ScribSD+: Scribble-supervised medical image segmentation based on simultaneous multi-scale knowledge distillation and class-wise contrastive regularization

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

While deep models have shown promising performance in medical image segmentation, they heavily rely on a large amount of well-annotated data, which is difficult to access, especially in clinical practice. On the other hand, high-accuracy deep models usually come in large model sizes, limiting their employment in real scenarios. In this work, we propose a novel asymmetric co-teacher framework, ACT-Net, to alleviate the burden on both expensive annotations and computational costs for semi-supervised knowledge distillation. We advance teacher-student learning with a co-teacher network to facilitate asymmetric knowledge distillation from large models to small ones by alternating student and teacher roles, obtaining tiny but accurate models for clinical employment. To verify the effectiveness of our ACT-Net, we employ the ACDC dataset for cardiac substructure segmentation in our experiments. Extensive experimental results demonstrate that ACT-Net outperforms other knowledge distillation methods and achieves lossless segmentation performance with 250x fewer parameters.

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

MSKD: Structured knowledge distillation for efficient medical image segmentation

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.

Automatic image segmentation is a critical component of medical image analysis, and hence quantifying segmentation performance is crucial. Challenges in medical image segmentation are mainly due to spatial variations of regions to be segmented and imbalance in distribution of classes. Commonly used metrics treat all detected pixels, indiscriminately. However, pixels in smaller segments must be treated differently from pixels in larger segments, as detection of smaller ones aid in early treatment of associated disease and are also easier to miss. To address this, we propose a novel evaluation metric for segmentation performance, emphasizing smaller segments, by assigning higher weightage to smaller segment pixels. Weighted false positives are also considered in deriving the new metric named, "SSEGEP"(Small SEGment Emphasized Performance evaluation metric), (range : 0(Bad) to 1(Good)). The experiments were performed on diverse anatomies(eye, liver, pancreas and breast) from publicly available datasets to show applicability of the proposed metric across different imaging techniques. Mean opinion score (MOS) and statistical significance testing is used to quantify the relevance of proposed approach. Across 33 fundus images, where the largest exudate is 1.41%, and the smallest is 0.0002% of the image, the proposed metric is 30% closer to MOS, as compared to Dice Similarity Coefficient (DSC). Statistical significance testing resulted in promising p-value of order 10^{-18} with SSEGEP for hepatic tumor compared to DSC. The proposed metric is found to perform better for the images having multiple segments for a single label.

Artificial intelligence algorithms have been used in a wide range of applications in clinical aided diagnosis, such as automatic MR image segmentation and seizure EEG signal analyses. In recent years, many machine learning-based automatic MR brain image segmentation methods have been proposed as auxiliary methods of medical image analysis in clinical treatment. Nevertheless, many problems regarding precise medical images, which cannot be effectively utilized to improve partition performance, remain to be solved. Due to the poor contrast in grayscale images, the ambiguity and complexity of MR images, and individual variability, the performance of classic algorithms in medical image segmentation still needs improvement. In this paper, we introduce a distributed multitask fuzzy c-means (MT-FCM) clustering algorithm for MR brain image segmentation that can extract knowledge common among different clustering tasks. The proposed distributed MT-FCM algorithm can effectively exploit information common among different but related MR brain image segmentation tasks and can avoid the negative effects caused by noisy data that exist in some MR images. Experimental results on clinical MR brain images demonstrate that the distributed MT-FCM method demonstrates more desirable performance than the classic signal task method.

MC-DC: An MLP-CNN Based Dual-path Complementary Network for Medical Image Segmentation

