Average Dice Coefficient Research Articles

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

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

Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography

Achieving precise pedicle screw placement in posterior lumbar interbody fusion (PLIF) is essential but difficult due to the intricacies of manual preoperative planning with CT scans. We analyzed CT data from 316 PLIF patients, using Mimics software for manual planning by two surgeons. A deep learning model was trained on 228 patients and validated on 88 patients, assessing planning efficiency and accuracy. Automatic planning successfully segmented and placed screws in all 316 cases, significantly outperforming manual planning in speed. The Dice coefficient for segmentation accuracy was 0.95. The difference in mean pedicle transverse angle (PTA) and pedicle sagittal angle (PSA) for automatic planning screws compared to manual planning screws was 1.63 ± 0.83° and 1.39 ± 1.03°, respectively, and these differences were either statistically comparable or not significantly different compared to the variability of manual planning screws. The average Dice coefficient of implanted screws was 0.63 ± 0.08, and the consistency between automatic screws and manual reference screws was higher than that of internal screws (Dice 0.62 ± 0.09). Compared with manual screws, automatic screws were shorter (46.58 ± 3.09 mm) and thinner (6.24 ± 0.35 mm), and the difference was statistically significant. In qualitative validation, 97.7% of the automatic planning screws were rated Gertzbein–Robbins (GR) Class A and 97.3% of the automatic planning screws were rated Badu Class 0. Deep learning software automates lumbosacral pedicle screw planning, enhancing surgical efficiency and accuracy.

Research and implementation of intelligent diagnostic system for temporomandibular joint disorder

Temporomandibular joint disorder (TMD) is a common oral and maxillofacial disease, which is difficult to detect due to its subtle early symptoms. In this study, a TMD intelligent diagnostic system implemented on edge computing devices was proposed, which can achieve rapid detection of TMD in clinical diagnosis and facilitate its early-stage clinical intervention. The proposed system first automatically segments the important components of the temporomandibular joint, followed by quantitative measurement of the joint gap area, and finally predicts the existence of TMD according to the measurements. In terms of segmentation, this study employs semi-supervised learning to achieve the accurate segmentation of temporomandibular joint, with an average Dice coefficient (DC) of 0.846. A 3D region extraction algorithm for the temporomandibular joint gap area is also developed, based on which an automatic TMD diagnosis model is proposed, with an accuracy of 83.87%. In summary, the intelligent TMD diagnosis system developed in this paper can be deployed at edge computing devices within a local area network, which is able to achieve rapid detecting and intelligent diagnosis of TMD with privacy guarantee.

Towards a general computed tomography image segmentation model for anatomical structures and lesions

Numerous deep-learning models have been developed using task-specific data, but they ignore the inherent connections among different tasks. By jointly learning a wide range of segmentation tasks, we prove that a general medical image segmentation model can improve segmentation performance for computerized tomography (CT) volumes. The proposed general CT image segmentation (gCIS) model utilizes a common transformer-based encoder for all tasks and incorporates automatic pathway modules for task prompt-based decoding. It is trained on one of the largest datasets, comprising 36,419 CT scans and 83 tasks. gCIS can automatically perform various segmentation tasks using automatic pathway modules of decoding networks through text prompt inputs, achieving an average Dice coefficient of 82.84%. Furthermore, the proposed automatic pathway routing mechanism allows for parameter pruning of the network during deployment, and gCIS can also be quickly adapted to unseen tasks with minimal training samples while maintaining great performance.

On-site burn severity assessment using smartphone-captured color burn wound images

Accurate assessment of burn severity is crucial for the management of burn injuries. Currently, clinicians mainly rely on visual inspection to assess burns, characterized by notable inter-observer discrepancies. In this study, we introduce an innovative analysis platform using color burn wound images for automatic burn severity assessment. To do this, we propose a novel joint-task deep learning model, which is capable of simultaneously segmenting both burn regions and body parts, the two crucial components in calculating the percentage of total body surface area (%TBSA). Asymmetric attention mechanism is introduced, allowing attention guidance from the body part segmentation task to the burn region segmentation task. A user-friendly mobile application is developed to facilitate a fast assessment of burn severity at clinical settings. The proposed framework was evaluated on a dataset comprising 1340 color burn wound images captured on-site at clinical settings. The average Dice coefficients for burn depth segmentation and body part segmentation are 85.12 % and 85.36 %, respectively. The R2 for %TBSA assessment is 0.9136. The source codes for the joint-task framework and the application are released on Github (https://github.com/xjtu-mia/BurnAnalysis). The proposed platform holds the potential to be widely used at clinical settings to facilitate a fast and precise burn assessment.

