An Automatically Generated Texture-based Atlas of the Lungs

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedings – Annual report year: 2018Researchpeer-review

Standard

An Automatically Generated Texture-based Atlas of the Lungs. / Cid, Yashin Dicente; Puonti, Oula; Platon, Alexandra; Van Leemput, Koen; Mueller, Henning; Poletti, Pierre-Alexandre.

Medical Imaging 2018: Computer-Aided Diagnosis. Vol. 10575 SPIE - International Society for Optical Engineering, 2018. 105753A.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedings – Annual report year: 2018Researchpeer-review

Harvard

Cid, YD, Puonti, O, Platon, A, Van Leemput, K, Mueller, H & Poletti, P-A 2018, An Automatically Generated Texture-based Atlas of the Lungs. in Medical Imaging 2018: Computer-Aided Diagnosis. vol. 10575, 105753A, SPIE - International Society for Optical Engineering, SPIE Medical Imaging 2018, Houston, United States, 10/02/2018. https://doi.org/10.1117/12.2294004

APA

Cid, Y. D., Puonti, O., Platon, A., Van Leemput, K., Mueller, H., & Poletti, P-A. (2018). An Automatically Generated Texture-based Atlas of the Lungs. In Medical Imaging 2018: Computer-Aided Diagnosis (Vol. 10575). [105753A] SPIE - International Society for Optical Engineering. https://doi.org/10.1117/12.2294004

CBE

Cid YD, Puonti O, Platon A, Van Leemput K, Mueller H, Poletti P-A. 2018. An Automatically Generated Texture-based Atlas of the Lungs. In Medical Imaging 2018: Computer-Aided Diagnosis. SPIE - International Society for Optical Engineering. https://doi.org/10.1117/12.2294004

MLA

Cid, Yashin Dicente et al. "An Automatically Generated Texture-based Atlas of the Lungs". Medical Imaging 2018: Computer-Aided Diagnosis. SPIE - International Society for Optical Engineering. 2018. https://doi.org/10.1117/12.2294004

Vancouver

Cid YD, Puonti O, Platon A, Van Leemput K, Mueller H, Poletti P-A. An Automatically Generated Texture-based Atlas of the Lungs. In Medical Imaging 2018: Computer-Aided Diagnosis. Vol. 10575. SPIE - International Society for Optical Engineering. 2018. 105753A https://doi.org/10.1117/12.2294004

Author

Cid, Yashin Dicente ; Puonti, Oula ; Platon, Alexandra ; Van Leemput, Koen ; Mueller, Henning ; Poletti, Pierre-Alexandre. / An Automatically Generated Texture-based Atlas of the Lungs. Medical Imaging 2018: Computer-Aided Diagnosis. Vol. 10575 SPIE - International Society for Optical Engineering, 2018.

Bibtex

@inproceedings{5773c71f78ab4892b5f852cd539dea57,
title = "An Automatically Generated Texture-based Atlas of the Lungs",
abstract = "Many pulmonary diseases can be characterized by visual abnormalities on lung CT scans. Some diseases manifest similar defects but require completely different treatments, as is the case for Pulmonary Hypertension (PH) and Pulmonary Embolism (PE): both present hypo- and hyper-perfused regions but with different distribution across the lung and require different treatment protocols. Finding these distributions by visual inspection is not trivial even for trained radiologists who currently use invasive catheterism to diagnose PH. A Computer-Aided Diagnosis (CAD) tool that could facilitate the non-invasive diagnosis of these diseases can benefit both the radiologists and the patients. Most of the visual differences in the parenchyma can be characterized using texture descriptors. Current CAD systems often use texture information but the texture is either computed in a patch-based fashion, or based on an anatomical division of the lung. The difficulty of precisely finding these divisions in abnormal lungs calls for new tools for obtaining new meaningful divisions of the lungs.In this paper we present a method for unsupervised segmentation of lung CT scans into subregions that are similar in terms of texture and spatial proximity. To this extent, we combine a previously validated Riesz-wavelet texture descriptor with a well-known superpixel segmentation approach that we extend to 3D. We demonstrate the feasibility and accuracy of our approach on a simulated texture dataset, and show preliminary results for CT scans of the lung comparing subjects suffering either from PH or PE. The resulting texture-based atlas of individual lungs can potentially help physicians in diagnosis or be used for studying common texture distributions related to other diseases.",
keywords = "Lung atlas, 3D texture, Riesz-wavelet, Supervoxels",
author = "Cid, {Yashin Dicente} and Oula Puonti and Alexandra Platon and {Van Leemput}, Koen and Henning Mueller and Pierre-Alexandre Poletti",
year = "2018",
doi = "10.1117/12.2294004",
language = "English",
volume = "10575",
booktitle = "Medical Imaging 2018: Computer-Aided Diagnosis",
publisher = "SPIE - International Society for Optical Engineering",

