An Integrated Deep Architecture for Lesion Detection in Breast MRI

2020 ◽  
pp. 646-659
Author(s):  
Ghazal Rouhafzay ◽  
Yonggang Li ◽  
Haitao Guan ◽  
Chang Shu ◽  
Rafik Goubran ◽  
...  
Keyword(s):  
Breast Mri ◽  
Lesion Detection ◽  
Deep Architecture

scholarly journals Evaluation of a Nonrigid Motion Compensation Technique Based on Spatiotemporal Features for Small Lesion Detection in Breast MRI

2012 ◽  
Vol 2012 ◽  
pp. 1-10 ◽  
Author(s):  
F. Steinbruecker ◽  
A. Meyer-Baese ◽  
T. Schlossbauer ◽  
D. Cremers
Keyword(s):  
Breast Cancer ◽  
Motion Compensation ◽  
Rigid Motion ◽  
Breast Mri ◽  
Lesion Detection ◽  
Nonrigid Motion ◽  
Small Lesion ◽  
Spatiotemporal Features ◽  
Optical Flow Method ◽  
Compensation Technique

Motion-induced artifacts represent a major problem in detection and diagnosis of breast cancer in dynamic contrast-enhanced magnetic resonance imaging. The goal of this paper is to evaluate the performance of a new nonrigid motion correction algorithm based on the optical flow method. For each of the small lesions, we extracted morphological and dynamical features describing both global and local shape, and kinetics behavior. In this paper, we compare the performance of each extracted feature set under consideration of several 2D or 3D motion compensation parameters for the differential diagnosis of enhancing lesions in breast MRI. Based on several simulation results, we determined the optimal motion compensation parameters. Our results have shown that motion compensation can improve the classification results. The results suggest that the computerized analysis system based on the non-rigid motion compensation technique and spatiotemporal features has the potential to increase the diagnostic accuracy of MRI mammography for small lesions and can be used as a basis for computer-aided diagnosis of breast cancer with MR mammography.

Enhanced Lesion Detection in Breast MRI Using Parallel and Cascaded Integration of Deep Learning Models

2021 ◽  
pp. 1-21
Author(s):  
Ghazal Rouhafzay ◽  
Yonggang Li ◽  
Haitao Guan ◽  
Chang Shu ◽  
Rafik Goubran ◽  
...  
Keyword(s):  
Deep Learning ◽  
Breast Mri ◽  
Lesion Detection ◽  
Learning Models

Automated breast cancer lesion detection on breast MRI using artificial intelligence.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e14612-e14612 ◽  
Author(s):  
Nataly Tapia Negrete ◽  
Ruquaiyah Takhtawala ◽  
Madeleine Shaver ◽  
Turkay Kart ◽  
Yang Zhang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Artificial Intelligence ◽  
Breast Tumor ◽  
Breast Mri ◽  
Lesion Detection ◽  
Tumor Segmentation ◽  
Dice Similarity Coefficient ◽  
Data Set ◽  
Post Contrast

e14612 Background: Over 40,000 women in the US will die from breast cancer. Early detection of cancer is crucial and is a potential avenue to improve survival. The objective of this research study is to develop a convoluted neural network (CNN), a subset of artificial intelligence, in order to enhance computerized detection of breast lesions on MRIs. Methods: This is an institutional review board approved retrospective study with post contrast MRI data from 238 patients. Breast tumor segmentation was automated with a hybrid 3D/2D CNN designed adapted from U-net, a popular neural network architecture in biomedical image analysis. T1 post-contrast MRI volumes were used to train the network. The data set was separated into training (80%) and validation (20%) sets. Re-sampling and normalization using z-scores were applied to each volume before training. Contracting and expanding arms of the model consist of successive convolutions followed by batch normalization and ReLU operations. Ground truth was established through manual segmentation and previously conducted readings of the images used to train our network. Results: A 5-fold cross validation was performed for analysis. The Dice similarity coefficient was used to assess segmentation accuracy. The hybrid 3D/2D U-Net architecture yielded a Dice score of 0.753 and a Pearson correlation of 0.548 for the breast tumor segmentation. Conclusions: These results demonstrated the feasibility for artificial intelligence applications in accurately identifying the presence of lesions on breast MRI images.

scholarly journals Comparison of Cartesian and radial acquisition on short-tau inversion recovery (STIR) sequences in breast MRI

