Brain MRI scans are often found in four modalities, consisting of T1-weighted with and without contrast enhancement (T1ce and T1w), T2-weighted imaging (T2w), and Flair. Leveraging complementary information from these different modalities enables models to learn richer, more discriminative features for understanding brain anatomy, which could be used in downstream tasks such as anomaly detection. However, in clinical practice, not all MRI modalities are always available due to various reasons. This makes missing modality generation a critical challenge in medical image analysis. In this paper, we propose SLaM-DiMM, a novel missing modality generation framework that harnesses the power of diffusion models to synthesize any of the four target MRI modalities from other available modalities. Our approach not only generates high-fidelity images but also ensures structural coherence across the depth of the volume through a dedicated coherence enhancement mechanism. Qualitative and quantitative evaluations on the BraTS-Lighthouse-2025 Challenge dataset demonstrate the effectiveness of the proposed approach in synthesizing anatomically plausible and structurally consistent results. Code is available at https://github.com/BheeshmSharma/SLaM-DiMM-MICCAI-BraTS-Challenge-2025.

We present ENSAM (Equivariant, Normalized, Segment Anything Model), a lightweight and promptable model for universal 3D medical image segmentation. ENSAM combines a SegResNet-based encoder with a prompt encoder and mask decoder in a U-Net-style architecture, using latent cross-attention, relative positional encoding, normalized attention, and the Muon optimizer for training. ENSAM is designed to achieve good performance under limited data and computational budgets, and is trained from scratch on under 5,000 volumes from multiple modalities (CT, MRI, PET, ultrasound, microscopy) on a single 32 GB GPU in 6 hours. As part of the CVPR 2025 Foundation Models for Interactive 3D Biomedical Image Segmentation Challenge, ENSAM was evaluated on hidden test set with multimodal 3D medical images, obtaining a DSC AUC of 2.404, NSD AUC of 2.266, final DSC of 0.627, and final NSD of 0.597, outperforming two previously published baseline models (VISTA3D, SAM-Med3D) and matching the third (SegVol), surpassing its performance in final DSC but trailing behind in the other three metrics. In the coreset track of the challenge, ENSAM ranks 5th of 10 overall and best among the approaches not utilizing pretrained weights. Ablation studies confirm that our use of relative positional encodings and the Muon optimizer each substantially speed up convergence and improve segmentation quality.

The rapid advancement of generative AI in medical imaging has introduced both significant opportunities and serious challenges, especially the risk that fake medical images could undermine healthcare systems. These synthetic images pose serious risks, such as diagnostic deception, financial fraud, and misinformation. However, research on medical forensics to counter these threats remains limited, and there is a critical lack of comprehensive datasets specifically tailored for this field. Additionally, existing media forensic methods, which are primarily designed for natural or facial images, are inadequate for capturing the distinct characteristics and subtle artifacts of AI-generated medical images. To tackle these challenges, we introduce \textbf{MedForensics}, a large-scale medical forensics dataset encompassing six medical modalities and twelve state-of-the-art medical generative models. We also propose \textbf{DSKI}, a novel \textbf{D}ual-\textbf{S}tage \textbf{K}nowledge \textbf{I}nfusing detector that constructs a vision-language feature space tailored for the detection of AI-generated medical images. DSKI comprises two core components: 1) a cross-domain fine-trace adapter (CDFA) for extracting subtle forgery clues from both spatial and noise domains during training, and 2) a medical forensic retrieval module (MFRM) that boosts detection accuracy through few-shot retrieval during testing. Experimental results demonstrate that DSKI significantly outperforms both existing methods and human experts, achieving superior accuracy across multiple medical modalities.

