Learning from partially annotated OPT images by contextual relevance ranking

Wenqi Li; Jianguo Zhang; Wei-Shi Zheng; Maria Coats; Frank A. Carey; Stephen J. McKenna

doi:10.1007/978-3-642-40760-4_54

Learning from partially annotated OPT images by contextual relevance ranking

Wenqi Li
, Jianguo Zhang
, Wei-Shi Zheng
, Maria Coats
, Frank A. Carey
, Stephen J. McKenna

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

1 Citation (Scopus)

Abstract

Annotations delineating regions of interest can provide valuable information for training medical image classification and segmentation methods. However the process of obtaining annotations is tedious and time-consuming, especially for high-resolution volumetric images. In this paper we present a novel learning framework to reduce the requirement of manual annotations while achieving competitive classification performance. The approach is evaluated on a dataset with 59 3D optical projection tomography images of colorectal polyps. The results show that the proposed method can robustly infer patterns from partially annotated images with low computational cost.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013
Subtitle of host publication	16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III
Editors	Kensaku Mori, Ichiro Sakuma, Yoshinobu Sato, Christian Barillot, Nassir Navab
Place of Publication	Berlin
Publisher	Springer
Pages	429-436
Number of pages	8
ISBN (Electronic)	9783642407604
ISBN (Print)	9783642407598
DOIs	https://doi.org/10.1007/978-3-642-40760-4_54
Publication status	Published - 2013
Event	16th International Conference on Medical Image Computing and Computer Assisted Intervention - Toyoda Auditorium, Nagoya University, Nagoya, Japan Duration: 22 Sept 2013 → 26 Sept 2013 http://www.miccai2013.org/index.html

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	8151
ISSN (Print)	0302-9743

Conference

Conference	16th International Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated title	MICCAI 2013
Country/Territory	Japan
City	Nagoya
Period	22/09/13 → 26/09/13
Internet address	http://www.miccai2013.org/index.html

Keywords

Algorithms
Artificial Intelligence
Colonic Polyps
Humans
Image Enhancement
Image Interpretation, Computer-Assisted
Microscopy
Pattern Recognition, Automated
Reproducibility of Results
Sensitivity and Specificity
Tomography, Optical

Access to Document

10.1007/978-3-642-40760-4_54

Analysis of Colorectal Polyps in Optical Projection Tomography
Li, W. (Author), Zhang, J. (Supervisor) & McKenna, S. (Supervisor), 2015
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

Li, W., Zhang, J., Zheng, W.-S., Coats, M., Carey, F. A., & McKenna, S. J. (2013). Learning from partially annotated OPT images by contextual relevance ranking. In K. Mori, I. Sakuma, Y. Sato, C. Barillot, & N. Navab (Eds.), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III (pp. 429-436). (Lecture notes in computer science; Vol. 8151). Springer . https://doi.org/10.1007/978-3-642-40760-4_54

Li, Wenqi ; Zhang, Jianguo ; Zheng, Wei-Shi et al. / Learning from partially annotated OPT images by contextual relevance ranking. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III. editor / Kensaku Mori ; Ichiro Sakuma ; Yoshinobu Sato ; Christian Barillot ; Nassir Navab. Berlin : Springer , 2013. pp. 429-436 (Lecture notes in computer science).

@inproceedings{7bc7dab8d0e348f7981c9b18cb52e1c4,

title = "Learning from partially annotated OPT images by contextual relevance ranking",

abstract = "Annotations delineating regions of interest can provide valuable information for training medical image classification and segmentation methods. However the process of obtaining annotations is tedious and time-consuming, especially for high-resolution volumetric images. In this paper we present a novel learning framework to reduce the requirement of manual annotations while achieving competitive classification performance. The approach is evaluated on a dataset with 59 3D optical projection tomography images of colorectal polyps. The results show that the proposed method can robustly infer patterns from partially annotated images with low computational cost.",

keywords = "Algorithms, Artificial Intelligence, Colonic Polyps, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Microscopy, Pattern Recognition, Automated, Reproducibility of Results, Sensitivity and Specificity, Tomography, Optical",

author = "Wenqi Li and Jianguo Zhang and Wei-Shi Zheng and Maria Coats and Carey, \{Frank A.\} and McKenna, \{Stephen J.\}",

