Data binary encoding has proven to be a versatile tool for optimizing data processing and memory efficiency in various machine learning applications. This includes deep barcoding, generating barcodes from deep learning feature extraction for image retrieval of similar cases among millions of indexed images. Despite the recent advancement in barcode generation methods, converting high-dimensional feature vectors (e.g., deep features) to compact and discriminative binary barcodes is still an urgent necessity and remains an unresolved problem. Difference-based binarization of features is one of the most efficient binarization methods, transforming continuous feature vectors into binary sequences and capturing trend information. However, the performance of this method is highly dependent on the ordering of the input features, leading to a significant combinatorial challenge. This research addresses this problem by optimizing feature sequences based on retrieval performance metrics. Our approach identifies optimal feature orderings, leading to substantial improvements in retrieval effectiveness compared to arbitrary or default orderings. We assess the performance of the proposed approach in various medical and non-medical image retrieval tasks. This evaluation includes medical images from The Cancer Genome Atlas (TCGA), a comprehensive publicly available dataset, as well as COVID-19 Chest X-rays dataset. In addition, we evaluate the proposed approach on non-medical benchmark image datasets, such as CIFAR-10, CIFAR-100, and Fashion-MNIST. Our findings demonstrate the importance of optimizing binary barcode representation to significantly enhance accuracy for fast image retrieval across a wide range of applications, highlighting the applicability and potential of barcodes in various domains.

Multimodal electronic health record (EHR) data provide richer, complementary insights into patient health compared to single-modality data. However, effectively integrating diverse data modalities for clinical prediction modeling remains challenging due to the substantial data requirements. We introduce a novel architecture, Mixture-of-Multimodal-Agents (MoMA), designed to leverage multiple large language model (LLM) agents for clinical prediction tasks using multimodal EHR data. MoMA employs specialized LLM agents ("specialist agents") to convert non-textual modalities, such as medical images and laboratory results, into structured textual summaries. These summaries, together with clinical notes, are combined by another LLM ("aggregator agent") to generate a unified multimodal summary, which is then used by a third LLM ("predictor agent") to produce clinical predictions. Evaluating MoMA on three prediction tasks using real-world datasets with different modality combinations and prediction settings, MoMA outperforms current state-of-the-art methods, highlighting its enhanced accuracy and flexibility across various tasks.

Magnetic resonance (MR)-to-computed tomography (CT) translation offers significant advantages, including the elimination of radiation exposure associated with CT scans and the mitigation of imaging artifacts caused by patient motion. The existing approaches are based on single-modality MR-to-CT translation, with limited research exploring multimodal fusion. To address this limitation, we introduce Multi-modal MR to CT (MM2CT) translation method by leveraging multimodal T1- and T2-weighted MRI data, an innovative Mamba-based framework for multi-modal medical image synthesis. Mamba effectively overcomes the limited local receptive field in CNNs and the high computational complexity issues in Transformers. MM2CT leverages this advantage to maintain long-range dependencies modeling capabilities while achieving multi-modal MR feature integration. Additionally, we incorporate a dynamic local convolution module and a dynamic enhancement module to improve MRI-to-CT synthesis. The experiments on a public pelvis dataset demonstrate that MM2CT achieves state-of-the-art performance in terms of Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR). Our code is publicly available at https://github.com/Gots-ch/MM2CT.

This study presents an unsupervised deep learning approach for computed tomography (CT) image reconstruction, leveraging the inherent similarities between deep neural network training and conventional iterative reconstruction methods. By incorporating forward and backward projection layers within the deep learning framework, we demonstrate the feasibility of reconstructing images from projection data without relying on ground-truth images. Our method is evaluated on the two-dimensional 2DeteCT dataset, showcasing superior performance in terms of mean squared error (MSE) and structural similarity index (SSIM) compared to traditional filtered backprojection (FBP) and maximum likelihood (ML) reconstruction techniques. Additionally, our approach significantly reduces reconstruction time, making it a promising alternative for real-time medical imaging applications. Future work will focus on extending this methodology to three-dimensional reconstructions and enhancing the adaptability of the projection geometry.

Artifacts pose a significant challenge in medical imaging, impacting diagnostic accuracy and downstream analysis. While image-based approaches for detecting artifacts can be effective, they often rely on preprocessing methods that can lead to information loss and high-memory-demand medical images, thereby limiting the scalability of classification models. In this work, we propose the use of implicit neural representations (INRs) for image quality assessment. INRs provide a compact and continuous representation of medical images, naturally handling variations in resolution and image size while reducing memory overhead. We develop deep weight space networks, graph neural networks, and relational attention transformers that operate on INRs to achieve image quality assessment. Our method is evaluated on the ACDC dataset with synthetically generated artifact patterns, demonstrating its effectiveness in assessing image quality while achieving similar performance with fewer parameters.

AI-powered medical devices have driven the need for real-time, on-device inference such as biomedical image classification. Deployment of deep learning models at the edge is now used for applications such as anomaly detection and classification in medical images. However, achieving this level of performance on edge devices remains challenging due to limitations in model size and computational capacity. To address this, we present MedMambaLite, a hardware-aware Mamba-based model optimized through knowledge distillation for medical image classification. We start with a powerful MedMamba model, integrating a Mamba structure for efficient feature extraction in medical imaging. We make the model lighter and faster in training and inference by modifying and reducing the redundancies in the architecture. We then distill its knowledge into a smaller student model by reducing the embedding dimensions. The optimized model achieves 94.5% overall accuracy on 10 MedMNIST datasets. It also reduces parameters 22.8x compared to MedMamba. Deployment on an NVIDIA Jetson Orin Nano achieves 35.6 GOPS/J energy per inference. This outperforms MedMamba by 63% improvement in energy per inference.

As medical imaging is central to diagnostic processes, automating the generation of radiology reports has become increasingly relevant to assist radiologists with their heavy workloads. Most current methods rely solely on global image features, failing to capture fine-grained organ relationships crucial for accurate reporting. To this end, we propose CT-GRAPH, a hierarchical graph attention network that explicitly models radiological knowledge by structuring anatomical regions into a graph, linking fine-grained organ features to coarser anatomical systems and a global patient context. Our method leverages pretrained 3D medical feature encoders to obtain global and organ-level features by utilizing anatomical masks. These features are further refined within the graph and then integrated into a large language model to generate detailed medical reports. We evaluate our approach for the task of report generation on the large-scale chest CT dataset CT-RATE. We provide an in-depth analysis of pretrained feature encoders for CT report generation and show that our method achieves a substantial improvement of absolute 7.9\% in F1 score over current state-of-the-art methods. The code is publicly available at https://github.com/hakal104/CT-GRAPH.

Medical image understanding plays a crucial role in enabling automated diagnosis and data-driven clinical decision support. However, its progress is impeded by two primary challenges: the limited availability of high-quality annotated medical data and an overreliance on global image features, which often miss subtle but clinically significant pathological regions. To address these issues, we introduce RegionMed-CLIP, a region-aware multimodal contrastive learning framework that explicitly incorporates localized pathological signals along with holistic semantic representations. The core of our method is an innovative region-of-interest (ROI) processor that adaptively integrates fine-grained regional features with the global context, supported by a progressive training strategy that enhances hierarchical multimodal alignment. To enable large-scale region-level representation learning, we construct MedRegion-500k, a comprehensive medical image-text corpus that features extensive regional annotations and multilevel clinical descriptions. Extensive experiments on image-text retrieval, zero-shot classification, and visual question answering tasks demonstrate that RegionMed-CLIP consistently exceeds state-of-the-art vision language models by a wide margin. Our results highlight the critical importance of region-aware contrastive pre-training and position RegionMed-CLIP as a robust foundation for advancing multimodal medical image understanding.

Medical image segmentation plays a crucial role in AI-assisted diagnostics, surgical planning, and treatment monitoring. Accurate and robust segmentation models are essential for enabling reliable, data-driven clinical decision making across diverse imaging modalities. Given the inherent variability in image characteristics across modalities, developing a unified model capable of generalizing effectively to multiple modalities would be highly beneficial. This model could streamline clinical workflows and reduce the need for modality-specific training. However, real-world deployment faces major challenges, including data scarcity, domain shift between modalities (e.g., CT vs. MRI), and privacy restrictions that prevent data sharing. To address these issues, we propose FedGIN, a Federated Learning (FL) framework that enables multimodal organ segmentation without sharing raw patient data. Our method integrates a lightweight Global Intensity Non-linear (GIN) augmentation module that harmonizes modality-specific intensity distributions during local training. We evaluated FedGIN using two types of datasets: an imputed dataset and a complete dataset. In the limited dataset scenario, the model was initially trained using only MRI data, and CT data was added to assess its performance improvements. In the complete dataset scenario, both MRI and CT data were fully utilized for training on all clients. In the limited-data scenario, FedGIN achieved a 12 to 18% improvement in 3D Dice scores on MRI test cases compared to FL without GIN and consistently outperformed local baselines. In the complete dataset scenario, FedGIN demonstrated near-centralized performance, with a 30% Dice score improvement over the MRI-only baseline and a 10% improvement over the CT-only baseline, highlighting its strong cross-modality generalization under privacy constraints.

Routine duplex ultrasound surveillance is recommended after femoral-popliteal and femoral-tibial-pedal vein bypass grafts at various post-operative intervals. Currently, there is no systematic method for bypass graft surveillance using a set of peak systolic velocities (PSVs) collected during these exams. This research aims to explore the use of recurrent neural networks to predict the next set of PSVs, which can then indicate occlusion status. Recurrent neural network models were developed to predict occlusion and stenosis based on one to three prior sets of PSVs, with a sequence-to-sequence model utilized to forecast future PSVs within the stent graft and nearby arteries. The study employed 5-fold cross-validation for model performance comparison, revealing that the BiGRU model outperformed BiLSTM when two or more sets of PSVs were included, demonstrating that increasing duplex ultrasound exams improve prediction accuracy and reduces error rates. This work establishes a basis for integrating comprehensive clinical data, including demographics, comorbidities, symptoms, and other risk factors, with PSVs to enhance lower extremity bypass graft surveillance predictions.