Adaptation of a deep learning malignancy model from full-field digital mammography to digital breast tomosynthesis

Singh, Sadanand; Matthews, Thomas P.; Shah, Meet; Mombourquette, Brent; Tsue, Trevor; Long, Aaron; Almohsen, Ranya; Pedemonte, Stefano; Su, Jason

doi:10.48550/arxiv.2001.08381

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several recent works have used deep learning to either classify DBT scans for the presence of lesions [17][18][19][20][21][22][23][24][25][26][27][28][29] or localize lesion(s) within DBT scans. Localization tasks include determining the exact shape of these lesions, known as segmentation, 12,30,31 or drawing bounding boxes around them, known as detection.…”

Section: Introductionmentioning

confidence: 99%

A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis

Konz

Buda

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceAn accurate and robust artificial intelligence (AI) algorithm for detecting cancer in digital breast tomosynthesis (DBT) could significantly improve detection accuracy and reduce health care costs worldwide.ObjectivesTo make training and evaluation data for the development of AI algorithms for DBT analysis available, to develop well-defined benchmarks, and to create publicly available code for existing methods.Design, Setting, and ParticipantsThis diagnostic study is based on a multi-institutional international grand challenge in which research teams developed algorithms to detect lesions in DBT. A data set of 22 032 reconstructed DBT volumes was made available to research teams. Phase 1, in which teams were provided 700 scans from the training set, 120 from the validation set, and 180 from the test set, took place from December 2020 to January 2021, and phase 2, in which teams were given the full data set, took place from May to July 2021.Main Outcomes and MeasuresThe overall performance was evaluated by mean sensitivity for biopsied lesions using only DBT volumes with biopsied lesions; ties were broken by including all DBT volumes.ResultsA total of 8 teams participated in the challenge. The team with the highest mean sensitivity for biopsied lesions was the NYU B-Team, with 0.957 (95% CI, 0.924-0.984), and the second-place team, ZeDuS, had a mean sensitivity of 0.926 (95% CI, 0.881-0.964). When the results were aggregated, the mean sensitivity for all submitted algorithms was 0.879; for only those who participated in phase 2, it was 0.926.Conclusions and RelevanceIn this diagnostic study, an international competition produced algorithms with high sensitivity for using AI to detect lesions on DBT images. A standardized performance benchmark for the detection task using publicly available clinical imaging data was released, with detailed descriptions and analyses of submitted algorithms accompanied by a public release of their predictions and code for selected methods. These resources will serve as a foundation for future research on computer-assisted diagnosis methods for DBT, significantly lowering the barrier of entry for new researchers.

show abstract