To accelerate optical photon transport simulations in the GATE medical physics framework using a Generative Adversarial Network (GAN), while ensuring high modeling accuracy. Traditionally, detailed optical Monte Carlo methods have been the gold standard for modeling photon interactions in detectors, but their high computational cost remains a challenge. This study explores the integration of optiGAN, a Generative Adversarial Network (GAN) model into GATE 10, the new Python-based version of the GATE medical physics simulation framework released in November 2024.
Approach: The goal of optiGAN is to accelerate optical photon transport simulations while maintaining modelling accuracy. The optiGAN model, based on a GAN architecture, was integrated into GATE 10 as a computationally efficient alternative to traditional optical Monte Carlo simulations. To ensure consistency, optical photon transport modules were implemented in GATE 10 and validated against GATE v9.3 under identical simulation conditions. Subsequently, simulations using full Monte Carlo tracking in GATE 10 were compared to those using GATE 10-optiGAN.
Main results: Validation studies confirmed that GATE 10 produces results consistent with GATE v9.3. Simulations using GATE 10-optiGAN showed over 92% similarity to Monte Carlo-based GATE 10 results, based on the Jensen-Shannon distance across multiple photon transport parameters. optiGAN successfully captured multimodal distributions of photon position, direction, and energy at the photodetector face. Simulation time analysis revealed a reduction of approximately 50% in execution time with GATE 10-optiGAN compared to full Monte Carlo simulations.
Significance: The study confirms both the fidelity of optical photon transport modeling in GATE 10 and the effective integration of deep learning-based acceleration through optiGAN. This advancement enables large-scale, high-fidelity optical simulations with significantly reduced computational cost, supporting broader applications in medical imaging and detector design.

The present study aims to construct a random forest (RF) model based on ultrasound radiomics and elastography, offering a new approach for the differentiation of thyroid nodules (TNs). We retrospectively analyzed 152 TNs from 127 patients and developed four machine learning models. The examination was performed using the Resona 9Pro equipped with a 15-4 MHz linear array probe. The region of interest (ROI) was delineated with 3D Slicer. Using the RF algorithm, four models were developed based on sound touch elastography (STE) parameters, strain elastography (SE) parameters, and the selected radiomic features: the STE model, SE model, radiomics model, and the combined model. Decision Curve Analysis (DCA) is employed to assess the clinical benefit of each model. The DeLong test is used to determine whether the area under the curves (AUC) values of different models are statistically significant. A total of 1396 radiomic features were extracted using the Pyradiomics package. After screening, a total of 7 radiomic features were ultimately included in the construction of the model. In STE, SE, radiomics model, and combined model, the AUCs are 0.699 (95% CI: 0.570-0.828), 0.812 (95% CI: 0.683-0.941), 0.851 (95% CI: 0.739-0.964) and 0.911 (95% CI: 0.806-1.000), respectively. In these models, the combined model and the radiomics model exhibited outstanding performance. The combined model, integrating elastography and radiomics, demonstrates superior predictive accuracy compared to single models, offering a promising approach for the diagnosis of TNs.

Identification of the mandibular incisive canal (MIC) prior to anterior implant placement is often challenging. The present study aimed to validate an enhanced artificial intelligence (AI)-driven model dedicated to automated segmentation of MIC on cone beam computed tomography (CBCT) scans and to compare its accuracy and time efficiency with simultaneous segmentation of both mandibular canal (MC) and MIC by either human experts or a previously trained AI model. An enhanced AI model was developed based on 100 CBCT scans using expert-optimized MIC segmentation within the Virtual Patient Creator platform. The performance of the enhanced AI model was tested against human experts and a previously trained AI model using another 40 CBCT scans. Performance metrics included intersection over union (IoU), dice similarity coefficient (DSC), recall, precision, accuracy, and root mean square error (RSME). Time efficiency was also evaluated. The enhanced AI model had IoU of 93%, DSC of 93%, recall of 94%, precision of 93%, accuracy of 99%, and RMSE of 0.23 mm. These values were significantly higher than those of the previously trained AI model for all metrics, and for manual segmentation for IoU, DSC, recall, and accuracy (p < 0.0001). The enhanced AI model demonstrated significant time efficiency, completing segmentation in 17.6 s (125 times faster than manual segmentation) (p < 0.0001). The enhanced AI model proved to allow a unique and accurate automated MIC segmentation with high accuracy and time efficiency. Besides, its performance was superior to human expert segmentation and a previously trained AI model segmentation.

