We present a multimodal AI pipeline to streamline patient selection and quality assessment for radiology AI development. Our system evaluates patient clinical histories, imaging protocols, and data quality, embedding results into imaging metadata. Using FiftyOne researchers can rapidly filter and assemble high-quality cohorts in minutes instead of weeks, freeing radiologists for clinical work and accelerating AI tool development.

AI-based diagnostic tools for skin cancer have become increasingly popular due to their efficiency and low cost. However, a critical limitation of many existing models is their lack of diversity in training data—particularly the underrepresentation of darker skin tones. As a result, these models tend to perform poorly on non-white patients, increasing the risk of misdiagnosis or delayed diagnosis and contributing to significant health disparities. This project aims to address this issue by developing a diagnostic tool capable of accurately identifying malignant skin lesions across all skin tones

Radiologists need a lot of time and experience to interpret medical images in a correct way and infer diagnoses from them. Pixel Diagnose is a tool to help radiologists navigate the huge amount of available data. It aids them in the differential diagnosis process.

Foundations of Machine Learning and Deep Learning; Medical Imaging and Computer Vision; Video Processing and Pose Estimation; Comprehensive Project Work and Integration

Workshop covering Foundations of Machine Learning and Deep Learning; Medical Imaging and Computer Vision; Video Processing and Pose Estimation; Comprehensive Project Work and Integration.