Micro-ultrasound (micro-US) is a promising imaging technique for cancer detection and computer-assisted visualization. This study investigates prostate capsule segmentation using deep learning techniques from micro-US images, addressing the challenges posed by the ambiguous boundaries of the prostate capsule. Existing methods often struggle in such cases, motivating the development of a tailored approach. This study introduces an adaptive focal loss function that dynamically emphasizes both hard and easy regions, taking into account their respective difficulty levels and annotation variability. The proposed methodology has two primary strategies: integrating a standard focal loss function as a baseline to design an adaptive focal loss function for proper prostate capsule segmentation. The focal loss baseline provides a robust foundation, incorporating class balancing and focusing on examples that are difficult to classify. The adaptive focal loss offers additional flexibility, addressing the fuzzy region of the prostate capsule and annotation variability by dilating the hard regions identified through discrepancies between expert and non-expert annotations. The proposed method dynamically adjusts the segmentation model's weights better to identify the fuzzy regions of the prostate capsule. The proposed adaptive focal loss function demonstrates superior performance, achieving a mean dice coefficient (DSC) of 0.940 and a mean Hausdorff distance (HD) of 1.949 mm in the testing dataset. These results highlight the effectiveness of integrating advanced loss functions and adaptive techniques into deep learning models. This enhances the accuracy of prostate capsule segmentation in micro-US images, offering the potential to improve clinical decision-making in prostate cancer diagnosis and treatment planning.

Deep Feedback Models (DFMs) are a new class of stateful neural networks that combine bottom up input with high level representations over time. This feedback mechanism introduces dynamics into otherwise static architectures, enabling DFMs to iteratively refine their internal state and mimic aspects of biological decision making. We model this process as a differential equation solved through a recurrent neural network, stabilized via exponential decay to ensure convergence. To evaluate their effectiveness, we measure DFMs under two key conditions: robustness to noise and generalization with limited data. In both object recognition and segmentation tasks, DFMs consistently outperform their feedforward counterparts, particularly in low data or high noise regimes. In addition, DFMs translate to medical imaging settings, while being robust against various types of noise corruption. These findings highlight the importance of feedback in achieving stable, robust, and generalizable learning. Code is available at https://github.com/DCalhas/deep_feedback_models.

Accurate segmentation of breast tumors in magnetic resonance images (MRI) is essential for breast cancer diagnosis, yet existing methods face challenges in capturing irregular tumor shapes and effectively integrating local and global features. To address these limitations, we propose an uncertainty-gated deformable network to leverage the complementary information from CNN and Transformers. Specifically, we incorporates deformable feature modeling into both convolution and attention modules, enabling adaptive receptive fields for irregular tumor contours. We also design an Uncertainty-Gated Enhancing Module (U-GEM) to selectively exchange complementary features between CNN and Transformer based on pixel-wise uncertainty, enhancing both local and global representations. Additionally, a Boundary-sensitive Deep Supervision Loss is introduced to further improve tumor boundary delineation. Comprehensive experiments on two clinical breast MRI datasets demonstrate that our method achieves superior segmentation performance compared with state-of-the-art methods, highlighting its clinical potential for accurate breast tumor delineation.

Ultrahigh-field susceptibility-weighted imaging (SWI) provides excellent tissue contrast and anatomical details of brain. However, ultrahigh-field magnetic resonance (MR) scanner often expensive and provides uncomfortable noise experience for patient. Therefore, some deep learning approaches have been proposed to synthesis high-field MR images from low-filed MR images, most existing methods rely on generative adversarial network (GAN) and achieve acceptable results. While the dilemma in train process of GAN, generally recognized, limits the synthesis performance in SWI images for its microvascular structure. Diffusion models, as a promising alternative, indirectly characterize the gaussian noise to the target image with a slow sampling through a considerable number of steps. To address this limitation, we presented a generative diffusion-based deep learning imaging model, named conditional denoising diffusion probabilistic model (CDDPM), for synthesizing high-field (7 Tesla) SWI images form low-field (3 Tesla) SWI images and assess clinical applicability. Crucially, the experiment results demonstrate that the diffusion-based model that synthesizes 7T SWI from 3T SWI images is potentially to providing an alternative way to achieve the advantages of ultra-high field 7T MR images for deep medullary veins visualization.

