Int J CARS (2017) 12:1271–1280 DOI 10.1007/s11548-017-1622-5 ORIGINAL ARTICLE Deformable appearance pyramids for anatomy representation, landmark detection and pathology classiﬁcation 1 1 2 Qiang Zhang · Abhir Bhalerao · Charles Hutchinson Received: 28 January 2017 / Accepted: 23 May 2017 / Published online: 3 June 2017 © The Author(s) 2017. This article is an open access publication Abstract Conclusion A new appearance model is introduced with Purpose Representation of anatomy appearance is one of several conﬁgurations presented and evaluated. The DAPs the key problems in medical image analysis. An appearance can be readily applied for other clinical problems for the model represents the anatomies with parametric forms, which tasks of prior learning, landmark detection and pathology are then vectorised for prior learning, segmentation and clas- classiﬁcation. siﬁcation tasks. Methods We propose a part-based parametric appearance Keywords Deformable part models · Deformable appear- model we refer to as a deformable appearance pyramid ance pyramids · Landmark detection · Classiﬁcation (DAP). The parts are delineated by multi-scale local feature pyramids extracted from an image pyramid. Each anatomy is represented by an appearance pyramid, with the variabil- Introduction ity within a population approximated by local translations of the multi-scale parts and linear
International Journal of Computer Assisted Radiology and Surgery – Springer Journals
Published: Jun 3, 2017
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud