Assessment of deep learning algorithms to predict histopathological diagnosis of breast cancer: first Moroccan prospective study on a private dataset

• Published in: BMC research notes Vol. 15; no. 1; p. 66
• Main Authors: El Agouri, H, Azizi, M, El Attar, H, El Khannoussi, M, Ibrahimi, A, Kabbaj, R, Kadiri, H, BekarSabein, S, EchCharif, S, Mounjid, C, El Khannoussi, B
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 19-02-2022; BioMed Central; BMC
• Subjects: Accuracy; Algorithms; Artificial intelligence; Breast cancer; Breast carcinoma; Breast Neoplasms - diagnosis; Breast Neoplasms - pathology; Cancer therapies; Classification; Computer applications; Convolutional Neural Networks; COVID-19; Datasets; Deep Learning; Diagnosis; Digital pathology; Digitization; Female; Health aspects; Humans; Invasiveness; Learning algorithms; Machine learning; Microscopy; Neural networks; Neural Networks, Computer; Pathology; Prognosis; Prospective Studies; Public health; Research Note; Risk factors; Morocco; Deep learning; Digital pathology; Breast cancer; Convolutional Neural Networks; Artificial intelligence; Machine learning
• ISSN: 1756-0500; 1756-0500
• DOI: 10.1186/s13104-022-05936-1

Breast cancer is a critical public health issue and a leading cause of cancer-related deaths among women worldwide. Its early diagnosis and detection can effectively help in increasing the chances of survival rate. For this reason, the diagnosis and classification of breast cancer using Deep learning algorithms have attracted a lot of attention. Therefore, our study aimed to design a computational approach based on deep convolutional neural networks for an efficient classification of breast cancer histopathological images by using our own created dataset. We collected overall 328 digital slides, from 116 of surgical breast specimens diagnosed with invasive breast carcinoma of non-specific type, and referred to the histopathology department of the National Institute of Oncology in Rabat, Morocco. We used two models of deep neural network architectures in order to accurately classify the images into one of three categories: normal tissue-benign lesions, in situ carcinoma or invasive carcinoma.
Both Resnet50 and Xception models achieved comparable results, with a small advantage to Xception extracted features. We reported high degrees of overall correct classification accuracy (88%), and sensitivity (95%) for detection of carcinoma cases, which is important for diagnostic pathology workflow in order to assist pathologists for diagnosing breast cancer with precision. The results of the present study showed that the designed classification model has a good generalization performance in predicting diagnosis of breast cancer, in spite of the limited size of the data. To our knowledge, this approach can be highly compared with other common methods in the automated analysis of breast cancer images reported in literature.