Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study
Inter-pathologist agreement for nuclear atypia scoring of breast cancer is poor. To address this problem, previous studies suggested some criteria for describing the variations appearance of tumor cells relative to normal cells. However, these criteria were still assessed subjectively by pathologists. Previous studies used quantitative computer-extracted features for scoring. However, application of these tools is limited as further improvement in their accuracy is required. This study proposes COMPASS (COMputer-assisted analysis combined with Pathologist’s ASSessment) for reproducible nuclear atypia scoring. COMPASS relies on both cytological criteria assessed subjectively by pathologists as well as computer-extracted textural features. Using machine learning, COMPASS combines these two sets of features and output nuclear atypia score. COMPASS’s performance was evaluated using 300 images for which expert-consensus derived reference nuclear pleomorphism scores were available, and they were scanned by two scanners from different vendors. A personalized model was built for three pathologists who gave scores to six atypia-related criteria for each image. Leave-one-out cross validation (LOOCV) was used. COMPASS was trained and tested for each pathologist separately. Percentage agreement between COMPASS and the reference nuclear scores was 93.8%, 92.9%, and 93.1% for three pathologists. COMPASS’s performance in nuclear grading was almost identical for both scanners, with Cohen’s kappa ranging from 0.80 to 0.86 for different pathologists and different scanners. Independently, the images were also assessed by two experienced senior pathologists. Cohen’s kappa of COMPASS was comparable to the Cohen’s kappa for two senior pathologists (0.79 and 0.68).
KeywordsBreast Breast cancer Microscopy Nuclear atypia grading Nuclear pleomorphism grading Pattern recognition
We would like to thank Mitosis-Atypia challenge organizers who collected the data utilized in the study and kindly provided us the access to their dataset after the challenge time. We also acknowledge the University of Sydney HPC Service at the University of Sydney for providing the high-performance computing resources that have contributed to the research results reported within this paper.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they have no conflict of interest.
- 1.Mook S, Schmidt MK, Rutgers EJ, van de Velde AO, Visser O, Rutgers SM, Armstrong N, van’t Veer LJ, Ravdin PM: Calibration and discriminatory accuracy of prognosis calculation for breast cancer with the online adjuvant! Program: A hospital-based retrospective cohort study. Lancet Oncol 10(11):1070–1076, 2009CrossRefGoogle Scholar
- 3.Bueno-de-Mesquita JM, Nuyten D, Wesseling J, van Tinteren H, Linn S, van De Vijver M: The impact of inter-observer variation in pathological assessment of node-negative breast cancer on clinical risk assessment and patient selection for adjuvant systemic treatment. Ann Oncol 21(1):40–47, 2009CrossRefGoogle Scholar
- 6.Longacre TA, Ennis M, Quenneville LA, Bane AL, Bleiweiss IJ, Carter BA, Catelano E, Hendrickson MR, Hibshoosh H, Layfield LJ: Interobserver agreement and reproducibility in classification of invasive breast carcinoma: An NCI breast cancer family registry study. Mod Pathol 19(2):195–207, 2006CrossRefGoogle Scholar
- 7.Meyer JS, Alvarez C, Milikowski C, Olson N, Russo I, Russo J, Glass A, Zehnbauer BA, Lister K, Parwaresch R: Breast carcinoma malignancy grading by Bloom–Richardson system vs proliferation index: Reproducibility of grade and advantages of proliferation index. Mod Pathol 18(8):1067–1078, 2005CrossRefGoogle Scholar
- 11.Cosatto E, Miller M, Graf HP, Meyer JS. Grading nuclear pleomorphism on histological micrographs. InPattern Recognition, 2008. ICPR 2008. 19th International Conference on 2008 Dec 8 (pp. 1-4). IEEE.Google Scholar
- 14.Zhang R, Chen H-j, Wei B, Zhang H-y, Pang Z-g, Zhu H, Zhang Z, Fu J, Bu H: Reproducibility of the Nottingham modification of the Scarff-Bloom-Richardson histological grading system and the complementary value of Ki-67 to this system. Chin Med J (Engl Ed) 123(15):1976, 2010Google Scholar
- 19.Macenko M, Niethammer M, Marron JS, Borland D, Woosley JT, Guan X, Schmitt C, and Thomas NE, A method for normalizing histology slides for quantitative analysis. pp. 1107–1110Google Scholar
- 25.Viera AJ, Garrett JM: Understanding interobserver agreement: The kappa statistic. Fam Med 37(5):360–363, 2005Google Scholar
- 28.Gandomkar Z, Brennan PC, Mello-Thoms C. A framework for distinguishing benign from malignant breast histopathological images using deep residual networks. In14th International Workshop on Breast Imaging (IWBI 2018), International Society for Optics and Photonics, Vol. 10718, p. 107180U, 2018.Google Scholar
- 29.Cireşan DC, Giusti A, Gambardella LM, and Schmidhuber J, Mitosis detection in breast cancer histology images with deep neural networks. pp. 411–418Google Scholar
- 31.Gandomkar Z, Tay K, Brennan PC, and Mello-Thoms C, A model based on temporal dynamics of fixations for distinguishing expert radiologists’ scanpaths. p. 1013606Google Scholar
- 33.Gandomkar Z, Tay K, Ryder W, Brennan PC, and Mello-Thoms C, Predicting radiologists’ true and false positive decisions in reading mammograms by using gaze parameters and image-based features. p. 978715Google Scholar