Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.

This review explores the transformative role of artificial intelligence (AI) in the early detection and prognosis prediction of diabetic retinopathy (DR), a leading cause of vision loss in diabetic patients. AI, particularly deep learning and convolutional neural networks (CNNs), has demonstrated remarkable accuracy in analyzing retinal images, identifying early-stage DR with high sensitivity and specificity. These advancements address critical challenges such as intergrader variability in manual screening and the limited availability of specialists, especially in underserved regions. The integration of AI with telemedicine has further enhanced accessibility, enabling remote screening through portable devices and smartphone-based imaging. Economically, AI-based systems reduce healthcare costs by optimizing resource allocation and minimizing unnecessary referrals. Key findings highlight the dominance of Medicine (819 documents) and Computer Science (613 documents) in research output, reflecting the interdisciplinary nature of this field. Geographically, China, the United States, and India lead in contributions, underscoring global efforts to combat DR. Despite these successes, challenges such as algorithmic bias, data privacy, and the need for explainable AI (XAI) remain. Future research should focus on multi-center validation, diverse AI methodologies, and clinician-friendly tools to ensure equitable adoption. By addressing these gaps, AI can revolutionize DR management, reducing the global burden of diabetes-related blindness through early intervention and scalable solutions.

Large language models (LLMs) like ChatGPT are increasingly used in medicine due to their ability to synthesize information and support clinical decision-making. While prior research has evaluated ChatGPT's performance on medical board exams, limited data exist on radiology-specific exams especially considering prompt strategies and input modalities. This meta-analysis reviews ChatGPT's performance on radiology board-style questions, assessing accuracy across radiology subspecialties, prompt engineering methods, GPT model versions, and input modalities. Searches in PubMed and SCOPUS identified 163 articles, of which 16 met inclusion criteria after excluding irrelevant topics and non-board exam evaluations. Data extracted included subspecialty topics, accuracy, question count, GPT model, input modality, prompting strategies, and access dates. Statistical analyses included two-proportion z-tests, a binomial generalized linear model (GLM), and meta-regression with random effects (Stata v18.0, R v4.3.1). Across 7024 questions, overall accuracy was 58.83 % (95 % CI, 55.53-62.13). Performance varied widely by subspecialty, highest in emergency radiology (73.00 %) and lowest in musculoskeletal radiology (49.24 %). GPT-4 and GPT-4o significantly outperformed GPT-3.5 (p < .001), but visual inputs yielded lower accuracy (46.52 %) compared to textual inputs (67.10 %, p < .001). Prompting strategies showed significant improvement (p < .01) with basic prompts (66.23 %) compared to no prompts (59.70 %). A modest but significant decline in performance over time was also observed (p < .001). ChatGPT demonstrates promising but inconsistent performance in radiology board-style questions. Limitations in visual reasoning, heterogeneity across studies, and prompt engineering variability highlight areas requiring targeted optimization.

Background & purposeLate radiation-associated dysphagia after head and neck cancer (HNC) significantly impacts patients health and quality of life. Conventional normal tissue complication probability (NTCP) models use discrete dose parameters to predict toxicity risk but fail to fully capture the complexity of this side effect. Deep learning (DL) offers potential improvements by incorporating 3D dose data for all anatomical structures involved in swallowing. This study aims to enhance dysphagia prediction with 3D DL NTCP models compared to conventional NTCP models. Materials & methodsA multi-institutional cohort of 1484 HNC patients was used to train and validate a 3D DL model (Residual Network) incorporating 3D dose distributions, organ-at-risk segmentations, and CT scans, with or without patient- or treatment-related data. Predictions of grade [&ge;]2 dysphagia (CTCAEv4) at six months post-treatment were evaluated using area under the curve (AUC) and calibration curves. Results were compared to a conventional NTCP model based on pre-treatment dysphagia, tumour location, and mean dose to swallowing organs. Attention maps highlighting regions of interest for individual patients were assessed. ResultsDL models outperformed the conventional NTCP model in both the independent test set (AUC=0.80-0.84 versus 0.76) and external test set (AUC=0.73-0.74 versus 0.63) in AUC and calibration. Attention maps showed a focus on the oral cavity and superior pharyngeal constrictor muscle. ConclusionDL NTCP models performed better than the conventional NTCP model, suggesting the benefit of using 3D-input over the conventional discrete dose parameters. Attention maps highlighted relevant regions linked to dysphagia, supporting the utility of DL for improved predictions.

