You are here

Imaging Tools for Cancer Research

The goal of our work in Biomedical Imaging is two-fold: One, to develop advanced imaging tools for biomedical research in partnership with the National Cancer Institute and other organizations. Secondly, to conduct research in Content Based Image Retrieval (CBIR) to index and retrieve medical images by image features (e.g., shape, color and texture), augmented by textual features as well. This work includes the development of the CervigramFinder for retrieval of uterine cervix images by image features, SPIRS for retrieval of digitized x-ray images of the spine from NHANES II and a distributed global system (SPIRS-IRMA) for image retrieval by both high-level and detailed features of medical images, in collaboration with Aachen University, Germany.

CBIR is also an aspect of the Image Text Indexing (ITI) project that seeks to automatically index illustrations in medical articles by processing text in figure captions and mentions in the article, as well as image features in the illustrations.

Publications/Tools: 
KC S, Aafaque A, Antani SK, Thoma GR. Line Segment-Based Stitched Multipanel Figure Separation for Effective Biomedical CBIR. Int. J. Patt. Recogn. Artif. Intelligence 31, 1757003 (2017) https://doi.org/10.1142/S0218001417570038.
Guo P, Almubarak H, Banerjee K, Stanley RJ, Long LR, Antani SK, Thoma GR, Zuna R, Frazier S, Moss R, Stoecker W. Enhancements in localized classification for uterine cervical cancer digital histology image assessment. J Pathol Inform. 2016 Dec 30;7:51. doi: 10.4103/2153-3539.197193. eCollection 2016.
Ben Abacha A, de Herrera A, Wang Ke, Long LR, Antani SK, Demner-Fushman D. Named entity recognition in functional neuroimaging literature. 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Kansas City, MO, 2017, pp. 2218-2220.
Mrabet Y, Vougiouklis P, Kilicoglu H, Gardent C, Demner-Fushman D, Hare J, Simperl E. Aligning Texts and Knowledge Bases with Semantic Sentence Simplification. WebNLG 2016.
Xu T, Zhang H, Xin C, Kim E, Long LR, Xue Z, Antani SK, Huang Z. Multi-feature based Benchmark for Cervical Dysplasia Classification Evaluation. Pattern Recognition. ISSN 0031-3203, DOI: 10.1016/j.patcog.2016.09.027.
Guo P, Banerjee K, Stanley RJ, Long LR, Antani SK, Thoma GR, Frazier SR, Moss RH, Stoecker WV. Nuclei-Based Features for Uterine Cervical Cancer Histology Image Analysis with Fusion-based Classification. DOI 10.1109/JBHI.2015.2483318 IEEE Journal of Biomedical and Health Informatics
Xu T, Xin C, Long LR, Antani SK, Xue Z, Kim E, Huang X. A New Image Data Set and Benchmark for Cervical Dysplasia Classification Evaluation. Machine Learning in Medical Imaging: 6th International Workshop, MLMI 2015, LNCS 9352, pp. 26–35, 2015. DOI: 10.1007/978-3-319-24888-2 4.
Rahman MM, Antani SK, Demner-Fushman D, Thoma GR. Biomedical image representation approach using visualness and spatial information in a concept feature space for interactive region-of-interest-based retrieval. J Med Imaging (Bellingham). 2015 Oct;2(4):046502. doi: 10.1117/1.JMI.2.4.046502. Epub 2015 Dec 30.
Ruiz A, Allette K, Francis D, Lamping E, Jaeger S, Folio L, Apolo A. Patterns of soft tissue metastasis in patients with urothelial carcinoma using tumor volume heatmaps [Poster]. NIH Summer Research Program Poster Day, Aug 6, 2015
Vajda S, Rangoni Y, Cecotti H. Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition. Pattern Recognit Lett. 2015 Jun 1;58:23-28.

Pages