A Review on “Efficient Hybrid Methodology for Early Detection of Breast Cancer in Digital Mammograms using Autoencoder Deep Learning”
Ashish R. Dankekar, Avinash Sharma, Jitendrakumar Mishra · 2024
The most prevalent form of cancer in humans is breast cancer. The term cancer was first used to describe the illness in Egypt around 1600 BC. Despite the fact that since then, research and studies have been conducted to mitigate the effects of this illness, it is still regarded as one of the most lethal diseases of all time due to mortality from breast cancer. Modern medicine has recently created numerous methods and strategies for the early detection of breast cancer. There are many different datasets, hybrid machine learning methods, decision trees, KNN, SVM, naive bays, etc. employed. The majority of technologies rely on cutting-edge tools including deep learning algorithms, medical image processing and machine learning strategies. There have been numerous machine learning experiments conducted in the past. In their respective fields, decision trees, KNN, SVM, naive bays and other neural network techniques outperform the competition. However, a recently developed method is currently being used to classify breast cancer. A new approach is deep learning. Deep learning is used to get over the limits of machine learning. Data science regularly uses deep learning techniques, such as convolution neural networks, recurrent neural networks, deep belief networks and others. Deep learning algorithms outperform machine learning strategies in terms of performance. Images are captured in their most alluring states. CNN is used in our investigation to classify the images. CNN is, in essence, the most extensively utilised system for classifying images. The objective of this study is to determine the best early detection and life-saving strategy for breast cancer.