PurposeTo develop a deep learning model - Cornea nnU-Net Extractor (CUNEX) - for full-thickness corneal segmentation of anterior segment optical coherence tomography (AS-OCT) images and evaluate its utility in artificial intelligence (AI) research. MethodsWe trained and evaluated CUNEX using nnU-Net on 600 AS-OCT images (CSO MS-39) from 300 patients: 100 normal, 100 keratoconus (KC), and 100 Fuchs endothelial corneal dystrophy (FECD) eyes. To assess generalizability, we externally validated CUNEX on 1,168 AS-OCT images from an infectious keratitis dataset acquired from a different device (Casia SS-1000). We benchmarked CUNEX against two recent models, CorneaNet and ScLNet. We then applied CUNEX to our dataset of 194,599 scans from 37,499 patients as preprocessing for a classification model evaluating whether segmentation improves AI prediction, including age, sex, and disease staging (KC and FECD). ResultsCUNEX achieved Dice similarity coefficient (DSC) and intersection over union (IoU) scores ranging from 94-95% and 90-99%, respectively, across healthy, KC, and FECD eyes. This was similar to ScLNet (within 3%) but better than CorneaNet (8-35% lower). On external validation, CUNEX maintained high performance (DSC 83%; IoU 71%) while ScLNet (DSC 14%; IoU 8%) and CorneaNet (DSC 16%; IoU 9%) failed to generalize. Unexpectedly, segmentation minimally impacted classification accuracy except for sex prediction, where accuracy dropped from 81 to 68%, suggesting sex-related features may lie outside the cornea. ConclusionCUNEX delivers the first open-source generalizable corneal segmentation model using the latest framework, supporting its use in clinical analysis and AI workflows across diseases and imaging platforms. It is available at https://github.com/lkandakji/CUNEX.

In acute neck infections, magnetic resonance imaging (MRI) shows retropharyngeal edema (RPE), which is a prognostic imaging biomarker for a severe course of illness. This study aimed to develop a deep learning-based algorithm for the automated detection of RPE. We developed a deep neural network consisting of two parts using axial T2-weighted water-only Dixon MRI images from 479 patients with acute neck infections annotated by radiologists at both slice and patient levels. First, a convolutional neural network (CNN) classified individual slices; second, an algorithm classified patients based on a stack of slices. Model performance was compared with the radiologists' assessment as a reference standard. Accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUROC) were calculated. The proposed CNN was compared with InceptionV3, and the patient-level classification algorithm was compared with traditional machine learning models. Of the 479 patients, 244 (51%) were positive and 235 (49%) negative for RPE. Our model achieved accuracy, sensitivity, specificity, and AUROC of 94.6%, 83.3%, 96.2%, and 94.1% at the slice level, and 87.4%, 86.5%, 88.2%, and 94.8% at the patient level, respectively. The proposed CNN was faster than InceptionV3 but equally accurate. Our patient classification algorithm outperformed traditional machine learning models. A deep learning model, based on weakly annotated data and computationally manageable training, achieved high accuracy for automatically detecting RPE on MRI in patients with acute neck infections. Our automated method for detecting relevant MRI findings was efficiently trained and might be easily deployed in practice to study clinical applicability. This approach might improve early detection of patients at high risk for a severe course of acute neck infections. Deep learning automatically detected retropharyngeal edema on MRI in acute neck infections. Areas under the receiver operating characteristic curve were 94.1% at the slice level and 94.8% at the patient level. The proposed convolutional neural network was lightweight and required only weakly annotated data.

