LLRHNet: Multiple Lesions Segmentation Using Local-Long Range Features.

Accurate and reliable detection of white matter hyperintensities and their volume quantification can provide valuable clinical information to assess neurologic disease progression. In this work, a stacked generalization ensemble of orthogonal 3D convolutional neural networks, StackGen-Net, is explored for improving automated detection of white matter hyperintensities in 3D T2-FLAIR images. Individual convolutional neural networks in StackGen-Net were trained on 2.5D patches from orthogonal reformatting of 3D-FLAIR (n = 21) to yield white matter hyperintensity posteriors. A meta convolutional neural network was trained to learn the functional mapping from orthogonal white matter hyperintensity posteriors to the final white matter hyperintensity prediction. The impact of training data and architecture choices on white matter hyperintensity segmentation performance was systematically evaluated on a test cohort (n = 9). The segmentation performance of StackGen-Net was compared with state-of-the-art convolutional neural network techniques on an independent test cohort from the Alzheimer's Disease Neuroimaging Initiative-3 (n = 20). StackGen-Net outperformed individual convolutional neural networks in the ensemble and their combination using averaging or majority voting. In a comparison with state-of-the-art white matter hyperintensity segmentation techniques, StackGen-Net achieved a significantly higher Dice score (0.76 [SD, 0.08], F1-lesion (0.74 [SD, 0.13]), and area under precision-recall curve (0.84 [SD, 0.09]), and the lowest absolute volume difference (13.3% [SD, 9.1%]). StackGen-Net performance in Dice scores (median = 0.74) did not significantly differ (P = .22) from interobserver (median = 0.73) variability between 2 experienced neuroradiologists. We found no significant difference (P = .15) in white matter hyperintensity lesion volumes from StackGen-Net predictions and ground truth annotations. A stacked generalization of convolutional neural networks, utilizing multiplanar lesion information using 2.5D spatial context, greatly improved the segmentation performance of StackGen-Net compared with traditional ensemble techniques and some state-of-the-art deep learning models for 3D-FLAIR.

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.

We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered ”normal”. Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions’ segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.

Medical image segmentation is an essential process in disease analysis and diagnosis, in which medical images are divided into specific areas of anatomic or pathological structures. However, this process has challenges, such as the quality, variability, and complexity of medical images. Thus, we propose a medical image segmentation method using the Convolutional Neural Network (CNN) and the Histogram Equalization (HE) image preprocessing. We evaluated medical image segmentation using 2 secondary datasets, namely Lung CT-Scan and Chest X-Rays, with 267 and 3616 images, respectively. The HE method uses an averaging of the optimal cumulative distribution function (CDF) values with a range of 0 to 39. The experimental results show that adding the HE method can increase the accuracy of CNN on the Lung CT-Scan and Chest X-rays data sets, respectively, by 0.73 percentage points from 91.28% to 92.08 % and 1.23 percentage points from 95.56% to 96.85% for the training process. The results of the testing process (validation) have an increase in accuracy of 2.82 percentage points from 89.77% to 92.59% and 0.91 percentage points from 96.06% to 96.97%. Implementing the HE method increases accuracy in CNN medical image segmentation based on the value of dice similarity coefficient (DSC) and structural similarity index measurement (SSIM) close to 0.95.

Medical image segmentation is crucial for improving healthcare outcomes. Convolutional neural networks (CNNs) have been widely applied in medical image analysis; however, their inherent inductive biases limit their ability to capture global contextual information. Vision transformer (ViT) architectures address this limitation by leveraging attention mechanisms to model global relationships; however, they typically require large-scale datasets for effective training, which is challenging in the field of medical imaging due to limited data availability. This study aimed to integrate the advantages of CNN and ViT architectures to improve segmentation performance on small-scale medical image datasets. In this study, we established a U-shaped network architecture based on a Transformer-assisted convolutional neural network (TAC-UNet). The TAC-UNet is primarily composed of a hybrid structure integrating CNN and Transformer components. Specifically, the hybrid architecture follows a dual-path design in which the Transformer branch continuously conveys global contextual information to the CNN backbone. This allows the CNN backbone to enhance its global perception while building on the local features it extracts, thereby improving its ability to comprehend complex image structures. A channel cross-attention (CCA) module is also incorporated as a bridge between the encoder and decoder to better reconcile the semantic discrepancies between them. Detailed experiments on three public datasets were conducted. Specifically, our model was trained on 30 images from the Multi-organ Nucleus Segmentation (MoNuSeg) training dataset, 85 images from the Gland Segmentation (GlaS) training dataset, and 551 images from the Computer Vision Center Colorectal Cancer-Clinic Database (CVC-ClinicDB) dataset. We evaluated the performance of our model on the corresponding test sets. Our TAC-UNet achieved the best Dice scores (80.36%, 90.70%, and 91.81% on the MoNuSeg, GlaS, and CVC-ClinicDB datasets, respectively) of all the models. Compared to other CNN-based, Transformer-based, and hybrid methods, the TAC-UNet demonstrated significantly superior segmentation performance. Our TAC-UNet model showed advanced segmentation performance on small-scale medical image datasets. The detailed experimental results showed the effectiveness of the method. Our model's code is available at: https://github.com/hejlhello/TAC-UNet.

