No abstract

Breast cancer has become a critical disease in women. The number of patients with breast cancer is quite high in India. It is of paramount importance to detect the disease in advance. Digital histopathology is one of the most advanced techniques for detection using machine learning. Artificial intelligence is going to be like a sunrise in the field of medicine. Deep neural networks have been successfully applied to the problem under consideration in the past. As, we know the feature extraction is one of the essential and crucial steps in case of classification. In this paper, we compare two approaches, first is feature extraction using traditional Handcrafted based and other is Transfer Learning based model (Pre-trained) for multiclass classification of Breast Cancer using Convolutional Neural Network (CNN) as a classifier. The models are trained using handcrafted features like Seeped Up Robust Features (SURF) and Dense Scale Invariant Feature Transform (DSIFT) techniques, later these extracted features are encoded by Locality Constrained Linear Coding method (LLC). In pre-trained model we have used VGG16, VGG19, ResNet50, GoogLeNet for feature extraction. The maximum accuracy for “SURF+CNN” is 92.88% for Handcrafted feature and in case of Pre-trained “GoogLeNet+ CNN” model gives 94%, both for 400X magnification factor.

No abstract

No abstract

Breast cancer is the leading cause of cancer death among women. Early identification of breast cancer allows patients to receive appropriate therapy, increasing their chances of survival. However, the early and precise detection of breast cancer is more challenging for researchers. Besides, histopathological image is the most effective tool for precise and early detection of breast cancer. Although it has restricted efficiency, breast cancer detection is the main challenge in medical image analysis. This study develops an Enhanced Cat Swarm Optimization-based Deep Convolutional Neural Network (ECSO-based DCNN) for the classification of breast cancer. Pre-processing is also more crucial in image processing since it improves image quality by removing noise from an input image. The segmentation process is used through a designed deep holoentropy-correlative segmentation method, where significant blood cells are extracted. The breast cancer detection and classification are performed using DCNN, which is trained by devised ECSO algorithm. The execution of the introduced deep holoentropy-correlative blood cell segmentation model with optimized DCNN for breast cancer categorization is performed using BreakHis and Breast Cancer Histopathological Annotation and Diagnosis (BreCaHAD) datasets. The proposed ECSO-based DCNN model obtained better performance with accuracy, sensitivity, and specificity of 96.26%, 97.6%, and 93.57%.