Vision-language models (VLMs) pre-trained at large scale have shown unprecedented transferability capabilities and are being progressively integrated into medical image analysis. Although its discriminative potential has been widely explored, its reliability aspect remains overlooked. This work investigates their behavior under the increasingly popular split conformal prediction (SCP) framework, which theoretically guarantees a given error level on output sets by leveraging a labeled calibration set. However, the zero-shot performance of VLMs is inherently limited, and common practice involves few-shot transfer learning pipelines, which cannot absorb the rigid exchangeability assumptions of SCP. To alleviate this issue, we propose full conformal adaptation, a novel setting for jointly adapting and conformalizing pre-trained foundation models, which operates transductively over each test data point using a few-shot adaptation set. Moreover, we complement this framework with SS-Text, a novel training-free linear probe solver for VLMs that alleviates the computational cost of such a transductive approach. We provide comprehensive experiments using 3 different modality-specialized medical VLMs and 9 adaptation tasks. Our framework requires exactly the same data as SCP, and provides consistent relative improvements of up to 27% on set efficiency while maintaining the same coverage guarantees.

Medical segmentation plays an important role in clinical applications like radiation therapy and surgical guidance, but acquiring clinically acceptable results is difficult. In recent years, progress has been witnessed with the success of utilizing transformer-like models, such as combining the attention mechanism with CNN. In particular, transformer-based segmentation models can extract global information more effectively, compensating for the drawbacks of CNN modules that focus on local features. However, utilizing transformer architecture is not easy, because training transformer-based models can be resource-demanding. Moreover, due to the distinct characteristics in the medical field, especially when encountering mid-sized and small organs with compact regions, their results often seem unsatisfactory. For example, using ViT to segment medical images directly only gives a DSC of less than 50\%, which is far lower than the clinically acceptable score of 80\%. In this paper, we used Mask2Former with deformable attention to reduce computation and proposed offset adjustment strategies to encourage sampling points within the same organs during attention weights computation, thereby integrating compact foreground information better. Additionally, we utilized the 4th feature map in Mask2Former to provide a coarse location of organs, and employed an FCN-based auxiliary head to help train Mask2Former more quickly using Dice loss. We show that our model achieves SOTA (State-of-the-Art) performance on the HaNSeg and SegRap2023 datasets, especially on mid-sized and small organs.Our code is available at link https://github.com/earis/Offsetadjustment\_Background-location\_Decoder\_Mask2former.

Deep convolutional neural networks (CNNs) are advancing rapidly in medical research, demonstrating promising results in diagnosis and prediction within radiology and pathology. This study evaluates the efficacy of deep learning algorithms for detecting and diagnosing dental caries using cone-beam computed tomography (CBCT) with the Mask R-CNN architecture while comparing various hyperparameters to enhance detection. A total of 2,128 CBCT images were divided into training and validation and test datasets in a 7:1:1 ratio. For the verification of tooth recognition, the data from the validation set were randomly selected for analysis. Three groups of Mask R-CNN networks were compared: A scratch-trained baseline using randomly initialized weights (R group); A transfer learning approach with models pre-trained on COCO for object detection (C group); A variant pre-trained on ImageNetfor for object detection (I group). All configurations maintained identical hyperparameter settings to ensure fair comparison. The deep learning model used ResNet-50 as the backbone network and was trained to 300epoch respectively. We assessed training loss, detection and training times, diagnostic accuracy, specificity, positive and negative predictive values, and coverage precision to compare performance across the groups. Transfer learning significantly reduced training times compared to non-transfer learning approach (p < 0.05). The average detection time for group R was 0.269 ± 0.176 s, whereas groups I (0.323 ± 0.196 s) and C (0.346 ± 0.195 s) exhibited significantly longer detection times (p < 0.05). C-group, trained for 200 epochs, achieved a mean average precision (mAP) of 81.095, outperforming all other groups. The mAP for caries recognition in group R, trained for 300 epochs, was 53.328, with detection times under 0.5 s. Overall, C-group demonstrated significantly higher average precision across all epochs (100, 200, and 300) (p < 0.05). Neural networks pre-trained with COCO transfer learning exhibit superior annotation accuracy compared to those pre-trained with ImageNet. This suggests that COCO's diverse and richly annotated images offer more relevant features for detecting dental structures and carious lesions. Furthermore, employing ResNet-50 as the backbone architecture enhances the detection of teeth and carious regions, achieving significant improvements with just 200 training epochs, potentially increasing the efficiency of clinical image interpretation.

Ocular and non-ocular diseases significantly impact millions of people worldwide, leading to vision impairment or blindness if not detected and managed early. Many individuals could be prevented from becoming blind by treating these diseases early on and stopping their progression. Despite advances in medical imaging and diagnostic tools, the manual detection of these diseases remains labor-intensive, time-consuming, and dependent on the expert's experience. Computer-aided diagnosis (CAD) has been transformed by machine learning (ML), providing promising methods for the automated detection and grading of diseases using various retinal imaging modalities. In this paper, we present a comprehensive systematic literature review that discusses the use of ML techniques to detect diseases from retinal images, utilizing both single and multi-modal imaging approaches. We analyze the efficiency of various Deep Learning and classical ML models, highlighting their achievements in accuracy, sensitivity, and specificity. Even with these advancements, the review identifies several critical challenges. We propose future research directions to address these issues. By overcoming these challenges, the potential of ML to enhance diagnostic accuracy and patient outcomes can be fully realized, opening the way for more reliable and effective ocular and non-ocular disease management.

