Dice Similarity Coefficient Research Articles

Development and validation of a robotic system for milling individualized jawbone cavities in oral and maxillofacial surgery

ObjectivesThis study aimed to develop and validate a robotic system capable of performing accurate and minimally invasive jawbone milling procedures in oral and maxillofacial surgery. MethodsThe robotic hardware system mainly includes a UR5E arm (Universal Robots, Denmark) and the binocular positioning system (FusionTrack 250, Atracsys LLC, Switzerland). The robotic software (Dental Navi 3.0.0, Yakebot Technology Ltd., China) is capable of generating cutting tool paths based on three-dimensional shape description files, typically in the stereolithography format, and selected cutting tool parameters, as well as designing surgical accessories. Fully impacted supernumerary tooth models in the maxilla were fabricated using software and three-dimensional printing. Following the planning of a customized cavity to fully expose the tooth, maxillary bone milling was performed on both the robot and static guide groups (n = 8). After milling, all models underwent scanning for assessment. ResultsIn the experiment with fully buried supernumerary tooth models in the maxilla, the root mean square, translation error, over-removal rate, and maximum distance were significantly smaller in the robot group compared to the static guide group. Moreover, the overlap ratio and Dice coefficient were significantly greater in the robot group. No statistically significant differences were observed between the two groups in terms of the rotation error (P = 0.80) or under-removal rate (P = 0.92). ConclusionsThis study has developed a robotic system for milling individualized jawbone cavities in oral and maxillofacial surgery, and its accuracy has been preliminarily verified to meet clinical requirements. Clinical significanceThe robotic system can achieve precise, minimally invasive, individualized jawbone milling in a variety of oral and maxillofacial surgeries, including tooth autotransplantation, surgical reshaping for zygomatic fibrous dysplasia, removal of fully impacted supernumerary or impacted teeth, and endodontic microsurgery, among other relevant clinical applications.

Specialized gray matter segmentation via a generative adversarial network: application on brain white matter hyperintensities classification.

White matter hyperintensities (WMH) observed in T2 fluid-attenuated inversion recovery (FLAIR) images have emerged as potential markers of neurodegenerative diseases like Multiple Sclerosis (MS). Lacking comprehensive automated WMH classification systems in current research, there is a need to develop accurate detection and classification methods for WMH that will benefit the diagnosis and monitoring of brain diseases. Juxtacortical WMH (JCWMH) is a less explored subtype of WMH, primarily due to the hard definition of the cortex in FLAIR images, which is escalated by the presence of lesions to obtain appropriate gray matter (GM) masks. In this study, we present a method to perform a specialized GM segmentation developed for the classification of WMH, especially JCWMH. Using T1 and FLAIR images, we propose a pipeline to integrate masks of white matter, cerebrospinal fluid, ventricles, and WMH to create a unique mask to refine the primary GM map. Subsequently, we utilize this pipeline to generate paired data for training a conditional generative adversarial network (cGAN) to substitute the pipeline and reduce the inputs to only FLAIR images. The classification of WMH is then based on the distances between WMH and ventricular and GM masks. Due to the lack of multi-class labeled WMH datasets and the need for extensive data for training deep learning models, we attempted to collect a large local dataset and manually segment and label some data for WMH and ventricles. In JCWMH classification, the proposed method exhibited a Dice similarity coefficient, precision, and sensitivity of 0.76, 0.69, and 0.84, respectively. With values of 0.66, 0.55, and 0.81, the proposed method clearly outperformed the approach commonly used in the literature, which uses extracted GM masks from registered T1 images on FLAIR. After training, the method proves its efficiency by providing results in less than one second. In contrast, the usual approach would require at least two minutes for registration and segmentation alone. The proposed method is automated and fast and requires no initialization as it works exclusively with FLAIR images. Such innovative methods will undoubtedly facilitate accurate and meaningful analysis of WMH in clinical practice by reducing complexity and increasing efficiency.

