False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM)
Introduction: Interpretation of mammogram is a challenging task and the performance level of readers is known to vary widely between general radiologist and breast imaging experts. R2-CAD is a software-based system to identify regions of the mammogram with suspicious features and to draw the reader’...
Main Authors: | , , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2009
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/2138/ http://irep.iium.edu.my/2138/ http://irep.iium.edu.my/2138/1/2009_ABDA_R2CAD_STUDY.pdf |
id |
iium-2138 |
---|---|
recordtype |
eprints |
spelling |
iium-21382011-10-06T00:58:36Z http://irep.iium.edu.my/2138/ False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) Hassan, Radhiana Samad Cheung, Humairah Abdul Rashid, Mohd Amran Che Mohamed, Siti Kamariah Y, Fitrina Yusrin R Medicine (General) RC Internal medicine Introduction: Interpretation of mammogram is a challenging task and the performance level of readers is known to vary widely between general radiologist and breast imaging experts. R2-CAD is a software-based system to identify regions of the mammogram with suspicious features and to draw the reader’s attention to these areas and decide whether they are genuinely abnormal. It has been available for several years with FDA Approval and was recently brought to our centre with the use of FFDM. Method: This is a retrospective study of cases from January 2008 until May 2008. We collected all 191 cases of mammogram with R2-CAD highlighted lesion during this period. The images were traced and reviewed. The CAD-prompt lesion was documented and correlation with supplementary imaging, FNAC or biopsy was done to conclude the CAD-prompt lesion. Result: R2-CAD highlighted calcification in 41 patients (21.5%), lump in 122 patients (63.9%) and both calcification and lump in 28 patients (14.7%). The R2-CAD detected malignant lesions in 13 patients (6.8%), benign lesions in 67 patients (35.1%) and normal breast tissue (false positive) in 111 patients (58.1%) Conclusion: R2-CAD has a high false positive rate and low detection rate for malignant lesions. As such, it should be used as an aid not the first line mammographic interpretation. 2009 Conference or Workshop Item NonPeerReviewed application/pdf en http://irep.iium.edu.my/2138/1/2009_ABDA_R2CAD_STUDY.pdf Hassan, Radhiana and Samad Cheung, Humairah and Abdul Rashid, Mohd Amran and Che Mohamed, Siti Kamariah and Y, Fitrina Yusrin (2009) False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM). In: 7th Asian Breast Disease Association (ABDA) Teaching Course and Workshop, 31 October - 2 November 2009, Kuantan, Pahang, Malaysia. (Unpublished) http://www.abda-breast.org/TC-Kuantan2009.html |
repository_type |
Digital Repository |
institution_category |
Local University |
institution |
International Islamic University Malaysia |
building |
IIUM Repository |
collection |
Online Access |
language |
English |
topic |
R Medicine (General) RC Internal medicine |
spellingShingle |
R Medicine (General) RC Internal medicine Hassan, Radhiana Samad Cheung, Humairah Abdul Rashid, Mohd Amran Che Mohamed, Siti Kamariah Y, Fitrina Yusrin False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) |
description |
Introduction: Interpretation of mammogram is a challenging task and the performance level of readers is known to vary widely between general radiologist and breast imaging experts. R2-CAD is a software-based system to identify regions of the mammogram with suspicious features and to draw the reader’s attention to these areas and decide whether they are genuinely abnormal. It has been available for several years with FDA Approval and was recently brought to our centre with the use of FFDM.
Method: This is a retrospective study of cases from January 2008 until May 2008. We collected all 191 cases of mammogram with R2-CAD highlighted lesion during this period. The images were traced and reviewed. The CAD-prompt lesion was documented and correlation with supplementary imaging, FNAC or biopsy was done to conclude the CAD-prompt lesion.
Result:
R2-CAD highlighted calcification in 41 patients (21.5%), lump in 122 patients (63.9%) and both calcification and lump in 28 patients (14.7%). The R2-CAD detected malignant lesions in 13 patients (6.8%), benign lesions in 67 patients (35.1%) and normal breast tissue (false positive) in 111 patients (58.1%)
Conclusion:
R2-CAD has a high false positive rate and low detection rate for malignant lesions. As such, it should be used as an aid not the first line mammographic interpretation.
|
format |
Conference or Workshop Item |
author |
Hassan, Radhiana Samad Cheung, Humairah Abdul Rashid, Mohd Amran Che Mohamed, Siti Kamariah Y, Fitrina Yusrin |
author_facet |
Hassan, Radhiana Samad Cheung, Humairah Abdul Rashid, Mohd Amran Che Mohamed, Siti Kamariah Y, Fitrina Yusrin |
author_sort |
Hassan, Radhiana |
title |
False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) |
title_short |
False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) |
title_full |
False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) |
title_fullStr |
False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) |
title_full_unstemmed |
False positive detection rate of R2-CAD in evaluation of breast lesions at Full-Field-Digital Mammogram (FFDM) |
title_sort |
false positive detection rate of r2-cad in evaluation of breast lesions at full-field-digital mammogram (ffdm) |
publishDate |
2009 |
url |
http://irep.iium.edu.my/2138/ http://irep.iium.edu.my/2138/ http://irep.iium.edu.my/2138/1/2009_ABDA_R2CAD_STUDY.pdf |
first_indexed |
2023-09-18T20:09:40Z |
last_indexed |
2023-09-18T20:09:40Z |
_version_ |
1777407392628080640 |