Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models

Radiologists highly desire fully automated versatile AI for medical imaging interpretation. However, the lack of extensively annotated large-scale multi-disease datasets has hindered the achievement of this goal. In this paper, we explore the feasibility of leveraging language as a naturally high-quality supervision for chest CT imaging. In light of the limited availability of image-report pairs, we bootstrap the understanding of 3D chest CT images by distilling chest-related diagnostic knowledge from an extensively pre-trained 2D X-ray expert model. Specifically, we propose a language-guided retrieval method to match each 3D CT image with its semantically closest 2D X-ray image, and perform pair-wise and semantic relation knowledge distillation. Subsequently, we use contrastive learning to align images and reports within the same patient while distinguishing them from the other patients. However, the challenge arises when patients have similar semantic diagnoses, such as healthy patients, potentially confusing if treated as negatives. We introduce a robust contrastive learning that identifies and corrects these false negatives. We train our model with over 12,000 pairs of chest CT images and radiology reports. Extensive experiments across multiple scenarios, including zero-shot learning, report generation, and fine-tuning processes, demonstrate the model's feasibility in interpreting chest CT images.

Using Large Context for Kidney Multi-Structure Segmentation from CTA Images

Accurate and automated segmentation of multi-structure (i.e., kidneys, renal tu-mors, arteries, and veins) from 3D CTA is one of the most important tasks for surgery-based renal cancer treatment (e.g., laparoscopic partial nephrectomy). This paper briefly presents the main technique details of the multi-structure seg-mentation method in MICCAI 2022 KIPA challenge. The main contribution of this paper is that we design the 3D UNet with the large context information cap-turing capability. Our method ranked eighth on the MICCAI 2022 KIPA chal-lenge open testing dataset with a mean position of 8.2. Our code and trained models are publicly available at https://github.com/fengjiejiejiejie/kipa22_nnunet.