2017 ◽  
Vol 50 (4) ◽  
pp. 216-223 ◽  
Author(s):  
Domiziana Santucci ◽  
Sheila S. Lee ◽  
Heidi Hartman ◽  
Shyama Walgampaya ◽  
Mamdoh AlObaidy ◽  
...  
Keyword(s):  
Lymph Node ◽  
Image Quality ◽  
Chest Wall ◽  
Breast Mri ◽  
Motion Artifacts ◽  
Lesion Detection ◽  
Fat Suppression ◽  
Inversion Recovery ◽  
Observer Agreement ◽  
Short Tau Inversion Recovery

Abstract Objective: The purpose of this study was to compare two short-tau inversion recovery (STIR) sequences, Cartesian and radial (BLADE) acquisitions, for breast magnetic resonance imaging (MRI) examinations. Materials and Methods: Ninety-six women underwent 1.5 T breast MRI exam (48 Cartesian and 48 BLADE). Qualitative analysis including image artifacts, image quality, fat-suppression, chest-wall depiction, lesion detection, lymph node depiction and overall impression were evaluated by three blinded readers. Signal to noise ratios (SNRs) were calculated. Cronbach's alpha test was used to assess inter-observer agreement. Subanalyses of image quality, chest-wall depiction and overall impression in 15 patients with implants and image quality in 31 patients with clips were correlated using Pearson test. Wilcoxon rank sum test and t-test were performed. Results: Motion artifacts were present in 100% and in 0% of the Cartesian and the BLADE exams, respectively. Chemical-shift artifacts were present in 8% of the Cartesian exams. Flow artifacts were more frequent on BLADE. BLADE sequence was statistically superior to Cartesian for all qualitative features (p < 0.05) except for fat-suppression (p = 0.054). In the subanalysis, BLADE was superior for implants and clips (p < 0.05). SNR was statistically greater for BLADE (48.35 vs. 16.17). Cronbach ranged from 0.502 to 0.813. Conclusion: BLADE appears to be superior to Cartesian acquisition of STIR imaging as measured by improved image quality, fewer artifacts, and improved chest wall and lymph node depiction.

scholarly journals Automatic lesion detection, segmentation and characterization via 3D multiscale morphological sifting in breast MRI

2020 ◽  
Vol 6 (6) ◽  
pp. 065027
Author(s):  
Hang Min ◽  
Darryl McClymont ◽  
Shekhar S Chandra ◽  
Stuart Crozier ◽  
Andrew P Bradley
Keyword(s):  
Breast Mri ◽  
Lesion Detection

Evaluation of a known breast cancer using an abbreviated breast MRI protocol: Correlation of imaging characteristics and pathology with lesion detection and conspicuity

2016 ◽  
Vol 85 (4) ◽  
pp. 815-823 ◽  
Author(s):  
Laura Heacock ◽  
Amy N. Melsaether ◽  
Samantha L. Heller ◽  
Yiming Gao ◽  
Kristine M. Pysarenko ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Mri ◽  
Lesion Detection ◽  
Imaging Characteristics ◽  
Mri Protocol ◽  
Abbreviated Breast Mri

Significance of Incidentally Detected Subcentimeter Enhancing Lesions on Preoperative Breast MRI: Role of Second-Look Ultrasound in Lesion Detection and Management

2015 ◽  
Vol 204 (3) ◽  
pp. W357-W362 ◽  
Author(s):  
Se Jin Nam ◽  
Eun-Kyung Kim ◽  
Min Jung Kim ◽  
Hee Jung Moon ◽  
Jung Hyun Yoon
Keyword(s):  
Breast Mri ◽  
Lesion Detection ◽  
Second Look ◽  
Preoperative Breast Mri

What to Do if Breast MRI Isn't a Screening Option

Ob Gyn News ◽  
2005 ◽  
Vol 40 (6) ◽  
pp. 16
Author(s):  
BRUCE JANCIN
Keyword(s):  
Breast Mri

Breast MRI Shows Promise for High-Risk Women

2005 ◽  
Vol 38 (11) ◽  
pp. 44
Author(s):  
GINA SHAW
Keyword(s):  
High Risk ◽  
Breast Mri ◽  
High Risk Women
Sign in / Sign up

Export Citation Format

Share Document