Thyroid hormones are significant for controlling metabolism, and two common thyroid disorders, such as hypothyroidism. The hyperthyroidism are directly affect the metabolic rate of the human body. Predicting and diagnosing thyroid disease remain significant challenges in medical research due to the complexity of thyroid hormone regulation and its impact on metabolism. Therefore, this paper proposes a Complex-valued Spatio-Temporal Graph Convolution Neural Network optimized with Giraffe Kicking Optimization Algorithm for Thyroid Nodule Classification in Ultrasound Images (CSGCNN-GKOA-TNC-UI). Here, the ultrasound images are collected through DDTI (Digital Database of Thyroid ultrasound Imageries) dataset. The gathered data is given into the pre-processing stage using Bilinear Double-Order Filter (BDOF) approach to eradicate the noise and increase the input images quality. The pre-processing image is given into the Deep Adaptive Fuzzy Clustering (DAFC) for Region of Interest (RoI) segmentation. The segmented image is fed to the Multi-Objective Matched Synchro Squeezing Chirplet Transform (MMSSCT) for extracting the features, like Geometric features and Morphological features. The extracted features are fed into the CSGCNN, which classifies the Thyroid Nodule into Benign Nodules and Malign Nodules. Finally, Giraffe Kicking Optimization Algorithm (GKOA) is considered to enhance the CSGCNN classifier. The CSGCNN-GKOA-TNC-UI algorithm is implemented in MATLAB. The CSGCNN-GKOA-TNC-UI approach attains 34.9%, 21.5% and 26.8% higher f-score, 18.6%, 29.3 and 19.2% higher accuracy when compared with existing models: Thyroid diagnosis with classification utilizing DNN depending on hybrid meta-heuristic with LSTM method (LSTM-TNC-UI), innovative full-scale connected network for segmenting thyroid nodule in UI (FCG Net-TNC-UI), and Adversarial architecture dependent multi-scale fusion method for segmenting thyroid nodule (AMSeg-TNC-UI) methods respectively. The proposed model enhances thyroid nodule classification accuracy, aiding radiologists and endocrinologists. By reducing misclassification, it minimizes unnecessary biopsies and enables early malignancy detection.

Reliable medical image synthesis is crucial for clinical applications and downstream tasks, where high-quality anatomical structure and predictive confidence are essential. Existing studies have made significant progress by embedding prior conditional knowledge, such as conditional images or textual information, to synthesize natural images. However, medical image synthesis remains a challenging task due to: 1) Data scarcity: High-quality medical text prompt are extremely rare and require specialized expertise. 2) Insufficient uncertainty estimation: The uncertainty estimation is critical for evaluating the confidence of reliable medical image synthesis. This paper presents a novel approach for medical image synthesis, driven by radiomics prompts and combined with Monte Carlo Compression Sampling (MCCS) to ensure reliability. For the first time, our method leverages clinically focused radiomics prompts to condition the generation process, guiding the model to produce reliable medical images. Furthermore, the innovative MCCS algorithm employs Monte Carlo methods to randomly select and compress sampling steps within the denoising diffusion implicit models (DDIM), enabling efficient uncertainty quantification. Additionally, we introduce a MambaTrans architecture to model long-range dependencies in medical images and embed prior conditions (e.g., radiomics prompts). Extensive experiments on benchmark medical imaging datasets demonstrate that our approach significantly improves image quality and reliability, outperforming SoTA methods in both qualitative and quantitative evaluations.

Enhancing the resolution of Magnetic Resonance Imaging (MRI) through super-resolution (SR) reconstruction is crucial for boosting diagnostic precision. However, current SR methods primarily rely on single LR images or multi-contrast features, limiting detail restoration. Inspired by video frame interpolation, this work utilizes the spatiotemporal correlations between adjacent slices to reformulate the SR task of anisotropic 3D-MRI image into the generation of new high-resolution (HR) slices between adjacent 2D slices. The generated SR slices are subsequently combined with the HR adjacent slices to create a new HR 3D-MRI image. We propose a innovative network architecture termed DGWMSR, comprising a backbone network and a feature supplement module (FSM). The backbone's core innovations include the displacement former block (DFB) module, which independently extracts structural and displacement features, and the maskdisplacement vector network (MDVNet) which combines with Warp mechanism to facilitate edge pixel detailing. The DFB integrates the inter-slice attention (ISA) mechanism into the Transformer, effectively minimizing the mutual interference between the two types of features and mitigating volume effects during reconstruction. Additionally, the FSM module combines self-attention with feed-forward neural network, which emphasizes critical details derived from the backbone architecture. Experimental results demonstrate the DGWMSR network outperforms current MRI SR methods on Kirby21, ANVIL-adult, and MSSEG datasets. Our code has been made publicly available on GitHub at https://github.com/Dohbby/DGWMSR.

Medical image segmentation models struggle with rare abnormalities due to scarce annotated pathological data. We propose DiffAug a novel framework that combines textguided diffusion-based generation with automatic segmentation validation to address this challenge. Our proposed approach uses latent diffusion models conditioned on medical text descriptions and spatial masks to synthesize abnormalities via inpainting on normal images. Generated samples undergo dynamic quality validation through a latentspace segmentation network that ensures accurate localization while enabling single-step inference. The text prompts, derived from medical literature, guide the generation of diverse abnormality types without requiring manual annotation. Our validation mechanism filters synthetic samples based on spatial accuracy, maintaining quality while operating efficiently through direct latent estimation. Evaluated on three medical imaging benchmarks (CVC-ClinicDB, Kvasir-SEG, REFUGE2), our framework achieves state-of-the-art performance with 8-10% Dice improvements over baselines and reduces false negative rates by up to 28% for challenging cases like small polyps and flat lesions critical for early detection in screening applications.

To develop and evaluate a Dual-modality Complementary Feature Attention Network (DCFAN) that integrates spatial and stiffness information from B-mode ultrasound and shear wave elastography (SWE) for improved breast tumor classification and axillary lymph node (ALN) metastasis prediction. A total of 387 paired B-mode and SWE images from 218 patients were retrospectively analyzed. The proposed DCFAN incorporates attention mechanisms to effectively fuse structural features from B-mode ultrasound with stiffness features from SWE. Two classification tasks were performed: (1) differentiating benign from malignant tumors, and (2) classifying benign tumors, malignant tumors without ALN metastasis, and malignant tumors with ALN metastasis. Model performance was assessed using accuracy, sensitivity, specificity, and AUC, and compared with conventional CNN-based models and two radiologists with varying experience. In Task 1, DCFAN achieved an accuracy of 94.36% ± 1.45% and the highest AUC of 0.97. In Task 2, it attained 91.70% ± 3.77% accuracy and an average AUC of 0.83. The multimodal approach significantly outperformed the single-modality models in both tasks. Notably, in Task 1, DCFAN demonstrated higher specificity (94.9%) compared to the experienced radiologist (p = 0.002), and yielded higher F1-scores than both radiologists. It also outperformed several state-of-the-art deep learning models in diagnostic accuracy. DCFAN demonstrated robust and superior performance over existing CNN-based methods and radiologists in both breast tumor classification and ALN metastasis prediction. This approach may serve as a valuable assistive tool to enhance diagnostic accuracy in breast ultrasound.

Magnetic Resonance Imaging (MRI) is indispensable in clinical practice but remains constrained by fragmented, multi-stage workflows encompassing acquisition, reconstruction, segmentation, detection, diagnosis, and reporting. While deep learning has achieved progress in individual tasks, existing approaches are often anatomy- or application-specific and lack generalizability across diverse clinical settings. Moreover, current pipelines rarely integrate imaging data with complementary language information that radiologists rely on in routine practice. Here, we introduce OmniMRI, a unified vision-language foundation model designed to generalize across the entire MRI workflow. OmniMRI is trained on a large-scale, heterogeneous corpus curated from 60 public datasets, over 220,000 MRI volumes and 19 million MRI slices, incorporating image-only data, paired vision-text data, and instruction-response data. Its multi-stage training paradigm, comprising self-supervised vision pretraining, vision-language alignment, multimodal pretraining, and multi-task instruction tuning, progressively equips the model with transferable visual representations, cross-modal reasoning, and robust instruction-following capabilities. Qualitative results demonstrate OmniMRI's ability to perform diverse tasks within a single architecture, including MRI reconstruction, anatomical and pathological segmentation, abnormality detection, diagnostic suggestion, and radiology report generation. These findings highlight OmniMRI's potential to consolidate fragmented pipelines into a scalable, generalist framework, paving the way toward foundation models that unify imaging and clinical language for comprehensive, end-to-end MRI interpretation.

