TY - GEN
T1 - Visualizing structures in confocal microscopy datasets through clusterization
T2 - 32nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2019
AU - Beltran, Lizeth Andrea Castellanos
AU - Cruz, Carolina Uribe
AU - Dos Santos, Jorge Luiz
AU - Shivakumar, Pranavkumar
AU - Bezerra, Jorge
AU - Dal Sasso Freitas, Carla Maria
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Three-dimensional datasets from biological tissues have increased with the evolution of confocal microscopy. Hepatology researchers have used confocal microscopy for investigating the microanatomy of bile ducts. Bile ducts are complex tubular tissues consisting of many juxtaposed microstructures with distinct characteristics. Since confocal images are difficult to segment because of the noise introduced during the specimen preparation, traditional quantitative analyses used in medical datasets are difficult to perform on confocal microscopy data and require extensive user intervention. Thus, the visual exploration and analysis of bile ducts pose a challenge in hepatology research, requiring different methods. This paper investigates the application of unsupervised machine learning to extract relevant structures from confocal microscopy datasets representing bile ducts. Our approach consists of pre-processing, clustering, and 3D visualization. For clustering, we explore the density-based spatial clustering for applications with noise (DBSCAN) algorithm, using gradient information for guiding the clustering. We obtained a better visualization of the most prominent vessels and internal structures.
AB - Three-dimensional datasets from biological tissues have increased with the evolution of confocal microscopy. Hepatology researchers have used confocal microscopy for investigating the microanatomy of bile ducts. Bile ducts are complex tubular tissues consisting of many juxtaposed microstructures with distinct characteristics. Since confocal images are difficult to segment because of the noise introduced during the specimen preparation, traditional quantitative analyses used in medical datasets are difficult to perform on confocal microscopy data and require extensive user intervention. Thus, the visual exploration and analysis of bile ducts pose a challenge in hepatology research, requiring different methods. This paper investigates the application of unsupervised machine learning to extract relevant structures from confocal microscopy datasets representing bile ducts. Our approach consists of pre-processing, clustering, and 3D visualization. For clustering, we explore the density-based spatial clustering for applications with noise (DBSCAN) algorithm, using gradient information for guiding the clustering. We obtained a better visualization of the most prominent vessels and internal structures.
KW - Confocal microscopy data
KW - DBSCAN clustering
KW - Image processing
KW - Volumetric visualization
UR - http://www.scopus.com/inward/record.url?scp=85070962880&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070962880&partnerID=8YFLogxK
U2 - 10.1109/CBMS.2019.00086
DO - 10.1109/CBMS.2019.00086
M3 - Conference contribution
AN - SCOPUS:85070962880
T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems
SP - 405
EP - 410
BT - Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 5 June 2019 through 7 June 2019
ER -