Multi-phase liver lesions classification using relevant visual words based on mutual information

Idit Diamant; Jacob Goldberger; Eyal Klang; Michal Amitai; Hayit Greenspan

doi:10.1109/isbi.2015.7163898

Multi-phase liver lesions classification using relevant visual words based on mutual information

Idit Diamant, Jacob Goldberger, Eyal Klang, Michal Amitai, Hayit Greenspan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

20 Scopus citations

Abstract

We present a novel method for automated diagnosis of liver lesions in multi-phase CT images. Our approach is a variant of the Bag-of-Visual-Words (BoVW) method. It improves the BoVW model by selecting the most relevant words to be used for the input representation using a mutual information based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. We validated our algorithm on 85 multi-phase CT images of 4 categories: hemangiomas, Focal Nodular Hyper-plasia (FNH), Hepatic Cellular Carcinoma (HCC) and cholangiocarcinoma. The new algorithm suggested in this paper improves the classical BoVW method sensitivity by 7% and specificity by 3%. The shift from single-phase liver data to a multi-phase representation is shown to substantially improve classification results. Overall, the system presented reaches state-of-the-art classification results of 82.4% sensitivity and 92.7% specificity on the 4 category lesion data, a challenging clinical diagnosis task.

Original language	English
Title of host publication	2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015
Publisher	IEEE Computer Society
Pages	407-410
Number of pages	4
ISBN (Electronic)	9781479923748
DOIs	https://doi.org/10.1109/isbi.2015.7163898
State	Published - 21 Jul 2015
Event	12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States Duration: 16 Apr 2015 → 19 Apr 2015

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2015-July
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
Country/Territory	United States
City	Brooklyn
Period	16/04/15 → 19/04/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

Liver lesions
automated diagnosis
classification
feature selection
mutual information
visual words

Access to Document

10.1109/isbi.2015.7163898

Cite this

Diamant, I., Goldberger, J., Klang, E., Amitai, M., & Greenspan, H. (2015). Multi-phase liver lesions classification using relevant visual words based on mutual information. In 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015 (pp. 407-410). Article 7163898 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2015-July). IEEE Computer Society. https://doi.org/10.1109/isbi.2015.7163898

@inproceedings{a9f91cc9326e4ef0a504eb06406a066e,

title = "Multi-phase liver lesions classification using relevant visual words based on mutual information",

abstract = "We present a novel method for automated diagnosis of liver lesions in multi-phase CT images. Our approach is a variant of the Bag-of-Visual-Words (BoVW) method. It improves the BoVW model by selecting the most relevant words to be used for the input representation using a mutual information based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. We validated our algorithm on 85 multi-phase CT images of 4 categories: hemangiomas, Focal Nodular Hyper-plasia (FNH), Hepatic Cellular Carcinoma (HCC) and cholangiocarcinoma. The new algorithm suggested in this paper improves the classical BoVW method sensitivity by 7% and specificity by 3%. The shift from single-phase liver data to a multi-phase representation is shown to substantially improve classification results. Overall, the system presented reaches state-of-the-art classification results of 82.4% sensitivity and 92.7% specificity on the 4 category lesion data, a challenging clinical diagnosis task.",

keywords = "Liver lesions, automated diagnosis, classification, feature selection, mutual information, visual words",

author = "Idit Diamant and Jacob Goldberger and Eyal Klang and Michal Amitai and Hayit Greenspan",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 ; Conference date: 16-04-2015 Through 19-04-2015",

year = "2015",

month = jul,

day = "21",

doi = "10.1109/isbi.2015.7163898",

language = "אנגלית",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "407--410",

booktitle = "2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015",

address = "ארצות הברית",

}

Diamant, I, Goldberger, J, Klang, E, Amitai, M & Greenspan, H 2015, Multi-phase liver lesions classification using relevant visual words based on mutual information. in 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015., 7163898, Proceedings - International Symposium on Biomedical Imaging, vol. 2015-July, IEEE Computer Society, pp. 407-410, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 16/04/15. https://doi.org/10.1109/isbi.2015.7163898

Multi-phase liver lesions classification using relevant visual words based on mutual information. / Diamant, Idit; Goldberger, Jacob; Klang, Eyal et al.
2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. IEEE Computer Society, 2015. p. 407-410 7163898 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2015-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-phase liver lesions classification using relevant visual words based on mutual information

AU - Diamant, Idit

AU - Goldberger, Jacob

AU - Klang, Eyal

AU - Amitai, Michal

AU - Greenspan, Hayit

PY - 2015/7/21

Y1 - 2015/7/21

N2 - We present a novel method for automated diagnosis of liver lesions in multi-phase CT images. Our approach is a variant of the Bag-of-Visual-Words (BoVW) method. It improves the BoVW model by selecting the most relevant words to be used for the input representation using a mutual information based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. We validated our algorithm on 85 multi-phase CT images of 4 categories: hemangiomas, Focal Nodular Hyper-plasia (FNH), Hepatic Cellular Carcinoma (HCC) and cholangiocarcinoma. The new algorithm suggested in this paper improves the classical BoVW method sensitivity by 7% and specificity by 3%. The shift from single-phase liver data to a multi-phase representation is shown to substantially improve classification results. Overall, the system presented reaches state-of-the-art classification results of 82.4% sensitivity and 92.7% specificity on the 4 category lesion data, a challenging clinical diagnosis task.

AB - We present a novel method for automated diagnosis of liver lesions in multi-phase CT images. Our approach is a variant of the Bag-of-Visual-Words (BoVW) method. It improves the BoVW model by selecting the most relevant words to be used for the input representation using a mutual information based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. We validated our algorithm on 85 multi-phase CT images of 4 categories: hemangiomas, Focal Nodular Hyper-plasia (FNH), Hepatic Cellular Carcinoma (HCC) and cholangiocarcinoma. The new algorithm suggested in this paper improves the classical BoVW method sensitivity by 7% and specificity by 3%. The shift from single-phase liver data to a multi-phase representation is shown to substantially improve classification results. Overall, the system presented reaches state-of-the-art classification results of 82.4% sensitivity and 92.7% specificity on the 4 category lesion data, a challenging clinical diagnosis task.

KW - Liver lesions

KW - automated diagnosis

KW - classification

KW - feature selection

KW - mutual information

KW - visual words

UR - http://www.scopus.com/inward/record.url?scp=84944322193&partnerID=8YFLogxK

U2 - 10.1109/isbi.2015.7163898

DO - 10.1109/isbi.2015.7163898

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84944322193

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 407

EP - 410

BT - 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015

PB - IEEE Computer Society

T2 - 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015

Y2 - 16 April 2015 through 19 April 2015

ER -

Diamant I, Goldberger J, Klang E, Amitai M, Greenspan H. Multi-phase liver lesions classification using relevant visual words based on mutual information. In 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. IEEE Computer Society. 2015. p. 407-410. 7163898. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/isbi.2015.7163898

Multi-phase liver lesions classification using relevant visual words based on mutual information

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this