AI generated annotations for Breast, Brain, Liver, Lungs and Prostate cancer collections in National Cancer Institute Imaging Data Commons

TL;DR

This paper presents the development of AI-generated annotations for multiple cancer types in the NCI Imaging Data Commons, using nnU-Net models trained on open datasets, with radiologist review, to create high-quality, standardized, publicly accessible imaging datasets.

Contribution

The work introduces a large-scale, high-quality AI-annotated imaging dataset for various cancers, integrating AI and radiologist input, and standardizing annotations in DICOM format for the NCI IDC.

Findings

Created annotated datasets for 11 IDC collections across multiple modalities.

Trained nnU-Net models on open-source datasets for accurate segmentation.

Annotations reviewed and corrected by radiologists to ensure quality.

Abstract

AI in Medical Imaging project aims to enhance the National Cancer Institute's (NCI) Image Data Commons (IDC) by developing nnU-Net models and providing AI-assisted segmentations for cancer radiology images. We created high-quality, AI-annotated imaging datasets for 11 IDC collections. These datasets include images from various modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), covering the lungs, breast, brain, kidneys, prostate, and liver. The nnU-Net models were trained using open-source datasets. A portion of the AI-generated annotations was reviewed and corrected by radiologists. Both the AI and radiologist annotations were encoded in compliance with the the Digital Imaging and Communications in Medicine (DICOM) standard, ensuring seamless integration into the IDC collections. All models, images, and annotations are publicly accessible, facilitating further research and development in cancer imaging. This work supports the advancement of imaging tools and algorithms by providing comprehensive and accurate annotated datasets.