Diagnosis of breast cancer in light microscopic and mammographic images textures using relative entropy via kernel estimation

2015 ◽  
Vol 54 (4) ◽  
pp. 561-573 ◽  
Author(s):  
Sevcan Aytac Korkmaz ◽  
Mehmet Fatih Korkmaz ◽  
Mustafa Poyraz
Keyword(s):  
Breast Cancer ◽  
Relative Entropy ◽  
Kernel Estimation ◽  
Mammographic Images

scholarly journals Lesion Detection in Breast Tomosynthesis Using Efficient Deep Learning and Data Augmentation Techniques

2021 ◽  
Author(s):  
Loay Hassan ◽  
Mohamed Abedl-Nasser ◽  
Adel Saleh ◽  
Domenec Puig
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Breast Lesion ◽  
Data Augmentation ◽  
Digital Breast Tomosynthesis ◽  
Lesion Detection ◽  
Detection Methods ◽  
Breast Tomosynthesis ◽  
Mammographic Images ◽  
Augmentation Techniques

Digital breast tomosynthesis (DBT) is one of the powerful breast cancer screening technologies. DBT can improve the ability of radiologists to detect breast cancer, especially in the case of dense breasts, where it beats mammography. Although many automated methods were proposed to detect breast lesions in mammographic images, very few methods were proposed for DBT due to the unavailability of enough annotated DBT images for training object detectors. In this paper, we present fully automated deep-learning breast lesion detection methods. Specifically, we study the effectiveness of two data augmentation techniques (channel replication and channel-concatenation) with five state-of-the-art deep learning detection models. Our preliminary results on a challenging publically available DBT dataset showed that the channel-concatenation data augmentation technique can significantly improve the breast lesion detection results for deep learning-based breast lesion detectors.

Automatic detection of various patterns of calcification distribution on mammograms: a graph convolution network approach (Preprint)

2021 ◽  
Author(s):  
Melissa Min-Szu Yao ◽  
Hao Du ◽  
Mikael Hartman ◽  
Wing P. Chan ◽  
Mengling Feng
Keyword(s):  
Breast Cancer ◽  
Breast Imaging ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Automatic Detection ◽  
Ground Truth ◽  
Architectural Distortion ◽  
Breast Cancers ◽  
Convolutional Network ◽  
Mammographic Images

UNSTRUCTURED Purpose: To develop a novel artificial intelligence (AI) model algorithm focusing on automatic detection and classification of various patterns of calcification distribution in mammographic images using a unique graph convolution approach. Materials and methods: Images from 200 patients classified as Category 4 or 5 according to the American College of Radiology Breast Imaging Reporting and Database System, which showed calcifications according to the mammographic reports and diagnosed breast cancers. The calcification distributions were classified as either diffuse, segmental, regional, grouped, or linear. Excluded were mammograms with (1) breast cancer as a single or combined characterization such as a mass, asymmetry, or architectural distortion with or without calcifications; (2) hidden calcifications that were difficult to mark; or (3) incomplete medical records. Results: A graph convolutional network-based model was developed. 401 mammographic images from 200 cases of breast cancer were divided based on calcification distribution pattern: diffuse (n = 24), regional (n = 111), group (n = 201), linear (n = 8) or segmental (n = 57). The classification performances were measured using metrics including precision, recall, F1 score, accuracy and multi-class area under receiver operating characteristic curve. The proposed achieved precision of 0.483 ± 0.015, sensitivity of 0.606 (0.030), specificity of 0.862 ± 0.018, F1 score of 0.527 ± 0.035, accuracy of 60.642% ± 3.040% and area under the curve of 0.754 ± 0.019, finding method to be superior compared to all baseline models. The predicted linear and diffuse classifications were highly similar to the ground truth, and the predicted grouped and regional classifications were also superior compared to baseline models. Conclusion: The proposed deep neural network framework is an AI solution to automatically detect and classify calcification distribution patterns on mammographic images highly suspected of showing breast cancers. Further study of the AI model in an actual clinical setting and additional data collection will improve its performance.

scholarly journals Breast Cancer Conspicuity on Simultaneously Acquired Digital Mammographic Images versus Digital Breast Tomosynthesis Images

Radiology ◽  
2019 ◽  
Vol 292 (1) ◽  
pp. 69-76 ◽  
Author(s):  
Katrina E. Korhonen ◽  
Emily F. Conant ◽  
Eric A. Cohen ◽  
Marie Synnestvedt ◽  
Elizabeth S. McDonald ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Digital Breast Tomosynthesis ◽  
Breast Tomosynthesis ◽  
Mammographic Images

scholarly journals Classification of Breast Cancer from Digital Mammography Using Deep Learning

2020 ◽  
Vol 23 (65) ◽  
pp. 56-66 ◽  
Author(s):  
José Daniel López-Cabrera ◽  
Luis Alberto López Rodríguez ◽  
Marlén Pérez-Díaz
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Current Trend ◽  
Malignant Tumour ◽  
Final Diagnosis ◽  
Diagnostic Systems ◽  
Human Errors ◽  
Low Contrast ◽  
Mammographic Images ◽  
In Series

