Automated Detection of DCIS in Whole-Slide H&E Stained Breast Histopathology Images
- 5 April 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 35 (9) , 2141-2150
Abstract
This paper presents and evaluates a fully automatic method for detection of ductal carcinoma in situ (DCIS) in digitized hematoxylin and eosin (H&E) stained histopathological slides of breast tissue. The proposed method applies multi-scale superpixel classification to detect epithelial regions in whole-slide images (WSIs). Subsequently, spatial clustering is utilized to delineate regions representing meaningful structures within the tissue such as ducts and lobules. A region-based classifier employing a large set of features including statistical and structural texture features and architectural features is then trained to discriminate between DCIS and benign/normal structures. The system is evaluated on two datasets containing a total of 205 WSIs of breast tissue. Evaluation was conducted both on the slide and the lesion level using FROC analysis. The results show that to detect at least one true positive in every DCIS containing slide, the system finds 2.6 false positives per WSI. The results of the per-lesion evaluation show that it is possible to detect 80% and 83% of the DCIS lesions in an abnormal slide, at an average of 2.0 and 3.0 false positives per WSI, respectively. Collectively, the result of the experiments demonstrate the efficacy and accuracy of the proposed method as well as its potential for application in routine pathological diagnostics. To the best of our knowledge, this is the first DCIS detection algorithm working fully automatically on WSIs.Keywords
Funding Information
- European Union FP7 funded VPH-PRISM project (601040)
This publication has 28 references indexed in Scilit:
- Intraductal proliferative lesions of the breast: morphology, associated risk and molecular biologyLaboratory Investigation, 2010
- Automatic segmentation of colon glands using object-graphsMedical Image Analysis, 2010
- Computer-aided prognosis of neuroblastoma on whole-slide images: Classification of stromal developmentPattern Recognition, 2009
- Graph clusteringComputer Science Review, 2007
- Benign Breast Diseases: Classification, Diagnosis, and ManagementThe Oncologist, 2006
- Survey of Clustering AlgorithmsIEEE Transactions on Neural Networks, 2005
- Molecular evolution of breast cancerThe Journal of Pathology, 2005
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- Relative neighborhood graphs and their relativesProceedings of the IEEE, 1992
- Atypical hyperplastic lesions of the female breast: A long-term follow-up studyPlastic and Reconstructive Surgery, 1986