A Simple Framework Uniting Visual In-context Learning with Masked Image Modeling to Improve Ultrasound Segmentation

Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning (ICL) is a new and exciting area of research in computer vision. Unlike conventional deep learning, ICL emphasizes the model's ability to adapt to new tasks based on given examples quickly. Inspired by MAE-VQGAN, we proposed a new simple visual ICL method called SimICL, combining visual ICL pairing images with masked image modeling (MIM) designed for self-supervised learning. We validated our method on bony structures segmentation in a wrist ultrasound (US) dataset with limited annotations, where the clinical objective was to segment bony structures to help with further fracture detection. We used a test set containing 3822 images from 18 patients for bony region segmentation. SimICL achieved an remarkably high Dice coeffient (DC) of 0.96 and Jaccard Index (IoU) of 0.92, surpassing state-of-the-art segmentation and visual ICL models (a maximum DC 0.86 and IoU 0.76), with SimICL DC and IoU increasing up to 0.10 and 0.16. This remarkably high agreement with limited manual annotations indicates SimICL could be used for training AI models even on small US datasets. This could dramatically decrease the human expert time required for image labeling compared to conventional approaches, and enhance the real-world use of AI assistance in US image analysis.

Application Of Vision-Language Models For Assessing Osteoarthritis Disease Severity

Osteoarthritis (OA) poses a global health challenge, demanding precise diagnostic methods. Current radiographic assessments are time consuming and prone to variability, prompting the need for automated solutions. The existing deep learning models for OA assessment are unimodal single task systems and they don't incorporate relevant text information such as patient demographics, disease history, or physician reports. This study investigates employing Vision Language Processing (VLP) models to predict OA severity using Xray images and corresponding reports. Our method leverages Xray images of the knee and diverse report templates generated from tabular OA scoring values to train a CLIP (Contrastive Language Image PreTraining) style VLP model. Furthermore, we incorporate additional contrasting captions to enforce the model to discriminate between positive and negative reports. Results demonstrate the efficacy of these models in learning text image representations and their contextual relationships, showcase potential advancement in OA assessment, and establish a foundation for specialized vision language models in medical contexts.