Breast cancer is the most frequent in females. Mammography has proven to be the most effective method for the early detection of this type of cancer. Mammographic images are sometimes difficult to understand, due to the nature of the anomalies, the low contrast image and the composition of the mammary tissues, as well as various technological factors such as spatial resolution of the image or noise. Computer-aided diagnostic systems have been developed to increase the accuracy of mammographic examinations and be used by physicians as a second opinion in obtaining the final diagnosis, and thus reduce human errors. Convolutional neural networks are a current trend in computer vision tasks, due to the great performance they have achieved. The present investigation was based on this type of networks to classify into three classes, normal, benign and malignant tumour. Due to the fact that the miniMIAS database used has a low number of images, the transfer learning technique was applied to the Inception v3 pre-trained network. Two convolutional neural network architectures were implemented, obtaining in the architecture with three classes, 86.05% accuracy. On the other hand, in the architecture with two neural networks in series, an accuracy of 88.2% was reached.

scholarly journals Breast Cancer Detection via Mammographic Images : A Survey

2020 ◽  
pp. 173-195
Author(s):  
Mary Walowe Mwadulo ◽  
Raphael Angulu ◽  
Stephen Makau Mutua
Keyword(s):  
Breast Cancer ◽  
Cancer Cells ◽  
Cancer Detection ◽  
Breast Cancer Cells ◽  
Cost Effective ◽  
Breast Cancer Detection ◽  
Term Survival ◽  
Mammographic Images ◽  
Cancer Breast ◽  
Future Work

Breast cancer is a top killer disease for women globally. The long term survival rate of women can be improved through early and effective screening of breast cancer cells. Currently, a mammogram is the recommended tool for breast cancer screening since it can identify breast cancer cells several years before physical signs appear and it is cost effective. This paper analyzes mammographic detection of breast cancer by providing an explanation on development and classification of Breast Cancer, Image representation models for breast tumor, mammography technologies, a discussion on various mammographic signs of breast cancer, breast cancer feature extraction techniques, popular breast cancer classification techniques, comparative analysis of existing mammogram breast cancer databases, and a review of mammographic breast cancer detection studies are presented. Finally, a highlight on future work is given.

scholarly journals Self-Organization Map Based Segmentation of Breast Cancer

2018 ◽  
Vol 7 (2) ◽  
pp. 31-36
Author(s):  
A. Arokiyamary Delphina ◽  
M. Kamarasan ◽  
S. Sathiamoorthy
Keyword(s):  
Breast Cancer ◽  
Image Analysis ◽  
Self Organization ◽  
Segmentation Method ◽  
X Ray ◽  
Mammographic Images ◽  
Physical Testing ◽  
Graphic Images ◽  
Exploratory Report ◽  
Similar Texture

Breast cancer is second major leading cause of cancer fatality in women. Mammography prevails best method for initial detection of cancers of breast, capable of identifying small pieces up to two years before they grow large enough to be evident on physical testing. X-ray images of breast must be accurately evaluated to identify beginning signs of cancerous growth. Segmenting, or partitioning, Radio-graphic images into regions of similar texture is usually performed during method of image analysis and interpretation. The comparative lack of structure definition in mammographic images and implied transition from one texture to makes segmentation remarkably hard. The task of analyzing different texture areas can be considered form of exploratory report since priori awareness about number of different regions in image is not known. This paper presents a segmentation method by utilizing SOM.

A Computational Investigation of Breast Tumour on Mammogram Based on Pattern of Grey Scale Distribution

2019 ◽  
Vol 43 ◽  
pp. 67-73
Author(s):  
M.K. Lim ◽  
Wan Khairunizam ◽  
Wan Azani Mustafa
Keyword(s):  
Breast Cancer ◽  
Detection System ◽  
Wiener Filter ◽  
Breast Tumour ◽  
Computational Investigation ◽  
Mammographic Images ◽  
Cause Of Deaths ◽  
Analysis Society ◽  
Mammogram Image ◽  
Mammogram Images

Breast cancer is the utmost female tumor and the primary cause of deaths among female. Computer-Aided Detection (CAD) systems are widely used as a tool to detect and classify the abnormalities found in the mammographic images. A detection of breast tumor in a mammogram has been a challenge due to the different intensity distribution which leads to the misdiagnosis of breast cancer. This research proposes a dectection system that is capable to detect the presence of mass tumor from a mammogram image. A total of 160 mammogram images are acquired from Mammographic Image Analysis Society (MIAS) databse, which are 80 normal and 80 abnormal images. The mammogram images are rescaled to 300 x 300 resolution. The noise in the mammogram is suppressed by using a Wiener filter. The images are enhanced by using Power Law (Gamma) Transformation, ɣ = 2 for a better image quality. The greyscale information that contain tumor mass is extracted and used to model the proposed detection system by using 80% or 128 and of the total 160 mammogram images. The rest 20% or 32 mammogram images are used to test the performance of the proposed detection system. The experimental results show that performance of the proposed detection system has 90.93% accuracy.

Sign in / Sign up

Export Citation Format

Share Document