Bronchopulmonary dysplasia (BPD) is a chronic lung disease affecting 35% of extremely low birth weight infants. Defined by oxygen dependence at 36 weeks postmenstrual age, it causes lifelong respiratory complications. However, preventive interventions carry severe risks, including neurodevelopmental impairment, ventilator-induced lung injury, and systemic complications. Therefore, early BPD prognosis and prediction of BPD outcome is crucial to avoid unnecessary toxicity in low risk infants. Admission radiographs of extremely preterm infants are routinely acquired within 24h of life and could serve as a non-invasive prognostic tool. In this work, we developed and investigated a deep learning approach using chest X-rays from 163 extremely low-birth-weight infants ($\leq$32 weeks gestation, 401-999g) obtained within 24 hours of birth. We fine-tuned a ResNet-50 pretrained specifically on adult chest radiographs, employing progressive layer freezing with discriminative learning rates to prevent overfitting and evaluated a CutMix augmentation and linear probing. For moderate/severe BPD outcome prediction, our best performing model with progressive freezing, linear probing and CutMix achieved an AUROC of 0.78 $\pm$ 0.10, balanced accuracy of 0.69 $\pm$ 0.10, and an F1-score of 0.67 $\pm$ 0.11. In-domain pre-training significantly outperformed ImageNet initialization (p = 0.031) which confirms domain-specific pretraining to be important for BPD outcome prediction. Routine IRDS grades showed limited prognostic value (AUROC 0.57 $\pm$ 0.11), confirming the need of learned markers. Our approach demonstrates that domain-specific pretraining enables accurate BPD prediction from routine day-1 radiographs. Through progressive freezing and linear probing, the method remains computationally feasible for site-level implementation and future federated learning deployments.

Endovascular aortic aneurysm repair (EVAR) requires long-term surveillance to detect and treat postoperative complications. However, prediction models to optimise follow-up strategies are still lacking. The primary objective of this study is to develop predictive models of post-operative outcomes following elective EVAR using Artificial Intelligence (AI)-driven analysis. The secondary objective is to investigate morphological aortic changes following EVAR. This international, multicentre, observational study will retrospectively include 500 patients who underwent elective EVAR. Primary outcomes are EVAR postoperative complications including deaths, re-interventions, endoleaks, limb occlusion and stent-graft migration occurring within 1 year and at mid-term follow-up (1 to 3 years). Secondary outcomes are aortic anatomical changes. Morphological changes following EVAR will be analysed and compared based on preoperative and postoperative CT angiography (CTA) images (within 1 to 12 months, and at the last follow-up) using the AI-based software PRAEVAorta 2 (Nurea). Deep learning algorithms will be applied to stratify the risk of postoperative outcomes into low or high-risk categories. The training and testing dataset will be respectively composed of 70% and 30% of the cohort. The study protocol is designed to ensure that the sponsor and the investigators comply with the principles of the Declaration of Helsinki and the ICH E6 good clinical practice guideline. The study has been approved by the ethics committee of the University Hospital of Patras (Patras, Greece) under the number 492/05.12.2024. The results of the study will be presented at relevant national and international conferences and submitted for publication to peer-review journals.

The accurate early-stage diagnosis of gallbladder cancer (GBC) is regarded as one of the major challenges in the field of oncology. However, few studies have focused on the comprehensive classification of GBC based on multiple modalities. This study aims to develop a comprehensive diagnostic framework for GBC based on both imaging and non-imaging medical data. This retrospective study reviewed 298 clinical patients with gallbladder disease or volunteers from two devices. A novel end-to-end interpretable diagnostic framework for GBC is proposed to handle multiple medical modalities, including CT imaging, demographics, tumor markers, coagulation function tests, and routine blood tests. To achieve better feature extraction and fusion of the imaging modality, a novel global-hybrid-local network, namely GHL-Net, has also been developed. The ensemble learning strategy is employed to fuse multi-modality data and obtain the final classification result. In addition, two interpretable methods are applied to help clinicians understand the model-based decisions. Model performance was evaluated through accuracy, precision, specificity, sensitivity, F1-score, area under the curve (AUC), and matthews correlation coefficient (MCC). In both binary and multi-class classification scenarios, the proposed method showed better performance compared to other comparison methods in both datasets. Especially in the binary classification scenario, the proposed method achieved the highest accuracy, sensitivity, specificity, precision, F1-score, ROC-AUC, PR-AUC, and MCC of 95.24%, 93.55%, 96.87%, 96.67%, 95.08%, 0.9591, 0.9636, and 0.9051, respectively. The visualization results obtained based on the interpretable methods also demonstrated a high clinical relevance of the intermediate decision-making processes. Ablation studies then provided an in-depth understanding of our methodology. The machine learning-based framework can effectively improve the accuracy of GBC diagnosis and is expected to have a more significant impact in other cancer diagnosis scenarios.