Epiretinal membrane (ERM) is a vitreoretinal interface disease that, if not properly addressed, can lead to vision impairment and negatively affect quality of life. For ERM detection and treatment planning, Optical Coherence Tomography (OCT) has become the primary imaging modality, offering non-invasive, high-resolution cross-sectional imaging of the retina. Deep learning models have also led to good ERM detection performance on OCT images. Nevertheless, most deep learning models cannot be easily understood by clinicians, which limits their acceptance in clinical practice. Post-hoc explanation methods have been utilised to support the uptake of models, albeit, with partial success. In this study, we trained a sparse BagNet model, an inherently interpretable deep learning model, to detect ERM in OCT images. It performed on par with a comparable black-box model and generalised well to external data. In a multitask setting, it also accurately predicted other changes related to the ERM pathophysiology. Through a user study with ophthalmologists, we showed that the visual explanations readily provided by the sparse BagNet model for its decisions are well-aligned with clinical expertise. We propose potential directions for clinical implementation of the sparse BagNet model to guide clinical decisions in practice.

BackgroundAccurate histological grading of oral squamous cell carcinoma (OSCC) is critical for prognosis and treatment planning. Current methods lack automation for OSCC detection, subtyping, and differentiation from high-risk pre-malignant conditions like oral submucous fibrosis (OSMF). Further, analysis of whole-slide image (WSI) analysis is time-consuming and variable, limiting consistency. We present a clinically relevant deep learning framework that leverages weakly supervised learning and attention-based multiple instance learning (MIL) to enable automated OSCC grading and early prediction of malignant transformation from OSMF. MethodsWe conducted a multi-institutional retrospective cohort study using a curated dataset of 1,925 whole-slide images (WSIs), including 1,586 OSCC cases stratified into well-, moderately-, and poorly-differentiated subtypes (WD, MD, and PD), 128 normal controls, and 211 OSMF and OSMF with OSCC cases. We developed a two-stage deep learning pipeline named OralPatho. In stage one, an attention-based multiple instance learning (MIL) model was trained to perform binary classification (normal vs OSCC). In stage two, a gated attention mechanism with top-K patch selection was employed to classify the OSCC subtypes. Model performance was assessed using stratified 3-fold cross-validation and external validation on an independent dataset. FindingsThe binary classifier demonstrated robust performance with a mean F1-score exceeding 0.93 across all validation folds. The multiclass model achieved consistent macro-F1 scores of 0.72, 0.70, and 0.68, along with AUCs of 0.79 for WD, 0.71 for MD, and 0.61 for PD OSCC subtypes. Model generalizability was validated using an independent external dataset. Attention maps reliably highlighted clinically relevant histological features, supporting the systems interpretability and diagnostic alignment with expert pathological assessment. InterpretationThis study demonstrates the feasibility of attention-based, weakly supervised learning for accurate OSCC grading from whole-slide images. OralPatho combines high diagnostic performance with real-time interpretability, making it a scalable solution for both advanced pathology labs and resource-limited settings.

Sparse-view computed tomography (CT) is a practical solution to reduce radiation dose, but the resulting ill-posed inverse problem poses significant challenges for accurate image reconstruction. Although deep learning and diffusion-based methods have shown promising results, they often lack physical interpretability or suffer from high computational costs due to iterative sampling starting from random noise. Recent advances in generative modeling, particularly Poisson Flow Generative Models (PFGM), enable high-fidelity image synthesis by modeling the full data distribution. In this work, we propose Residual Poisson Flow (ResPF) Generative Models for efficient and accurate sparse-view CT reconstruction. Based on PFGM++, ResPF integrates conditional guidance from sparse measurements and employs a hijacking strategy to significantly reduce sampling cost by skipping redundant initial steps. However, skipping early stages can degrade reconstruction quality and introduce unrealistic structures. To address this, we embed a data-consistency into each iteration, ensuring fidelity to sparse-view measurements. Yet, PFGM sampling relies on a fixed ordinary differential equation (ODE) trajectory induced by electrostatic fields, which can be disrupted by step-wise data consistency, resulting in unstable or degraded reconstructions. Inspired by ResNet, we introduce a residual fusion module to linearly combine generative outputs with data-consistent reconstructions, effectively preserving trajectory continuity. To the best of our knowledge, this is the first application of Poisson flow models to sparse-view CT. Extensive experiments on synthetic and clinical datasets demonstrate that ResPF achieves superior reconstruction quality, faster inference, and stronger robustness compared to state-of-the-art iterative, learning-based, and diffusion models.