Deep learning‐based automated mitosis detection in histopathology images for breast cancer grading. Issue 4 (20th January 2022)

• Record Type: Journal Article
• Authors: Mathew, Tojo; Ajith, B.; Kini, Jyoti R.; Rajan, Jeny
• Is Part Of: International journal of imaging systems and technology. Volume 32:Issue 4(2022)
• Page Start: 1192
• Page End: 1208
• Publication Date: 2022-01-20
• Subjects: breast cancer -- cancer grading -- deep learning -- histopathology -- mitosis detection; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22703
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Cancer grade is an indicator of the aggressiveness of cancer. It is used for prognosis and treatment decisions. Conventionally cancer grading is performed manually by experienced pathologists via microscopic examination of pathology slides. Among the three factors involved in breast cancer grading (mitosis count, nuclear atypia, and tubule formation), mitotic cell counting is the most challenging task for pathologists. It is possible to automate this task by applying computational algorithms on pathology slides images. Lack of sufficiently large datasets and class imbalance between mitotic and non‐mitotic cells in slide images are the two major challenges in developing effective deep learning‐based methods for mitosis detection. In this paper, we propose a new approach and a method based on that to address these challenges. The high training data requirement of the advanced deep neural network is met by combining two datasets from different sources after a color‐normalization process. Class imbalance is addressed by the augmentation of the mitotic samples in a context‐preserving manner. Finally, a customized convolutional neural network classifier is used to classify the candidate cells into the target classes. We have used the publicly available datasets MITOS‐ATYPIA and MITOS for the experiments. Our method outperforms most of the recent methods that are based on independent datasets and at the same time offers adaptability to the combination of datasets from different sources.