Journal of Pathology Informatics

RESEARCH ARTICLE
Year
: 2015  |  Volume : 6  |  Issue : 1  |  Page : 39-

Automated image based prominent nucleoli detection


Choon K Yap1, Emarene M Kalaw2, Malay Singh3, Kian T Chong4, Danilo M Giron6, Chao-Hui Huang1, Li Cheng1, Yan N Law1, Hwee Kuan Lee1 
1 Imaging Informatics Division, Bioinformatics Institute, 30 Biopolis Street, #07-01, Matrix 138671, Singapore
2 Imaging Informatics Division, Bioinformatics Institute, 30 Biopolis Street, #07-01, Matrix 138671; Department of Pathology, Tan Tock Seng Hospital, 11 Jalan Tan Tock Seng, 308433, Singapore
3 Imaging Informatics Division, Bioinformatics Institute, 30 Biopolis Street, #07-01, Matrix 138671; Department of Computer Science, School of Computing, National University of Singapore, 13 Computing Drive, 117417, Singapore
4 Department of Urology, Tan Tock Seng Hospital, 11 Jalan Tan Tock Seng, 308433, Singapore

Correspondence Address:
Dr. Hwee Kuan Lee
Imaging Informatics Division, Bioinformatics Institute, 30 Biopolis Street, #07-01, Matrix 138671
Singapore

Introduction: Nucleolar changes in cancer cells are one of the cytologic features important to the tumor pathologist in cancer assessments of tissue biopsies. However, inter-observer variability and the manual approach to this work hamper the accuracy of the assessment by pathologists. In this paper, we propose a computational method for prominent nucleoli pattern detection. Materials and Methods: Thirty-five hematoxylin and eosin stained images were acquired from prostate cancer, breast cancer, renal clear cell cancer and renal papillary cell cancer tissues. Prostate cancer images were used for the development of a computer-based automated prominent nucleoli pattern detector built on a cascade farm. An ensemble of approximately 1000 cascades was constructed by permuting different combinations of classifiers such as support vector machines, eXclusive component analysis, boosting, and logistic regression. The output of cascades was then combined using the RankBoost algorithm. The output of our prominent nucleoli pattern detector is a ranked set of detected image patches of patterns of prominent nucleoli. Results: The mean number of detected prominent nucleoli patterns in the top 100 ranked detected objects was 58 in the prostate cancer dataset, 68 in the breast cancer dataset, 86 in the renal clear cell cancer dataset, and 76 in the renal papillary cell cancer dataset. The proposed cascade farm performs twice as good as the use of a single cascade proposed in the seminal paper by Viola and Jones. For comparison, a naive algorithm that randomly chooses a pixel as a nucleoli pattern would detect five correct patterns in the first 100 ranked objects. Conclusions: Detection of sparse nucleoli patterns in a large background of highly variable tissue patterns is a difficult challenge our method has overcome. This study developed an accurate prominent nucleoli pattern detector with the potential to be used in the clinical settings.


How to cite this article:
Yap CK, Kalaw EM, Singh M, Chong KT, Giron DM, Huang CH, Cheng L, Law YN, Lee HK. Automated image based prominent nucleoli detection.J Pathol Inform 2015;6:39-39


How to cite this URL:
Yap CK, Kalaw EM, Singh M, Chong KT, Giron DM, Huang CH, Cheng L, Law YN, Lee HK. Automated image based prominent nucleoli detection. J Pathol Inform [serial online] 2015 [cited 2019 Dec 15 ];6:39-39
Available from: http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2015;volume=6;issue=1;spage=39;epage=39;aulast=Yap;type=0