A novel metastatic tumor segmentation method with a new evaluation metric in clinic study.

Brain metastases are the most common brain malignancies. Automatic detection and segmentation of brain metastases provide significant assistance for radiologists in discovering the location of the lesion and making accurate clinical decisions on brain tumor type for precise treatment. However, due to the small size of the brain metastases, existing brain metastases segmentation produces unsatisfactory results and has not been evaluated on clinic datasets. In this work, we propose a new metastasis segmentation method DRAU-Net, which integrates a new attention mechanism multi-branch weighted attention module and DResConv module, making the extraction of tumor boundaries more complete. To enhance the evaluation of both the segmentation quality and the number of targets, we propose a novel medical image segmentation evaluation metric: multi-objective segmentation integrity metric, which effectively improves the evaluation results on multiple brain metastases with small size. Experimental results evaluated on the BraTS2023 dataset and collected clinical data show that the proposed method has achieved excellent performance with an average dice coefficient of 0.6858 and multi-objective segmentation integrity metric of 0.5582. Compared with other methods, our proposed method achieved the best performance in the task of segmenting metastatic tumors.

CDSG-SAM: A cross-domain self-generating prompt few-shot brain tumor segmentation pipeline based on SAM

In clinical practice, accurate segmentation of brain tumor regions is essential for patient treatment and survival. Accurate brain tumor segmentation is an important task and it is based on a large amount of labeled data. Clinical data are from different cities and device protocols, which leads to the poor generalization ability of the model. In addition, the small amount of clinical data also leads to the decline of the segmentation performance. In this paper, a cross-domain self-generating prompt few-shot brain tumor segmentation pipeline called CDSG-SAM is developed. This pipeline is based on the Segment Anything Model (SAM), which integrates a new Cross-domain self-attention (CDS) Adapter module and Self-Generating (SG) Prompt module. The SAM-based segmentation model is more suitable for few-shot medical image segmentation. A dynamic fuzzy support mask decoder module (DFSMD) is proposed in the decoder stage to enhance the accuracy of brain tumor segmentation edges. Furthermore, a Joint Loss function (JL) is designed to comprehensively consider multiple aspects of performance indicators to improve the accuracy and robustness of the model. Experimental results evaluated on the BraTS2021 glioma dataset, Clinical glioma brain tumor data (CBTD), and BraTS2023 metastatic tumor dataset show that the proposed pipeline has achieved excellent performance with an average dice coefficient of 0.918, 0.828, and 0.868 which outperforms than existing methods.

An Artificial Intelligence-Based Tool for Enhancing Pectoral Muscle Segmentation in Mammograms: Addressing Class Imbalance and Validation Challenges in Automated Breast Cancer Diagnosis.

Breast cancer remains a major health concern worldwide, requiring the advancement of early detection methods to improve prognosis and treatment outcomes. In this sense, mammography is regarded as the gold standard in breast cancer screening and early detection. However, in a scenario where extensive analysis is required, a large set of mammograms conducted by radiologists may carry out false negative or false positive diagnoses. Therefore, artificial intelligence has emerged in recent years as a method for enhancing timing in breast cancer diagnosis. Nonetheless, preprocessing stages are required to prepare the mammography dataset to enhance learning models to correctly identify breast anomalies. In this paper, we introduce a novel method employing convolutional neural networks (CNNs) to segment the pectoral muscle in 1288 mediolateral oblique mammograms (MLOs), thereby addressing class imbalance and overfitting between classes, and dataset augmentation based on translation, rotation, and scale transformation. The effectiveness of the model was assessed through a confusion matrix and performance metrics, highlighting an average Dice coefficient of 0.98 and a Jaccard index of 0.96. The outcomes demonstrate the model capability to accurately identify three classes: pectoral muscle, breast, and background. This study emphasizes the importance of tackling class imbalance problems and augmenting data for the training of models for reliable early breast cancer detection.