MP-FocalUNet: Multiscale parallel focal self-attention U-Net for medical image segmentation.

Brain white matter hyperintensities (WMHs) are linked to increased risk of cerebrovascular and neurodegenerative diseases among the elderly. Consequently, detection and characterization of WMHs are of significant clinical importance. We propose a novel approach for WMH segmentation from multi-contrast MRI where both voxel-based and lesion-based information are used to improve overall performance in both volume-oriented and object-oriented metrics. Our segmentation method (AMOS-2D) consists of four stages following a "generate-and-test" approach: pre-processing, Gaussian white matter (WM) modelling, hierarchical multi-threshold WMH segmentation and object-based WMH filtering using support vector machines. Data from 28 subjects was used in this study covering a wide range of lesion loads. Volumetric T1-weighted images and 2D fluid attenuated inversion recovery (FLAIR) images were used as basis for the WM model and lesion masks defined manually in each subject by experts were used for training and evaluating the proposed method. The method obtained an average agreement (in terms of the Dice similarity coefficient, DSC) with experts equivalent to inter-expert agreement both in terms of WMH number (DSC=0.637 vs. 0.651) and volume (DSC=0.743 vs. 0.781). It allowed higher accuracy in detecting WMH compared to alternative methods tested and was further found to be insensitive to WMH lesion burden. Good agreement with expert annotations combined with stable performance largely independent of lesion burden suggests that AMOS-2D will be a valuable tool for fully automated WMH segmentation in patients with cerebrovascular and neurodegenerative pathologies.

Estimating white matter hyperintensities volume in individuals with stroke using T1-weighted images

Convolutional Neural Networks (CNNs) have achieved remarkable segmentation accuracy in medical image segmentation tasks. However, the Vision Transformer (ViT) model, with its capability of extracting global information, offers a significant advantage in contextual information compared to the limited receptive field of convolutional kernels in CNNs. Despite this, ViT models struggle to fully detect and extract high-frequency signals, such as textures and boundaries, in medical images. These high-frequency features are essential in medical imaging, as targets like tumors and pathological organs exhibit significant differences in texture and boundaries across different stages. Additionally, the high resolution of medical images leads to computational complexity in the self-attention mechanism of ViTs. To address these limitations, we propose a medical image segmentation network framework based on frequency domain decomposition using a Laplacian pyramid. This approach selectively computes attention features for high-frequency signals in the original image to enhance spatial structural information effectively. During attention feature computation, we introduce Singular Value Decomposition (SVD) to extract an effective representation matrix from the original image, which is then applied in the attention computation process for linear projection. This method reduces computational complexity while preserving essential features. We demonstrated the segmentation validity and superiority of our model on the Abdominal Multi-Organ Segmentation dataset and the Dermatological Disease dataset, and on the Synapse dataset our model achieved a score of 82.68 on the Dice metrics and 17.23 mm on the HD metrics. Experimental results indicate that our model consistently exhibits segmentation effectiveness and improved accuracy across various datasets.

Objectives: To evaluate white matter hyperintensities (WMH) quantification reproducibility from multiple aspects of view and examine the effects of scan–rescan procedure, types of scanner, imaging protocols, scanner software upgrade, and automatic segmentation tools on WMH quantification results using magnetic resonance imaging (MRI).Methods: Six post-stroke subjects (4 males; mean age = 62.8, range = 58–72 years) were scanned and rescanned with both 3D T1-weighted, 2D and 3D T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) MRI across four different MRI scanners within 12 h. Two automated WMH segmentation and quantification tools were used to measure WMH volume based on each MR scan. Robustness was assessed using the coefficient of variation (CV), Dice similarity coefficient (DSC), and intra-class correlation (ICC).Results: Experimental results show that the best reproducibility was achieved by using 3D T2-FLAIR MRI under intra-scanner setting with CV ranging from 2.69 to 2.97%, while the largest variability resulted from comparing WMH volumes measured based on 2D T2-FLAIR MRI with those of 3D T2-FLAIR MRI, with CV values in the range of 15.62%–29.33%. The WMH quantification variability based on 2D MRIs is larger than 3D MRIs due to their large slice thickness. The DSC of WMH segmentation labels between intra-scanner MRIs ranges from 0.63 to 0.77, while that for inter-scanner MRIs is in the range of 0.63–0.65. In addition to image acquisition, the choice of automatic WMH segmentation tool also has a large impact on WMH quantification.Conclusion: WMH reproducibility is one of the primary issues to be considered in multicenter and longitudinal studies. The study provides solid guidance in assisting multicenter and longitudinal study design to achieve meaningful results with enough power.