}

RIS

TY - GEN

T1 - An Automatically Generated Texture-based Atlas of the Lungs

AU - Cid, Yashin Dicente

AU - Puonti, Oula

AU - Platon, Alexandra

AU - Van Leemput, Koen

AU - Mueller, Henning

AU - Poletti, Pierre-Alexandre

PY - 2018

Y1 - 2018

N2 - Many pulmonary diseases can be characterized by visual abnormalities on lung CT scans. Some diseases manifest similar defects but require completely different treatments, as is the case for Pulmonary Hypertension (PH) and Pulmonary Embolism (PE): both present hypo- and hyper-perfused regions but with different distribution across the lung and require different treatment protocols. Finding these distributions by visual inspection is not trivial even for trained radiologists who currently use invasive catheterism to diagnose PH. A Computer-Aided Diagnosis (CAD) tool that could facilitate the non-invasive diagnosis of these diseases can benefit both the radiologists and the patients. Most of the visual differences in the parenchyma can be characterized using texture descriptors. Current CAD systems often use texture information but the texture is either computed in a patch-based fashion, or based on an anatomical division of the lung. The difficulty of precisely finding these divisions in abnormal lungs calls for new tools for obtaining new meaningful divisions of the lungs.In this paper we present a method for unsupervised segmentation of lung CT scans into subregions that are similar in terms of texture and spatial proximity. To this extent, we combine a previously validated Riesz-wavelet texture descriptor with a well-known superpixel segmentation approach that we extend to 3D. We demonstrate the feasibility and accuracy of our approach on a simulated texture dataset, and show preliminary results for CT scans of the lung comparing subjects suffering either from PH or PE. The resulting texture-based atlas of individual lungs can potentially help physicians in diagnosis or be used for studying common texture distributions related to other diseases.

AB - Many pulmonary diseases can be characterized by visual abnormalities on lung CT scans. Some diseases manifest similar defects but require completely different treatments, as is the case for Pulmonary Hypertension (PH) and Pulmonary Embolism (PE): both present hypo- and hyper-perfused regions but with different distribution across the lung and require different treatment protocols. Finding these distributions by visual inspection is not trivial even for trained radiologists who currently use invasive catheterism to diagnose PH. A Computer-Aided Diagnosis (CAD) tool that could facilitate the non-invasive diagnosis of these diseases can benefit both the radiologists and the patients. Most of the visual differences in the parenchyma can be characterized using texture descriptors. Current CAD systems often use texture information but the texture is either computed in a patch-based fashion, or based on an anatomical division of the lung. The difficulty of precisely finding these divisions in abnormal lungs calls for new tools for obtaining new meaningful divisions of the lungs.In this paper we present a method for unsupervised segmentation of lung CT scans into subregions that are similar in terms of texture and spatial proximity. To this extent, we combine a previously validated Riesz-wavelet texture descriptor with a well-known superpixel segmentation approach that we extend to 3D. We demonstrate the feasibility and accuracy of our approach on a simulated texture dataset, and show preliminary results for CT scans of the lung comparing subjects suffering either from PH or PE. The resulting texture-based atlas of individual lungs can potentially help physicians in diagnosis or be used for studying common texture distributions related to other diseases.

KW - Lung atlas

KW - 3D texture

KW - Riesz-wavelet

KW - Supervoxels

U2 - 10.1117/12.2294004

DO - 10.1117/12.2294004

M3 - Article in proceedings

VL - 10575

BT - Medical Imaging 2018: Computer-Aided Diagnosis

PB - SPIE - International Society for Optical Engineering

ER -