Magnetic resonance imaging (MRI) reports are challenging for patients to interpret and may subject patients to unnecessary anxiety. The advent of advanced artificial intelligence (AI) large language models (LLMs), such as GPT-4o, hold promise for translating complex medical information into layman terms. This paper aims to evaluate the accuracy, helpfulness, and readability of GPT-4o in explaining MRI reports of patients with thoracolumbar fractures. MRI reports of 20 patients presenting with thoracic or lumbar vertebral body fractures were obtained. GPT-4o was prompted to explain the MRI report in layman's terms. The generated explanations were then presented to 7 board-certified spine surgeons for evaluation on the reports' helpfulness and accuracy. The MRI report text and GPT-4o explanations were then analyzed to grade the readability of the texts using the Flesch Readability Ease Score (FRES) and Flesch-Kincaid Grade Level (FKGL) Scale. The layman explanations provided by GPT-4o were found to be helpful by all surgeons in 17 cases, with 6 of 7 surgeons finding the information helpful in the remaining 3 cases. ChatGPT-generated layman reports were rated as "accurate" by all 7 surgeons in 11/20 cases (55%). In an additional 5/20 cases (25%), 6 out of 7 surgeons agreed on their accuracy. In the remaining 4/20 cases (20%), accuracy ratings varied, with 4 or 5 surgeons considering them accurate. Review of surgeon feedback on inaccuracies revealed that the radiology reports were often insufficiently detailed. The mean FRES score of the MRI reports was significantly lower than the GPT-4o explanations (32.15, SD 15.89 vs 53.9, SD 7.86; P<.001). The mean FKGL score of the MRI reports trended higher compared to the GPT-4o explanations (11th-12th grade vs 10th-11th grade level; P=.11). Overall helpfulness and readability ratings for AI-generated summaries of MRI reports were high, with few inaccuracies recorded. This study demonstrates the potential of GPT-4o to serve as a valuable tool for enhancing patient comprehension of MRI report findings.

Recent advancements in deep learning for medical image segmentation are often limited by the scarcity of high-quality training data.While diffusion models provide a potential solution by generating synthetic images, their effectiveness in medical imaging remains constrained due to their reliance on large-scale medical datasets and the need for higher image quality. To address these challenges, we present MedDiff-FT, a controllable medical image generation method that fine-tunes a diffusion foundation model to produce medical images with structural dependency and domain specificity in a data-efficient manner. During inference, a dynamic adaptive guiding mask enforces spatial constraints to ensure anatomically coherent synthesis, while a lightweight stochastic mask generator enhances diversity through hierarchical randomness injection. Additionally, an automated quality assessment protocol filters suboptimal outputs using feature-space metrics, followed by mask corrosion to refine fidelity. Evaluated on five medical segmentation datasets,MedDiff-FT's synthetic image-mask pairs improve SOTA method's segmentation performance by an average of 1% in Dice score. The framework effectively balances generation quality, diversity, and computational efficiency, offering a practical solution for medical data augmentation. The code is available at https://github.com/JianhaoXie1/MedDiff-FT.

Accurate fetal birth weight (FBW) estimation is essential for optimizing delivery decisions and reducing perinatal mortality. However, clinical methods for FBW estimation are inefficient, operator-dependent, and challenging to apply in cases of complex fetal anatomy. Existing deep learning methods are based on 2D standard ultrasound (US) images or videos that lack spatial information, limiting their prediction accuracy. In this study, we propose the first method for directly estimating FBW from 3D fetal US volumes. Our approach integrates a multi-scale feature fusion network (MFFN) and a synthetic sample-based learning framework (SSLF). The MFFN effectively extracts and fuses multi-scale features under sparse supervision by incorporating channel attention, spatial attention, and a ranking-based loss function. SSLF generates synthetic samples by simply combining fetal head and abdomen data from different fetuses, utilizing semi-supervised learning to improve prediction performance. Experimental results demonstrate that our method achieves superior performance, with a mean absolute error of $166.4\pm155.9$ $g$ and a mean absolute percentage error of $5.1\pm4.6$%, outperforming existing methods and approaching the accuracy of a senior doctor. Code is available at: https://github.com/Qioy-i/EFW.

