CAD on brain, fundus, and breast images

Hiroshi Fujita; Yoshikazu Uchiyama; Toshiaki Nakagawa; Daisuke Fukuoka; Yuji Hatanaka; Takeshi Hara; Yoshinori Hayashi; Yuji Ikedo; Gobert N Lee; Xin Gao; Xiangrong Zhou

doi:10.1007/978-3-540-79490-5_42

CAD on brain, fundus, and breast images

Hiroshi Fujita
, Yoshikazu Uchiyama
, Toshiaki Nakagawa
, Daisuke Fukuoka
, Yuji Hatanaka
, Takeshi Hara
, Yoshinori Hayashi
, Yuji Ikedo
, Gobert N Lee
, Xin Gao
, Xiangrong Zhou

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

1 Citation (Scopus)

Abstract

Three computer-aided detection (CAD) projects are hosted at the Gifu University, Japan as part of the "Knowledge Cluster Initiative" of the Japanese Government. These projects are regarding the development of CAD systems for the early detection of (1) cerebrovascular diseases using brain MRI and MRA images by detecting lacunar infarcts, unruptured aneurysms, and arterial occlusions; (2) ocular diseases such as glaucoma, diabetic retinopathy, and hypertensive retinopathy using retinal fundus images; and (3) breast cancers using ultrasound 3-D volumetric whole breast data by detecting the breast masses. The brain CAD system achieves a sensitivity of 96.8% at 0.71 false positive (FP) per image for the lacunar-infarct detection, and 93.8% at 1.2 FPs per patient for the small unruptured aneurysm detection. The sensitivity and specificity for the detection of abnormal cases with arterial occlusions in MRA images are 80.0% and 95.3%, respectively. For the glaucoma detection using the retinal fundus CAD system, a sensitivity and specificity of 77.8% and 74.5% are obtained in the analysis of the optic nerve head and a sensitivity of 61.5% at 1.3 FPs per image is achieved in the detection of the retinal nerve fiber layer defects. Hemorrhages and exudates in diabetic retinopathy diagnosis are detected at a sensitivity and specificity of 84.6% and 20.6%, respectively, for the former and 76.9% and 83.3%, respectively, for the latter. For hypertensive retinopathy, the arteriolar-narrowing scheme can identify 76.2% of true positives at 1.4 FPs per image. For the breast CAD system, the image viewer that constructs the breast volume image data is developed, which also includes the CAD function with a sensitivity of 80.5% at 3.8 FPs per breast. The CAD schemes are still being improved for all the systems along with an increase in the number of image databases. Clinical examinations will be started soon, and commercialized CAD systems for the above subjects will appear by the completion of this project.

Original language	English
Title of host publication	Medical Imaging and Informatics
Subtitle of host publication	2nd International Conference, MIMI 2007
Editors	Xiaohong Gao, Henning Müller, Martin Loomes, Richard Comley, Shuqian Luo
Place of Publication	Germany
Publisher	Springer Berlin
Pages	358-366
Number of pages	9
ISBN (Electronic)	978-3-540-79490-5
ISBN (Print)	3-540-79489-1, 978-3-540-79489-9
DOIs	https://doi.org/10.1007/978-3-540-79490-5_42
Publication status	Published - 2008
Externally published	Yes
Event	2nd International Conference on Medical Imaging and Informatics - Beijing, China Duration: 14 Aug 2007 → 16 Aug 2007

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	4987
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	2nd International Conference on Medical Imaging and Informatics
Abbreviated title	MIMI 2007
Country/Territory	China
City	Beijing
Period	14/08/07 → 16/08/07

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Arterial Occlusion
Brain MRA
Brain MRI
Breast Cancer
Cerebrovascular Disease
Computer-Aided Detection (CAD)
Diabetic Retinopathy
Glaucoma
Hypertensive Retinopathy
Lacunar Infarct
Retinal Fundus Image
Ultrasound Breast Images
Unruptured Aneurysm

Access to Document

10.1007/978-3-540-79490-5_42Licence: In Copyright

https://rdcu.be/dSppTLicence: In Copyright

Cite this

Fujita, H., Uchiyama, Y., Nakagawa, T., Fukuoka, D., Hatanaka, Y., Hara, T., Hayashi, Y., Ikedo, Y., Lee, G. N., Gao, X., & Zhou, X. (2008). CAD on brain, fundus, and breast images. In X. Gao, H. Müller, M. Loomes, R. Comley, & S. Luo (Eds.), Medical Imaging and Informatics: 2nd International Conference, MIMI 2007 (pp. 358-366). (Lecture Notes in Computer Science; Vol. 4987). Springer Berlin. https://doi.org/10.1007/978-3-540-79490-5_42