Sarcopenia is a progressive loss of muscle mass and function linked to poor surgical outcomes such as prolonged hospital stays, impaired mobility, and increased mortality. Although it can be assessed through cross-sectional imaging by measuring skeletal muscle area (SMA), the process is time-consuming and adds to clinical workloads, limiting timely detection and management; however, this process could become more efficient and scalable with the assistance of artificial intelligence applications. This paper presents high-quality three-dimensional cross-sectional computed tomography (CT) images of patients with sarcopenia collected at the Freeman Hospital, Newcastle upon Tyne Hospitals NHS Foundation Trust. Expert clinicians manually annotated the SMA at the third lumbar vertebra, generating precise segmentation masks. We develop deep-learning models to measure SMA in CT images and automate this task. Our methodology employed transfer learning and self-supervised learning approaches using labelled and unlabeled CT scan datasets. While we developed qualitative assessment models for detecting sarcopenia, we observed that the quantitative assessment of SMA is more precise and informative. This approach also mitigates the issue of class imbalance and limited data availability. Our model predicted the SMA, on average, with an error of +-3 percentage points against the manually measured SMA. The average dice similarity coefficient of the predicted masks was 93%. Our results, therefore, show a pathway to full automation of sarcopenia assessment and detection.

Brain tumors show significant health challenges due to their potential to cause critical neurological functions. Early and accurate diagnosis is crucial for effective treatment. In this research, we propose ResLink, a novel deep learning architecture for brain tumor classification using CT scan images. ResLink integrates novel area attention mechanisms with residual connections to enhance feature learning and spatial understanding for spatially rich image classification tasks. The model employs a multi-stage convolutional pipeline, incorporating dropout, regularization, and downsampling, followed by a final attention-based refinement for classification. Trained on a balanced dataset, ResLink achieves a high accuracy of 95% and demonstrates strong generalizability. This research demonstrates the potential of ResLink in improving brain tumor classification, offering a robust and efficient technique for medical imaging applications.

The Bosniak classification system is widely used to assess malignancy risk in renal cystic lesions, yet inter-observer variability poses significant challenges. Large language models (LLMs) may offer a standardized approach to classification when provided with textual descriptions, such as those found in radiology reports. This study evaluated the performance of five LLMs-GPT‑4 (ChatGPT), Gemini, Copilot, Perplexity, and NotebookLM-in classifying renal cysts based on synthetic textual descriptions mimicking CT report content. A synthetic dataset of 100 diagnostic scenarios (20 cases per Bosniak category) was constructed using established radiological criteria. Each LLM was evaluated using zero-shot and few-shot prompting strategies, while NotebookLM employed retrieval-augmented generation (RAG). Performance metrics included accuracy, sensitivity, and specificity. Statistical significance was assessed using McNemar's and chi-squared tests. GPT‑4 achieved the highest accuracy (87% zero-shot, 99% few-shot), followed by Copilot (81-86%), Gemini (55-69%), and Perplexity (43-69%). NotebookLM, tested only under RAG conditions, reached 87% accuracy. Few-shot learning significantly improved performance (p < 0.05). Classification of Bosniak IIF lesions remained challenging across models. When provided with well-structured textual descriptions, LLMs can accurately classify renal cysts. Few-shot prompting significantly enhances performance. However, persistent difficulties in classifying borderline lesions such as Bosniak IIF highlight the need for further refinement and real-world validation.

Aneurysmal subarachnoid hemorrhage (aSAH) is a life-threatening condition, and accurate prediction of functional outcomes is critical for optimizing patient management within the initial 3 days of presentation. However, existing clinical scoring systems and imaging assessments do not fully capture clinical variability in predicting outcomes. We developed a deep learning model integrating pre- and postoperative noncontrast CT (NCCT) imaging with clinical data to predict 3-month modified Rankin Scale (mRS) scores in aSAH patients. Using data from 1850 patients across four hospitals, we constructed and validated five models: preoperative, postoperative, stacking imaging, clinical, and fusion models. The fusion model significantly outperformed the others (all p<0.001), achieving a mean absolute error of 0.79 and an area under the curve of 0.92 in the external test. These findings demonstrate that this integrated deep learning model enables accurate prediction of 3-month outcomes and may serve as a prognostic support tool early in aSAH care.