The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various medical vision tasks. However, due to large spatial sizes with much higher dimensions of 3D medical images, the lack of hierarchical design for MAE may hinder the performance of downstream tasks. In this paper, we propose a novel Mask in Mask (MiM) pre-training framework for 3D medical images, which aims to advance MAE by learning discriminative representation from hierarchical visual tokens across varying scales. We introduce multiple levels of granularity for masked inputs from the volume, which are then reconstructed simultaneously ranging at both fine and coarse levels. Additionally, a cross-level alignment mechanism is applied to adjacent level volumes to enforce anatomical similarity hierarchically. Furthermore, we adopt a hybrid backbone to enhance the hierarchical representation learning efficiently during the pre-training. MiM was pre-trained on a large scale of available 3D volumetric images, i.e., Computed Tomography (CT) images containing various body parts. Extensive experiments on twelve public datasets demonstrate the superiority of MiM over other SSL methods in organ/tumor segmentation and disease classification. We further scale up the MiM to large pre-training datasets with more than 10k volumes, showing that large-scale pre-training can further enhance the performance of downstream tasks. Code is available at https://github.com/JiaxinZhuang/MiM.

Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning (DL) is widely used in this problem, but the performance of testing data (also known as target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (also known as source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment (SDA) to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT (NDCT) images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance.

Learning medical visual representations directly from paired radiology reports has become an emerging topic in representation learning. However, existing medical image-text joint learning methods are limited by instance or local supervision analysis, ignoring disease-level semantic correspondences. In this paper, we present a novel Multi-Granularity Cross-modal Alignment (MGCA) framework for generalized medical visual representation learning by harnessing the naturally exhibited semantic correspondences between medical image and radiology reports at three different levels, i.e., pathological region-level, instance-level, and disease-level. Specifically, we first incorporate the instance-wise alignment module by maximizing the agreement between image-report pairs. Further, for token-wise alignment, we introduce a bidirectional cross-attention strategy to explicitly learn the matching between fine-grained visual tokens and text tokens, followed by contrastive learning to align them. More important, to leverage the high-level inter-subject relationship semantic (e.g., disease) correspondences, we design a novel cross-modal disease-level alignment paradigm to enforce the cross-modal cluster assignment consistency. Extensive experimental results on seven downstream medical image datasets covering image classification, object detection, and semantic segmentation tasks demonstrate the stable and superior performance of our framework.

Deep learning has attracted rapidly increasing attention in the field of tomographic image reconstruction, especially for CT, MRI, PET/SPECT, ultrasound and optical imaging. Among various topics, sparse-view CT remains a challenge which targets a decent image reconstruction from very few projections. To address this challenge, in this article we propose a Dual-domain Residual-based Optimization NEtwork (DRONE). DRONE consists of three modules respectively for embedding, refinement, and awareness. In the embedding module, a sparse sinogram is first extended. Then, sparse-view artifacts are effectively suppressed in the image domain. After that, the refinement module recovers image details in the residual data and image domains synergistically. Finally, the results from the embedding and refinement modules in the data and image domains are regularized for optimized image quality in the awareness module, which ensures the consistency between measurements and images with the kernel awareness of compressed sensing. The DRONE network is trained, validated, and tested on preclinical and clinical datasets, demonstrating its merits in edge preservation, feature recovery, and reconstruction accuracy.