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

Matilda Landgren, Karl Sjöstrand, Mattias Ohlsson, Daniel Ståhl, Niels Christian Overgaard, Karl Åström, Rune Sixt, Lars Edenbrandt

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingResearchpeer-review

7 Citations (SciVal)

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.
Original languageEnglish
Title of host publicationLecture Notes in Computer Science
EditorsAnders Heyden, Fredrik Kahl
PublisherSpringer
Pages489-500
Number of pages12
Volume6688
ISBN (Print)978-3-642-21227-7 (online), 978-3-642-21226-0 (print)
DOIs
Publication statusPublished - 2011
Event17th Scandinavian Conference on Image Analysis (SCIA 2011) - Ystad, Sweden
Duration: 2011 May 232011 May 27

Publication series

Name
Volume6688
ISSN (Print)1611-3349
ISSN (Electronic)0302-9743

Conference

Conference17th Scandinavian Conference on Image Analysis (SCIA 2011)
Country/TerritorySweden
CityYstad
Period2011/05/232011/05/27

Subject classification (UKÄ)

  • Mathematics
  • Computer Vision and Robotics (Autonomous Systems)

Keywords

  • Computer Aided Diagnosis – Nuclear Imaging – Active Shape Models – Artificial Neural Networks

Fingerprint

Dive into the research topics of 'An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images'. Together they form a unique fingerprint.

Cite this