TY - GEN
T1 - Classification of tumor histopathology via sparse feature learning
AU - Nayak, Nandita
AU - Chang, Hang
AU - Borowsky, Alexander
AU - Spellman, Paul
AU - Parvin, Bahram
PY - 2013
Y1 - 2013
N2 - Our goal is to decompose whole slide images (WSI) of histology sections into distinct patches (e.g., viable tumor, necrosis) so that statistics of distinct histopathology can be linked with the outcome. Such an analysis requires a large cohort of histology sections that may originate from different laboratories, which may not use the same protocol in sample preparation. We have evaluated a method based on a variation of the restricted Boltzmann machine (RBM) that learns intrinsic features of the image signature in an unsupervised fashion. Computed code, from the learned representation, is then utilized to classify patches from a curated library of images. The system has been evaluated against a dataset of small image blocks of 1k-by-1k that have been extracted from glioblastoma multiforme (GBM) and clear cell kidney carcinoma (KIRC) from the cancer genome atlas (TCGA) archive. The learned model is then projected on each whole slide image (e.g., of size 20k-by-20k pixels or larger) for characterizing and visualizing tumor architecture. In the case of GBM, each WSI is decomposed into necrotic, transition into necrosis, and viable. In the case of the KIRC, each WSI is decomposed into tumor types, stroma, normal, and others. Evaluation of 1400 and 2500 samples of GBM and KIRC indicates a performance of 84% and 81%, respectively.
AB - Our goal is to decompose whole slide images (WSI) of histology sections into distinct patches (e.g., viable tumor, necrosis) so that statistics of distinct histopathology can be linked with the outcome. Such an analysis requires a large cohort of histology sections that may originate from different laboratories, which may not use the same protocol in sample preparation. We have evaluated a method based on a variation of the restricted Boltzmann machine (RBM) that learns intrinsic features of the image signature in an unsupervised fashion. Computed code, from the learned representation, is then utilized to classify patches from a curated library of images. The system has been evaluated against a dataset of small image blocks of 1k-by-1k that have been extracted from glioblastoma multiforme (GBM) and clear cell kidney carcinoma (KIRC) from the cancer genome atlas (TCGA) archive. The learned model is then projected on each whole slide image (e.g., of size 20k-by-20k pixels or larger) for characterizing and visualizing tumor architecture. In the case of GBM, each WSI is decomposed into necrotic, transition into necrosis, and viable. In the case of the KIRC, each WSI is decomposed into tumor types, stroma, normal, and others. Evaluation of 1400 and 2500 samples of GBM and KIRC indicates a performance of 84% and 81%, respectively.
KW - Tumor characterization
KW - feature learning
KW - sparse coding
KW - whole slide imaging
UR - http://www.scopus.com/inward/record.url?scp=84881643610&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84881643610&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2013.6556782
DO - 10.1109/ISBI.2013.6556782
M3 - Conference contribution
AN - SCOPUS:84881643610
SN - 9781467364546
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1348
EP - 1351
BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
T2 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
Y2 - 7 April 2013 through 11 April 2013
ER -