@inproceedings{27aa1165d6b844f8b8d64b2817a75d5a,

title = "CAD on brain, fundus, and breast images",

abstract = "Three computer-aided detection (CAD) projects are hosted at the Gifu University, Japan as part of the {"}Knowledge Cluster Initiative{"} of the Japanese Government. These projects are regarding the development of CAD systems for the early detection of (1) cerebrovascular diseases using brain MRI and MRA images by detecting lacunar infarcts, unruptured aneurysms, and arterial occlusions; (2) ocular diseases such as glaucoma, diabetic retinopathy, and hypertensive retinopathy using retinal fundus images; and (3) breast cancers using ultrasound 3-D volumetric whole breast data by detecting the breast masses. The brain CAD system achieves a sensitivity of 96.8\% at 0.71 false positive (FP) per image for the lacunar-infarct detection, and 93.8\% at 1.2 FPs per patient for the small unruptured aneurysm detection. The sensitivity and specificity for the detection of abnormal cases with arterial occlusions in MRA images are 80.0\% and 95.3\%, respectively. For the glaucoma detection using the retinal fundus CAD system, a sensitivity and specificity of 77.8\% and 74.5\% are obtained in the analysis of the optic nerve head and a sensitivity of 61.5\% at 1.3 FPs per image is achieved in the detection of the retinal nerve fiber layer defects. Hemorrhages and exudates in diabetic retinopathy diagnosis are detected at a sensitivity and specificity of 84.6\% and 20.6\%, respectively, for the former and 76.9\% and 83.3\%, respectively, for the latter. For hypertensive retinopathy, the arteriolar-narrowing scheme can identify 76.2\% of true positives at 1.4 FPs per image. For the breast CAD system, the image viewer that constructs the breast volume image data is developed, which also includes the CAD function with a sensitivity of 80.5\% at 3.8 FPs per breast. The CAD schemes are still being improved for all the systems along with an increase in the number of image databases. Clinical examinations will be started soon, and commercialized CAD systems for the above subjects will appear by the completion of this project.",

keywords = "Arterial Occlusion, Brain MRA, Brain MRI, Breast Cancer, Cerebrovascular Disease, Computer-Aided Detection (CAD), Diabetic Retinopathy, Glaucoma, Hypertensive Retinopathy, Lacunar Infarct, Retinal Fundus Image, Ultrasound Breast Images, Unruptured Aneurysm",

author = "Hiroshi Fujita and Yoshikazu Uchiyama and Toshiaki Nakagawa and Daisuke Fukuoka and Yuji Hatanaka and Takeshi Hara and Yoshinori Hayashi and Yuji Ikedo and Lee, \{Gobert N\} and Xin Gao and Xiangrong Zhou",

year = "2008",

doi = "10.1007/978-3-540-79490-5\_42",

language = "English",

isbn = "3-540-79489-1",

series = "Lecture Notes in Computer Science",

publisher = "Springer Berlin",

pages = "358--366",

editor = "Xiaohong Gao and Henning M{\"u}ller and Martin Loomes and Richard Comley and Shuqian Luo",

booktitle = "Medical Imaging and Informatics",

address = "Germany",

note = "2nd International Conference on Medical Imaging and Informatics, MIMI 2007 ; Conference date: 14-08-2007 Through 16-08-2007",

}

Fujita, H, Uchiyama, Y, Nakagawa, T, Fukuoka, D, Hatanaka, Y, Hara, T, Hayashi, Y, Ikedo, Y, Lee, GN, Gao, X & Zhou, X 2008, CAD on brain, fundus, and breast images. in X Gao, H Müller, M Loomes, R Comley & S Luo (eds), Medical Imaging and Informatics: 2nd International Conference, MIMI 2007. Lecture Notes in Computer Science, vol. 4987, Springer Berlin, Germany, pp. 358-366, 2nd International Conference on Medical Imaging and Informatics, Beijing, China, 14/08/07. https://doi.org/10.1007/978-3-540-79490-5_42

CAD on brain, fundus, and breast images. / Fujita, Hiroshi; Uchiyama, Yoshikazu; Nakagawa, Toshiaki et al.
Medical Imaging and Informatics: 2nd International Conference, MIMI 2007. ed. / Xiaohong Gao; Henning Müller; Martin Loomes; Richard Comley; Shuqian Luo. Germany: Springer Berlin, 2008. p. 358-366 (Lecture Notes in Computer Science; Vol. 4987).

