Journal
JOURNAL OF MEDICAL IMAGING
Volume 4, Issue 2, Pages -Publisher
SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
DOI: 10.1117/1.JMI.4.2.021105
Keywords
digital pathology; cancer detection; basal-cell carcinoma; classification; visual attention map; implicit relevance feedback; graphs
Funding
- Universidad Nacional de Colombia by means of Convocatoria del programa nacional de proyectos para el fortalecimiento de la investigacin, la creacin y la innovacin en posgrados de la Universidad Nacional de Colombia [23664]
- Colciencias by means of Convocatoria para Proyectos de Ciencia, Tecnologa e Innovacin en Salud [850-2015]
- National Cancer Institute of the National Institutes of Health [1U24CA199374-01, R01CA202752-01A1, R21CA179327-01, R21CA195152-0]
- National Institute of Diabetes and Digestive and Kidney Diseases [R01DK098503-02]
- DOD Prostate Cancer Synergistic Idea Development Award [PC120857]
- DOD Lung Cancer Idea Development New Investigator Award [LC130463]
- Case Comprehensive Cancer Center Pilot Grant VelaSano Grant from the Cleveland Clinic
- Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering at Case Western Reserve University
Ask authors/readers for more resources
Computational histomorphometric approaches typically use low-level image features for building machine learning classifiers. However, these approaches usually ignore high-level expert knowledge. A computational model (M_im) combines low-, mid-, and high-level image information to predict the likelihood of cancer in whole slide images. Handcrafted low-and mid-level features are computed from area, color, and spatial nuclei distributions. High-level information is implicitly captured from the recorded navigations of pathologists while exploring whole slide images during diagnostic tasks. This model was validated by predicting the presence of cancer in a set of unseen fields of view. The available database was composed of 24 cases of basal-cell carcinoma, from which 17 served to estimate the model parameters and the remaining 7 comprised the evaluation set. A total of 274 fields of view of size 1024 x 1024 pixels were extracted from the evaluation set. Then 176 patches from this set were used to train a support vector machine classifier to predict the presence of cancer on a patch-by-patch basis while the remaining 98 image patches were used for independent testing, ensuring that the training and test sets do not comprise patches from the same patient. A baseline model ( M_ex) estimated the cancer likelihood for each of the image patches. M_ex uses the same visual features as M_im, but its weights are estimated from nuclei manually labeled as cancerous or noncancerous by a pathologist. M_im achieved an accuracy of 74.49% and an F-measure of 80.31%, while M_ex yielded corresponding accuracy and F-measures of 73.47% and 77.97%, respectively. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available