Diabetes mellitus (DM) is a serious global health concern that poses a significant threat to human life. Beyond its direct impact, diabetes substantially increases the risk of developing severe complications such as hypertension, cardiovascular disease, and musculoskeletal disorders like arthritis and osteoporosis. The field of diabetes classification has advanced significantly with the use of diverse data modalities and sophisticated tools to identify individuals or groups as diabetic. But the task of predicting diabetes prior to its onset, particularly through the use of longitudinal multi-modal data, remains relatively underexplored. To better understand the risk factors associated with diabetes development among Qatari adults, this longitudinal research aims to investigate dual-energy X-ray absorptiometry (DXA)-derived whole-body and regional bone composition measures as potential predictors of diabetes onset. We proposed a case-control retrospective study, with a total of 1,382 participants contains 725 male participants (cases: 146, control: 579) and 657 female participants (case: 133, control: 524). We excluded participants with incomplete data points. To handle class imbalance, we augmented our data using Synthetic Minority Over-sampling Technique (SMOTE) and SMOTEENN (SMOTE with Edited Nearest Neighbors), and to further investigated the association between bones data features and diabetes status, we employed ANOVA analytical method. For diabetes onset prediction, we employed both conventional and deep learning (DL) models to predict risk factors associated with diabetes in Qatari adults. We used SHAP and probabilistic methods to investigate the association of identified risk factors with diabetes. During experimental analysis, we found that bone mineral density (BMD), bone mineral contents (BMC) in the hip, femoral neck, troch area, and lumbar spine showed an upward trend in diabetic patients with [Formula: see text]. Meanwhile, we found that patients with abnormal glucose metabolism had increased wards BMD and BMC with low Z-score compared to healthy participants. Consequently, it shows that the diabetic group has superior bone health than the control group in the cohort, because they exhibit higher BMD, muscle mass, and bone area across most body regions. Moreover, in the age group distribution analysis, we found that the diabetes prediction rate was higher among healthy participants in the younger age group 20-40 years. But as the age range increased, the model predictions became more accurate for diabetic participants, especially in the older age group 56-69 years. It is also observed that male participants demonstrated a higher susceptibility to diabetes onset compared to female participants. Shallow models outperformed the DL models by presenting improved accuracy (91.08%), AUROC (96%), and recall values (91%). This pivotal approach utilizing DXA scans highlights significant potential for the rapid and minimally invasive early detection of diabetes.

Quantifiable image patterns associated with disease progression and treatment response are critical tools for guiding individual treatment, and for developing novel therapies. Here, we show that unsupervised machine learning can identify a pattern vocabulary of liver tissue in magnetic resonance images that quantifies treatment response in diffuse liver disease. Deep clustering networks simultaneously encode and cluster patches of medical images into a low-dimensional latent space to establish a tissue vocabulary. The resulting tissue types capture differential tissue change and its location in the liver associated with treatment response. We demonstrate the utility of the vocabulary on a randomized controlled trial cohort of non-alcoholic steatohepatitis patients. First, we use the vocabulary to compare longitudinal liver change in a placebo and a treatment cohort. Results show that the method identifies specific liver tissue change pathways associated with treatment, and enables a better separation between treatment groups than established non-imaging measures. Moreover, we show that the vocabulary can predict biopsy derived features from non-invasive imaging data. We validate the method on a separate replication cohort to demonstrate the applicability of the proposed method.

Deep learning has significantly advanced the field of medical image classification, particularly with the adoption of Convolutional Neural Networks (CNNs). Various deep learning frameworks such as Keras, PyTorch and JAX offer unique advantages in model development and deployment. However, their comparative performance in medical imaging tasks remains underexplored. This study presents a comprehensive analysis of CNN implementations across these frameworks, using the PathMNIST dataset as a benchmark. We evaluate training efficiency, classification accuracy and inference speed to assess their suitability for real-world applications. Our findings highlight the trade-offs between computational speed and model accuracy, offering valuable insights for researchers and practitioners in medical image analysis.

