Abstract
Existing computational approaches have not yet resulted in effective and efficient computer-aided tools that are used in pathologists' daily practice. Focusing on a computer-based qualification for breast cancer diagnosis, the present study proposes two deep learning architectures to efficiently and effectively detect and classify mitosis in a histopathological tissue sample. The first method consists of two parts, entailing a preprocessing of the digital histological image and a free-handcrafted-feature Convolutional Neural Network (CNN) used for binary classification. Results show that the methodology proposed can achieve 95% accuracy in testing, with an F1-score of 94.35%. This result is higher than the results using classical image processing techniques and also higher than the approaches combining CCNs with handcrafted features. The second approach is an end-to-end methodology using semantic segmentation. Results showed that this algorithm can achieve an accuracy higher than 95% in testing and an average Dice index of 0.6, higher than the existing results using CNNs (0.9 F1-score). Additionally, due to the semantic properties of the deep learning approach, an end-to-end deep learning framework is viable to perform both tasks: detection and classification of mitosis. The results show the potential of deep learning in the analysis of Whole Slide Images (WSI) and its integration to computer-aided systems. The extension of this work to whole slide images is also addressed in the last sections; as well as, some computational key points that are useful when constructing a computer-aided-system inspired by the proposed technology.
Highlights
Recent estimations by the World Health Organization positioned breast cancer in the top 5 killing types of cancer in the world (DeSantis et al, 2015; World Health Organization, 2018)
A critical step in the Convolutional Neural Network (CNN) approach using the AlexNet is the detection of potential mitosis in the High Power Fields (HPF) frames
We have shown how two different deep learning approaches (i.e., AlexNet and U-Net) performs when dealing with the classification and detection of mitosis
Summary
Recent estimations by the World Health Organization positioned breast cancer in the top 5 killing types of cancer in the world (DeSantis et al, 2015; World Health Organization, 2018). Histological examination of tissue specimens remains the gold standard for diagnosis and accurate evaluation of breast diseases (Owens and Ashcroft, 1987). In order to objectively classify the tumor and determine the treatment strategy for patients with breast cancer, pathologists often use the Nottingham Histology Score (NHS), referred to as the Scarff-Bloom-Richardson grading system (Bloom and Richardson, 1957). NHS assigns a score from 1 to 3 to the tissue sample in three categories: (i) presence of glandular/tubular structures; (ii) nuclear pleomorphism; and (iii) mitotic count. The sum of all these scores will determine the cancer grading and its related severity. Due to their different stages and forms, mitotic counting is one of the most challenging and timeconsuming tasks for pathologists. The present article focuses on this particular challenge, one of the key features for an accurate diagnosis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
