Accurately and efficiently estimating the cortical thickness from magnetic resonance images (MRIs) is crucial for neuroscientific studies and clinical applications with various large-scale datasets. Diffeomorphic registration-based cortical thickness estimation (DiReCT) is a prominent traditional method of calculating such measures directly from original MRIs by applying diffeomorphic registration on segmented tissues. However, it suffers from prolonged computational time and limited reproducibility, impediments to its application in large-scale studies or real-time environments. This paper proposes a framework for cortical thickness estimation using deep learning-based anatomy segmentation and diffeomorphic registration. The framework begins by applying a convolutional neural network (CNN) segmentation model to the original image, generating a segmentation map that accurately delineates the cortical boundaries. Subsequently, a pair of distance maps generated from the segmentation map is injected into an unsupervised learning-based registration network for fast and diffeomorphic registration. A novel algorithm based on diffeomorphisms of different time points is proposed to calculate the final thickness map. We systematically evaluated and compared our method with surface-based measures from FreeSurfer on two distinct datasets. The experimental results demonstrated a superior performance of the proposed method, surpassing the performance of DiReCT and DL+DiReCT in terms of time efficiency and consistency with FreeSurfer. Our code and pre-trained models are publicly available at: https://github.com/wujiong-hub/DL-CTE.git.

This study evaluated the performance of a multi-stage Segmentation Residual Network (SegResNet)-based deep learning (DL) model for the automatic segmentation of cone-beam computed tomography (CBCT) images of patients with stage III and IV periodontitis. Seventy pre-processed CBCT scans from patients undergoing periodontal rehabilitation were used for training and validation. The model was tested on 10 CBCT scans independent from the training dataset by comparing results with semi-automatic (SA) segmentations. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC), Intersection over Union (IoU), and Hausdorff distance 95^th percentile (HD95). Linear periodontal measurements were performed on four tooth surfaces to assess the validity of the DL segmentation in the periodontal region. The DL model achieved a mean DSC of 0.9650 ± 0.0097, with an IoU of 0.9340 ± 0.0180 and HD95 of 0.4820 mm ± 0.1269 mm, showing strong agreement with SA segmentation. Linear measurements revealed high statistical correlations between the mesial, distal, and lingual surfaces, with intraclass correlation coefficients (ICC) of 0.9442 (p<0.0001), 0.9232 (p<0.0001), and 0.9598(p<0.0001), respectively, while buccal measurements revealed lower consistency, with an ICC of 0.7481 (p<0.0001). The DL method reduced the segmentation time by 47 times compared to the SA method. Acquired 3D models may enable precise treatment planning in cases where conventional diagnostic modalities are insufficient. However, the robustness of the model must be increased to improve its general reliability and consistency at the buccal aspect of the periodontal region. This study presents a DL model for the CBCT-based segmentation of periodontal defects, demonstrating high accuracy and a 47-fold time reduction compared to SA methods, thus improving the feasibility of 3D diagnostics for advanced periodontitis.

Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models.