Intelligent diagnostic method for developmental hip dislocation

BackgroundDevelopmental dislocation of the hip joint (DDH) is a condition that severely threatens children’s healthy growth. Without timely and correct treatment, it will lead to osteoarthritis and hip dysfunction in the evolution of children.ObjectiveIt is essential to develop an intelligent model for diagnosing hip dislocation and performing accurate quantitative analysis.MethodsIn this paper, 46 cases of computed tomography (CT) images were retrospectively collected, including 19 cases of hip dislocation and 27 cases of healthy people. The experiment first uses ITK-SNAP to sketch the ilium and femoral head in the original image. Then, it uses 3D U-Net to send the label of the background, ilium, and femoral head into three channels, respectively, to realize the three-dimensional segmentation of the ilium and femoral head. Next, the extraction of the surface of the acetabulum and femoral head is performed. Subsequently, the erroneous points are eliminated, and the spherical surfaces of the acetabulum and femoral head are fitted using the least squares method. Ultimately, the spherical center distance is calculated quantitatively to predict whether the hip joint is dislocated.ResultsUnder the independent test set, the segmentation average dice coefficients of the ilium and femoral head are 89% and 93%, respectively. The spherical center distance between the acetabulum and femoral head is calculated quantitatively. If the value exceeds 10 mm, it is considered a hip dislocation. Compared with the doctor’s diagnosis, the accuracy result is 94.4%.ConclusionThis paper successfully implements a precise and automated intelligent diagnostic system for the identification of hip dislocation. Commencing with the development of a 3D segmentation algorithm for the ilium and femoral head, we further introduce a novel method that computes the spherical distance for the prediction of hip dislocation. This approach provides robust quantitative analysis, thereby facilitating more informed clinical decision-making.

Focal cortical dysplasia lesion segmentation using multiscale transformer

ObjectivesAccurate segmentation of focal cortical dysplasia (FCD) lesions from MR images plays an important role in surgical planning and decision but is still challenging for radiologists and clinicians. In this study, we introduce a novel transformer-based model, designed for the end-to-end segmentation of FCD lesions from multi-channel MR images.MethodsThe core innovation of our proposed model is the integration of a convolutional neural network-based encoder-decoder structure with a multiscale transformer to augment the feature representation of lesions in the global field of view. Transformer pathways, composed of memory- and computation-efficient dual-self-attention modules, leverage feature maps from varying depths of the encoder to discern long-range interdependencies among feature positions and channels, thereby emphasizing areas and channels relevant to lesions. The proposed model was trained and evaluated on a public-open dataset including MR images of 85 patients using both subject-level and voxel-level metrics.ResultsExperimental results indicate that our model offers superior performance both quantitatively and qualitatively. It successfully identified lesions in 82.4% of patients, with a low false-positive lesion cluster rate of 0.176 ± 0.381 per patient. Furthermore, the model achieved an average Dice coefficient of 0.410 ± 0.288, outperforming five established methods.ConclusionIntegration of the transformer could enhance the feature presentation and segmentation performance of FCD lesions. The proposed model has the potential to serve as a valuable assistive tool for physicians, enabling rapid and accurate identification of FCD lesions. The source code and pre-trained model weights are available at https://github.com/zhangxd0530/MS-DSA-NET.Critical relevance statementThis multiscale transformer-based model performs segmentation of focal cortical dysplasia lesions, aiming to help radiologists and clinicians make accurate and efficient preoperative evaluations of focal cortical dysplasia patients from MR images.Key PointsThe first transformer-based model was built to explore focal cortical dysplasia lesion segmentation.Integration of global and local features enhances the segmentation performance of lesions.A valuable benchmark for model development and comparative analyses was provided.Graphical

Harnessing AI for precision tonsillitis diagnosis: a revolutionary approach in endoscopic analysis.