In this study, we develop a new CAD system for accurate thyroid cancer classification with emphasis on feature extraction. Prior studies have shown that thyroid texture is important for segregating the thyroid ultrasound images into different classes. Based upon our experience with breast cancer classification, we first conjuncture that the Discrete Cosine Transform (DCT) is the best descriptor for capturing textural features. Thyroid ultrasound images are particularly challenging as the gland is surrounded by multiple complex anatomical structures leading to variations in tissue density. Hence, we second conjuncture the importance of localization and propose that the Local DCT (LDCT) descriptor captures the textural features best in this context. Another disadvantage of complex anatomy around the thyroid gland is scattering of ultrasound waves resulting in noisy and unclear textures. Hence, we third conjuncture that one image descriptor is not enough to fully capture the textural features and propose the integration of another popular texture capturing descriptor (Improved Local Binary Pattern, ILBP) with LDCT. ILBP is known to be noise resilient as well. We term our novel descriptor as Binary Pattern Driven Local Discrete Cosine Transform (BPD-LDCT). Final classification is carried out using a non-linear SVM. The proposed CAD system is evaluated on the only two publicly available thyroid cancer datasets, namely TDID and AUITD. The evaluation is conducted in two stages. In Stage I, thyroid nodules are categorized as benign or malignant. In Stage II, the malignant cases are further sub-classified into TI-RADS (4) and TI-RADS (5). For Stage I classification, our proposed model demonstrates exceptional performance of nearly 100% on TDID and 97% on AUITD. In Stage II classification, the proposed model again attains excellent classification of close to 100% on TDID and 99% on AUITD.

White matter tractography is an advanced neuroimaging technique that reconstructs the 3D white matter pathways of the brain from diffusion MRI data. It can be framed as a pathfinding problem aiming to infer neural fiber trajectories from noisy and ambiguous measurements, facing challenges such as crossing, merging, and fanning white-matter configurations. In this paper, we propose a novel tractography method that leverages Transformers to model the sequential nature of white matter streamlines, enabling the prediction of fiber directions by integrating both the trajectory context and current diffusion MRI measurements. To incorporate spatial information, we utilize CNNs that extract microstructural features from local neighborhoods around each voxel. By combining these complementary sources of information, our approach improves the precision and completeness of neural pathway mapping compared to traditional tractography models. We evaluate our method with the Tractometer toolkit, achieving competitive performance against state-of-the-art approaches, and present qualitative results on the TractoInferno dataset, demonstrating strong generalization to real-world data.

Advancements in computational methods in medicine have brought about extensive improvement in the diagnosis of illness, with machine learning models such as Convolutional Neural Networks leading the charge. This work introduces PneumoNet, a novel deep-learning model designed for accurate pneumonia detection from chest X-ray images. Pneumonia detection from chest X-ray images is one of the greatest challenges in diagnostic practice and medical imaging. Proper identification of standard chest X-ray views or pneumonia-specific views is required to perform this task effectively. Contemporary methods, such as classical machine learning models and initial deep learning methods, guarantee good performance but are generally marred by accuracy, generalizability, and preprocessing issues. These techniques are generally marred by clinical usage constraints like high false positives and poor performance over a broad spectrum of datasets. A novel deep learning architecture, PneumoNet, has been proposed as a solution to these problems. PneumoNet applies a convolutional neural network (CNN) structure specifically employed for the improvement of accuracy and precision in image classification. The model employs several layers of convolution as well as pooling, followed by fully connected dense layers, for efficient extraction of intricate features in X-ray images. The innovation of this approach lies in its advanced layer structure and its training, which are optimized to enhance feature extraction and classification performance greatly. The model proposed here, PneumoNet, has been cross-validated and trained on a well-curated dataset that includes a balanced representation of normal and pneumonia cases. Quantitative results demonstrate the model's performance, with an overall accuracy of 98% and precision values of 96% for normal and 98% for pneumonia cases. The recall values for normal and pneumonia cases are 96% and 98%, respectively, highlighting the consistency of the model. These performance measures collectively indicate the promise of the proposed model to improve the diagnostic process, with a substantial advancement over current methods and paving the way for its application in clinical practice.