MULTI-SCALE MASS SEGMENTATION FOR MAMMOGRAMS VIA CASCADED RANDOM FORESTS

Min, Hang, Chandra, Shekhar S., Dhungel, Neeraj, Crozier, Stuart and Bradley, Andrew P. (2017). MULTI-SCALE MASS SEGMENTATION FOR MAMMOGRAMS VIA CASCADED RANDOM FORESTS. In: IEEE 14th International Symposium on Biomedical Imaging (ISBI) - From Nano to Macro, Melbourne Australia, (113-117). Apr 18-21, 2017.

Author Min, Hang
Chandra, Shekhar S.
Dhungel, Neeraj
Crozier, Stuart
Bradley, Andrew P.
Title of paper MULTI-SCALE MASS SEGMENTATION FOR MAMMOGRAMS VIA CASCADED RANDOM FORESTS
Conference name IEEE 14th International Symposium on Biomedical Imaging (ISBI) - From Nano to Macro
Conference location Melbourne Australia
Conference dates Apr 18-21, 2017
Journal name 2017 Ieee 14Th International Symposium On Biomedical Imaging (Isbi 2017)
Place of Publication NEW YORK
Publisher IEEE
Publication Year 2017
Year available 2017
Sub-type Fully published paper
Open Access Status Not yet assessed
ISBN 978-1-5090-1172-8
Start page 113
End page 117
Total pages 5
Language eng
Abstract/Summary Breast mass detection and segmentation are difficult tasks due to the variation in size and shape of breast masses. Constructing classifiers for this problem is also challenging due to the fact that normal tissue regions overwhelmingly outnumber abnormal regions. In this paper, we propose a novel approach for detecting and segmenting breast masses in mammography based on multi-scale morphological filtering and a self-adaptive cascade of random forests (CasRFs). CasRFs can cope with severe class imbalance by adding layers to the cascade until a minimum number of false-positives (FPs) is reached. The approach achieves an average sensitivity of 0.94 with 1.99 FPs/image on INbreast and a sensitivity of 0.77 with 3.93 FPs/image on DDSM BCRP.
Keyword Morphological Enhancement
Q-Index Code E1
Q-Index Status Provisional Code
Grant ID DP140102794
Institutional Status UQ

Document type: Conference Paper
Sub-type: Fully published paper
Collection: Unprocessed Records
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Google Scholar Search Google Scholar
Created: Sat, 16 Dec 2017, 23:46:00 EST