An effective diagnosis system and suitable treatment planning require the precise segmentation of thyroid nodules in ultrasound imaging. The advancement of imaging technologies has not resolved traditional imaging challenges, which include noise issues, limited contrast, and dependency on operator choices, thus highlighting the need for automated, reliable solutions. The researchers developed TATHA, an innovative deep learning architecture dedicated to improving thyroid ultrasound image segmentation accuracy. The model is evaluated using the digital database of thyroid ultrasound images, which includes 99 cases across three subsets containing 134 labelled images for training, validation, and testing. It incorporates data pre-treatment procedures that reduce speckle noise and enhance contrast, while edge detection provides high-quality input for segmentation. TATHA outperforms U-Net, PSPNet, and Vision Transformers across various datasets and cross-validation folds, achieving superior Dice scores, accuracy, and AUC results. The distributed thyroid segmentation framework generates reliable predictions by combining results from multiple feature extraction units. The findings confirm that these advancements make TATHA an essential tool for clinicians and researchers in thyroid imaging and clinical applications.

Ulcerative colitis (UC) is a chronic inflammatory disorder necessitating precise severity stratification to facilitate optimal therapeutic interventions. This study harnesses a triple-pronged deep learning methodology-including multimodal inference pipelines that eliminate domain-specific training, few-shot meta-learning, and Vision Transformer (ViT)-based ensembling-to classify UC severity within the HyperKvasir dataset. We systematically evaluate multiple vision transformer architectures, discovering that a Swin-Base model achieves an accuracy of 90%, while a soft-voting ensemble of diverse ViT backbones boosts performance to 93%. In parallel, we leverage multimodal pre-trained frameworks (e.g., CLIP, BLIP, FLAVA) integrated with conventional machine learning algorithms, yielding an accuracy of 83%. To address limited annotated data, we deploy few-shot meta-learning approaches (e.g., Matching Networks), attaining 83% accuracy in a 5-shot context. Furthermore, interpretability is enhanced via SHapley Additive exPlanations (SHAP), which interpret both local and global model behaviors, thereby fostering clinical trust in the model's inferences. These findings underscore the potential of contemporary representation learning and ensemble strategies for robust UC severity classification, highlighting the pivotal role of model transparency in facilitating medical image analysis.

Accurate medical image segmentation remains challenging due to blurred lesion boundaries (LBA), loss of high-frequency details (LHD), and difficulty in modeling long-range anatomical structures (DC-LRSS). Vision Mamba employs one-dimensional causal state-space recurrence to efficiently model global dependencies, thereby substantially mitigating DC-LRSS. However, its patch tokenization and 1D serialization disrupt local pixel adjacency and impose a low-pass filtering effect, resulting in Local High-frequency Information Capture Deficiency (LHICD) and two-dimensional Spatial Structure Degradation (2D-SSD), which in turn exacerbate LBA and LHD. In this work, we propose FaRMamba, a novel extension that explicitly addresses LHICD and 2D-SSD through two complementary modules. A Multi-Scale Frequency Transform Module (MSFM) restores attenuated high-frequency cues by isolating and reconstructing multi-band spectra via wavelet, cosine, and Fourier transforms. A Self-Supervised Reconstruction Auxiliary Encoder (SSRAE) enforces pixel-level reconstruction on the shared Mamba encoder to recover full 2D spatial correlations, enhancing both fine textures and global context. Extensive evaluations on CAMUS echocardiography, MRI-based Mouse-cochlea, and Kvasir-Seg endoscopy demonstrate that FaRMamba consistently outperforms competitive CNN-Transformer hybrids and existing Mamba variants, delivering superior boundary accuracy, detail preservation, and global coherence without prohibitive computational overhead. This work provides a flexible frequency-aware framework for future segmentation models that directly mitigates core challenges in medical imaging.