Diagnosing and treating tonsillitis pose no significant challenge for otolaryngologists; however, it can increase the infection risk for healthcare professionals amidst the coronavirus pandemic. In recent years, with the advancement of artificial intelligence (AI), its application in medical imaging has also thrived. This research is to identify the optimal convolutional neural network (CNN) algorithm for accurate diagnosis of tonsillitis and early precision treatment. Semi-supervised learning with pseudo-labels used for self-training was adopted to train our CNN, with the algorithm including UNet, PSPNet, and FPN. A total of 485 pharyngoscopic images from 485 participants were included, comprising healthy individuals (133 cases), patients with the common cold (295 cases), and patients with tonsillitis (57 cases). Both color and texture features from 485 images are extracted for analysis. UNet outperformed PSPNet and FPN in accurately segmenting oropharyngeal anatomy automatically, with average Dice coefficient of 97.74% and a pixel accuracy of 98.12%, making it suitable for enhancing the diagnosis of tonsillitis. The normal tonsils generally have more uniform and smooth textures and have pinkish color, similar to the surrounding mucosal tissues, while tonsillitis, particularly the antibiotic-required type, shows white or yellowish pus-filled spots or patches, and shows more granular or lumpy texture in contrast, indicating inflammation and changes in tissue structure. After training with 485 cases, our algorithm with UNet achieved accuracy rates of 93.75%, 97.1%, and 91.67% in differentiating the three tonsil groups, demonstrating excellent results. Our research highlights the potential of using UNet for fully automated semantic segmentation of oropharyngeal structures, which aids in subsequent feature extraction, machine learning, and enables accurate AI diagnosis of tonsillitis. This innovation shows promise for enhancing both the accuracy and speed of tonsillitis assessments.

Dual-Tree Complex Wavelet Pooling and Attention-Based Modified U-Net Architecture for Automated Breast Thermogram Segmentation and Classification.

Thermography is a non-invasive and non-contact method for detecting cancer in its initial stages by examining the temperature variation between both breasts. Preprocessing methods such as resizing, ROI (region of interest) segmentation, and augmentation are frequently used to enhance the accuracy of breast thermogram analysis. In this study, a modified U-Net architecture (DTCWAU-Net) that uses dual-tree complex wavelet transform (DTCWT) and attention gate for breast thermal image segmentation for frontal and lateral view thermograms, aiming to outline ROI for potential tumor detection, was proposed. The proposed approach achieved an average Dice coefficient of 93.03% and a sensitivity of 94.82%, showcasing its potential for accurate breast thermogram segmentation. Classification of breast thermograms into healthy or cancerous categories was carried out by extracting texture- and histogram-based features and deep features from segmented thermograms. Feature selection was performed using Neighborhood Component Analysis (NCA), followed by the application of machine learning classifiers. When compared to other state-of-the-art approaches for detecting breast cancer using a thermogram, the proposed methodology showed a higher accuracy of 99.90% for VGG16 deep features with NCA and Random Forest classifier. Simulation results expound that the proposed method can be used in breast cancer screening, facilitating early detection, and enhancing treatment outcomes.

Automated Lumen Segmentation in Carotid Artery Ultrasound Images Based on Adaptive Generated Shape Prior.

Ultrasound imaging is vital for diagnosing carotid artery vascular lesions, highlighting the importance of accurately segmenting lumens in ultrasound images to prevent, diagnose and treat vascular diseases. However, noise artifacts, blood residue and discontinuous lumens significantly affect segmentation accuracy. To achieve accurate lumen segmentation in low-quality images, we propose a novel segmentation algorithm which is guided by an adaptively generated shape prior. To tackle the above challenges, we introduce a shape-prior-based segmentation method for carotid artery lumen walls. The shape prior in this study is adaptively generated based on the evolutionary trend of vessel growth. Shape priors guide and constrain the active contour, resulting in precise segmentation. The efficacy of the proposed model was confirmed using 247 carotid artery ultrasound images, with experimental results showing an average Dice coefficient of 92.38%, demonstrating superior segmentation performance compared to existing mathematical models. Our method can quickly and effectively perform accurate lumen segmentation on low-quality carotid artery ultrasound images, which is of great significance for the diagnosis of cardiovascular and cerebrovascular diseases.

AB093. Pixel-wise classification of glioma using deep learning for accurate tumour mapping on magnetic resonance imaging.

Central nervous system (CNS) tumours, especially glioma, are a complex disease and many challenges are encountered in their treatment. Artificial intelligence (AI) has made a colossal impact in many walks of life at a low cost. However, this avenue still needs to be explored in healthcare settings, demanding investment of resources towards growth in this area. We aim to develop machine learning (ML) algorithms to facilitate the accurate diagnosis and precise mapping of the brain tumour. We queried the data from 2019 to 2022 and brain magnetic resonance imaging (MRI) of glioma patients were extracted. Images that had both T1-contrast and T2-fluid-attenuated inversion recovery (T2-FLAIR) volume sequences available were included. MRI images were annotated by a team supervised by a neuroradiologist. The extracted MRIs thus obtained were then fed to the preprocessing pipeline to extract brains using SynthStrip. They were further fed to the deep learning-based semantic segmentation pipelines using UNet-based architecture with convolutional neural network (CNN) at its backbone. Subsequently, the algorithm was tested to assess the efficacy in the pixel-wise diagnosis of tumours. In total, 69 samples of low-grade glioma (LGG) were used out of which 62 were used for fine-tuning a pre-trained model trained on brain tumor segmentation (BraTS) 2020 and 7 were used for testing. For the evaluation of the model, the Dice coefficient was used as the metric. The average Dice coefficient on the 7 test samples was 0.94. With the advent of technology, AI continues to modify our lifestyles. It is critical to adapt this technology in healthcare with the aim of improving the provision of patient care. We present our preliminary data for the use of ML algorithms in the diagnosis and segmentation of glioma. The promising result with comparable accuracy highlights the importance of early adaptation of this nascent technology.