Multi-scale and multi-receptive field-based feature fusion for robust segmentation of plant disease and fruit using agricultural images

The accurate and fast assessment of plant diseases and fruits is important for sustainable and productive agriculture. However, typically manual methods are adopted for the assessment of plant diseases and fruit, which is a time-consuming, resource-intensive, and error-prone approach. A few artificial intelligence (AI)-based methods have been introduced to automate this process, but they show limitations in attaining high performance in challenging imaging conditions such as occlusions, poor lighting, noise, indistinctive boundaries, and excessive morphological variations. Moreover, current approaches also lack in providing computationally efficient solutions. To overcome these issues, two novel architectures are developed to segment plant diseases and fruits with higher segmentation performance and less computational requirements. The efficient feature fusion segmentation network (EFFS-Net) is the base network, and a multi-scale dilated feature fusion segmentation network (MDFS-Net) is the final network of this study. EFFS-Net uses an identity skip path-based feature fusion mechanism with an efficient grouped convolutional depth (EGCD) to provide satisfactory segmentation performance with high computational efficiency. MDFS-Net uses a multi-scale feature fusion mechanism and fuses low-level information in the EGCD and other sections of the network to learn detailed input features for delivering promising performance even in challenging imaging conditions. MDFS-Net also applies multiple receptive fields to the low-level information in the effective receptive field processing (ERFP) block for fusion near the pixel classification stage for further performance enhancement.Both networks are evaluated using a Brazilian Arabica coffee leaf (BRACOL) image dataset, an Australian Center for Field Robotics orchard fruit (apple) dataset, and a necrotized cassava root cross-section image dataset. The proposed method provides a promising segmentation performance, achieving dice similarity coefficients of 88.81 %, 95.01 %, and 86.04 % with performance improvement of 3.5 %, 2.6 %, and 1.07 % on the three datasets, respectively, with approximately ten times less number of required trainable parameters compared with the state-of-the-art methods.

Improved ground truth annotation by multimodal image registration from 3D ultrasound to histopathology for resected tongue carcinoma.

This study's objectives are (1) to investigate the registration accuracy from intraoperative ultrasound (US) to histopathological images, (2) to assess the agreement and correlation between measurements in registered 3D US and histopathology, and (3) to train a nnUNet model for automatic segmentation of 3D US volumes of resected tongue specimens. Ten 3D US volumes were acquired, including the corresponding digitalized histopathological images (n = 29). Based on corresponding landmarks, the registrations between 3D US and histopathology images were calculated and evaluated using the target registration error (TRE). Tumor thickness and resection margins were measured based on three annotations: (1) manual histopathological tumor annotation (HTA), manual 3D US tumor annotation, and (2) the HTA registered in the 3D US. The agreement and correlation were computed between the measurements based on the HTA and those based on the manual US and registered HTA in US. A deep-learning model with nnUNet was trained on 151 3D US volumes. Segmentation metrics quantified the model's performance. The median TRE was 0.42mm. The smallest mean difference was between registered HTA in US and histopathology with 2.16mm (95% CI - 1.31; 5.63) and a correlation of 0.924 (p < 0.001). The nnUNet predicted the tumor with a Dice similarity coefficient of 0.621, an average surface distance of 1.15mm, and a Hausdorff distance of 3.70mm. Multimodal image registration enabled the HTA's registration in the US images and improved the agreement and correlation between the modalities. In the future, this could be used to annotate ground truth labels accurately.

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.

Blood Vessel Segmentation and Classification of Diabetic Retinopathy with Machine Learning-Based Ensemble Model

The incidence of diabetes has increased in recent times due to factors such as obesity and genetic predisposition. Diabetes wears out the eye vessels over time. Diabetic retinopathy (DR) is a serious disease that leads to vision problems. DR can be diagnosed by specialists who examine the fundus images of the eye at regular intervals. With 537 million diabetics in 2021, this method can be time-consuming, costly and inadequate. Artificial intelligence algorithms can provide fast and cost-effective solutions for DR diagnosis. In this study, the noise of blood vessels in fundus images was eliminated using the LinkNet-RCB7 model, and diabetic retinopathy was categorized into five classes using a machine learning-based ensemble model. Artificial intelligence-based classification training using images as input takes a long time and requires high resource requirements such as Random Access Memory (RAM) and Graphics Processing Unit (GPU). By using Gray Level Cooccurrence Matrix (GLCM) attributes in the classification phase, a lower resource requirement was aimed for. A Dice coefficient of 85.95% was achieved for the segmentation of blood vessels in the Stare dataset, in addition to 97.46% accuracy for binary classification and 96.10% accuracy for classifying DR into five classes in the dataset APTOS 2019.