In this paper, we present the VMSE U-Net and VM-Unet CBAM+ model, two cutting-edge deep learning architectures designed to enhance medical image segmentation. Our approach integrates Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) techniques into the traditional VM U-Net framework, significantly improving segmentation accuracy, feature localization, and computational efficiency. Both models show superior performance compared to the baseline VM-Unet across multiple datasets. Notably, VMSEUnet achieves the highest accuracy, IoU, precision, and recall while maintaining low loss values. It also exhibits exceptional computational efficiency with faster inference times and lower memory usage on both GPU and CPU. Overall, the study suggests that the enhanced architecture VMSE-Unet is a valuable tool for medical image analysis. These findings highlight its potential for real-world clinical applications, emphasizing the importance of further research to optimize accuracy, robustness, and computational efficiency.

In recent years, accelerated MRI reconstruction based on deep learning has led to significant improvements in image quality with impressive results for high acceleration factors. However, from a clinical perspective image quality is only secondary; much more important is that all clinically relevant information is preserved in the reconstruction from heavily undersampled data. In this paper, we show that existing techniques, even when considering resampling for diffusion-based reconstruction, can fail to reconstruct small and rare pathologies, thus leading to potentially wrong diagnosis decisions (false negatives). To uncover the potentially missing clinical information we propose ``Semantically Diverse Reconstructions'' (\SDR), a method which, given an original reconstruction, generates novel reconstructions with enhanced semantic variability while all of them are fully consistent with the measured data. To evaluate \SDR automatically we train an object detector on the fastMRI+ dataset. We show that \SDR significantly reduces the chance of false-negative diagnoses (higher recall) and improves mean average precision compared to the original reconstructions. The code is available on https://github.com/NikolasMorshuis/SDR

Deep learning-based diagnostic models often suffer performance drops due to distribution shifts between training (source) and test (target) domains. Collecting and labeling sufficient target domain data for model retraining represents an optimal solution, yet is limited by time and scarce resources. Active learning (AL) offers an efficient approach to reduce annotation costs while maintaining performance, but struggles to handle the challenge posed by distribution variations across different datasets. In this study, we propose a novel unsupervised Active learning framework for Domain Adaptation, named ADAptation, which efficiently selects informative samples from multi-domain data pools under limited annotation budget. As a fundamental step, our method first utilizes the distribution homogenization capabilities of diffusion models to bridge cross-dataset gaps by translating target images into source-domain style. We then introduce two key innovations: (a) a hypersphere-constrained contrastive learning network for compact feature clustering, and (b) a dual-scoring mechanism that quantifies and balances sample uncertainty and representativeness. Extensive experiments on four breast ultrasound datasets (three public and one in-house/multi-center) across five common deep classifiers demonstrate that our method surpasses existing strong AL-based competitors, validating its effectiveness and generalization for clinical domain adaptation. The code is available at the anonymized link: https://github.com/miccai25-966/ADAptation.

Deformable medical image registration is traditionally formulated as an optimization problem. While classical methods solve this problem iteratively, recent learning-based approaches use recurrent neural networks (RNNs) to mimic this process by unrolling the prediction of deformation fields in a fixed number of steps. However, classical methods typically converge after sufficient iterations, but learning-based unrolling methods lack a theoretical convergence guarantee and show instability empirically. In addition, unrolling methods have a practical bottleneck at training time: GPU memory usage grows linearly with the unrolling steps due to backpropagation through time (BPTT). To address both theoretical and practical challenges, we propose DEQReg, a novel registration framework based on Deep Equilibrium Models (DEQ), which formulates registration as an equilibrium-seeking problem, establishing a natural connection between classical optimization and learning-based unrolling methods. DEQReg maintains constant memory usage, enabling theoretically unlimited iteration steps. Through extensive evaluation on the public brain MRI and lung CT datasets, we show that DEQReg can achieve competitive registration performance, while substantially reducing memory consumption compared to state-of-the-art unrolling methods. We also reveal an intriguing phenomenon: the performance of existing unrolling methods first increases slightly then degrades irreversibly when the inference steps go beyond the training configuration. In contrast, DEQReg achieves stable convergence with its inbuilt equilibrium-seeking mechanism, bridging the gap between classical optimization-based and modern learning-based registration methods.

