Magnetic resonance imaging (MRI) is a leading modality for the diagnosis of liver cancer, significantly improving the classification of the lesion and patient outcomes. However, traditional MRI faces challenges including risks from contrast agent (CA) administration, time-consuming manual assessment, and limited annotated datasets. To address these limitations, we propose a Time-Conditioned Autoregressive Contrast Enhancement (T-CACE) framework for synthesizing multi-phase contrast-enhanced MRI (CEMRI) directly from non-contrast MRI (NCMRI). T-CACE introduces three core innovations: a conditional token encoding (CTE) mechanism that unifies anatomical priors and temporal phase information into latent representations; and a dynamic time-aware attention mask (DTAM) that adaptively modulates inter-phase information flow using a Gaussian-decayed attention mechanism, ensuring smooth and physiologically plausible transitions across phases. Furthermore, a constraint for temporal classification consistency (TCC) aligns the lesion classification output with the evolution of the physiological signal, further enhancing diagnostic reliability. Extensive experiments on two independent liver MRI datasets demonstrate that T-CACE outperforms state-of-the-art methods in image synthesis, segmentation, and lesion classification. This framework offers a clinically relevant and efficient alternative to traditional contrast-enhanced imaging, improving safety, diagnostic efficiency, and reliability for the assessment of liver lesion.

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.

Segmentation and quantitative measurement of liver tumors, including hemangiomas and hepatocellular carcinoma (HCC), using dynamic Magnetic Resonance Imaging (MRI) sequences are crucial for effective treatment and prognosis. However, these tasks remain challenging due to two key issues: (1) the severe class imbalance between tumors and background, particularly for small HCC lesions, which complicates precise feature extraction; and (2) the diverse imaging features across dynamic MRI phases, making effective fusion of multi-phase information difficult. To address these challenges, this study proposes the Uncertainty-guided and Cross-modality Attention Network (UgCmA-Net). UgCmA-Net incorporates three innovative components: (1) a cross-modality attention pyramid module within a parallel attention-based encoder, enhancing tumor-specific feature extraction across dynamic phases; (2) a fusion Transformer (F-Trans), where the non-local Transformer captures long-range dependencies, and the phase-aware Transformer fuses multi-phase dynamic MRI features; and (3) an uncertainty-guided auxiliary-primary segmentor, which improves edge confidence and segmentation accuracy through uncertainty estimation. The UgCmA-Net was validated using dynamic MRI sequences (T1 pre-contrast MRI, arterial-phase, portal venous phase, and delay-phase contrast-enhanced MRI) from 265 clinical subjects. Experimental results show that the proposed UgCmA-Net achieves state-of-the-art performance, with a dice similarity coefficient of 85.44%, Hausdorff Distance of 2.28 mm, and mean absolute error values of 1.85 mm, 1.90 mm, 6.52 mm, and 97.27 mm 2 for multi-index quantification of center point, max-diameter, circumference, and area, respectively. Statistical analysis confirms that the improvements are statistically significant (p < 0.05), demonstrating the robustness of the proposed method. These findings demonstrate that UgCmA-Net is highly effective for liver tumor segmentation and quantification, indicating its potential clinical value in liver tumor analysis and treatment planning.

Contrast-enhanced knowledge distillation promises to transform medical diagnostics and reveal promising approaches for tumor segmentation on non-contrast medical images. However, existing methods related to contrast-enhanced knowledge distillation still make it hard to distill reliable contrast-enhanced knowledge for tumor segmentation due to the limitations of (1) unable to quantify uncertainty information for reliable contrast-enhanced and non-contrast knowledge modeling, which leads to an over-confidence cross-domain adaptation for transferring contrast-enhanced knowledge; (2) using vision information only ignores rich semantic features in medical language, which make it hard to model complex tumor enhancement feature. In this study, we propose an evidence-guided and tumor-aware knowledge distillation (EGTA-KD) for transferring contrast-enhanced domain knowledge to non-contrast domain knowledge. Specifically, to achieve tumor-awareness by embedding semantic features from text, the tumor-aware cross-modal synchronizer (TACMS) is proposed to calculate tumor score maps for matching pixel wise image and text features. To achieve reliable cross-domain modeling for transferring contrast-enhanced knowledge, the innovative uncertainty-quantified evidence unit (UQEU) parameterizes the probability distribution within subjective logic to gather reliable evidence of contrast-enhanced knowledge while quantifying the uncertainty of prediction. Lastly, newly designed dual-level knowledge distillation (DLKD) minimizes tumor score map errors and matches evidence distribution for uncertainty-aware contrast-enhanced knowledge distillation. Extensive experiments of tumor segmentation on non-contrast medical images are performed using multi-modality medical image datasets (i.e., Brain MRI dataset, Liver MRI dataset, and Kidney CT dataset). Experimental results demonstrate the proposed EGTA-KD outperforms the other compared state-of-the-art methods, revealing its superiority of tumor segmentation on non-contrast medical images via uncertainty-aware contrast-enhanced knowledge distillation.