The Study of Echocardiography of Left Ventricle Segmentation Combining Transformer and Convolutional Neural Networks.

Accurate prediction of echocardiographic parameters is essential for diagnosis and treatment of cardiac disease, especially for segmentation of the left ventricle to obtain measurements such as left ventricular ejection fraction and volume. However, manually outlining left ventricle on echocardiographic images is a time-consuming and physician experience-dependent task. Therefore, it is crucial to develop an accurate and efficient automatic segmentation tool. Therefore, we aimed to explore a model to perform echocardiography of left ventricle segmentation by combining transformer and convolutional neural networks (CNN).ResNet-50 was used in CNN branch. The encoder-decoder architecture was used for transformer branch, which was fused to the corresponding feature maps of the CNN branches. Fusion module was used to effectively combine feature information from the CNN and transformer. Bridge attention used to increase sensitivity and prediction accuracy of model. The entire network was trained end-to-end using the binary cross-entropy with logits loss L.In this work, we propose an automatic left ventricular (LV) segmentation model based on Transformer and CNN that efficiently captures global dependencies and spatial details and create a fusion module using CBAM that fuses Transformer and CNN features. In addition, attention is also computed using multi-level fusion features to obtain the final attention segmentation map. The model was trained and evaluated on a large cardiac image dataset, EchoNet-Dynamic, with test dice coefficient of 92.4%.The results show that our model can better segment left ventricle. We also tested our model on clinical patient ultrasound images, and visualization results proved effectiveness of the model.

Real-time segmentation of biliary structure in pure laparoscopic donor hepatectomy

Pure laparoscopic donor hepatectomy (PLDH) has become a standard practice for living donor liver transplantation in expert centers. Accurate understanding of biliary structures is crucial during PLDH to minimize the risk of complications. This study aims to develop a deep learning-based segmentation model for real-time identification of biliary structures, assisting surgeons in determining the optimal transection site during PLDH. A single-institution retrospective feasibility analysis was conducted on 30 intraoperative videos of PLDH. All videos were selected for their use of the indocyanine green near-infrared fluorescence technique to identify biliary structure. From the analysis, 10 representative frames were extracted from each video specifically during the bile duct division phase, resulting in 300 frames. These frames underwent pixel-wise annotation to identify biliary structures and the transection site. A segmentation task was then performed using a DeepLabV3+ algorithm, equipped with a ResNet50 encoder, focusing on the bile duct (BD) and anterior wall (AW) for transection. The model’s performance was evaluated using the dice similarity coefficient (DSC). The model predicted biliary structures with a mean DSC of 0.728 ± 0.01 for BD and 0.429 ± 0.06 for AW. Inference was performed at a speed of 15.3 frames per second, demonstrating the feasibility of real-time recognition of anatomical structures during surgery. The deep learning-based semantic segmentation model exhibited promising performance in identifying biliary structures during PLDH. Future studies should focus on validating the clinical utility and generalizability of the model and comparing its efficacy with current gold standard practices to better evaluate its potential clinical applications.

MGA-Net: A novel mask-guided attention neural network for precision neonatal brain imaging

In this study, we introduce MGA-Net, a novel mask-guided attention neural network, which extends the U-net model for precision neonatal brain imaging. MGA-Net is designed to extract the brain from other structures and reconstruct high-quality brain images. The network employs a common encoder and two decoders: one for brain mask extraction and the other for brain region reconstruction. A key feature of MGA-Net is its high-level mask-guided attention module, which leverages features from the brain mask decoder to enhance image reconstruction. To enable the same encoder and decoder to process both MRI and ultrasound (US) images, MGA-Net integrates sinusoidal positional encoding. This encoding assigns distinct positional values to MRI and US images, allowing the model to effectively learn from both modalities. Consequently, features learned from a single modality can aid in learning a modality with less available data, such as US. We extensively validated the proposed MGA-Net on diverse and independent datasets from varied clinical settings and neonatal age groups. The metrics used for assessment included the DICE similarity coefficient, recall, and accuracy for image segmentation; structural similarity for image reconstruction; and root mean squared error for total brain volume estimation from 3D ultrasound images. Our results demonstrate that MGA-Net significantly outperforms traditional methods, offering superior performance in brain extraction and segmentation while achieving high precision in image reconstruction and volumetric analysis. Thus, MGA-Net represents a robust and effective preprocessing tool for MRI and 3D ultrasound images, marking a significant advance in neuroimaging that enhances both research and clinical diagnostics in the neonatal period and beyond.