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

Ultrasound imaging can distinctly display the morphology and structure of internal organs within the human body, enabling the examination of organs like the breast, liver, and thyroid. It can identify the locations of tumors, nodules, and other lesions, thereby serving as an efficacious tool for treatment detection and rehabilitation evaluation. Typically, the attending physician is required to manually demarcate the boundaries of lesion locations, such as tumors, in ultrasound images. Nevertheless, several issues exist. The high noise level in ultrasound images, the degradation of image quality due to the impact of surrounding tissues, and the influence of the operator’s experience and proficiency on the determination of lesion locations can all contribute to a reduction in the accuracy of delineating the boundaries of lesion sites. In the wake of the advancement of deep learning, its application in medical image segmentation is becoming increasingly prevalent. For instance, while the U-Net model has demonstrated a favorable performance in medical image segmentation, the convolution layers of the traditional U-Net model are relatively simplistic, leading to suboptimal extraction of global information. Moreover, due to the significant noise present in ultrasound images, the model is prone to interference. In this research, we propose an Attention Residual Network model (ARU-Net). By incorporating residual connections within the encoder section, the learning capacity of the model is enhanced. Additionally, a spatial hybrid convolution module is integrated to augment the model’s ability to extract global information and deepen the vertical architecture of the network. During the feature fusion stage of the skip connections, a channel attention mechanism and a multi-convolutional self-attention mechanism are respectively introduced to suppress noisy points within the fused feature maps, enabling the model to acquire more information regarding the target region. Finally, the predictive efficacy of the model was evaluated using publicly accessible breast ultrasound and thyroid ultrasound data. The ARU-Net achieved mean Intersection over Union (mIoU) values of 82.59% and 84.88%, accuracy values of 97.53% and 96.09%, and F1-score values of 90.06% and 89.7% for breast and thyroid ultrasound, respectively.

IntroductionNarrow Band Imaging (NBI) is an endoscopic visualization technique useful for upper aero-digestive tract (UADT) cancer detection and margins evaluation. However, NBI analysis is strongly operator-dependent and requires high expertise, thus limiting its wider implementation. Recently, artificial intelligence (AI) has demonstrated potential for applications in UADT videoendoscopy. Among AI methods, deep learning algorithms, and especially convolutional neural networks (CNNs), are particularly suitable for delineating cancers on videoendoscopy. This study is aimed to develop a CNN for automatic semantic segmentation of UADT cancer on endoscopic images.Materials and MethodsA dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma (LSCC) was collected and manually annotated. A novel DL segmentation model (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified using Xception as a backbone and incorporating ensemble features from other CNNs. The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, and DeepLabv3). SegMENT was then validated on two external datasets of NBI images of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously published study. The impact of in-domain transfer learning through an ensemble technique was evaluated on the external datasets.Results219 LSCC patients were retrospectively included in the study. A total of 683 videoframes composed the LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL models, obtaining the following median values: 0.68 intersection over union (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 accuracy. For the OCSCC and OPSCC datasets, results were superior compared to previously published data: the median performance metrics were, respectively, improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% and 14.7%, accuracy=4.1% and 10.3%.ConclusionSegMENT achieved promising performances, showing that automatic tumor segmentation in endoscopic images is feasible even within the highly heterogeneous and complex UADT environment. SegMENT outperformed the previously published results on the external validation cohorts. The model demonstrated potential for improved detection of early tumors, more precise biopsies, and better selection of resection margins.

Advances in deep learning models have significantly improved performance in medical tasks, but their complex structures and high computational requirements pose challenges for clinical implementation. Additionally, data privacy concerns limit the availability of comprehensive datasets needed to train accurate models. To address these issues, we propose a novel adaptive knowledge distillation (KD) framework for medical imaging segmentation that integrates intermediate and high-level feature pairwise relationships between teacher and student models. Our framework features adaptive multi-teacher distillation, where multiple teacher models, each trained on limited data from different sites and hospitals with various scanning protocols, distill their knowledge to a student model using adaptive weighting. This method allows each teacher to convey deep feature representations to the student’s intermediate layers, enhancing performance without increasing complexity. To validate the efficacy of our framework, we conducted extensive experiments on two publicly available medical datasets, focusing on prostate and spleen tumor segmentation tasks. Our adaptive KD approach significantly improved dice scores by up to 9%, surpassing all tested baseline models. These results highlight the potential of our KD framework to enhance medical imaging segmentation while ensuring data privacy and security. • Implement both single and multi-teacher distillation scenarios. • Apply adaptive multi-teacher distillation using limited data. • Distill intermediate and high-level features. • Conduct CT and MRI medical imaging segmentation experiments using public datasets.

Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry. In recent years, convolutional encoder-decoder solutions have achieved substantial progress in the field of automatic medical image segmentation. Due to the inherent bias in the convolution operations, prior models mainly focus on local visual cues formed by the neighboring pixels, but fail to fully model the long-range contextual dependencies. In this article, we propose a novel Transformer-based Attention Guided Network called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TransAttUnet</i> , in which the multi-level guided attention and multi-scale skip connection are designed to jointly enhance the performance of the semantical segmentation architecture. Inspired by Transformer, the self-aware attention (SAA) module with Transformer Self Attention (TSA) and Global Spatial Attention (GSA) is incorporated into TransAttUnet to effectively learn the non-local interactions among encoder features. Moreover, we also use additional multi-scale skip connections between decoder blocks to aggregate the upsampled features with different semantic scales. In this way, the representation ability of multi-scale context information is strengthened to generate discriminative features. Benefitting from these complementary components, the proposed TransAttUnet can effectively alleviate the loss of fine details caused by the stacking of convolution layers and the consecutive sampling operations, finally improving the segmentation quality of medical images. Extensive experiments were conducted on multiple medical image segmentation datasets from various imaging modalities, which demonstrate that the proposed method consistently outperforms the existing state-of-the-art methods.

Medical image segmentation and registration are two tasks to analyze the anatomical structures in clinical research. Still, deep-learning solutions utilizing the connections between segmentation and registration remain underdiscovered. This article designs a joint learning framework named RSegNet that can realize concurrent deformable registration and segmentation by minimizing an integrated loss function, including three parts: diffeomorphic registration loss, segmentation similarity loss, and dual-consistency supervision loss. The probabilistic diffeomorphic registration branch could benefit from the auxiliary segmentations available from the segmentation branch to achieve anatomical consistency and better deformation regularity by dual-consistency supervision. Simultaneously, the segmentation performance could also be improved by data augmentation based on the registration with well-behaved diffeomorphic guarantees. Experiments on the human brain 3-D magnetic resonance images have been implemented to demonstrate the effectiveness of our approach. We trained and validated RSegNet with 1000 images and tested its performances on four public datasets, which shows that our method successfully yields concurrent improvements of both segmentation and registration compared with separately trained networks. Specifically, our method can increase the accuracy of segmentation and registration by 7.0% and 1.4%, respectively, in terms of Dice scores. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Registration and segmentation of medical images are two significant tasks in medical research and clinical application. However, most existing approaches consider these two tasks independently while neglecting the potential association between them. Therefore, we suggest a new approach that combines these two tasks into one joint deep learning framework, boosting registration, and segmentation performance by introducing dual-consistency supervision. Besides, our framework could generate outputs within 1 s by taking an affinely aligned medical image pair as input, which is suitable for time-critical requirements in a clinic. We tested it on four public datasets and achieved state-of-the-art performance to demonstrate the proposed method’s feasibility and robustness. Furthermore, our proposed RSegNet is a general learning framework suitable for various image modalities and anatomical structures. Hence, we expect our framework to serve as a practical clinical tool to speed up medical image analysis procedures and improve diagnostic accuracy.

Deep Learning based classification and segmentation of medical imaging data, with special attention to the COVID-19 virus, is a desperately required application. The lives of millions of individuals are being impacted by this pandemic issue. The most frequent result that involves expert evaluation in COVID-19 computed tomography (CT) images of the lungs is ground glass turbidity. In light of this circumstance, some researchers suggest the appropriate deep learning models that, in the absence of trained diagnostic professionals in health centers, can serve as an alternative. Thus, the patient's CT images are categorize into three groups using the algorithm: COVID-19, CAP (Community Acquired Pneumonia), Normal, all with an assured high level of accuracy. The next step involves the use of two datasets for segmentation and classification. Using an image enhancement technique known as CLAHE (Contrast Limited Adaptive Histogram Equalization), noise and intensity uniformity were removed in this project. Normalization of the data and annotation reduce the constraint of a small dataset and expand the dataset size. ResNet50, VGG16 and Densenet169 architectures are used for transfer learning and yield the accuracy during classification are 95.94 %, 94.79 % and 97.00% respectively .Semantic segmentation and Instance Segmentation of medical images has been done where we got Dice value of 0.7348.