Improving lung nodule segmentation in thoracic CT scans through the ensemble of 3D U-Net models.

The current study explores the application of 3D U-Net architectures combined with Inception and ResNet modules for precise lung nodule detection through deep learning-based segmentation technique. This investigation is motivated by the objective of developing a Computer-Aided Diagnosis (CAD) system for effective diagnosis and prognostication of lung nodules in clinical settings. The proposed method trained four different 3D U-Net models on the retrospective dataset obtained from AIIMS Delhi. To augment the training dataset, affine transformations and intensity transforms were utilized. Preprocessing steps included CT scan voxel resampling, intensity normalization, and lung parenchyma segmentation. Model optimization utilized a hybrid loss function that combined Dice Loss and Focal Loss. The model performance of all four 3D U-Nets was evaluated patient-wise using dice coefficient and Jaccard coefficient, then averaged to obtain the average volumetric dice coefficient (DSCavg) and average Jaccard coefficient (IoUavg) on a test dataset comprising 53 CT scans. Additionally, an ensemble approach (Model-V) was utilized featuring 3D U-Net (Model-I), ResNet (Model-II), and Inception (Model-III) 3D U-Net architectures, combined with two distinct patch sizes for further investigation. The ensemble of models obtained the highest DSCavg of 0.84 ± 0.05 and IoUavg of 0.74 ± 0.06 on the test dataset, compared against individual models. It mitigated false positives, overestimations, and underestimations observed in individual U-Net models. Moreover, the ensemble of models reduced average false positives per scan in the test dataset (1.57 nodules/scan) compared to individual models (2.69-3.39 nodules/scan). The suggested ensemble approach presents a strong and effective strategy for automatically detecting and delineating lung nodules, potentially aiding CAD systems in clinical settings. This approach could assist radiologists in laborious and meticulous lung nodule detection tasks in CT scans, improving lung cancer diagnosis and treatment planning.

Automatic segmentation of knee CT images of tibial plateau fractures based on three-dimensional U-Net: Assisting junior physicians with Schatzker classification

PurposeThis study aimed to automatically segment knee computed tomography (CT) images of tibial plateau fractures using a three-dimensional (3D) U-net-based method, accurately construct 3D maps of tibial plateau fractures, and examine their usefulness for Schatzker classification in clinical practice. MethodsWe retrospectively enrolled 234 cases with tibial plateau fractures from our hospital in this study. The four constituent bones of the knee were manually annotated using ITK-SNAP software. Finally, image features were extracted using deep learning. The usefulness of the results for Schatzker classification was examined by an orthopaedic and a radiology resident. ResultsOn average, our model required < 40 s to process a 3D CT scan of the knee. The average Dice coefficient for all four knee bones was higher than 0.950, and highly accurate 3D maps of the tibia were produced. With the aid of the results of our model, the accuracy, sensitivity, and specificity of the Schatzker classification of both residents improved. ConclusionsThe proposed method can rapidly and accurately segment knee CT images of tibial plateau fractures and assist residents with Schatzker classification, which can help improve diagnostic efficiency and reduce the workload of junior doctors in clinical practice.

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique.

