A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry

Sebastian T. Gollmer; Thorsten M. Buzug

doi:10.1109/ISBI.2010.5490312

A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry

Institute of Medical Engineering

Abstract

We introduce a novel method for the evaluation of statistical shape models (SSM) that allows for quantifying the model quality wrt. global and local shape properties. The construction of SSM requires the identification of corresponding landmarks across a set of training shapes. Establishing such correspondence is a delicate matter and demands for automatic methods in a 3D setting. Conversely, the model quality needs to be evaluated to be able to compare different SSM in terms of specificity and generalization ability and to further improve the process of establishing correspondence. These well-known quantitative evaluation measures can be analyzed using various distance functions. The problem with popular landmark based metrics however is that the shape similarity of both the generated SSM and the actual object is disregarded. Evaluation of various models reveals that this can significantly corrupt the quality measures of the respective SSM, whereas the proposed method provides feasible results.

Original language	English
Title of host publication	2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
Number of pages	4
Publisher	IEEE
Publication date	09.08.2010
Pages	448-451
Article number	5490312
ISBN (Print)	978-1-4244-4125-9, 978-1-4244-4126-6
DOIs	https://doi.org/10.1109/ISBI.2010.5490312
Publication status	Published - 09.08.2010
Event	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Rotterdam, Netherlands Duration: 14.04.2010 → 17.04.2010 Conference number: 81301

UN SDGs

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

Access to Document

10.1109/ISBI.2010.5490312

Cite this

@inproceedings{1b2cd5a9c5034719bf75a0995ea50b36,

title = "A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry",

abstract = "We introduce a novel method for the evaluation of statistical shape models (SSM) that allows for quantifying the model quality wrt. global and local shape properties. The construction of SSM requires the identification of corresponding landmarks across a set of training shapes. Establishing such correspondence is a delicate matter and demands for automatic methods in a 3D setting. Conversely, the model quality needs to be evaluated to be able to compare different SSM in terms of specificity and generalization ability and to further improve the process of establishing correspondence. These well-known quantitative evaluation measures can be analyzed using various distance functions. The problem with popular landmark based metrics however is that the shape similarity of both the generated SSM and the actual object is disregarded. Evaluation of various models reveals that this can significantly corrupt the quality measures of the respective SSM, whereas the proposed method provides feasible results.",

author = "Gollmer, {Sebastian T.} and Buzug, {Thorsten M.}",

year = "2010",

month = aug,

day = "9",

doi = "10.1109/ISBI.2010.5490312",

language = "English",

isbn = "978-1-4244-4125-9",

series = "IEEE International Symposium on Biomedical Imaging ",

publisher = "IEEE",

pages = "448--451",

booktitle = "2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro",

note = "7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro <br/>, ISBI 2010 ; Conference date: 14-04-2010 Through 17-04-2010",

}

Gollmer, ST & Buzug, TM 2010, A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry. in 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro., 5490312, IEEE International Symposium on Biomedical Imaging , IEEE, pp. 448-451, 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro
, Rotterdam, Netherlands, 14.04.10. https://doi.org/10.1109/ISBI.2010.5490312

A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry. / Gollmer, Sebastian T.; Buzug, Thorsten M.
2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE, 2010. p. 448-451 5490312 (IEEE International Symposium on Biomedical Imaging ).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry

AU - Gollmer, Sebastian T.

AU - Buzug, Thorsten M.

N1 - Conference code: 81301

PY - 2010/8/9

Y1 - 2010/8/9

N2 - We introduce a novel method for the evaluation of statistical shape models (SSM) that allows for quantifying the model quality wrt. global and local shape properties. The construction of SSM requires the identification of corresponding landmarks across a set of training shapes. Establishing such correspondence is a delicate matter and demands for automatic methods in a 3D setting. Conversely, the model quality needs to be evaluated to be able to compare different SSM in terms of specificity and generalization ability and to further improve the process of establishing correspondence. These well-known quantitative evaluation measures can be analyzed using various distance functions. The problem with popular landmark based metrics however is that the shape similarity of both the generated SSM and the actual object is disregarded. Evaluation of various models reveals that this can significantly corrupt the quality measures of the respective SSM, whereas the proposed method provides feasible results.

AB - We introduce a novel method for the evaluation of statistical shape models (SSM) that allows for quantifying the model quality wrt. global and local shape properties. The construction of SSM requires the identification of corresponding landmarks across a set of training shapes. Establishing such correspondence is a delicate matter and demands for automatic methods in a 3D setting. Conversely, the model quality needs to be evaluated to be able to compare different SSM in terms of specificity and generalization ability and to further improve the process of establishing correspondence. These well-known quantitative evaluation measures can be analyzed using various distance functions. The problem with popular landmark based metrics however is that the shape similarity of both the generated SSM and the actual object is disregarded. Evaluation of various models reveals that this can significantly corrupt the quality measures of the respective SSM, whereas the proposed method provides feasible results.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-77955192488&origin=inward&txGid=3c118ec98ecf777155923cc1aea0bb52

U2 - 10.1109/ISBI.2010.5490312

DO - 10.1109/ISBI.2010.5490312

M3 - Conference contribution

SN - 978-1-4244-4125-9

SN - 978-1-4244-4126-6

T3 - IEEE International Symposium on Biomedical Imaging

SP - 448

EP - 451

BT - 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

PB - IEEE

T2 - 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro <br/>

Y2 - 14 April 2010 through 17 April 2010

ER -

A Method for Quantitative Evaluation of Statistical Shape Models Using Morphometry

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this