Rahat Shahrior

Rahat Shahrior

Auto-generated profile, based on publicly available information

Rahat Shahrior

Khulna University of Engineering & Technology, Khulna, Bangladesh

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2021
Verified
Conference Paper
Closed access
MKMohammad Badhruddouza Khan
Mohammad Badhruddouza Khan
PSPranto Soumik Saha
Pranto Soumik Saha
RSRahat Shahrior
Rahat Shahrior
Breast cancer is a comprehensively dreadful disease that primarily affects women worldwide. In a lifetime, one out of every eight women is diagnosed with breast cancer. The probability of patient survival rate increases if it is properly diagnosed at the benign stage. However, when a cancer cell metastasizes out from its original development site, it enters into a secondary stage with increasing aggression, infecting other organs via the bloodstream and lymph system. At this stage, the cancer cells become life-threatening, and the survival rate of patients falls drastically. So it is evident that early diagnosis is essential to minimize the extent of the metastasis. Traditional diagnostics procedures by a pathologist are time-consuming and subject to human error. In this study, a custom-designed CNN network is proposed to distinguish metastasis cells from non-metastasis cells from histopathological breast cancer images. This proposed model has obtained an impressive training accuracy of 94.98% and a validation accuracy of 94.08%. The achieved average area under the receiver operating characteristic curve (AVC), Fr-score, recall, and precision of the CNN model are respectively-0.985, 0.94, 0.94, and 0.94. The experimental studies demonstrate the proposed model's ability to distinguish metastasis cells with high accuracy.