A cost-effective computer-vision based breast cancer diagnosis

Abstract

In the last decade, there have been extensive reports of world health organization (WHO) on breast cancer. About 2.1 million women are affected every year and it is the second most leading cause of cancer death in women. Initial detection and diagnosis of cancer appreciably increase the chance of saving lives and reduce treatment costs. In this paper, we perform a survey of the techniques utilized in breast cancer detection and diagnosis in image processing, machine learning (ML), and deep learning (DL). We also proposed a novel computer-vision based cost-effective method for breast cancer detection and diagnosis. Along with the detection and diagnosis of breast cancer, our proposed method is capable of finding the exact position of the abnormality present in the breast that will help in breast-conserving surgery or partial mastectomy. The proposed method is the simplest and cost-effective approach that has produced highly accurate and useful outcomes when compared with the existing approach.

Fully convolutional network for automated detection and diagnosis of mammographic masses

“…Sethy et al performed a survey for the methods useful for the detection and dignosis of breast cancer and also developed a robust and cost effective approach using the HOG feature and SVM to detect and diagnose the breast cancer and achieved an accuracy of 99.64%. [ 40 ]. From the above literature , it can be observed that the majority of the CAD systems with conventional machine learning methods mainly used hand crafted features which is immensely dependent on the human experts.…”

Optimal deep transfer learning driven computer‐aided breast cancer classification using ultrasound images

“…In the feature extraction process, the feature is significantly classified into morphology, model-related, and texture, descriptor features are calculated by ROI details. Due to this highly complicated job calculation demand for medical specialists (Sethy et al, 2021), there is no economic existence of a CAD system with higher sensibility as well as specificity. Currently, convolutional neural networks (CNNs), and a deep learning (DL) method, have gained significant interest as a vigorous tool for extracting and studying proficient features straightforwardly from a provided data collection.…”