Enhanced gastric cancer classification and quantification interpretable framework using digital histopathology images

Recent developments have highlighted the critical role that computer-aided diagnosis (CAD) systems play in analyzing whole-slide digital histopathology images for detecting gastric cancer (GC). We present a novel framework for gastric histology classification and segmentation (GHCS) that offers modest yet meaningful improvements over existing CAD models for GC classification and segmentation. Our methodology achieves marginal improvements over conventional deep learning (DL) and machine learning (ML) models by adaptively focusing on pertinent characteristics of images. This contributes significantly to our study, highlighting that the proposed model, which performs well on normalized images, is robust in certain respects, particularly in handling variability and generalizing to different datasets. We anticipate that this robustness will lead to better results across various datasets. An expectation-maximizing Naïve Bayes classifier that uses an updated Gaussian Mixture Model is at the heart of the suggested GHCS framework. The effectiveness of our classifier is demonstrated by experimental validation on two publicly available datasets, which produced exceptional classification accuracies of 98.87% and 97.28% on validation sets and 98.47% and 97.31% on test sets. Our framework shows a slight but consistent improvement over previously existing techniques in gastric histopathology image classification tasks, as demonstrated by comparative analysis. This may be attributed to its ability to capture critical features of gastric histopathology images better. Furthermore, using an improved Fuzzy c-means method, our study produces good results in GC histopathology picture segmentation, outperforming state-of-the-art segmentation models with a Dice coefficient of 65.21% and a Jaccard index of 60.24%. The model’s interpretability is complemented by Grad-CAM visualizations, which help understand the decision-making process and increase the model’s trustworthiness for end-users, especially clinicians.

Dual phase hierarchical brain tumour detection and segmentation using unet based skip guidance residual convolutional transformer

Brain tumour segmentation and classification is an important approach to understanding tumour characteristics effectively. Accurate lesion segmentation requires many image modalities with varied contrasts. As a result, manual segmentation may not be suitable for large-scale research. The research has shown interest in developing various learning algorithms to detect and segment brain tumour (BT) images accurately based on the set of experimental images. Some of the issues noticed in the existing models, such as high computational complexity, high processing time, and less accuracy, were identified. In order to overcome these existing issues, a novel Dual-phase channel attentional Residual convolutional transformer Unet model (DCARCTUnet) is introduced for segmenting brain tumours. Initially, the input images are passed into the pre-processing stage to remove noise and blur. The Efficient Net model identified the pre-processed image as either normal or tumour. The proposed segmentation model can be integrated into three stages, namely dual phase channel attention module (DCAM), residual convolutional transformer Unet model and Pyramid skip guidance module (PSM). The proposed method uses the BRATS 2020–2021 dataset to analyze the results accurately. The results showed that the proposed model has a dice coefficient value of 0.99 and a Jaccard coefficient value of 0.98. Furthermore, performance analysis is carried out to demonstrate the effectiveness of the proposed model.

Deep learning-based segmentation for high-dose-rate brachytherapy in cervical cancer using 3D Prompt-ResUNet

