EARLY STAGE DETECTION AND CLASSIFICATION OF BREAST CANCER

Reddy, C and Mohan, Yeturi and Chandana, S and Kavya, S (2021) EARLY STAGE DETECTION AND CLASSIFICATION OF BREAST CANCER. In: ICASISET 2020, 16-17 May 2020, Chennai, India.

[thumbnail of eai.16-5-2020.2304093.pdf]
Preview
Text
eai.16-5-2020.2304093.pdf - Published Version

Download (675kB) | Preview

Abstract

One of the major diseases that affect young to old aged women in re-cent times is breast cancer. It almost ranks as the first cause for death in women across the world. The survival rate of people suffering with it ranges some-where between 40% and 60% depending on the development terms of particular countries. Hence, it becomes quite important to be able to diagnose such a dis-ease at a stage as early as possible, so the patient could look out on the available options for treatment. Therefore, in this project, we propose such a breast can-cer detection system which predicts the nature of the cancer, either benign or malignant by processing the mammographic image of the patient. The model basically uses a range of digital image processing techniques and also algo-rithms of ML in the process to output the prediction. It is trained using the MIAS breast cancer dataset. The input image is first resized, gray-scaled, and a gaussian filter is applied on it to remove background noises. It is then segment-ed and fed to the neural network, which gives the output prediction as an integer value (each value corresponding to a predicted class). The project also has a second stage where the severity of the cancer is also detected by taking input of other detailed attributes of the mammogram.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: mias resized gray-scaled gaussian filter segmented benign ma-lignant neural network predicted class mammogram
Subjects: Q Science > QA Mathematics > QA76 Computer software
Depositing User: EAI Editor III.
Date Deposited: 09 Mar 2021 09:46
Last Modified: 09 Mar 2021 09:46
URI: https://eprints.eudl.eu/id/eprint/1362

Actions (login required)

View Item
View Item