modal) is a challenging task which aims to automatically mark the abnormal region on given input image. The methods to tackle the problem often construct a U-shape autoencoders to map the input to a compressed vector in latent space and predict the final probability map. However, approaches for 3D multimodal image segmentation are still not fully explored and localization accuracy can be improved by designing proper structure based on prior. In this paper, we propose a supervised contrastive approach for 3D multi-modality medical image segmentation. A hybrid 3D-2D multi-modality fusion model is designed based on the input image prior. The 3D segmentation problem is converted to a sequence prediction task by 2D decoder with contrastive modeling. The combined framework (HDC, Hybrid Dimension Contrastive) achieves comparable or even greater performance to 3D counterpart while memory efficient. We conduct extensive experiments on two multimodal datasets of brain image BraTS and our epilepsy MRI-PET. The validation results show the effectiveness of our framework.