Advanced

An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images

Landgren, Matilda LU ; Sjöstrand, Karl; Ohlsson, Mattias LU ; Ståhl, Daniel LU ; Overgaard, Niels Christian LU ; Åström, Karl LU ; Sixt, Rune and Edenbrandt, Lars LU (2011) 17th Scandinavian Conference on Image Analysis (SCIA 2011) In Lecture Notes in Computer Science 6688. p.489-500
Abstract
Designing a system for computer aided diagnosis is a complex procedure requiring an understanding of the biology of the disease, insight into hospital workflow and awareness of available technical solutions. This paper aims to show that a valuable system can be designed for diagnosing kidney lesions in children and adolescents from 99m Tc-DMSA scintigraphy images. We present the chain of analysis and provide a discussion of its performance. On a per-lesion basis, the classification reached an ROC-curve area of 0.96 (sensitivity/specificity e.g. 97%/85%) measured using an independent test group consisting of 56 patients with 730 candidate lesions. We conclude that the presented system for diagnostic support has the potential of increasing... (More)
Designing a system for computer aided diagnosis is a complex procedure requiring an understanding of the biology of the disease, insight into hospital workflow and awareness of available technical solutions. This paper aims to show that a valuable system can be designed for diagnosing kidney lesions in children and adolescents from 99m Tc-DMSA scintigraphy images. We present the chain of analysis and provide a discussion of its performance. On a per-lesion basis, the classification reached an ROC-curve area of 0.96 (sensitivity/specificity e.g. 97%/85%) measured using an independent test group consisting of 56 patients with 730 candidate lesions. We conclude that the presented system for diagnostic support has the potential of increasing the quality of care regarding this type of examination. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Computer Aided Diagnosis – Nuclear Imaging – Active Shape Models – Artificial Neural Networks
in
Lecture Notes in Computer Science
editor
Heyden, Anders; Kahl, Fredrik; and
volume
6688
pages
12 pages
publisher
Springer
conference name
17th Scandinavian Conference on Image Analysis (SCIA 2011)
external identifiers
  • wos:000308543900046
  • scopus:79957506173
ISSN
1611-3349
0302-9743
ISBN
978-3-642-21227-7 (online)
978-3-642-21226-0 (print)
DOI
10.1007/978-3-642-21227-7_46
language
English
LU publication?
yes
id
e0d96be1-b612-4300-853d-4b813387f7d7 (old id 2214442)
date added to LUP
2011-12-29 13:20:35
date last changed
2017-08-27 03:41:36
@inproceedings{e0d96be1-b612-4300-853d-4b813387f7d7,
  abstract     = {Designing a system for computer aided diagnosis is a complex procedure requiring an understanding of the biology of the disease, insight into hospital workflow and awareness of available technical solutions. This paper aims to show that a valuable system can be designed for diagnosing kidney lesions in children and adolescents from 99m Tc-DMSA scintigraphy images. We present the chain of analysis and provide a discussion of its performance. On a per-lesion basis, the classification reached an ROC-curve area of 0.96 (sensitivity/specificity e.g. 97%/85%) measured using an independent test group consisting of 56 patients with 730 candidate lesions. We conclude that the presented system for diagnostic support has the potential of increasing the quality of care regarding this type of examination.},
  author       = {Landgren, Matilda and Sjöstrand, Karl and Ohlsson, Mattias and Ståhl, Daniel and Overgaard, Niels Christian and Åström, Karl and Sixt, Rune and Edenbrandt, Lars},
  booktitle    = {Lecture Notes in Computer Science},
  editor       = {Heyden, Anders and Kahl, Fredrik},
  isbn         = {978-3-642-21227-7 (online)},
  issn         = {1611-3349},
  keyword      = {Computer Aided Diagnosis – Nuclear Imaging – Active Shape Models – Artificial Neural Networks},
  language     = {eng},
  pages        = {489--500},
  publisher    = {Springer},
  title        = {An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images},
  url          = {http://dx.doi.org/10.1007/978-3-642-21227-7_46},
  volume       = {6688},
  year         = {2011},
}