Discovery - University of Dundee - Online Publications

Library & Learning Centre

Learning from partially annotated OPT images by contextual relevance ranking

Learning from partially annotated OPT images by contextual relevance ranking

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

View graph of relations

Info

Original languageEnglish
Title of host publicationMedical Image Computing and Computer-Assisted Intervention - MICCAI 2013
Subtitle of host publication16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part III
EditorsKensaku Mori, Ichiro Sakuma, Yoshinobu Sato, Christian Barillot, Nassir Navab
Place of PublicationBerlin
PublisherSpringer
Pages429-436
Number of pages8
ISBN (Electronic)9783642407604
ISBN (Print)9783642407598
DOIs
StatePublished - 2013
Event16th International Conference on Medical Image Computing and Computer Assisted Intervention - Nagoya, Japan

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume8151
ISSN (Print)0302-9743

Conference

Conference16th International Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated titleMICCAI 2013
CountryJapan
CityNagoya
Period22/09/1326/09/13
Internet address

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.

???studenttheses-relations???

Student Thesis

Documents

DOI

Library & Learning Centre

Contact | Accessibility | Policy