| Abstrakt: |
Breast cancer is an invasive tumor that develops in the breast tissue. It is the most common cancer and also the leading cause of cancer mortality among women worldwide. Survival from breast cancer can be increased through advances in screening methods and early diagnosis. Clinical examination, screening using imaging modalities and pathological assessment (biopsy test) are common methods of breast cancer diagnosis. Among these, pathological assessment is a gold standard due to its potential in identifying the cancer type, sub-type and stage. However, current diagnosis using this pathological assessment technique is commonly done through visual inspection microscopic images. This procedure is time consuming, tedious and subjective which may lead to misdiagnosis. In this paper, a multi-class classification system for breast cancer type, sub-type and grade is proposed based on deep learning technique. The system was trained and validated using histopathological images acquired from Jimma University Medical Center (JUMC) using digital camera (Optikam PRO5) mounted on Optika microscope by four levels of magnification (40x, 100x, 200x, 400x), and also from 'BreakHis' and 'zendo' online datasets. All images were pre-processed and enhanced prior to feeding to the ResNet 50 pre-trained model. The developed system is capable of classifying breast cancer into binary classes (benign and malignant) and multi-classes (sub-types). Identification of cancer grade was done for cancers that are classified as invasive ductal carcinomas. Test results showed that, the proposed method is 96.75%, 96.7%, 95.78%, and 93.86% accurate for binary classification, benign sub-type classification, malignant sub-type classification, and grade identification, respectively. The proposed method can be used as a decision support system for physicians especially in developing countries where both the means and the expertise are in scarce. Early and accurate detection of cancer type increases the chance of successful treatment resulting a reduction in breast cancer mortality rate. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink