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

doi:10.1007/978-3-642-21227-7_46

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

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

7 Citeringar (SciVal)

Sammanfattning

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.

Originalspråk	engelska
Titel på värdpublikation	Lecture Notes in Computer Science
Redaktörer	Anders Heyden, Fredrik Kahl
Förlag	Springer
Sidor	489-500
Antal sidor	12
Volym	6688
ISBN (tryckt)	978-3-642-21227-7 (online), 978-3-642-21226-0 (print)
DOI	https://doi.org/10.1007/978-3-642-21227-7_46
Status	Published - 2011
Evenemang	17th Scandinavian Conference on Image Analysis (SCIA 2011) - Ystad, Sverige Varaktighet: 2011 maj 23 → 2011 maj 27

Publikationsserier

Namn
Volym	6688
ISSN (tryckt)	1611-3349
ISSN (elektroniskt)	0302-9743

Konferens

Konferens	17th Scandinavian Conference on Image Analysis (SCIA 2011)
Land/Territorium	Sverige
Ort	Ystad
Period	2011/05/23 → 2011/05/27

Ämnesklassifikation (UKÄ)

Matematik
Datorseende och robotik (autonoma system)

Tillgång till dokument

10.1007/978-3-642-21227-7_46

7 Citeringar
1 Doktorsavhandling (sammanläggning)

Analysis of Medical Images: Registration, Segmentation and Classification
Bidragets översatta titel : Analys av medicinska bilder: Registrering, segmentering och klassificeringLandgren, M., 2016, Centre for Mathematical Sciences, Lund University. 155 s.
Forskningsoutput: Avhandling › Doktorsavhandling (sammanläggning)

Öppen tillgång
Fil

Citera det här

Landgren, M., Sjöstrand, K., Ohlsson, M., Ståhl, D., Overgaard, N. C., Åström, K., Sixt, R., & Edenbrandt, L. (2011). An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images. I A. Heyden, & F. Kahl (Red.), Lecture Notes in Computer Science (Vol. 6688, s. 489-500). Springer. https://doi.org/10.1007/978-3-642-21227-7_46

Landgren, Matilda ; Sjöstrand, Karl ; Ohlsson, Mattias ; Ståhl, Daniel ; Overgaard, Niels Christian ; Åström, Karl ; Sixt, Rune ; Edenbrandt, Lars. / An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images. Lecture Notes in Computer Science. redaktör / Anders Heyden ; Fredrik Kahl. Vol. 6688 Springer, 2011. s. 489-500

@inproceedings{e0d96be1b6124300853d4b813387f7d7,

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

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.",

keywords = "Computer Aided Diagnosis – Nuclear Imaging – Active Shape Models – Artificial Neural Networks",

author = "Matilda Landgren and Karl Sj{\"o}strand and Mattias Ohlsson and Daniel St{\aa}hl and Overgaard, {Niels Christian} and Karl {\AA}str{\"o}m and Rune Sixt and Lars Edenbrandt",

year = "2011",

doi = "10.1007/978-3-642-21227-7_46",

language = "English",

isbn = "978-3-642-21227-7 (online)",

volume = "6688",

publisher = "Springer",

pages = "489--500",

editor = "Anders Heyden and Fredrik Kahl",

booktitle = "Lecture Notes in Computer Science",

address = "Germany",

note = "17th Scandinavian Conference on Image Analysis (SCIA 2011) ; Conference date: 23-05-2011 Through 27-05-2011",

}

Landgren, M, Sjöstrand, K, Ohlsson, M, Ståhl, D, Overgaard, NC , Åström, K, Sixt, R & Edenbrandt, L 2011, An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images. i A Heyden & F Kahl (red), Lecture Notes in Computer Science. vol. 6688, Springer, s. 489-500, 17th Scandinavian Conference on Image Analysis (SCIA 2011), Ystad, Sverige, 2011/05/23. https://doi.org/10.1007/978-3-642-21227-7_46

An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images. / Landgren, Matilda; Sjöstrand, Karl; Ohlsson, Mattias; Ståhl, Daniel; Overgaard, Niels Christian ; Åström, Karl; Sixt, Rune; Edenbrandt, Lars.

Lecture Notes in Computer Science. red. / Anders Heyden; Fredrik Kahl. Vol. 6688 Springer, 2011. s. 489-500.

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

TY - GEN

T1 - An Automated System for the Detection and Diagnosis of Kidney Lesions in Children from Scintigraphy Images

AU - Landgren, Matilda

AU - Sjöstrand, Karl

AU - Ohlsson, Mattias

AU - Ståhl, Daniel

AU - Overgaard, Niels Christian

AU - Åström, Karl

AU - Sixt, Rune

AU - Edenbrandt, Lars

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

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

U2 - 10.1007/978-3-642-21227-7_46

DO - 10.1007/978-3-642-21227-7_46

M3 - Paper in conference proceeding

SN - 978-3-642-21227-7 (online)

SN - 978-3-642-21226-0 (print)

VL - 6688

SP - 489

EP - 500

BT - Lecture Notes in Computer Science

A2 - Heyden, Anders

A2 - Kahl, Fredrik

PB - Springer

T2 - 17th Scandinavian Conference on Image Analysis (SCIA 2011)

Y2 - 23 May 2011 through 27 May 2011

ER -

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

Sammanfattning

Publikationsserier

Konferens

Ämnesklassifikation (UKÄ)

Tillgång till dokument

Fingeravtryck

Forskningsoutput

Analysis of Medical Images: Registration, Segmentation and Classification

Citera det här