===Year 3: High-throughput truthing of microscope slides to validate artificial intelligence algorithms analyzing digital scans of pathology slides: data collection to create the medical device development tool (MDDT)===

In Year 3 of the High Throughput Truthing project, the team will collect data at various collaborating sites and conferences. [[BR]]
Check out our completed work from [HighThroughputTruthingYear1 Year 1] and [HighThroughputTruthingYear2 Year 2] in the HTT project [[BR]]


'''Pitch:'''::
     We are crowdsourcing pathologists to collect data (images + pathologist annotations) that can be qualified by the FDA/CDRH medical device development tool program (MDDT). If successful, the MDDT qualified data along with a statistical software package for data analysis would be available to any algorithm developer to be used to validate their algorithm performance in a submission to the FDA/CDRH.


Researchers from the U.S. Food and Drug Administration, alongside academic collaborators, are collecting pathologist annotations as data for AI/ML algorithm validation for tumor infiltrating lymphocyte (TIL) detection and quantitation. We are asking board-certified anatomic pathologists and anatomic pathology residents to score 80 ROIs as part of a research study. We anticipate that this task will take participants a total of 30 minutes. The data are intended to inform the agency’s approach to novel algorithm validation, ensuring high quality commercial products with a faster FDA-pipeline to approval. [[BR]] [[BR]]

===[HTTdataCollectionTraining Complete the HTT Data Collection Training]===


NOTE:   EVERYTHING BELOW THIS WILL BE MOVED




__[=#point3]Training documents:__ [[BR]]
'''The Study:''' [[File(dataCollectionTutorialHTT.pdf)]] – This __'''DRAFT'''__ tutorial outlines the project, and provides a demonstration of your tasks for all three data collection platforms.

'''The Clinical Task:''' [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6267863/ TILs evaluation manuscript], [https://ncihub.org/groups/eedapstudies/wiki/HighThroughputTruthingYear3/File:TutorialWebsiteAdapted29012020.pdf TILs training slides] – Participating pathologists can review the clinical training slides (required to participate), and read the related manuscript if possible. These materials were created by the [https://www.tilsinbreastcancer.org/ TILs in breast cancer working group].

'''The Hardware Used in the Study:''' [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4478997/ eeDAP] – Annotations will be collected in digital and microscope modes. For the microscope mode, we will use eeDAP, an Evaluation Environment for Digital and Analog Pathology (eeDAP), a registration system between the microscope and digital whole slide images.

__[=#point4]Consent Form:__ [[BR]]
[[File(HTT_IRBinformedConsent.pdf)]]

__[=#point5]Exit Survey:__ [[BR]]
Please complete [https://docs.google.com/forms/d/e/1FAIpQLSfoh2f4RoxFAgDPPoU430P6Uo26PMbRLmrboLL9wfaF5LA9gQ/viewform this Survey] when you finish data collection, and help us improve the HTT project.

__[=#point6]Get Involved:__ [[BR]]
 * Supply glass slides and their scanned versions
 * Help create a Continuing Medical Education course in conjunction with this project
 * Host an analog (microscope + eeDAP) data collection event at your clinical site
 * Help spread the word, recruit your colleagues to participate in online data collection

__[=#point7]Thank you. For more information contact:__ [[BR]]
'''Brandon Gallas''', !PhD, ([mailto:brandon.gallas@fda.hhs.gov brandon.gallas@fda.hhs.gov]) [[BR]]
FDA/CDRH/OSEL Division of Imaging, Diagnostics, and Software Reliability [[BR]]
on behalf of the High-Throughput Truthing (HTT) Project