Interactive segmentation methods utilize user-provided positive and negative clicks to guide the model in accurately segmenting target objects. Compared to fully automatic medical image segmentation, these methods can achieve higher segmentation accuracy with limited image data, demonstrating significant potential in clinical applications. Typically, for each new click provided by the user, conventional interactive segmentation methods reprocess the entire network by re-inputting the click into the segmentation model, which greatly increases the user’s interaction burden and deviates from the intended goal of interactive segmentation tasks. To address this issue, we propose an efficient segmentation network, ESM-Net, for interactive medical image segmentation. It obtains high-quality segmentation masks based on the user’s initial clicks, reducing the complexity of subsequent refinement steps. Recent studies have demonstrated the strong performance of the Mamba model in various vision tasks; however, its application in interactive segmentation remains unexplored. In our study, we incorporate the Mamba module into our framework for the first time and enhance its spatial representation capabilities by developing a Spatial Augmented Convolution (SAC) module. These components are combined as the fundamental building blocks of our network. Furthermore, we designed a novel and efficient segmentation head to fuse multi-scale features extracted from the encoder, optimizing the generation of the predicted segmentation masks. Through comprehensive experiments, our method achieved state-of-the-art performance on three medical image datasets. Specifically, we achieved 1.43 NoC@90 on the Kvasir-SEG dataset, 1.57 NoC@90 on the CVC-ClinicDB polyp segmentation dataset, and 1.03 NoC@90 on the ADAM retinal disk segmentation dataset. The assessments on these three medical image datasets highlight the effectiveness of our approach in interactive medical image segmentation.

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

White matter hyperintensities (WMHs) are regions of abnormally high intensity on T2-weighted or fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI). Accurate and reproducible automatic segmentation of WMHs is important since WMHs are often seen in the elderly and are associated with various geriatric and psychiatric disorders. We developed a fully automated monospectral segmentation method for WMHs using FLAIR MRIs. Through this method, we introduce an optimal threshold intensity (I O ) for segmenting WMHs, which varies with WMHs volume (V WMH), and we establish the I O -V WMH relationship. Our method showed accurate validations in volumetric and spatial agreements of automatically segmented WMHs compared with manually segmented WMHs for 32 confirmatory images. Bland-Altman values of volumetric agreement were 0.96 ± 8.311ml (bias and 95% confidence interval), and the similarity index of spatial agreement was 0.762 ± 0.127 (mean ± standard deviation). Furthermore, similar validation accuracies were obtained in the images acquired from different scanners. The proposed segmentation method uses only FLAIR MRIs, has the potential to be accurate with images obtained from different scanners, and can be implemented with a fully automated procedure. In our study, validation results were obtained with FLAIR MRIs from only two scanner types. The design of the method may allow its use in large multicenter studies with correct efficiency.

MultiTrans: Multi-branch transformer network for medical image segmentation

Semisupervised strategy has been utilized to alleviate issues from segmentation applications due to challenges in collecting abundant annotated segmentation masks, which is an essential prerequisite for training high-performance 3D convolutional neural networks (CNNs) . Existing semisupervised segmentation methods are mainly concerned with how to generate the pseudo labels with regularization but not evaluate the quality of the pseudo labels explicitly. To alleviate this problem, we offer a simple yet effective reciprocal learning strategy for semisupervised volumetric medical image segmentation, which generates more reliable pseudo labels for the unannotateddata. Our proposed reciprocal learning is achieved through a pair of networks, one as a teacher network and the other as a student network. The student network learns from pseudo labels generated by the teacher network. In addition, the teacher network autonomously optimizes its parameters based on the reciprocal feedback signals from the student's performance on the annotated images. The efficacy of the proposed method is evaluated on three medical image data sets, including 82 pancreas computed tomography (CT) scans (training/testing: 62/20), 100 left atrium gadolinium-enhanced magnetic resonance (MR) scans (training/testing: 80/20), and 200 breast cancer MR scans (training/testing: 68/132). The comparison methods include mean teacher (MT) model, uncertainty-aware MT (UA-MT) model, shape-aware adversarial network (SASSNet), and transformation-consistent self-ensembling model (TCSM). The evaluation metrics are Dice similarity coefficient (Dice), Jaccard index (Jaccard), 95% Hausdorff distance (95HD), and average surface distance (ASD). The Wilcoxon signed-rank test is used to conduct the statisticalanalyses. By utilizing 20% labeled data and 80% unlabeled data for training, our proposed method achieves an average Dice of 84.77%/90.46%/78.53%, Jaccard of 73.71%/82.67%/69.00%, ASD of 1.58/1.90/0.57, and 95HD of 6.24/5.97/4.34 on pancreas/left atrium/breast data sets, respectively. These results outperform several cutting-edge semisupervised approaches, showing the feasibility of our method for the challenging semisupervised segmentationapplications. The proposed reciprocal learning strategy is a general semisupervised solution and has the potential to be applied for other 3D segmentationtasks.