Background: Manual extraction of pancreatic cystic lesion (PCL) features from radiology reports is labor-intensive, limiting large-scale studies needed to advance PCL research. Purpose: To develop and evaluate large language models (LLMs) that automatically extract PCL features from MRI/CT reports and assign risk categories based on guidelines. Materials and Methods: We curated a training dataset of 6,000 abdominal MRI/CT reports (2005-2024) from 5,134 patients that described PCLs. Labels were generated by GPT-4o using chain-of-thought (CoT) prompting to extract PCL and main pancreatic duct features. Two open-source LLMs were fine-tuned using QLoRA on GPT-4o-generated CoT data. Features were mapped to risk categories per institutional guideline based on the 2017 ACR White Paper. Evaluation was performed on 285 held-out human-annotated reports. Model outputs for 100 cases were independently reviewed by three radiologists. Feature extraction was evaluated using exact match accuracy, risk categorization with macro-averaged F1 score, and radiologist-model agreement with Fleiss' Kappa. Results: CoT fine-tuning improved feature extraction accuracy for LLaMA (80% to 97%) and DeepSeek (79% to 98%), matching GPT-4o (97%). Risk categorization F1 scores also improved (LLaMA: 0.95; DeepSeek: 0.94), closely matching GPT-4o (0.97), with no statistically significant differences. Radiologist inter-reader agreement was high (Fleiss' Kappa = 0.888) and showed no statistically significant difference with the addition of DeepSeek-FT-CoT (Fleiss' Kappa = 0.893) or GPT-CoT (Fleiss' Kappa = 0.897), indicating that both models achieved agreement levels on par with radiologists. Conclusion: Fine-tuned open-source LLMs with CoT supervision enable accurate, interpretable, and efficient phenotyping for large-scale PCL research, achieving performance comparable to GPT-4o.

Medical image segmentation plays an important role in computer-aided diagnosis. Traditional convolution-based U-shape segmentation architectures are usually limited by the local receptive field. Existing vision transformers have been widely applied to diverse medical segmentation frameworks due to their superior capabilities of capturing global contexts. Despite the advantage, the real-world application of vision transformers is challenged by their non-linear self-attention mechanism, requiring huge computational costs. To address this issue, the selective state space model (SSM) Mamba has gained recognition for its adeptness in modeling long-range dependencies in sequential data, particularly noted for its efficient memory costs. In this paper, we propose MambaVesselNet++, a Hybrid CNN-Mamba framework for medical image segmentation. Our MambaVesselNet++ is comprised of a hybrid image encoder (Hi-Encoder) and a bifocal fusion decoder (BF-Decoder). In Hi-Encoder, we first devise the texture-aware layer to capture low-level semantic features by leveraging convolutions. Then, we utilize Mamba to effectively model long-range dependencies with linear complexity. The Bi-Decoder adopts skip connections to combine local and global information of the Hi-Encoder for the accurate generation of segmentation masks. Extensive experiments demonstrate that MambaVesselNet++ outperforms current convolution-based, transformer-based, and Mamba-based state-of-the-arts across diverse medical 2D, 3D, and instance segmentation tasks. The code is available at https://github.com/CC0117/MambaVesselNet.

Automated breast cancer classification from mammography remains a significant challenge due to subtle distinctions between benign and malignant tissue. In this work, we present a hybrid framework combining deep convolutional features from a ResNet-50 backbone with handcrafted descriptors and transformer-based embeddings. Using the CBIS-DDSM dataset, we benchmark our ResNet-50 baseline (AUC: 78.1%) and demonstrate that fusing handcrafted features with deep ResNet-50 and DINOv2 features improves AUC to 79.6% (setup d1), with a peak recall of 80.5% (setup d1) and highest F1 score of 67.4% (setup d1). Our experiments show that handcrafted features not only complement deep representations but also enhance performance beyond transformer-based embeddings. This hybrid fusion approach achieves results comparable to state-of-the-art methods while maintaining architectural simplicity and computational efficiency, making it a practical and effective solution for clinical decision support.

Prognostic evaluation in patients with colorectal liver metastases (CRLM) remains challenging due to suboptimal accuracy of conventional clinical models. This study developed and validated a robust machine learning model for predicting postoperative recurrence risk. Preliminary ensemble models achieved exceptionally high performance (AUC $>$ 0.98) but incorporated postoperative features, introducing data leakage risks. To enhance clinical applicability, we restricted input variables to preoperative baseline clinical parameters and radiomic features from contrast-enhanced CT imaging, specifically targeting recurrence prediction at 3, 6, and 12 months postoperatively. The 3-month recurrence prediction model demonstrated optimal performance with an AUC of 0.723 in cross-validation. Decision curve analysis revealed that across threshold probabilities of 0.55-0.95, the model consistently provided greater net benefit than "treat-all" or "treat-none" strategies, supporting its utility in postoperative surveillance and therapeutic decision-making. This study successfully developed a robust predictive model for early CRLM recurrence with confirmed clinical utility. Importantly, it highlights the critical risk of data leakage in clinical prognostic modeling and proposes a rigorous framework to mitigate this issue, enhancing model reliability and translational value in real-world settings.