Abdominal multi-organ segmentation is one of the most important topics in the field of medical image analysis, and it plays an important role in supporting clinical workflows such as disease diagnosis and treatment planning. In this study, an efficient multi-organ segmentation method called Swin-PSAxialNet based on the nnU-Net architecture is proposed. It was designed specifically for the precise segmentation of 11 abdominal organs in CT images. The proposed network has made the following improvements compared to nnU-Net. Firstly, Space-to-depth (SPD) modules and parameter-shared axial attention (PSAA) feature extraction blocks were introduced, enhancing the capability of 3D image feature extraction. Secondly, a multi-scale image fusion approach was employed to capture detailed information and spatial features, improving the capability of extracting subtle features and edge features. Lastly, a parameter-sharing method was introduced to reduce the model's computational cost and training speed. The proposed network achieves an average Dice coefficient of 0.93342 for the segmentation task involving 11 organs. Experimental results indicate the notable superiority of Swin-PSAxialNet over previous mainstream segmentation methods. The method shows excellent accuracy and low computational costs in segmenting major abdominal organs.

Kidney, ureter, and urinary bladder segmentation based on non-contrast enhanced computed tomography images using modified U-Net

This study was performed to segment the urinary system as the basis for diagnosing urinary system diseases on non-contrast computed tomography (CT). This study was conducted with images obtained between January 2016 and December 2020. During the study period, non-contrast abdominopelvic CT scans of patients and diagnosed and treated with urinary stones at the emergency departments of two institutions were collected. Region of interest extraction was first performed, and urinary system segmentation was performed using a modified U-Net. Thereafter, fivefold cross-validation was performed to evaluate the robustness of the model performance. In fivefold cross-validation results of the segmentation of the urinary system, the average dice coefficient was 0.8673, and the dice coefficients for each class (kidney, ureter, and urinary bladder) were 0.9651, 0.7172, and 0.9196, respectively. In the test dataset, the average dice coefficient of best performing model in fivefold cross validation for whole urinary system was 0.8623, and the dice coefficients for each class (kidney, ureter, and urinary bladder) were 0.9613, 0.7225, and 0.9032, respectively. The segmentation of the urinary system using the modified U-Net proposed in this study could be the basis for the detection of kidney, ureter, and urinary bladder lesions, such as stones and tumours, through machine learning.

Adaptive Multi-Dimensional Weighted Network With Category-Aware Contrastive Learning for Fine-Grained Hand Bone Segmentation.

Accurately delineating and categorizing individual hand bones in 3D ultrasound (US) is a promising technology for precise digital diagnostic analysis. However, this is a challenging task due to the inherent imaging limitations of the US and the insignificant feature differences among numerous bones. In this study, we have proposed a novel deep learning-based solution for pediatric hand bone segmentation in the US. Our method is unique in that it allows for effective detailed feature mining through an adaptive multi-dimensional weighting attention mechanism. It innovatively implements a category-aware contrastive learning method to highlight inter-class semantic feature differences, thereby enhancing the category discrimination performance of the model. Extensive experiments on the challenging pediatric clinical hand 3D US datasets show the outstanding performance of the proposed method in segmenting thirty-eight bone structures, with the average Dice coefficient of 90.0%. The results outperform other state-of-the-art methods, demonstrating its effectiveness in fine-grained hand bone segmentation. Our method will be globally released as a plugin in the 3D Slicer, providing an innovative and reliable tool for relevant clinical applications.

G-MBRMD: Lightweight liver segmentation model based on guided teaching with multi-head boundary reconstruction mapping distillation

Background and Objectives:Liver segmentation is pivotal for the quantitative analysis of liver cancer. Although current deep learning methods have garnered remarkable achievements for medical image segmentation, they come with high computational costs, significantly limiting their practical application in the medical field. Therefore, the development of an efficient and lightweight liver segmentation model becomes particularly important. Methods:In our paper, we propose a real-time, lightweight liver segmentation model named G-MBRMD. Specifically, we employ a Transformer-based complex model as the teacher and a convolution-based lightweight model as the student. By introducing proposed multi-head mapping and boundary reconstruction strategies during the knowledge distillation process, Our method effectively guides the student model to gradually comprehend and master the global boundary processing capabilities of the complex teacher model, significantly enhancing the student model’s segmentation performance without adding any computational complexity. Results:On the LITS dataset, we conducted rigorous comparative and ablation experiments, four key metrics were used for evaluation, including model size, inference speed, Dice coefficient, and HD95. Compared to other methods, our proposed model achieved an average Dice coefficient of 90.14±16.78%, with only 0.6 MB memory and 0.095 s inference speed for a single image on a standard CPU. Importantly, this approach improved the average Dice coefficient of the baseline student model by 1.64% without increasing computational complexity. Conclusion:The results demonstrate that our method successfully realizes the unification of segmentation precision and lightness, and greatly enhances its potential for widespread application in practical settings.