Computed tomography (CT) attenuation correction scans are an intrinsic part of positron emission tomography (PET) myocardial perfusion imaging using PET/CT, but anatomic information is rarely derived from these ultralow-dose CT scans. We aimed to assess the association between deep learning-derived cardiac chamber volumes (right atrial, right ventricular, left ventricular, and left atrial) and mass (left ventricular) from these scans with myocardial flow reserve and heart failure hospitalization. We included 18 079 patients with consecutive cardiac PET/CT from 6 sites. A deep learning model estimated cardiac chamber volumes and left ventricular mass from computed tomography attenuation correction imaging. Associations between deep learning-derived CT mass and volumes with heart failure hospitalization and reduced myocardial flow reserve were assessed in a multivariable analysis. During a median follow-up of 4.3 years, 1721 (9.5%) patients experienced heart failure hospitalization. Patients with 3 or 4 abnormal chamber volumes were 7× more likely to be hospitalized for heart failure compared with patients with normal volumes. In adjusted analyses, left atrial volume (hazard ratio [HR], 1.25 [95% CI, 1.19-1.30]), right atrial volume (HR, 1.29 [95% CI, 1.23-1.35]), right ventricular volume (HR, 1.25 [95% CI, 1.20-1.31]), left ventricular volume (HR, 1.27 [95% CI, 1.23-1.35]), and left ventricular mass (HR, 1.25 [95% CI, 1.18-1.32]) were independently associated with heart failure hospitalization. In multivariable analyses, left atrial volume (odds ratio, 1.14 [95% CI, 1.0-1.19]) and ventricular mass (odds ratio, 1.12 [95% CI, 1.6-1.17]) were independent predictors of reduced myocardial flow reserve. Deep learning-derived chamber volumes and left ventricular mass from computed tomography attenuation correction were predictive of heart failure hospitalization and reduced myocardial flow reserve in patients undergoing cardiac PET perfusion imaging. This anatomic data can be routinely reported along with other PET/CT parameters to improve risk prediction.

Currently, cervical anesthesia is performed using three main approaches: superficial cervical plexus block, deep cervical plexus block, and intermediate plexus nerve block. However, each technique carries inherent risks and demands significant clinical expertise. Ultrasound imaging, known for its real-time visualization capabilities and accessibility, is widely used in both diagnostic and interventional procedures. Nevertheless, accurate segmentation of small and irregularly shaped structures such as the cervical and brachial plexuses remains challenging due to image noise, complex anatomical morphology, and limited annotated training data. This study introduces DEMAC-Net-a dual-encoder, multiattention collaborative network-to significantly improve the segmentation accuracy of these neural structures. By precisely identifying the cervical nerve pathway (CNP) and adjacent anatomical tissues, DEMAC-Net aims to assist clinicians, especially those less experienced, in effectively guiding anesthesia procedures and accurately identifying optimal needle insertion points. Consequently, this improvement is expected to enhance clinical safety, reduce procedural risks, and streamline decision-making efficiency during ultrasound-guided regional anesthesia. DEMAC-Net combines a dual-encoder architecture with the Spatial Understanding Convolution Kernel (SUCK) and the Spatial-Channel Attention Module (SCAM) to extract multi-scale features effectively. Additionally, a Global Attention Gate (GAG) and inter-layer fusion modules refine relevant features while suppressing noise. A novel dataset, Neck Ultrasound Dataset (NUSD), was introduced, containing 1,500 annotated ultrasound images across seven anatomical regions. Extensive experiments were conducted on both NUSD and the BUSI public dataset, comparing DEMAC-Net to state-of-the-art models using metrics such as Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). On the NUSD dataset, DEMAC-Net achieved a mean DSC of 93.3%, outperforming existing models. For external validation on the BUSI dataset, it demonstrated superior generalization, achieving a DSC of 87.2% and a mean IoU of 77.4%, surpassing other advanced methods. Notably, DEMAC-Net displayed consistent segmentation stability across all tested structures. The proposed DEMAC-Net significantly improves segmentation accuracy for small nerves and complex anatomical structures in ultrasound images, outperforming existing methods in terms of accuracy and computational efficiency. This framework holds great potential for enhancing ultrasound-guided procedures, such as peripheral nerve blocks, by providing more precise anatomical localization, ultimately improving clinical outcomes.