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

TY - GEN

T1 - CAD on brain, fundus, and breast images

AU - Fujita, Hiroshi

AU - Uchiyama, Yoshikazu

AU - Nakagawa, Toshiaki

AU - Fukuoka, Daisuke

AU - Hatanaka, Yuji

AU - Hara, Takeshi

AU - Hayashi, Yoshinori

AU - Ikedo, Yuji

AU - Lee, Gobert N

AU - Gao, Xin

AU - Zhou, Xiangrong

PY - 2008

Y1 - 2008

N2 - Three computer-aided detection (CAD) projects are hosted at the Gifu University, Japan as part of the "Knowledge Cluster Initiative" of the Japanese Government. These projects are regarding the development of CAD systems for the early detection of (1) cerebrovascular diseases using brain MRI and MRA images by detecting lacunar infarcts, unruptured aneurysms, and arterial occlusions; (2) ocular diseases such as glaucoma, diabetic retinopathy, and hypertensive retinopathy using retinal fundus images; and (3) breast cancers using ultrasound 3-D volumetric whole breast data by detecting the breast masses. The brain CAD system achieves a sensitivity of 96.8% at 0.71 false positive (FP) per image for the lacunar-infarct detection, and 93.8% at 1.2 FPs per patient for the small unruptured aneurysm detection. The sensitivity and specificity for the detection of abnormal cases with arterial occlusions in MRA images are 80.0% and 95.3%, respectively. For the glaucoma detection using the retinal fundus CAD system, a sensitivity and specificity of 77.8% and 74.5% are obtained in the analysis of the optic nerve head and a sensitivity of 61.5% at 1.3 FPs per image is achieved in the detection of the retinal nerve fiber layer defects. Hemorrhages and exudates in diabetic retinopathy diagnosis are detected at a sensitivity and specificity of 84.6% and 20.6%, respectively, for the former and 76.9% and 83.3%, respectively, for the latter. For hypertensive retinopathy, the arteriolar-narrowing scheme can identify 76.2% of true positives at 1.4 FPs per image. For the breast CAD system, the image viewer that constructs the breast volume image data is developed, which also includes the CAD function with a sensitivity of 80.5% at 3.8 FPs per breast. The CAD schemes are still being improved for all the systems along with an increase in the number of image databases. Clinical examinations will be started soon, and commercialized CAD systems for the above subjects will appear by the completion of this project.

AB - Three computer-aided detection (CAD) projects are hosted at the Gifu University, Japan as part of the "Knowledge Cluster Initiative" of the Japanese Government. These projects are regarding the development of CAD systems for the early detection of (1) cerebrovascular diseases using brain MRI and MRA images by detecting lacunar infarcts, unruptured aneurysms, and arterial occlusions; (2) ocular diseases such as glaucoma, diabetic retinopathy, and hypertensive retinopathy using retinal fundus images; and (3) breast cancers using ultrasound 3-D volumetric whole breast data by detecting the breast masses. The brain CAD system achieves a sensitivity of 96.8% at 0.71 false positive (FP) per image for the lacunar-infarct detection, and 93.8% at 1.2 FPs per patient for the small unruptured aneurysm detection. The sensitivity and specificity for the detection of abnormal cases with arterial occlusions in MRA images are 80.0% and 95.3%, respectively. For the glaucoma detection using the retinal fundus CAD system, a sensitivity and specificity of 77.8% and 74.5% are obtained in the analysis of the optic nerve head and a sensitivity of 61.5% at 1.3 FPs per image is achieved in the detection of the retinal nerve fiber layer defects. Hemorrhages and exudates in diabetic retinopathy diagnosis are detected at a sensitivity and specificity of 84.6% and 20.6%, respectively, for the former and 76.9% and 83.3%, respectively, for the latter. For hypertensive retinopathy, the arteriolar-narrowing scheme can identify 76.2% of true positives at 1.4 FPs per image. For the breast CAD system, the image viewer that constructs the breast volume image data is developed, which also includes the CAD function with a sensitivity of 80.5% at 3.8 FPs per breast. The CAD schemes are still being improved for all the systems along with an increase in the number of image databases. Clinical examinations will be started soon, and commercialized CAD systems for the above subjects will appear by the completion of this project.

KW - Arterial Occlusion

KW - Brain MRA

KW - Brain MRI

KW - Breast Cancer

KW - Cerebrovascular Disease

KW - Computer-Aided Detection (CAD)

KW - Diabetic Retinopathy

KW - Glaucoma

KW - Hypertensive Retinopathy

KW - Lacunar Infarct

KW - Retinal Fundus Image

KW - Ultrasound Breast Images

KW - Unruptured Aneurysm

UR - https://www.scopus.com/pages/publications/45849139759

U2 - 10.1007/978-3-540-79490-5_42

DO - 10.1007/978-3-540-79490-5_42

M3 - Conference contribution

AN - SCOPUS:45849139759

SN - 3-540-79489-1

SN - 978-3-540-79489-9

T3 - Lecture Notes in Computer Science

SP - 358

EP - 366

BT - Medical Imaging and Informatics

A2 - Gao, Xiaohong

A2 - Müller, Henning

A2 - Loomes, Martin

A2 - Comley, Richard

A2 - Luo, Shuqian

PB - Springer Berlin

CY - Germany

T2 - 2nd International Conference on Medical Imaging and Informatics

Y2 - 14 August 2007 through 16 August 2007

ER -

CAD on brain, fundus, and breast images

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this