Bronchopulmonary dysplasia (BPD) is a chronic lung disease affecting 35% of extremely low birth weight infants. Defined by oxygen dependence at 36 weeks postmenstrual age, it causes lifelong respiratory complications. However, preventive interventions carry severe risks, including neurodevelopmental impairment, ventilator-induced lung injury, and systemic complications. Therefore, early BPD prognosis and prediction of BPD outcome is crucial to avoid unnecessary toxicity in low risk infants. Admission radiographs of extremely preterm infants are routinely acquired within 24h of life and could serve as a non-invasive prognostic tool. In this work, we developed and investigated a deep learning approach using chest X-rays from 163 extremely low-birth-weight infants ($\leq$32 weeks gestation, 401-999g) obtained within 24 hours of birth. We fine-tuned a ResNet-50 pretrained specifically on adult chest radiographs, employing progressive layer freezing with discriminative learning rates to prevent overfitting and evaluated a CutMix augmentation and linear probing. For moderate/severe BPD outcome prediction, our best performing model with progressive freezing, linear probing and CutMix achieved an AUROC of 0.78 $\pm$ 0.10, balanced accuracy of 0.69 $\pm$ 0.10, and an F1-score of 0.67 $\pm$ 0.11. In-domain pre-training significantly outperformed ImageNet initialization (p = 0.031) which confirms domain-specific pretraining to be important for BPD outcome prediction. Routine IRDS grades showed limited prognostic value (AUROC 0.57 $\pm$ 0.11), confirming the need of learned markers. Our approach demonstrates that domain-specific pretraining enables accurate BPD prediction from routine day-1 radiographs. Through progressive freezing and linear probing, the method remains computationally feasible for site-level implementation and future federated learning deployments.

Radiologists rely on eye movements to navigate and interpret medical images. A trained radiologist possesses knowledge about the potential diseases that may be present in the images and, when searching, follows a mental checklist to locate them using their gaze. This is a key observation, yet existing models fail to capture the underlying intent behind each fixation. In this paper, we introduce a deep learning-based approach, RadGazeIntent, designed to model this behavior: having an intention to find something and actively searching for it. Our transformer-based architecture processes both the temporal and spatial dimensions of gaze data, transforming fine-grained fixation features into coarse, meaningful representations of diagnostic intent to interpret radiologists' goals. To capture the nuances of radiologists' varied intention-driven behaviors, we process existing medical eye-tracking datasets to create three intention-labeled subsets: RadSeq (Systematic Sequential Search), RadExplore (Uncertainty-driven Exploration), and RadHybrid (Hybrid Pattern). Experimental results demonstrate RadGazeIntent's ability to predict which findings radiologists are examining at specific moments, outperforming baseline methods across all intention-labeled datasets.

Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Very recently, SAEs were also adopted for the visual domain, enabling the discovery of visual concepts and their patch-wise attribution to tokens in the transformer model. While a growing number of foundation models emerged for medical imaging, tools for explaining their inferences are still lacking. In this work, we show the applicability of SAEs for hematology. We propose CytoSAE, a sparse autoencoder which is trained on over 40,000 peripheral blood single-cell images. CytoSAE generalizes to diverse and out-of-domain datasets, including bone marrow cytology, where it identifies morphologically relevant concepts which we validated with medical experts. Furthermore, we demonstrate scenarios in which CytoSAE can generate patient-specific and disease-specific concepts, enabling the detection of pathognomonic cells and localized cellular abnormalities at the patch level. We quantified the effect of concepts on a patient-level AML subtype classification task and show that CytoSAE concepts reach performance comparable to the state-of-the-art, while offering explainability on the sub-cellular level. Source code and model weights are available at https://github.com/dynamical-inference/cytosae.

The prediction and management of sudden cardiac death risk continue to pose significant challenges in cardiovascular care despite advances in therapies over the last two decades. Late gadolinium enhancement (LGE) on cardiac magnetic resonance-a marker of myocardial fibrosis-is a powerful non-invasive tool with the potential to aid the prediction of sudden death and direct the use of preventative therapies in several cardiovascular conditions. In this state-of-the-art review, we provide a critical appraisal of the current evidence base underpinning the utility of LGE in both ischaemic and non-ischaemic cardiomyopathies together with a focus on future perspectives and the role for machine learning and digital twin technologies.