We developed an AI-driven software solution to quantify metastatic bone disease from WB-DWI scans. Core technologies include: (i) a weakly-supervised Residual U-Net model generating a skeleton probability map to isolate bone; (ii) a statistical framework for WB-DWI intensity normalisation, obtaining a signal-normalised b=900s/mm^2 (b900) image; and (iii) a shallow convolutional neural network that processes outputs from (i) and (ii) to generate a mask of suspected bone lesions, characterised by higher b900 signal intensity due to restricted water diffusion. This mask is applied to the gADC map to extract TDV and gADC statistics. We tested the tool using expert-defined metastatic bone disease delineations on 66 datasets, assessed repeatability of imaging biomarkers (N=10), and compared software-based response assessment with a construct reference standard based on clinical, laboratory and imaging assessments (N=118). Dice score between manual and automated delineations was 0.6 for lesions within pelvis and spine, with an average surface distance of 2mm. Relative differences for log-transformed TDV (log-TDV) and median gADC were below 9% and 5%, respectively. Repeatability analysis showed coefficients of variation of 4.57% for log-TDV and 3.54% for median gADC, with intraclass correlation coefficients above 0.9. The software achieved 80.5% accuracy, 84.3% sensitivity, and 85.7% specificity in assessing response to treatment compared to the construct reference standard. Computation time generating a mask averaged 90 seconds per scan. Our software enables reproducible TDV and gADC quantification from WB-DWI scans for monitoring metastatic bone disease response, thus providing potentially useful measurements for clinical decision-making in APC patients.

Glioma is one of the most lethal types of brain tumors, accounting for approximately 33% of all diagnosed brain tumor cases. Accurate segmentation and classification are crucial for precise glioma characterization, emphasizing early detection of malignancy, effective treatment planning, and prevention of tumor progression. Magnetic Resonance Imaging (MRI) serves as a non-invasive imaging modality that allows detailed examination of gliomas without exposure to ionizing radiation. However, manual analysis of MRI scans is impractical, time-consuming, subjective, and requires specialized expertise from radiologists. To address this, computer-aided diagnosis (CAD) systems have greatly evolved as powerful tools to support neuro-oncologists in the brain cancer screening process. In this work, we present a glioma classification framework based on 3D multi-modal MRI segmentation using the CNN models SegResNet and Swin UNETR which incorporates transformer mechanisms for enhancing segmentation performance. MRI images undergo preprocessing with a Gaussian filter and skull stripping to improve tissue localization. Key textural features are then extracted from segmented tumor regions using Gabor Transform, Discrete Wavelet Transform (DWT), and deep features from ResNet50. These features are fused, normalized, and classified using a Support Vector Machine (SVM) to distinguish between Low-Grade Glioma (LGG) and High-Grade Glioma (HGG). Extensive experiments on benchmark datasets, including BRATS2020 and BRATS2023, demonstrate the effectiveness of the proposed approach. Our model achieved Dice scores of 0.815 for Tumor Core, 0.909 for Whole Tumor, and 0.829 for Enhancing Tumor. Concerning classification, the framework attained 97% accuracy, 94% precision, 96% recall, and a 95% F1-score. These results highlight the potential of the proposed framework to provide reliable support for radiologists in the early detection and classification of gliomas.

Sincalide-stimulated cholescintigraphy (SSC) calculates the gallbladder ejection fraction (GBEF) to diagnose functional gallbladder disorder. Currently, artificial intelligence (AI)-driven workflows that integrate real-time image processing and organ function calculation remain unexplored in nuclear medicine practice. This pilot study explored an AI-based application for gallbladder radioactivity tracking. We retrospectively analyzed 20 SSC exams, categorized into 10 easy and 10 challenging cases. Two human operators (H1 and H2) independently annotated the gallbladder regions of interest manually over the course of the 60-minute SSC. A U-Net-based deep learning model was developed to automatically segment gallbladder masks, and a 10-fold cross-validation was performed for both easy and challenging cases. The AI-generated masks were compared with human-annotated ones, with Dice similarity coefficients (DICE) used to assess agreement. AI achieved an average DICE of 0.746 against H1 and 0.676 against H2, performing better in easy cases (0.781) than in challenging ones (0.641). Visual inspection showed AI was prone to errors with patient motion or low-count activity. This study highlights AI's potential in real-time gallbladder tracking and GBEF calculation during SSC. AI-enabled real-time evaluation of nuclear imaging data holds promise for advancing clinical workflows by providing instantaneous organ function assessments and feedback to technologists. This AI-enabled workflow could enhance diagnostic efficiency, reduce scan duration, and improve patient comfort by alleviating symptoms associated with SSC, such as abdominal discomfort due to sincalide administration.