Objective.To develop and evaluate a 3D Prompt-ResUNet module that utilized the prompt-based model combined with 3D nnUNet for rapid and consistent autosegmentation of high-risk clinical target volume (HRCTV) and organ at risk (OAR) in high-dose-rate brachytherapy for cervical cancer patients.Approach.We used 73 computed tomography scans and 62 magnetic resonance imaging scans from 135 (103 for training, 16 for validation, and 16 for testing) cervical cancer patients across two hospitals for HRCTV and OAR segmentation. A novel comparison of the deep learning neural networks 3D Prompt-ResUNet, nnUNet, and segment anything model-Med3D was applied for the segmentation. Evaluation was conducted in two parts: geometric and clinical assessments. Quantitative metrics included the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95%), Jaccard index (JI), and Matthews correlation coefficient (MCC). Clinical evaluation involved interobserver comparison, 4-grade expert scoring, and a double-blinded Turing test.Main results.The Prompt-ResUNet model performed most similarly to experienced radiation oncologists, outperforming less experienced ones. During testing, the DSC, HD95% (mm), JI, and MCC value (mean ± SD) for HRCTV were 0.92 ± 0.03, 2.91 ± 0.69, 0.85 ± 0.04, and 0.92 ± 0.02, respectively. For the bladder, these values were 0.93 ± 0.05, 3.07 ± 1.05, 0.87 ± 0.08, and 0.93 ± 0.05, respectively. For the rectum, they were 0.87 ± 0.03, 3.54 ± 1.46, 0.78 ± 0.05, and 0.87 ± 0.03, respectively. For the sigmoid, they were 0.76 ± 0.11, 7.54 ± 5.54, 0.63 ± 0.14, and 0.78 ± 0.09, respectively. The Prompt-ResUNet achieved a clinical viability score of at least 2 in all evaluation cases (100%) for both HRCTV and bladder and exceeded the 30% positive rate benchmark for all evaluated structures in the Turing test.Significance.The Prompt-ResUNet architecture demonstrated high consistency with ground truth in autosegmentation of HRCTV and OARs, reducing interobserver variability and shortening treatment times.

Revealing in vivo broiler chicken growth state: Integrating CT imaging and deep learning for non-invasive reproductive phenotypic measurement

The measurement of body dimensions in broiler chickens has long been of great interest to the poultry industry, especially regarding reproductive phenotypes closely linked to breeding traits and the growth status of roosters. Existing measurement methods suffer from subjectivity, destructiveness, and various limitations. Therefore, we propose a novel method for the in vivo measurement of broiler chicken reproductive phenotype based on a three-dimensional medical imaging segmentation network. Leveraging our proposed FDTR medical imaging segmentation algorithm, this method achieves robust segmentation performance on a broiler chicken dataset. However, due to the morphological diversity and extreme class imbalance of broiler chicken reproductive phenotypes, we introduce a meta-learning paradigm and design a specialized decoder path. Ultimately, we establish relationships between the predicted results obtained from the segmentation network and the reproductive phenotypes to achieve phenotypic measurement. To evaluate this method, we collected and constructed the YF2023 broiler chicken reproductive phenotype dataset. Extensive cross-validation experiments demonstrate that the proposed method effectively measures the reproductive phenotypes of live roosters using computed tomography (CT) medical imaging. The proposed segmentation model achieves a mean fold dice similarity coefficient (DSC) of 0.6353, a mean fold Hausdorff distance (HD) of 11.84 mm, and a mean fold average volume distance (AVD) of 1.72 mm3. In addition, we evaluated our model’s generalization performance on unseen data, where the model achieved a DSC of 0.6825, an HD of 7.58 mm, and an AVD of 1.40 mm3. The predicted results exhibit a mean correlation coefficient of 66.18% with the weights of reproductive phenotype. This validates the enormous potential of the method in broiler chicken breeding and provides new insights and solutions for the accurate segmentation of broiler chicken reproductive phenotype. The code is available at https://github.com/Github-XKou/MetaFDTR.

Skin lesion segmentation using deep learning algorithm with ant colony optimization

BackgroundSegmentation of skin lesions remains essential in histological diagnosis and skin cancer surveillance. Recent advances in deep learning have paved the way for greater improvements in medical imaging. The Hybrid Residual Networks (ResUNet) model, supplemented with Ant Colony Optimization (ACO), represents the synergy of these improvements aimed at improving the efficiency and effectiveness of skin lesion diagnosis.ObjectiveThis paper seeks to evaluate the effectiveness of the Hybrid ResUNet model for skin lesion classification and assess its impact on optimizing ACO performance to bridge the gap between computational efficiency and clinical utility.MethodsThe study used a deep learning design on a complex dataset that included a variety of skin lesions. The method includes training a Hybrid ResUNet model with standard parameters and fine-tuning using ACO for hyperparameter optimization. Performance was evaluated using traditional metrics such as accuracy, dice coefficient, and Jaccard index compared with existing models such as residual network (ResNet) and U-Net.ResultsThe proposed hybrid ResUNet model exhibited excellent classification accuracy, reflected in the noticeable improvement in all evaluated metrics. His ability to describe complex lesions was particularly outstanding, improving diagnostic accuracy. Our experimental results demonstrate that the proposed Hybrid ResUNet model outperforms existing state-of-the-art methods, achieving an accuracy of 95.8%, a Dice coefficient of 93.1%, and a Jaccard index of 87.5.ConclusionThe addition of ResUNet to ACO in the proposed Hybrid ResUNet model significantly improves the classification of skin lesions. This integration goes beyond traditional paradigms and demonstrates a viable strategy for deploying AI-powered tools in clinical settings.Future workFuture investigations will focus on increasing the version's abilities by using multi-modal imaging information, experimenting with alternative optimization algorithms, and comparing real-world medical applicability. There is also a promising scope for enhancing computational performance and exploring the model's interpretability for more clinical adoption.

