Tumor detection method of small animals on X-ray images

Yuji Karita, Toshiyuki Tanaka, Isao Kabaya, Mikiya Kano, Isamu Iwayoshi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Tumor diagnosis by X-ray images is a standard way in small animals. But it is difficult to decide tumor region of X-ray images, and veterinarians have to diagnose many X-ray images. Therefore, there is increasing demand for the development of CAD (Computer Aided Diagnosis) system to support veterinarians. We use X-ray images of small animals such as dogs. In this paper, automatic detection of tumor region from X-ray images is studied. We use normalized correlation between original image and template image to emphasize tumor region. This template image is based on feature of tumor. We also use Quoit filter to detect tumor candidate regions. Then, we calculate two feature values, mean of intensity and roundness in these regions, and classify these two feature values into four patterns by K-means clustering to decide true tumor region. As a result, some tumor region can be detected.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages698-702
Number of pages5
DOIs
Publication statusPublished - 2007
EventSICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 - Takamatsu, Japan
Duration: 2007 Sep 172007 Sep 20

Other

OtherSICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007
CountryJapan
CityTakamatsu
Period07/9/1707/9/20

Fingerprint

Tumors
Animals
X rays
Computer aided diagnosis

Keywords

  • Clustering
  • Correlation
  • Filter
  • Small animals
  • X-ray images

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Karita, Y., Tanaka, T., Kabaya, I., Kano, M., & Iwayoshi, I. (2007). Tumor detection method of small animals on X-ray images. In Proceedings of the SICE Annual Conference (pp. 698-702). [4421072] https://doi.org/10.1109/SICE.2007.4421072

Tumor detection method of small animals on X-ray images. / Karita, Yuji; Tanaka, Toshiyuki; Kabaya, Isao; Kano, Mikiya; Iwayoshi, Isamu.

Proceedings of the SICE Annual Conference. 2007. p. 698-702 4421072.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Karita, Y, Tanaka, T, Kabaya, I, Kano, M & Iwayoshi, I 2007, Tumor detection method of small animals on X-ray images. in Proceedings of the SICE Annual Conference., 4421072, pp. 698-702, SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007, Takamatsu, Japan, 07/9/17. https://doi.org/10.1109/SICE.2007.4421072
Karita Y, Tanaka T, Kabaya I, Kano M, Iwayoshi I. Tumor detection method of small animals on X-ray images. In Proceedings of the SICE Annual Conference. 2007. p. 698-702. 4421072 https://doi.org/10.1109/SICE.2007.4421072
Karita, Yuji ; Tanaka, Toshiyuki ; Kabaya, Isao ; Kano, Mikiya ; Iwayoshi, Isamu. / Tumor detection method of small animals on X-ray images. Proceedings of the SICE Annual Conference. 2007. pp. 698-702
@inproceedings{2ab3defcff804a01819c4aff2a2f23d3,
title = "Tumor detection method of small animals on X-ray images",
abstract = "Tumor diagnosis by X-ray images is a standard way in small animals. But it is difficult to decide tumor region of X-ray images, and veterinarians have to diagnose many X-ray images. Therefore, there is increasing demand for the development of CAD (Computer Aided Diagnosis) system to support veterinarians. We use X-ray images of small animals such as dogs. In this paper, automatic detection of tumor region from X-ray images is studied. We use normalized correlation between original image and template image to emphasize tumor region. This template image is based on feature of tumor. We also use Quoit filter to detect tumor candidate regions. Then, we calculate two feature values, mean of intensity and roundness in these regions, and classify these two feature values into four patterns by K-means clustering to decide true tumor region. As a result, some tumor region can be detected.",
keywords = "Clustering, Correlation, Filter, Small animals, X-ray images",
author = "Yuji Karita and Toshiyuki Tanaka and Isao Kabaya and Mikiya Kano and Isamu Iwayoshi",
year = "2007",
doi = "10.1109/SICE.2007.4421072",
language = "English",
isbn = "4907764286",
pages = "698--702",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Tumor detection method of small animals on X-ray images

AU - Karita, Yuji

AU - Tanaka, Toshiyuki

AU - Kabaya, Isao

AU - Kano, Mikiya

AU - Iwayoshi, Isamu

PY - 2007

Y1 - 2007

N2 - Tumor diagnosis by X-ray images is a standard way in small animals. But it is difficult to decide tumor region of X-ray images, and veterinarians have to diagnose many X-ray images. Therefore, there is increasing demand for the development of CAD (Computer Aided Diagnosis) system to support veterinarians. We use X-ray images of small animals such as dogs. In this paper, automatic detection of tumor region from X-ray images is studied. We use normalized correlation between original image and template image to emphasize tumor region. This template image is based on feature of tumor. We also use Quoit filter to detect tumor candidate regions. Then, we calculate two feature values, mean of intensity and roundness in these regions, and classify these two feature values into four patterns by K-means clustering to decide true tumor region. As a result, some tumor region can be detected.

AB - Tumor diagnosis by X-ray images is a standard way in small animals. But it is difficult to decide tumor region of X-ray images, and veterinarians have to diagnose many X-ray images. Therefore, there is increasing demand for the development of CAD (Computer Aided Diagnosis) system to support veterinarians. We use X-ray images of small animals such as dogs. In this paper, automatic detection of tumor region from X-ray images is studied. We use normalized correlation between original image and template image to emphasize tumor region. This template image is based on feature of tumor. We also use Quoit filter to detect tumor candidate regions. Then, we calculate two feature values, mean of intensity and roundness in these regions, and classify these two feature values into four patterns by K-means clustering to decide true tumor region. As a result, some tumor region can be detected.

KW - Clustering

KW - Correlation

KW - Filter

KW - Small animals

KW - X-ray images

UR - http://www.scopus.com/inward/record.url?scp=50349092420&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50349092420&partnerID=8YFLogxK

U2 - 10.1109/SICE.2007.4421072

DO - 10.1109/SICE.2007.4421072

M3 - Conference contribution

AN - SCOPUS:50349092420

SN - 4907764286

SN - 9784907764289

SP - 698

EP - 702

BT - Proceedings of the SICE Annual Conference

ER -