SPIE-AAPM-NCI DAIR DBTex Challenge now open for submissions

BELLINGHAM, Washington, USA — SPIE, the international society for optics and photonics, in conjunction with the American Association of Physicists in Medicine (AAPM), the National Cancer Institute (NCI), and the Duke Center for Artificial Intelligence in Radiology (DAIR), is organizing the Digital Breast Tomosynthesis Lesion Detection Challenge (DBTex).

Researchers can participate in the DBTex Challenge by submitting results from their algorithms for the detection of biopsy-proven breast lesions on digital breast tomosynthesis (DBT) images. The DBTex Challenge will provide a unique opportunity for participants to compare their breast lesion detection algorithms with those of others from academia, industry, and government in a structured, direct way using a large set of DBT images. The results of the competition will be showcased at a special session of the Computer-Aided Diagnosis (CAD) conference, part of the SPIE Medical Imaging 2021 Digital Forum. In addition, participants in the DBTex Challenge are encouraged to submit their work for peer review to the SPIE's Journal of Medical Imaging.

The winning team will receive a $1,000 prize sponsored by DAIR, contingent on making their code publicly available on GitHub. Depositing of code is only required in order to be eligible to win the prize, but all participants are encouraged to make their code publicly available. Additionally, two individuals from each of the two top-performing teams as well as one individual from the third best-performing team will receive a fee waiver for attending the SPIE Medical Imaging Digital Forum in order to present their methods during the meeting.

"The increased transparency and reproducibility of this challenge will help advance the work on deep learning in breast cancer screening," says Duke University professor and Chair of SPIE Medical Imaging's Computer-Aided Diagnosis (CAD) Conference Maciej Mazurowski. "Since the dataset will remain publicly available, we hope that the work will continue far beyond the competition."

Key dates for the DBTex Challenge:

• 14 December 2020: Release date of training set cases with truth.
• 4 January 2021: Release date of validation set cases.
• 15 January 2020: Release date of test set cases.
• 25 January 2021: Submission date for participants' test set output.
• 4 February 2021: Challenge results released to participants.
• 15-19 February 2021: SPIE Medical Imaging Digital Forum.

The Challenge is the fourth such challenge led by SPIE, AAPM, and NCI — the first to include a collaboration with DAIR — and to be showcased at SPIE Medical Imaging. Previous challenges included 2015's LUNGx Challenge, which tasked participants to classify lung nodules on diagnostic computed tomography (CT) scans as benign or malignant; the two-part PROSTATEx Challenge in 2017, which focused on the development of quantitative image-analysis methods for the diagnostic classification of clinically significant prostate lesions and quantitative MRI biomarkers used to determine Gleason Grade Group in prostate cancers; and 2018's BreastPathQ Cancer Cellularity Challenge which focused on developing and accessing cancer cellularity, a quantitative estimation task in digital pathology.

For more information, access to the training data, and to participate in the DBTex Challenge please visit the Challenge webpage.

About SPIE

SPIE is the international society for optics and photonics, an educational not-for-profit organization founded in 1955 to advance light-based science, engineering, and technology. The Society serves more than 258,000 constituents from 184 countries, offering conferences and their published proceedings, continuing education, books, journals, and the SPIE Digital Library. In 2020, SPIE provided over $5 million in community support including scholarships and awards, outreach and advocacy programs, travel grants, public policy, and educational resources. www.spie.org.

________________________________________
Contact:
Daneet Steffens
Public Relations Manager
daneets@spie.org
+1 360 685 5478
@SPIEtweets