TY - GEN
T1 - Pre-Processing Techniques to Facilitate Better Detection of Breast Abnormalities Using Digital Mammogram
AU - Bhattacharjee, Sangita
AU - Poddar, Sandeep
AU - Bhaumik, Amiya
AU - Maitra, Indra Kanta
AU - Susanna, Dewi
AU - Ware, Andrew
N1 - Publisher Copyright:
© 2023 American Institute of Physics Inc.. All rights reserved.
PY - 2023/8/24
Y1 - 2023/8/24
N2 - Digital Mammography is a popular technique for early, non-invasive, breast cancer detection. It is based on the identification and analysis of abnormalities in the breast tissue. Digital Mammography offers the potential for the development of algorithms that can enable computer-aided detection (CAD). This paper proposes such an algorithm based on a three-step process. The first step involves contrast enhancement using the Contrast Limited Adaptive Histogram Equalization (CLAHE) method. 2nd Step is Isolation of Pectoral Muscle from ROI: The medial oblique view has been improved, and the breast and lymph nodes are now more visibly visible in it. The pectoral muscle is kept separate from the area of interest for further investigation (ROI). "Region growth" enables the process of grouping pixels or smaller portions in the image to merge and become larger sections or regions on the basis of some preconceived specifications. The fundamental method is to start from the tip known as the "seed", and then grow in the area by adding adjacent pixels.
AB - Digital Mammography is a popular technique for early, non-invasive, breast cancer detection. It is based on the identification and analysis of abnormalities in the breast tissue. Digital Mammography offers the potential for the development of algorithms that can enable computer-aided detection (CAD). This paper proposes such an algorithm based on a three-step process. The first step involves contrast enhancement using the Contrast Limited Adaptive Histogram Equalization (CLAHE) method. 2nd Step is Isolation of Pectoral Muscle from ROI: The medial oblique view has been improved, and the breast and lymph nodes are now more visibly visible in it. The pectoral muscle is kept separate from the area of interest for further investigation (ROI). "Region growth" enables the process of grouping pixels or smaller portions in the image to merge and become larger sections or regions on the basis of some preconceived specifications. The fundamental method is to start from the tip known as the "seed", and then grow in the area by adding adjacent pixels.
UR - http://www.scopus.com/inward/record.url?scp=85187568828&partnerID=8YFLogxK
U2 - 10.1063/5.0165148
DO - 10.1063/5.0165148
M3 - Conference contribution
AN - SCOPUS:85187568828
T3 - AIP Conference Proceedings
BT - AIP Conference Proceedings
A2 - Poddar, Sandeep
A2 - Ghazali, Sheikh Ahmad Izaddin Sheikh Mohd
A2 - Biswas, Hari Shankar
A2 - Chakrabarti, Prasun
A2 - Kanungo, Priyadarshi
A2 - Rani, Yavana
A2 - Das, Urmisha
PB - American Institute of Physics
T2 - 2022 Sustainable Developments in Materials Science, Technology and Engineering: Sustainable Development in Material Science of Today Is the Innovation of Tomorrow
Y2 - 22 April 2022 through 23 April 2022
ER -
