Petrick Nicholas, Akbar Shazia, Cha Kenny H, Nofech-Mozes Sharon, Sahiner Berkman, Gavrielides Marios A, Kalpathy-Cramer Jayashree, Drukker Karen, Martel Anne L
U.S. Food and Drug Administration, Center for Devices and Radiological Health, Silver Spring, Maryland, United States.
University of Toronto, Medical Biophysics, Toronto, Ontario, Canada.
J Med Imaging (Bellingham). 2021 May;8(3):034501. doi: 10.1117/1.JMI.8.3.034501. Epub 2021 May 8.
: The breast pathology quantitative biomarkers (BreastPathQ) challenge was a grand challenge organized jointly by the International Society for Optics and Photonics (SPIE), the American Association of Physicists in Medicine (AAPM), the U.S. National Cancer Institute (NCI), and the U.S. Food and Drug Administration (FDA). The task of the BreastPathQ challenge was computerized estimation of tumor cellularity (TC) in breast cancer histology images following neoadjuvant treatment. : A total of 39 teams developed, validated, and tested their TC estimation algorithms during the challenge. The training, validation, and testing sets consisted of 2394, 185, and 1119 image patches originating from 63, 6, and 27 scanned pathology slides from 33, 4, and 18 patients, respectively. The summary performance metric used for comparing and ranking algorithms was the average prediction probability concordance (PK) using scores from two pathologists as the TC reference standard. : Test PK performance ranged from 0.497 to 0.941 across the 100 submitted algorithms. The submitted algorithms generally performed well in estimating TC, with high-performing algorithms obtaining comparable results to the average interrater PK of 0.927 from the two pathologists providing the reference TC scores. : The SPIE-AAPM-NCI BreastPathQ challenge was a success, indicating that artificial intelligence/machine learning algorithms may be able to approach human performance for cellularity assessment and may have some utility in clinical practice for improving efficiency and reducing reader variability. The BreastPathQ challenge can be accessed on the Grand Challenge website.
乳腺病理定量生物标志物（BreastPathQ）挑战赛是由国际光学与光子学学会（SPIE）、美国医学物理学会（AAPM）、美国国立癌症研究所（NCI）和美国食品药品监督管理局（FDA）联合举办的一项重大挑战赛。BreastPathQ挑战赛的任务是对新辅助治疗后的乳腺癌组织学图像中的肿瘤细胞密度（TC）进行计算机化估计。
共有39个团队在挑战赛期间开发、验证并测试了他们的TC估计算法。训练集、验证集和测试集分别由来自33名、4名和18名患者的63张、6张和27张扫描病理切片中的2394个、185个和1119个图像块组成。用于比较和排名算法的综合性能指标是使用两名病理学家的评分作为TC参考标准的平均预测概率一致性（PK）。
在提交的100种算法中，测试PK性能范围为0.497至0.941。提交的算法在估计TC方面总体表现良好，高性能算法获得的结果与提供参考TC评分的两名病理学家的平均评分者间PK 0.927相当。
SPIE - AAPM - NCI BreastPathQ挑战赛取得了成功，表明人工智能/机器学习算法在细胞密度评估方面可能能够接近人类表现，并且在临床实践中可能具有提高效率和减少阅片者差异的作用。可在重大挑战赛网站上访问BreastPathQ挑战赛。
