Blending Ensemble of Fine-Tuned Convolutional Neural Networks Applied to Mammary Image Classification

Abstract

Medical images classification is a challenging research topic in the field of computer vision, especially when applied to diagnosis of breast cancer (BC). Nowadays, histopathological image is marked as the gold standard for diagnosing BC. However, such diagnosis is heavily dependent on the clinician's experience, which is extremely time consuming and is subjected to human error even for experienced doctors. To address those problems, this paper implements an automated method for distinguishing the benign from the malignant tumor based on a convolutional neural network (CNN). Traditional deep CNN and machine learning methods not only lead to poor performance, but also fail to make full use of the long-term dependence between some key features and image tags. To further meet the high accuracy requirement of diagnosis, according to the characteristics of histopathological images, we propose a novel CNN framework. Firstly, a normal image is augmented to solve the problem about having a limited database. Secondly, we introduce transfer learning to obtain more accurate weight parameters that were pre-trained on the ImageNet. Thirdly, we combine various features extracted by many individual models to obtain comprehensive features. Finally, random forest is introduced to enforce classification. The experimental results show that novel CNN frameworks have better performance compared with individual models, including DenseNet and ResNet. Experimental results are able to prove the effectiveness of our strategy.

Continuous Use Intention of Mobile Social Network Information Service Based on User Behavior Perception

“…Literature [ 14 ] put forward four hypotheses about the attitude and behavior of LBS information users and obtained relevant conclusions by sending out questionnaires to college students to collect data and analyze them. Literature [ 15 ] introduces the theory of self-construction, proposes a model of self-construction for users to accept mobile location services, and verifies it; Literature [ 16 ] uses social capital theory to analyze the impact of LBS's interpersonal communication on individual network capital, information capital, credit capital, emotion, and influence of capital. Reference [ 17 ] introduces influencing factors such as individual conformity into the original model of TAM users, builds a new hypothesis model, verifies the hypothesis, and puts forward suggestions for the development of the mobile location service industry.…”

A Novel Framework for Classifying Leather Surface Defects Based on a Parameter Optimized Residual Network

“…In the medical field, the pathological features were extracted from the pathological images for performing the diagnosis of different stages of diseases by a deep convolution network. This could be applied to prevent and effectively diagnose the infections of various diseases [11]- [15]. In the agriculture, the convolution network was used to classify the patches of images for the diagnosis of the growing stages of the diseases [16], [17].…”