TY - JOUR
T1 - Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning
AU - Vu, Tiep Huu
AU - Mousavi, Hojjat Seyed
AU - Monga, Vishal
AU - Rao, Ganesh
AU - Rao, U. K.Arvind
N1 - Funding Information:
Research was supported by the Army Research Office (ARO)grant number W911NF-14-1-0421 (to V.M.), National Institute of Health NIHgrant KNS070928 (to G.R.), NCI Cancer Center SupportGrant NCI P30 CA016672 and Career Development Award from the Brain Tumor SPORE (to A.R.).
PY - 2016/3
Y1 - 2016/3
N2 - In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available.
AB - In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available.
UR - http://www.scopus.com/inward/record.url?scp=84963758189&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84963758189&partnerID=8YFLogxK
U2 - 10.1109/TMI.2015.2493530
DO - 10.1109/TMI.2015.2493530
M3 - Article
C2 - 26513781
AN - SCOPUS:84963758189
VL - 35
SP - 738
EP - 751
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
SN - 0278-0062
IS - 3
M1 - 7303944
ER -