scholarly journals Feature Fusion Based on Convolutional Neural Network for Breast Cancer Auxiliary Diagnosis

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xiaofan Cheng ◽  
Liang Tan ◽  
Fangpeng Ming
Keyword(s):  
Breast Cancer ◽  
Feature Fusion ◽  
Hot Spot ◽  
Image Features ◽  
Remote Areas ◽  
Medical Standards ◽  
Medical Facilities ◽  
Diagnosis Rate ◽  
Malignant Breast ◽  
Basic Network

Cancer is one of the leading causes of death in many countries. Breast cancer is one of the most common cancers in women. Especially in remote areas with low medical standards, the diagnosis efficiency of breast cancer is extremely low due to insufficient medical facilities and doctors. Therefore, in-depth research on how to improve the diagnosis rate of breast cancer has become a hot spot. With the development of society and science, people use artificial intelligence to improve the auxiliary diagnosis of diseases in the existing medical system, which can become a solution for detecting and accurately diagnosing breast cancer. The paper proposes an auxiliary diagnosis model that uses deep learning in view of the low rate of human diagnosis by doctors in remote areas. The model uses classic convolutional neural networks, including VGG16, InceptionV3, and ResNet50 to extract breast cancer image features, then merge these features, and finally train the model VIRNets for auxiliary diagnosis. Experimental results prove that for the recognition of benign and malignant breast cancer pathological images under different magnifications, VIRNets have a high generalization and strong robustness, and their accuracy is better than their basic network and other structures of the network. Therefore, the solution provides a certain practical value for assisting doctors in the diagnosis of breast cancer in real scenes.

scholarly journals A New Modified Recurrent Extreme Learning with PSO Machine Based on Feature Fusion with CNN Deep Features for Breast Cancer Detection

2020 ◽  
Vol 1 (3) ◽  
pp. 15-21
Author(s):  
Surendra Prasad M ◽  
◽  
Manimurugan S ◽  
Keyword(s):  
Breast Cancer ◽  
Extreme Learning Machine ◽  
Feature Fusion ◽  
Early Recognition ◽  
Breast Cancer Mortality ◽  
Texture Features ◽  
Mass Detection ◽  
Bee Colony ◽  
Malignant Breast ◽  
Learning Machine

Breast cancer is a prevalent cause of death, and is the only form of cancer that is common among women worldwide and mammograms-based computer-aided diagnosis (CAD) program that allows early detection, diagnosis and treatment of breast cancer. But the performance of the current CAD systems is still unsatisfactory. Early recognition of lumps will reduce overall breast cancer mortality. This study investigates a method of breast CAD, focused on feature fusion with deep features of the Convolutional Neural Network (CNN). First, present a scheme of mass detection based on CNN deep features and modified clustering of the Extreme Learning Machine (MRELM). It forecasts load through Recurrent Extreme Learning Machine (RELM) and utilizes Artificial Bee Colony (ABC) to optimize weights and biases. Second, a collection of features is constructed that relays deep features, morphological features, texture features, and density features. Third, MRELM classifier is developed to distinguish benign and malignant breast masses using the fused feature set. Extensive studies show the precision and efficacy of the proposed method of mass diagnosis and classification of breast cancer.

scholarly journals Contrast-enhanced ultrasound of breast fibromatosis: a case report

2021 ◽  
Vol 49 (5) ◽  
pp. 030006052110106
Author(s):  
Shanhong Lin ◽  
Yong Cao ◽  
Libin Chen ◽  
Mei Chen ◽  
Shengmin Zhang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Rare Case ◽  
Common Type ◽  
Breast Lesions ◽  
Contrast Enhanced Ultrasound ◽  
High Similarity ◽  
Potential Value ◽  
Contrast Enhanced ◽  
Malignant Breast ◽  
Contrast Enhanced Ultrasonography

We herein present a rare case of breast fibromatosis, the contrast-enhanced ultrasonography (CEUS) findings of which we believe have never been described. The high similarity between the clinical and imaging manifestations of breast cancer makes its differential diagnosis difficult. In this report, we describe the CEUS findings of a less common type of fibromatosis, discuss the potential value of CEUS to differentiate it from malignant breast lesions, and briefly review the literature.

