In this paper, we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC). Our framework comprises three classification stages: i) a random forest (RF) classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii) a more complex discriminative restricted Boltzmann machine (DRBM) classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii) a detector to detect clusters of μCs from the individual μC detection results, using two different criteria. From the two-stage RF-DRBM classifier, we are able to distinguish μCs using explicitly computed features, as well as learn implicit features that are able to further discriminate between confusing cases. Experimental evaluation is conducted on the original Mammographic Image Analysis Society (MIAS) and mini-MIAS databases, as well as our own Seoul National University Bundang Hospital digital mammographic database. It is shown that the proposed method outperforms comparable methods in terms of receiver operating characteristic (ROC) and precision-recall curves for detection of individual μCs and free-response receiver operating characteristic (FROC) curve for detection of clustered μCs.
MIAS DB - File 1
The Mammographic Image Analysis Society Digital Mammographic Database
* Approval for redistribution provided by J. Suckling (js369@cam.ac.uk)
CREDITS: Organiser: J Suckling; Truth-Data: C R M Boggis and I Hutt; Co-Workers: S Astley, D Betal, N Cerneaz, D R Dance, S-L Kok, J Parker, I Ricketts, J Savage, E Stamatakis and P Taylor. Special Thanks: N Karrsemeijer.
========================================================
REFERENCE:
J Suckling et al (1994) "The Mammographic Image Analysis Society Digital Mammogram Database" Exerpta Medica. International Congress Series 1069 pp 375-378.
========================================================
MIAS-DB.zip
MIAS DB - File 2
The Mammographic Image Analysis Society
Digital Mammographic Database
* Approval for redistribution provided by J. Suckling (js369@cam.ac.uk)
CREDITS:
Organiser: J Suckling; Truth-Data: C R M Boggis and I Hutt; Co-Workers: S Astley, D Betal, N Cerneaz, D R Dance, S-L Kok, J Parker, I Ricketts, J Savage, E Stamatakis and P Taylor. Special Thanks: N Karrsemeijer.
=========================================================
REFERENCE:
J Suckling et al (1994) "The Mammographic Image Analysis Society Digital Mammogram Database" Exerpta Medica. International Congress Series 1069 pp 375-378.
=========================================================
MIAS-DB.z01
SNUBH-MDB-mCi
The Seoul National University Bundang Hospital Digital Mammographic Database - with Individual MC Annotations (SNUBH-MDB-mCi)
See also our webpage at http://cv.snu.ac.kr/research/cascade-mc-detector15/index.html for updated information.
For questions regarding data, e-mail: syshin@snu.ac.kr
INFORMATION:
1) The size of all images are 1914 pixels x 2294 pixels.
2) This zip-file contains 49 mammograms with micro-calcifications (μCs) and corresponding annotations for individual μCs and μC clusters.
- The files named as '****_i.txt' are annotation files for individual μCs and list (x,y) coordinates of each μC.
- The files named as '****_c.txt' are annotation files for μC clusters and list bounding boxes of each μC cluster. A bounding box is represented as two (x,y) coordinates, upper left corner and lower right corner.
- Coordinate system origin is the upper-left corner.
SNUBH-MDB-μCi.zip
Annotations of Individual Microcalcification in mini-MIAS DB
These files contain image pixel coordinates of individual microcalcifications in the images from the mini-MIAS database, available from http://peipa.essex.ac.uk/info/mias.html. The file name corresponds to the particular image name in the mini-MIAS database.
See also our webpage at http://cv.snu.ac.kr/research/cascade-mc-detector15/index.html for updated information.
For questions regarding data, e-mail: syshin@snu.ac.kr
mini-MIAS-ind_μC-annotations.zip