A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms

Myopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings. To evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists. The Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024. DL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation. MM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE). The 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P < .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P < .001). In this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

Automated segmentation and source prediction of bone tumors using ConvNeXtv2 Fusion based Mask R-CNN to identify lung cancer metastasis

Lung cancer, which is a leading cause of cancer-related deaths worldwide, frequently metastasizes to the bones, significantly diminishing patients’ quality of life and complicating treatment strategies. This study aims to develop an advanced 3D Mask R-CNN model, enhanced with the ConvNeXt-V2 backbone, for the automatic segmentation of bone tumors and identification of lung cancer metastasis to support personalized treatment planning. Data were collected from two hospitals: Center A (106 patients) and Center B (265 patients). The data from Center B were used for training, while Center A’s dataset served as an independent external validation set. High-resolution CT scans with 1 mm slice thickness and no inter-slice gaps were utilized, and the regions of interest (ROIs) were manually segmented and validated by two experienced radiologists. The 3D Mask R-CNN model achieved a Dice Similarity Coefficient (DSC) of 0.856, a sensitivity of 0.921, and a specificity of 0.961 on the training set. On the test set, it achieved a DSC of 0.849, a sensitivity of 0.911, and a specificity of 0.931. For the classification task, the model attained an AUC of 0.865, an accuracy of 0.866, a sensitivity of 0.875, and a specificity of 0.835 on the training set, while achieving an AUC of 0.842, an accuracy of 0.836, a sensitivity of 0.847, and a specificity of 0.819 on the test set. These results highlight the model’s potential in improving the accuracy of bone tumor segmentation and lung cancer metastasis detection, paving the way for enhanced diagnostic workflows and personalized treatment strategies in clinical oncology.

Applying a Deep Learning Model for Total Kidney Volume Measurement in Autosomal Dominant Polycystic Kidney Disease.

Autosomal dominant polycystic kidney disease (ADPKD) is the most common hereditary renal disease leading to end-stage renal disease. Total kidney volume (TKV) measurement has been considered as a surrogate in the evaluation of disease severity and prognostic predictor of ADPKD. However, the traditional manual measurement of TKV by medical professionals is labor-intensive, time-consuming, and human error prone. In this investigation, we conducted TKV measurements utilizing magnetic resonance imaging (MRI) data. The dataset consisted of 30 patients with ADPKD and 10 healthy individuals. To calculate TKV, we trained models using both coronal- and axial-section MRI images. The process involved extracting images in Digital Imaging and Communications in Medicine (DICOM) format, followed by augmentation and labeling. We employed a U-net model for image segmentation, generating mask images of the target areas. Subsequent post-processing steps and TKV estimation were performed based on the outputs obtained from these mask images. The average TKV, as assessed by medical professionals from the testing dataset, was 1501.84 ± 965.85 mL with axial-section images and 1740.31 ± 1172.21 mL with coronal-section images, respectively (p = 0.73). Utilizing the deep learning model, the mean TKV derived from axial- and coronal-section images was 1536.33 ± 958.68 mL and 1636.25 ± 964.67 mL, respectively (p = 0.85). The discrepancy in mean TKV between medical professionals and the deep learning model was 44.23 ± 58.69 mL with axial-section images (p = 0.8) and 329.12 ± 352.56 mL with coronal-section images (p = 0.9), respectively. The average variability in TKV measurement was 21.6% with the coronal-section model and 3.95% with the axial-section model. The axial-section model demonstrated a mean Dice Similarity Coefficient (DSC) of 0.89 ± 0.27 and an average patient-wise Jaccard coefficient of 0.86 ± 0.27, while the mean DSC and Jaccard coefficient of the coronal-section model were 0.82 ± 0.29 and 0.77 ± 0.31, respectively. The integration of deep learning into image processing and interpretation is becoming increasingly prevalent in clinical practice. In our pilot study, we conducted a comparative analysis of the performance of a deep learning model alongside corresponding axial- and coronal-section models, a comparison that has been less explored in prior research. Our findings suggest that our deep learning model for TKV measurement performs comparably to medical professionals. However, we observed that varying image orientations could introduce measurement bias. Specifically, our AI model exhibited superior performance with axial-section images compared to coronal-section images.

