ACR's Platform-Model Communication for AI API - Test Site

The American College of Radiology’s Data Science Institute (ACR DSI) has drafted a model API in collaboration with industry, organizational and other partners that it believes will lower the barrier for entry for developers looking to enter the healthcare space, as well as help to standardize communications to the models created, allowing them to be platform agnostic.

Please use the following page to register your system, select a use case and set parameters. The page will then post a request for inference using the API to the systems internet facing URI endpoint. Additional information on the API can be found here.

ACR would like to acknowledge its partnership with SIIM in preparing resources for use in this testing, as well as Datatility for providing our S3 capabilities.

In addition, for those systems POSTing results as DICOM SR, WG20, WG23 and WG27 would like to ask if an attempt could be made to generate a second object represented as JSON per DICOM supplement 219. These objects can be posted to the S3 endpoint or emailed to bbialecki@acr.org.

Please get started by creating a new system. Returning users choose the system tab

Data Citations

Brain MRI for subdural hematoma use cases contain images from:
Bullitt E, Zeng D, Gerig G, Aylward S, Joshi S, Smith JK, Lin W, Ewend MG (2005) Vessel tortuosity and brain tumor malignancy: A blinded study. Academic Radiology 12:1232-1240 The MR brain images from healthy volunteers used in this project were collected and made available by the CASILab at The University of North Carolina at Chapel Hill and were distributed by the MIDAS Data Server at Kitware, Inc.

All other images were collected from public dataset published by The Cancer Imaging Archive (TCIA).
Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of Digital Imaging. 2013; 26(6): 1045-1057. doi: 10.1007/s10278-013-9622-7.
Desai, S., Baghal, A., Wongsurawat, T., Al-Shukri, S., Gates, K., Farmer, P., Rutherford, M., Blake, G.D., Nolan, T., Powell, T., Sexton, K., Bennett, W., Prior, F. (2020). Data from Chest Imaging with Clinical and Genomic Correlates Representing a Rural COVID-19 Positive Population [Data set]. The Cancer Imaging Archive. DOI: . https://doi.org/10.7937/tcia.2020.py71-5978
McCollough, C.H., Chen, B., Holmes, D., III, Duan, X., Yu, Z., Yu, L., Leng, S., Fletcher, J. (2020). Data from Low Dose CT Image and Projection Data [Data set]. The Cancer Imaging Archive.https://doi.org/10.7937/9npb-2637
Kinahan, P., Muzi, M., Bialecki, B., Herman, B., & Coombs, L. (2019). Data from the ACRIN 6668 Trial NSCLC-FDG-PET [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/tcia.2019.30ilqfcl