dp-BREATH: Heat maps and probabilistic classification assisting the analysis of abnormal lung regions.


Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
May 2019
Historique:
received: 05 07 2018
revised: 15 01 2019
accepted: 21 01 2019
entrez: 4 5 2019
pubmed: 3 5 2019
medline: 26 11 2019
Statut: ppublish

Résumé

Identifying abnormalities in chest CT scans is an important and challenging task, demanding time and effort from specialists. Different parts of a single lung image may present both normal and abnormal characteristics. Thus, detecting a single lung as healthy (normal) or not is inaccurate. In this work we propose dp-BREATH, a method capable of detecting abnormalities in pulmonary tissue regions and directing the specialist's attention to the lung region containing them. It starts by highlighting regions that may indicate pulmonary abnormalities based on the healthy pulmonary tissue behavior using a superpixel-based approach and a heat map visualization. This is achieved by modeling regions of healthy tissue using a statistical model. All regions considered abnormal are modeled and classified according to their probability of containing each of the studied abnormalities. Further, dp-BREATH provides a better recognition of radiological patterns, with the likelihood of a selected lung region to contain abnormalities. We validate the statistical model of healthy and abnormal detection using a representative dataset of chest CT scans. The model has shown almost no overlap between healthy and abnormal regions, and the detection of abnormalities presented precision higher than 86%, for all recall values. Additionally, the fitted models describing pulmonary radiological patterns present precision of up to 87%, with a high separation for three of five radiological patterns. dp-BREATH's heat map representation and its list of radiological patterns probabilities provided are intuitive methods to assist physicians during diagnosis.

Sections du résumé

BACKGROUND AND OBJECTIVE OBJECTIVE
Identifying abnormalities in chest CT scans is an important and challenging task, demanding time and effort from specialists. Different parts of a single lung image may present both normal and abnormal characteristics. Thus, detecting a single lung as healthy (normal) or not is inaccurate.
METHODS METHODS
In this work we propose dp-BREATH, a method capable of detecting abnormalities in pulmonary tissue regions and directing the specialist's attention to the lung region containing them. It starts by highlighting regions that may indicate pulmonary abnormalities based on the healthy pulmonary tissue behavior using a superpixel-based approach and a heat map visualization. This is achieved by modeling regions of healthy tissue using a statistical model. All regions considered abnormal are modeled and classified according to their probability of containing each of the studied abnormalities. Further, dp-BREATH provides a better recognition of radiological patterns, with the likelihood of a selected lung region to contain abnormalities.
RESULTS RESULTS
We validate the statistical model of healthy and abnormal detection using a representative dataset of chest CT scans. The model has shown almost no overlap between healthy and abnormal regions, and the detection of abnormalities presented precision higher than 86%, for all recall values. Additionally, the fitted models describing pulmonary radiological patterns present precision of up to 87%, with a high separation for three of five radiological patterns.
CONCLUSIONS CONCLUSIONS
dp-BREATH's heat map representation and its list of radiological patterns probabilities provided are intuitive methods to assist physicians during diagnosis.

Identifiants

pubmed: 31046993
pii: S0169-2607(18)31103-9
doi: 10.1016/j.cmpb.2019.01.014
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

27-34

Informations de copyright

Copyright © 2019 Elsevier B.V. All rights reserved.

Auteurs

Mirela T Cazzolato (MT)

Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos, SP 13.566-590, Brazil. Electronic address: mirelac@usp.br.

Lucas C Scabora (LC)

Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos, SP 13.566-590, Brazil.

Marcos R Nesso (MR)

Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos, SP 13.566-590, Brazil.

Luis F Milano-Oliveira (LF)

Department of Computer Science, University of Londrina, Londrina, PR 86.057-970, Brazil.

Alceu F Costa (AF)

Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos, SP 13.566-590, Brazil.

Daniel S Kaster (DS)

Department of Computer Science, University of Londrina, Londrina, PR 86.057-970, Brazil.

Marcel Koenigkam-Santos (M)

Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, SP 14049-900, Brazil.

Paulo Mazzoncini de Azevedo-Marques (P)

Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, SP 14049-900, Brazil.

Caetano Traina (C)

Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos, SP 13.566-590, Brazil.

Agma J M Traina (AJM)

Institute of Mathematics and Computer Sciences, University of São Paulo, São Carlos, SP 13.566-590, Brazil. Electronic address: agma@icmc.usp.br.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH