Year: 2023
Type: article
Abstract: Mammography is the major diagnostic tool for detecting breast cancer early, alerting the patient to abnormalities long before she would notice them physically. Using digital mammography pictures, the Computer Aided Diagnosis (CAD) technology detects breast abnormalities. To forecast the required items, deep learning techniques learn the image's characteristics using a small set of expert-annotated data. In recent years, the accuracy of convolutional neural networks (CNN) has soared in a variety of image processing tasks, including image detection, identification, and classification. This work offers an automated approach for detecting and classifying breast cancer lesions in mammograms, using the state-of-the-art object detection deep learning technique Faster R-CNN. In order to train the Faster R-CNN network, the proposed CAD system employs a total of 330 mammography pictures, 121 of which have been annotated. Using the testing dataset, the suggested method achieved a mAP (mean Average Precision) of 0.857.
Authors: Kumar, Indrajeet, Gudur, Rashmi
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7217788233