Academic integrity is crucial in dental education, especially during practical exams assessing competencies. Traditional oversight may not detect sophisticated academic dishonesty methods like radiograph substitution or tampering. This study aimed to develop and evaluate a novel artificial intelligence (AI) model utilizing a Siamese neural network to detect inconsistencies in radiographic images taken for root canal treatment (RCT) procedures in preclinical endodontic courses, thereby enhancing educational integrity. A Siamese neural network was designed to compare radiographs from different RCT procedures. The model was trained on 3390 radiographs, with data augmentation applied to improve generalizability. The dataset was split into training, validation, and testing subsets. Performance metrics included accuracy, precision, sensitivity (recall), and F1-score. Cross-validation and hyperparameter tuning optimized the model. Our AI model achieved an accuracy of 89.31%, a precision of 76.82%, a sensitivity of 84.82%, and an F1-score of 80.50%. The optimal similarity threshold was 0.48, where maximum accuracy was observed. The confusion matrix indicated a high rate of correct classifications, and cross-validation confirmed the model's robustness with a standard deviation of 1.95% across folds. The AI-driven Siamese neural network effectively detects radiographic inconsistencies in RCT preclinical procedures. Implementing this novel model will serve as an objective tool to uphold academic integrity in dental education, enhance the fairness and reliability of assessments, promote a culture of honesty amongst students, and reduce the administrative burden on educators.

BackgroundLimited-angle Computed Tomography imaging suffers from severe artifacts in the reconstructed image due to incomplete projection data. Deep learning methods have been developed currently to address the challenges of robustness and low contrast of the limited-angle CT reconstruction with a relatively effective way.ObjectiveTo improve the low contrast of the current limited-angle CT reconstruction image, enhance the robustness of the reconstruction method and the contrast of the limited-angle image.MethodIn this paper, we proposed a limited-angle CT reconstruction method that combining the Fourier domain reweighting and wavelet domain enhancement, which fused information from different domains, thereby getting high-resolution reconstruction images.ResultsWe verified the feasibility and effectiveness of the proposed solution through experiments, and the reconstruction results are improved compared with the state-of-the-art methods.ConclusionsThe proposed method enhances some features of the original image domain data from different domains, which is beneficial to the reasonable diffusion and restoration of diffuse detail texture features.

As the frontline data for cancer diagnosis, microscopic pathology images are fundamental for providing patients with rapid and accurate treatment. However, despite their practical value, the deep learning community has largely overlooked their usage. This paper proposes a novel approach to classifying microscopy images as time series data, addressing the unique challenges posed by their manual acquisition and weakly labeled nature. The proposed method fits image sequences of varying lengths to a fixed-length target by leveraging Dynamic Time-series Warping (DTW). Attention-based pooling is employed to predict the class of the case simultaneously. We demonstrate the effectiveness of our approach by comparing performance with various baselines and showcasing the benefits of using various inference strategies in achieving stable and reliable results. Ablation studies further validate the contribution of each component. Our approach contributes to medical image analysis by not only embracing microscopic images but also lifting them to a trustworthy level of performance.

<b>Background/Objectives</b>: Different sized calcified masses called pulp stones are often detected in dental pulp and can impact dental procedures. The current research was conducted with the aim of measuring the ability of artificial intelligence algorithms to accurately diagnose pulp and pulp stone calcifications on panoramic radiographs. <b>Methods</b>: We used 713 panoramic radiographs, on which a minimum of one pulp stone was detected, identified retrospectively, and included in the study-4675 pulp stones and 5085 pulps were marked on these radiographs using CVAT v1.7.0 labeling software. <b>Results</b>: In the test dataset, the AI model segmented 462 panoramic radiographs for pulp stone and 220 panoramic radiographs for pulp. The dice coefficient and Intersection over Union (IoU) recorded for the Pulp Segmentation model were 0.84 and 0.758, respectively. Precision and recall were computed to be 0.858 and 0.827, respectively. The Pulp Stone Segmentation model achieved a dice coefficient of 0.759 and an IoU of 0.686, with precision and recall of 0.792 and 0.773, respectively. <b>Conclusions</b>: Pulp and pulp stones can successfully be identified using artificial intelligence algorithms. This study provides evidence that artificial intelligence software using deep learning algorithms can be valuable adjunct tools in aiding clinicians in radiographic diagnosis. Further research in which larger datasets are examined are needed to enhance the capability of artificial intelligence models to make accurate diagnoses.