USCT-UNet: Rethinking the Semantic Gap in U-Net Network from U-shaped Skip Connections with Multichannel Fusion Transformer.

Medical image segmentation is a crucial component of computer-aided clinical diagnosis, with state-of-the-art models often being variants of U-Net. Despite their success, these models' skip connections introduce an unnecessary semantic gap between the encoder and decoder, which hinders their ability to achieve the high precision required for clinical applications. Awareness of this semantic gap and its detrimental influences have increased over time. However, a quantitative understanding of how this semantic gap compromises accuracy and reliability remains lacking, emphasizing the need for effective mitigation strategies. In response, we present the first quantitative evaluation of the semantic gap between corresponding layers of U-Net and identify two key characteristics: 1) The direct skip connection (DSC) exhibits a semantic gap that negatively impacts models' performance; 2) The magnitude of the semantic gap varies across different layers. Based on these findings, we re-examine this issue through the lens of skip connections. We introduce a Multichannel Fusion Transformer (MCFT) and propose a novel USCT-UNet architecture, which incorporates U-shaped skip connections (USC) to replace DSC, allocates varying numbers of MCFT blocks based on the semantic gap magnitude at different layers, and employs a spatial channel cross-attention (SCCA) module to facilitate the fusion of features between the decoder and USC. We evaluate USCT-UNet on four challenging datasets, and the results demonstrate that it effectively eliminates the semantic gap. Compared to using DSC, our USC and SCCA strategies achieve maximum improvements of 4.79% in the Dice coefficient, 5.70% in mean intersection over union (MIoU), and 3.26 in Hausdorff distance.

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.

Deep bone oncology Diagnostics: Computed tomography based Machine learning for detection of bone tumors from breast cancer metastasis

PurposeThe objective of this study is to develop a novel diagnostic tool using deep learning and radiomics to distinguish bone tumors on CT images as metastases from breast cancer. By providing a more accurate and reliable method for identifying metastatic bone tumors, this approach aims to significantly improve clinical decision-making and patient management in the context of breast cancer. MethodsThis study utilized CT images of bone tumors from 178 patients, including 78 cases of breast cancer bone metastases and 100 cases of non-breast cancer bone metastases. The dataset was processed using the Medical Image Segmentation via Self-distilling TransUNet (MISSU) model for automated segmentation. Radiomics features were extracted from the segmented tumor regions using the Pyradiomics library, capturing various aspects of tumor phenotype. Feature selection was conducted using LASSO regression to identify the most predictive features. The model’s performance was evaluated using ten-fold cross-validation, with metrics including accuracy, sensitivity, specificity, and the Dice similarity coefficient. ResultsThe developed radiomics model using the SVM algorithm achieved high discriminatory power, with an AUC of 0.936 on the training set and 0.953 on the test set. The model’s performance metrics demonstrated strong accuracy, sensitivity, and specificity. Specifically, the accuracy was 0.864 for the training set and 0.853 for the test set. Sensitivity values were 0.838 and 0.789 for the training and test sets, respectively, while specificity values were 0.896 and 0.933 for the training and test sets, respectively. These results indicate that the SVM model effectively distinguishes between bone metastases originating from breast cancer and other origins. Additionally, the average Dice similarity coefficient for the automated segmentation was 0.915, demonstrating a high level of agreement with manual segmentations. ConclusionThis study demonstrates the potential of combining CT-based radiomics and deep learning for the accurate detection of bone metastases from breast cancer. The high-performance metrics indicate that this approach can significantly enhance diagnostic accuracy, aiding in early detection and improving patient outcomes. Future research should focus on validating these findings on larger datasets, integrating the model into clinical workflows, and exploring its use in personalized treatment planning.