scholarly journals Predicting Implicit User Preferences with Multimodal Feature Fusion for Similar User Recommendation in Social Media

2021 ◽  
Vol 11 (3) ◽  
pp. 1064
Author(s):  
Jenq-Haur Wang ◽  
Yen-Tsang Wu ◽  
Long Wang
Keyword(s):  
Social Media ◽  
Feature Fusion ◽  
Relevant Information ◽  
Image Features ◽  
User Preferences ◽  
User Preference ◽  
Late Fusion ◽  
Multimodal Features ◽  
Fusion Methods ◽  
Text Features

In social networks, users can easily share information and express their opinions. Given the huge amount of data posted by many users, it is difficult to search for relevant information. In addition to individual posts, it would be useful if we can recommend groups of people with similar interests. Past studies on user preference learning focused on single-modal features such as review contents or demographic information of users. However, such information is usually not easy to obtain in most social media without explicit user feedback. In this paper, we propose a multimodal feature fusion approach to implicit user preference prediction which combines text and image features from user posts for recommending similar users in social media. First, we use the convolutional neural network (CNN) and TextCNN models to extract image and text features, respectively. Then, these features are combined using early and late fusion methods as a representation of user preferences. Lastly, a list of users with the most similar preferences are recommended. The experimental results on real-world Instagram data show that the best performance can be achieved when we apply late fusion of individual classification results for images and texts, with the best average top-k accuracy of 0.491. This validates the effectiveness of utilizing deep learning methods for fusing multimodal features to represent social user preferences. Further investigation is needed to verify the performance in different types of social media.

scholarly journals Blood levels of Polycyclic Aromatic Hydrocarbons in Women with Benign and Malignant Breast Lesions: A case-control study

2011 ◽  
Vol 1 (2) ◽  
pp. 80-86 ◽  
Author(s):  
Vipul K Singh ◽  
M Anand ◽  
D Rawtani ◽  
Uday P Singh ◽  
DK Patel ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Polycyclic Aromatic Hydrocarbons ◽  
Aromatic Hydrocarbons ◽  
Case Control Study ◽  
Case Control ◽  
Breast Lesions ◽  
Total Pahs ◽  
Polycyclic Aromatic ◽  
Malignant Breast ◽  
Control Study

Objective: As part of our program to investigate the possible role of environmental pollutants in the incidence of breast cancer in India, we conducted for the first time a hospital based case-control study where blood polycyclic aromatic hydrocarbons (PAHs) levels were determined in women suffering from benign and malignant breast lesions, and compared with those of disease free controls drawn from similar socioeconomic environment residing in and around New Delhi, India. Material & Methods: Anthracene, phenanthrene, fluoranthene, naphthalene, pyrene, benzo (a) pyrene, benzo (k) fluoranthene and dibenzo (a,h) anthracene were determined by HPLC-FD. Results: Level of total PAHs in control, benign and malignant groups (30 numbers in each) were 142.05 ± 50.84, 185.99 ± 61.97 and 200.74 ± 55.05 μg / L respectively. Mean levels of naphthalene, phenanthrene, pyrene and benzo (k) fluoranthene were higher in both malignant and benign groups than in control but the difference was not statistically significant. Of the total PAHs, 3–ringed compounds were found much higher (89%) in controls than in benign (52%) and malignant groups (54%). However, the percentage sum of 2, 4 and 5-ringed PAHs were much higher in malignant (46%) and benign (48%) groups when compared with those of controls (11%). Conclusion: Results of the present study indicate that higher levels of PAHs (especially non-carcinogenic), though statistically non-significant, were present in cases with benign and malignant breast lesions than in those of controls. Key Words: Polycyclic Aromatic Hydrocarbons; Breast cancer; Benign lesions; HPLC-FD  DOI: 10.3126/ajms.v1i2.2924Asian Journal of Medical Sciences 1 (2010) 80-86

Sign in / Sign up

Export Citation Format

Share Document