Thoracic Radiologists for Data-Annotation Project (QUR00153)

Medcase's client is seeking the expertise of United States Board Certified Radiologists with Thoracic Fellowships to contribute to their upcoming data-annotation project.

Project Summary:

Early global studies into the power of AI for incidental pulmonary nodules (IPNs) shows exciting promise. The latest evidence shows one lung cancer detected for every 1,120 chest X-rays (CXRs) has major implications to diagnose and treat people earlier – and potentially save lives.

The AI algorithm from our client is raising the bar for incidental pulmonary nodule detection. In a retrospective study performed on missed or mislabeled CXR data, the algorithm achieved impressive impressive results for detection of pulmonary nodules.

By acting as a second pair of eyes for radiologists, the algorithm can help detect subtle anatomical anomalies that may otherwise go unnoticed, particularly in asymptomatic patients. This FDA-cleared solution serves as a crucial second reader, assisting in the review of chest radiographs.

In another multi-center study, the algorithm demonstrated an impressive AUC of 94% for scan-level nodule detection, highlighting its potential to significantly impact patient outcomes by identifying early signs of lung cancer that can be easily missed.

By harnessing the power of AI for opportunistic lung cancer surveillance, healthcare providers can adopt a proactive approach to early detection, without significant new investment, and ultimately improving patient survival rates.

Your pulmonary embolism (PE) annotation work will be furthering the developments of this algorithm by enabling the curation of high quality training datasets.

Project Details:

• The radiologist will be responsible for accurately labeling contrast-enhanced CT (CECT) and CT pulmonary angiogram (CTPA) studies for pulmonary embolism (PE) in both lungs.
• Focus will be on annotating acute PE down to the sub-segmental level.
• Project annotation will be done on the Redbrick platform (training will be provided if needed).
• Each case will be reviewed by 3 radiologists and a majority system will be used to classify PE vs non PE labeling. Training on annotation requirements and quality assurance question answer support will also be provided by client and Medcase radiologists.
• The estimated time for annotating each case is deemed to be 12-15 mins.
• There will be 12-18 hours of work per week for this project, throughout the project duration (subject to change based on client's needs and your availability).

Requirements:

• USBC Radiologist with thoracic fellowship and 7+ years of experience. 
• Experience with the data-annotation tool RedBrick (preferred, not required).
• Available to commit ~12-18 hours per week to this project (negotiable within a reasonable range).

For your valued time and insight, you will be compensated a competitive hourly rate.