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

Author(s)

Cazzolato, Mirela T. ^[1] ; Scabora, Lucas C. ^[1] ; Nesso-Jr, Marcos R. ; Milano-Oliveira, Luis F. ^[2] ; Costa, Alceu F. ^[3] ; Kaster, Daniel S. ^[2] ; Koenigkam-Santos, Marcel ^[4] ; de Azevedo-Marques, Paulo Mazzoncini ^[4] ; Traina-Jr, Caetano ; Traina, Agma J. M. ^[5]

Affiliation

^[1] Univ Sao Paulo, Inst Math & Comp Sci, BR-13566590 Sao Carlos, SP - Brazil

^[2] Univ Londrina, Dept Comp Sci, BR-86057970 Londrina, PR - Brazil

^[3] Nesso-Jr, Jr., Marcos R., Univ Sao Paulo, Inst Math & Comp Sci, BR-13566590 Sao Carlos, SP - Brazil

^[4] Univ Sao Paulo, Ribeirao Preto Med Sch, BR-14049900 Ribeirao Preto, SP - Brazil

^[5] Traina-Jr, Jr., Caetano, Nesso-Jr, Jr., Marcos R., Univ Sao Paulo, Inst Math & Comp Sci, BR-13566590 Sao Carlos, SP - Brazil

• Document type: Journal article
• Source: COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE; v. 173, p. 27-34, MAY 2019.
• Web of Science Citations: 2

Abstract

Background and 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: 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: 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: dp-BREATH's heat map representation and its list of radiological patterns probabilities provided are intuitive methods to assist physicians during diagnosis. (c) 2019 Elsevier B.V. All rights reserved. (AU)

• FAPESP's process: 16/17078-0 - Mining, indexing and visualizing Big Data in clinical decision support systems (MIVisBD)
• Grantee: Agma Juci Machado Traina
• Support type: Research Projects - Thematic Grants
• FAPESP's process: 16/17330-1 - Storage and Navigation Operations on Graphs in Relational DBMS
• Grantee: Lucas de Carvalho Scabora
• Support type: Scholarships in Brazil - Doctorate
• FAPESP's process: 18/24414-2 - A framework for integration of feature extraction techniques and complex databases for MIVisBD
• Grantee: Mirela Teixeira Cazzolato
• Support type: Scholarships in Brazil - Technical Training Program - Technical Training