All-in-one medical image restoration (MedIR) aims to address multiple MedIR tasks using a unified model, concurrently recovering various high-quality (HQ) medical images (e.g., MRI, CT, and PET) from low-quality (LQ) counterparts. However, all-in-one MedIR presents significant challenges due to the heterogeneity across different tasks. Each task involves distinct degradations, leading to diverse information losses in LQ images. Existing methods struggle to handle these diverse information losses associated with different tasks. To address these challenges, we propose a latent diffusion-enhanced vector-quantized codebook prior and develop \textbf{DiffCode}, a novel framework leveraging this prior for all-in-one MedIR. Specifically, to compensate for diverse information losses associated with different tasks, DiffCode constructs a task-adaptive codebook bank to integrate task-specific HQ prior features across tasks, capturing a comprehensive prior. Furthermore, to enhance prior retrieval from the codebook bank, DiffCode introduces a latent diffusion strategy that utilizes the diffusion model's powerful mapping capabilities to iteratively refine the latent feature distribution, estimating more accurate HQ prior features during restoration. With the help of the task-adaptive codebook bank and latent diffusion strategy, DiffCode achieves superior performance in both quantitative metrics and visual quality across three MedIR tasks: MRI super-resolution, CT denoising, and PET synthesis.

Diffusion MRI (dMRI) is an advanced imaging technique that enables in-vivo tracking of white matter fiber tracts and estimates the underlying cellular microstructure of brain tissues. Groupwise registration of dMRI data from multiple individuals is an important task for brain template creation and investigation of inter-subject brain variability. However, groupwise registration is a challenging task due to the uniqueness of dMRI data that include multi-dimensional, orientation-dependent signals that describe not only the strength but also the orientation of water diffusion in brain tissues. Deep learning approaches have shown successful performance in standard subject-to-subject dMRI registration. However, no deep learning methods have yet been proposed for groupwise dMRI registration. . In this work, we propose Deep Diffusion MRI Template (DDTemplate), which is a novel deep-learning-based method building upon the popular VoxelMorph framework to take into account dMRI fiber tract information. DDTemplate enables joint usage of whole-brain tissue microstructure and tract-specific fiber orientation information to ensure alignment of white matter fiber tracts and whole brain anatomical structures. We propose a novel deep learning framework that simultaneously trains a groupwise dMRI registration network and generates a population brain template. During inference, the trained model can be applied to register unseen subjects to the learned template. We compare DDTemplate with several state-of-the-art registration methods and demonstrate superior performance on dMRI data from multiple cohorts (adolescents, young adults, and elderly adults) acquired from different scanners. Furthermore, as a testbed task, we perform a between-population analysis to investigate sex differences in the brain, using the popular Tract-Based Spatial Statistics (TBSS) method that relies on groupwise dMRI registration. We find that using DDTemplate can increase the sensitivity in population difference detection, showing the potential of our method's utility in real neuroscientific applications.

Artificial Intelligence (AI), and particularly deep learning (DL), has shown great promise to revolutionize healthcare. However, clinical translation is often hindered by demanding hardware requirements. In this study, we assess the effectiveness of optimization techniques for DL models in healthcare applications, targeting varying AI workloads across the domains of radiology, histopathology, and medical RGB imaging, while evaluating across hardware configurations. The assessed AI workloads focus on both segmentation and classification workloads, by virtue of brain extraction in Magnetic Resonance Imaging (MRI), colorectal cancer delineation in Hematoxylin & Eosin (H&E) stained digitized tissue sections, and diabetic foot ulcer classification in RGB images. We quantitatively evaluate model performance in terms of model runtime during inference (including speedup, latency, and memory usage) and model utility on unseen data. Our results demonstrate that optimization techniques can substantially improve model runtime, without compromising model utility. These findings suggest that optimization techniques can facilitate the clinical translation of AI models in low-resource environments, making them more practical for real-world healthcare applications even in underserved regions.