year = "2013",

doi = "10.1007/978-3-642-40760-4\_54",

language = "English",

isbn = "9783642407598",

series = "Lecture notes in computer science",

publisher = "Springer ",

pages = "429--436",

editor = "Kensaku Mori and Ichiro Sakuma and Yoshinobu Sato and Christian Barillot and Nassir Navab",

booktitle = "Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013",

note = "16th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2013 ; Conference date: 22-09-2013 Through 26-09-2013",

url = "http://www.miccai2013.org/index.html",

}

Li, W, Zhang, J, Zheng, W-S, Coats, M, Carey, FA & McKenna, SJ 2013, Learning from partially annotated OPT images by contextual relevance ranking. in K Mori, I Sakuma, Y Sato, C Barillot & N Navab (eds), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III. Lecture notes in computer science, vol. 8151, Springer , Berlin, pp. 429-436, 16th International Conference on Medical Image Computing and Computer Assisted Intervention, Nagoya, Japan, 22/09/13. https://doi.org/10.1007/978-3-642-40760-4_54

Learning from partially annotated OPT images by contextual relevance ranking. / Li, Wenqi; Zhang, Jianguo; Zheng, Wei-Shi et al.
Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III. ed. / Kensaku Mori; Ichiro Sakuma; Yoshinobu Sato; Christian Barillot; Nassir Navab. Berlin: Springer , 2013. p. 429-436 (Lecture notes in computer science; Vol. 8151).

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

TY - GEN

T1 - Learning from partially annotated OPT images by contextual relevance ranking

AU - Li, Wenqi

AU - Zhang, Jianguo

AU - Zheng, Wei-Shi

AU - Coats, Maria

AU - Carey, Frank A.

AU - McKenna, Stephen J.

PY - 2013

Y1 - 2013

N2 - Annotations delineating regions of interest can provide valuable information for training medical image classification and segmentation methods. However the process of obtaining annotations is tedious and time-consuming, especially for high-resolution volumetric images. In this paper we present a novel learning framework to reduce the requirement of manual annotations while achieving competitive classification performance. The approach is evaluated on a dataset with 59 3D optical projection tomography images of colorectal polyps. The results show that the proposed method can robustly infer patterns from partially annotated images with low computational cost.

AB - Annotations delineating regions of interest can provide valuable information for training medical image classification and segmentation methods. However the process of obtaining annotations is tedious and time-consuming, especially for high-resolution volumetric images. In this paper we present a novel learning framework to reduce the requirement of manual annotations while achieving competitive classification performance. The approach is evaluated on a dataset with 59 3D optical projection tomography images of colorectal polyps. The results show that the proposed method can robustly infer patterns from partially annotated images with low computational cost.

KW - Algorithms

KW - Artificial Intelligence

KW - Colonic Polyps

KW - Humans

KW - Image Enhancement

KW - Image Interpretation, Computer-Assisted

KW - Microscopy

KW - Pattern Recognition, Automated

KW - Reproducibility of Results

KW - Sensitivity and Specificity

KW - Tomography, Optical

U2 - 10.1007/978-3-642-40760-4_54

DO - 10.1007/978-3-642-40760-4_54

M3 - Conference contribution

C2 - 24505790

SN - 9783642407598

T3 - Lecture notes in computer science

SP - 429

EP - 436

BT - Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013

A2 - Mori, Kensaku

A2 - Sakuma, Ichiro

A2 - Sato, Yoshinobu

A2 - Barillot, Christian

A2 - Navab, Nassir

PB - Springer

CY - Berlin

T2 - 16th International Conference on Medical Image Computing and Computer Assisted Intervention

Y2 - 22 September 2013 through 26 September 2013

ER -

Li W, Zhang J, Zheng WS, Coats M, Carey FA, McKenna SJ. Learning from partially annotated OPT images by contextual relevance ranking. In Mori K, Sakuma I, Sato Y, Barillot C, Navab N, editors, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III. Berlin: Springer . 2013. p. 429-436. (Lecture notes in computer science). doi: 10.1007/978-3-642-40760-4_54

Learning from partially annotated OPT images by contextual relevance ranking

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Student theses

Analysis of Colorectal Polyps in Optical Projection Tomography

Cite this