To evaluate the accuracy and reliability of a novel automated 3D CT-based method for measuring femoral neck anteversion (FNA) compared to three traditional manual methods. A total of 126 femurs from 63 full-length CT scans (35 men and 28 women; average age: 52.0 ± 14.7 years) were analyzed. The automated method used a deep learning network for femur segmentation, landmark identification, and anteversion calculation, with results generated based on two axes: Auto_GT (using the greater trochanter-to-intercondylar notch center axis) and Auto_P (using the piriformis fossa-to-intercondylar notch center axis). These results were validated through manual landmark annotation. The same dataset was assessed using three conventional manual methods: Murphy, Reikeras, and Lee methods. Intra- and inter-observer reliability were assessed using intraclass correlation coefficients (ICCs), and pairwise comparisons analyzed correlations and differences between methods. The automated methods produced consistent FNA measurements (Auto_GT: 17.59 ± 9.16° vs. Auto_P: 17.37 ± 9.17° on the right; 15.08 ± 9.88° vs. 14.84 ± 9.90° on the left). Intra-observer ICCs ranged from 0.864 to 0.961, and inter-observer ICCs between Auto_GT and the manual methods were high, except for the Lee method. No significant differences were observed between the two automated methods or between the automated and manual verification methods. Moreover, strong correlations (R > 0.9, p < 0.001) were found between Auto_GT and the manual methods. The novel automated 3D CT-based method demonstrates strong reproducibility and reliability for measuring femoral neck anteversion, with performance comparable to traditional manual techniques. These results indicate its potential utility for preoperative planning, postoperative evaluation, and computer-assisted orthopedic procedures. Not applicable.

Hip fractures, particularly among the elderly, impose a significant public health burden due to increased morbidity and mortality. Femoral neck fractures, commonly resulting from low-energy falls, can lead to severe complications such as avascular necrosis, and often necessitate total hip arthroplasty. This study harnesses AI to enhance musculoskeletal assessments by performing automatic muscle segmentation on whole thigh CT scans and detailed cortical measurements using the StradView program. The primary aim is to improve the prediction and prevention of severe femoral neck fractures, ultimately supporting more effective rehabilitation and treatment strategies. This study measured anatomical features from whole thigh CT scans of 60 femoral neck fracture patients. An AI-driven individual muscle segmentation model (a dice score of 0.84) segmented 27 muscles in the thigh region, to calculate muscle volumes. Proximal femoral bone parameters were measured using StradView, including average cortical thickness, inner density and FWHM at four regions. Correlation analysis evaluated relationships between muscle features, cortical parameters, and fracture displacement. Machine learning models (Random Forest, SVM and Multi-layer Perceptron) predicted displacement using these variables. Correlation analysis showed significant associations between femoral neck displacement and trabecular density at the femoral neck/intertrochanter, as well as volumes of specific thigh muscles such as the Tensor fasciae latae. Machine learning models using a combined feature set of thigh muscle volumes and proximal femoral parameters performed best in predicting displacement, with the Random Forest model achieving an F1 score of 0.91 and SVM model 0.93. Decreased volumes of the Tensor fasciae latae, Rectus femoris, and Semimembranosus muscles, coupled with reduced trabecular density at the femoral neck and intertrochanter, were significantly associated with increased fracture displacement. Notably, our SVM model-integrating both muscle and femoral features-achieved the highest predictive performance. These findings underscore the critical importance of muscle strength and bone density in rehabilitation planning and highlight the potential of AI-driven predictive models for improving clinical outcomes in femoral neck fractures.