Objectives Parametric tissue mapping enables quantitative cardiac tissue characterization but is limited by inter-observer variability during manual delineation. Traditional approaches relying on average relaxation values and single cutoffs may oversimplify myocardial complexity. This study evaluates whether deep learning (DL) can achieve segmentation accuracy comparable to inter-observer variability, explores the utility of statistical features beyond mean T1/T2 values, and assesses whether machine learning (ML) combining multiple features enhances disease detection. Materials & Methods T1 and T2 maps were manually segmented. The test subset was independently annotated by two observers, and inter-observer variability was assessed. A DL model was trained to segment left ventricle blood pool and myocardium. Average (A), lower quartile (LQ), median (M), and upper quartile (UQ) were computed for the myocardial pixels and employed in classification by applying cutoffs or in ML. Dice similarity coefficient (DICE) and mean absolute percentage error evaluated segmentation performance. Bland-Altman plots assessed inter-user and model-observer agreement. Receiver operating characteristic analysis determined optimal cutoffs. Pearson correlation compared features from model and manual segmentations. F1-score, precision, and recall evaluated classification performance. Wilcoxon test assessed differences between classification methods, with p < 0.05 considered statistically significant. Results 144 subjects were split into training (100), validation (15) and evaluation (29) subsets. Segmentation model achieved a DICE of 85.4%, surpassing inter-observer agreement. Random forest applied to all features increased F1-score (92.7%, p < 0.001). Conclusion DL facilitates segmentation of T1/ T2 maps. Combining multiple features with ML improves disease detection.

In recent years, generative artificial intelligence (AI), particularly large language models (LLMs) and their multimodal counterparts, multimodal large language models, including vision language models, have generated considerable interest in the global AI discourse. LLMs, or pre-trained language models (such as ChatGPT, Med-PaLM, LLaMA), are neural network architectures trained on extensive text data, excelling in language comprehension and generation. Multimodal LLMs, a subset of foundation models, are trained on multimodal data sets, integrating text with another modality, such as images, to learn universal representations akin to human cognition better. This versatility enables them to excel in tasks like chatbots, translation, and creative writing while facilitating knowledge sharing through transfer learning, federated learning, and synthetic data creation. Several of these models can have potentially appealing applications in the medical domain, including, but not limited to, enhancing patient care by processing patient data; summarizing reports and relevant literature; providing diagnostic, treatment, and follow-up recommendations; and ancillary tasks like coding and billing. As radiologists enter this promising but uncharted territory, it is imperative for them to be familiar with the basic terminology and processes of LLMs. Herein, we present an overview of the LLMs and their potential applications and challenges in the imaging domain.

PET/CT imaging data contains a wealth of quantitative information that can provide valuable contributions to characterising tumours. A growing body of work focuses on the use of deep-learning (DL) techniques for denoising PET data. These models are clinically evaluated prior to use, however, quantitative image assessment provides potential for further evaluation. This work uses radiomic features to compare two manufacturer deep-learning (DL) image enhancement algorithms, one of which has been commercialised, against 'gold-standard' image reconstruction techniques in phantom data and a sarcoma patient data set (N=20). All studies in the retrospective sarcoma clinical [ <math xmlns="http://www.w3.org/1998/Math/MathML"><mmultiscripts><mrow></mrow> <mrow></mrow> <mn>18</mn></mmultiscripts> </math> F]FDG dataset were acquired on either a GE Discovery 690 or 710 PET/CT scanner with volumes segmented by an experienced nuclear medicine radiologist. The modular heterogeneous imaging phantom used in this work was filled with [ <math xmlns="http://www.w3.org/1998/Math/MathML"><mmultiscripts><mrow></mrow> <mrow></mrow> <mn>18</mn></mmultiscripts> </math> F]FDG, and five repeat acquisitions of the phantom were acquired on a GE Discovery 710 PET/CT scanner. The DL-enhanced images were compared to 'gold-standard' images the algorithms were trained to emulate and input images. The difference between image sets was tested for significance in 93 international biomarker standardisation initiative (IBSI) standardised radiomic features. Comparing DL-enhanced images to the 'gold-standard', 4.0% and 9.7% radiomic features measured significantly different (p_critical < 0.0005) in the phantom and patient data respectively (averaged over the two DL algorithms). Larger differences were observed comparing DL-enhanced images to algorithm input images with 29.8% and 43.0% of radiomic features measuring significantly different in the phantom and patient data respectively (averaged over the two DL algorithms). DL-enhanced images were found to be similar to images generated using the 'gold-standard' target image reconstruction method with more than 80% of radiomic features not significantly different in all comparisons across unseen phantom and sarcoma patient data. This result offers insight into the performance of the DL algorithms, and demonstrate potential applications for DL algorithms in harmonisation for radiomics and for radiomic features in quantitative evaluation of DL algorithms.