Multi-contrast magnetic resonance imaging (MRI) has important value in clinical applications because it can reflect comprehensive tissue characterization from anatomy and function to metabolism. Previous studies utilize abundant details in high-resolution (HR) reference (Ref) images to guide the super-resolution (SR) of low-resolution (LR) images, termed multi-contrast MRI SR. Yet, their clinical applications are hindered by: 1) discrepancies in MRI equipment and acquisition protocols across hospitals (which lead to gaps in data distribution), and 2) lack of paired LR and HR images in certain modalities for supervised training. Herein, we rethink multi-contrast MRI from a clinical perspective, and propose an implicit sampling and generation (ISG) network plus an unsupervised fine-tuning (FT) framework. Briefly, the ISG network possesses a powerful representation capability, enabling arbitrary-scale LR inputs and SR outputs. The fine-tuning framework, as a test-time training technique, allows models to be adapted to testing data. Experiments are conducted on two clinical datasets containing amide proton transfer weighted (APTw) images from tumor patients and fluid-attenuated inversion recovery (FLAIR) images from a 5T scanner, respectively. For tumor patients, our ISG+FT proves $4{\times }$ SR capacity in APTw metabolic images, receiving good recognition from radiologists. In both quantitative and qualitative evaluations, ISG+FT outperforms state-of-the-art baselines. The ablation and robustness study further demonstrate the rationality of ISG+FT. Overall, our proposed method shows considerable promise in clinical scenarios.

Chemical Exchange Saturation Transfer Magn-etic Resonance Imaging (CEST-MRI) is a promising approach for detecting tissue metabolic changes. However, due to the constraints of scan time and contrast-noise-ratio, CEST-MRI always exhibits low spatial resolution, hindering the clinical applications especially for detection of small lesions. Many super-resolution (SR) methods have shown good performance in medical images. However, when applied to CEST-MRI, these methods have two shortcomings that may limit their performance. Firstly, CEST-MRI has an additional frequency dimension, but the information along this dimension is not fully utilized. The second is that these SR methods mainly focus on improving the quality of the CEST-weighted images, while the accuracy of the quantitative maps is the most concerned aspect for CEST-MRI. To address these shortcomings, we propose a Cross-space Optimization-based Mutual learning nETwork (COMET) for SR of CEST-MRI. COMET incorporates novel spatio-frequency extraction modules and a mutual learning module to leverage and combine information from both spatial and frequency spaces, thereby enhancing the SR performance. Furthermore, we propose a novel CEST-based normalization loss to address the normalization-induced distribution problem and preserve the sharpness of quantitative maps, enabling more accurate CEST-MRI quantification. COMET is evaluated on an ischemia rat brain dataset and a human brain dataset. The results demonstrate COMET achieves 8-fold SR, providing accurate quantitative maps. Moreover, COMET outperforms all other state-of-the-art SR methods. Additionally, COMET exhibits its potential in prospective study.

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pretrained models on the training domains. We first address TTA as a feature revision problem due to the domain gap between source domains and target domains. After that, we follow the two measurements alignment and uniformity to discuss the test time feature revision. For test time feature uniformity, we propose a test time self-distillation strategy to guarantee the consistency of uniformity between representations of the current batch and all the previous batches. For test time feature alignment, we propose a memorized spatial local clustering strategy to align the representations among the neighborhood samples for the upcoming batch. To deal with the common noisy label problem, we propound the entropy and consistency filters to select and drop the possible noisy labels. To prove the scalability and efficacy of our method, we conduct experiments on four domain generalization bench marks and four medical image segmentation tasks with various backbones. Experiment results show that our method not only improves baseline stably but also outperforms existing state-of-the-art test time adaptation methods.

Multi-modality medical imaging is crucial in clinical treatment as it can provide complementary information for medical image segmentation. However, collecting multi-modal data in clinical is difficult due to the limitation of the scan time and other clinical situations. As such, it is clinically meaningful to develop an image segmentation paradigm to handle this missing modality problem. In this paper, we propose a prototype knowledge distillation (ProtoKD) method to tackle the challenging problem, especially for the toughest scenario when only single modal data can be accessed. Specifically, our ProtoKD can not only distillate the pixel-wise knowledge of multi-modality data to single-modality data but also transfer intra-class and inter-class feature variations, such that the student model could learn more robust feature representation from the teacher model and inference with only one single modality data. Our method achieves state-of-the-art performance on BraTS benchmark.

In real teaching scenarios, an excellent teacher always teaches what he (or she) is good at but the student is not. This gives the student the best assistance in making up for his (or her) weaknesses and becoming a good one overall. Enlightened by this, we introduce the "Teaching what you Should Teach" strategy into a knowledge distillation framework, and propose a data-based distillation method named "TST" that searches for desirable augmented samples to assist in distilling more efficiently and rationally. To be specific, we design a neural network-based data augmentation module with priori bias to find out what meets the teacher's strengths but the student's weaknesses, by learning magnitudes and probabilities to generate suitable data samples. By training the data augmentation module and the generalized distillation paradigm alternately, a student model is learned with excellent generalization ability. To verify the effectiveness of our method, we conducted extensive comparative experiments on object recognition, detection, and segmentation tasks. The results on the CIFAR-100, ImageNet-1k, MS-COCO, and Cityscapes datasets demonstrate that our method achieves state-of-the-art performance on almost all teacher-student pairs. Furthermore, we conduct visualization studies to explore what magnitudes and probabilities are needed for the distillation process.

Multi-contrast magnetic resonance imaging can provide comprehensive information for clinical diagnosis. However, multi-contrast imaging suffers from long acquisition time, which makes it inhibitive for daily clinical practice. Subsampling k-space is one of the main methods to speed up scan time. Missing k-space samples will lead to inevitable serious artifacts and noise. Considering the assumption that different contrast modalities share some mutual information, it may be possible to exploit this redundancy to accelerate multi-contrast imaging acquisition. Recently, generative adversarial network shows superior performance in image reconstruction and synthesis. Some studies based on k-space reconstruction also exhibit superior performance over conventional state-of-art method. In this study, we propose a cross-domain two-stage generative adversarial network for multi-contrast images reconstruction based on prior full-sampled contrast and undersampled information. The new approach integrates reconstruction and synthesis, which estimates and completes the missing k-space and then refines in image space. It takes one fully-sampled contrast modality data and highly undersampled data from several other modalities as input, and outputs high quality images for each contrast simultaneously. The network is trained and tested on a public brain dataset from healthy subjects. Quantitative comparisons against baseline clearly indicate that the proposed method can effectively reconstruct undersampled images. Even under high acceleration, the network still can recover texture details and reduce artifacts.