Computer-aided pulmonary image analysis in small animal models

Ziyue Xu, Ulas Bagci, Awais Mansoor, Gabriela Kramer-Marek, Brian Luna, Andre Kubler, Bappaditya Dey, Brent Foster, Georgios Z. Papadakis, Jeremy V. Camp, Colleen Jonsson, William R. Bishai, Sanjay Jain, Jayaram K. Udupa, Daniel J. Mollura

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Purpose: To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models. Methods: The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters. Results: 133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90% for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT09 data set. Conclusions: The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.

Original languageEnglish (US)
Pages (from-to)3896-3910
Number of pages15
JournalMedical Physics
Volume42
Issue number7
DOIs
StatePublished - Jul 1 2015
Externally publishedYes

Fingerprint

Animal Models
Lung
Lung Diseases
Communicable Diseases
Total Lung Capacity
Sensitivity and Specificity
Ferrets
Research
Pathology
Rabbits

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Xu, Z., Bagci, U., Mansoor, A., Kramer-Marek, G., Luna, B., Kubler, A., ... Mollura, D. J. (2015). Computer-aided pulmonary image analysis in small animal models. Medical Physics, 42(7), 3896-3910. https://doi.org/10.1118/1.4921618

Computer-aided pulmonary image analysis in small animal models. / Xu, Ziyue; Bagci, Ulas; Mansoor, Awais; Kramer-Marek, Gabriela; Luna, Brian; Kubler, Andre; Dey, Bappaditya; Foster, Brent; Papadakis, Georgios Z.; Camp, Jeremy V.; Jonsson, Colleen; Bishai, William R.; Jain, Sanjay; Udupa, Jayaram K.; Mollura, Daniel J.

In: Medical Physics, Vol. 42, No. 7, 01.07.2015, p. 3896-3910.

Research output: Contribution to journalArticle

Xu, Z, Bagci, U, Mansoor, A, Kramer-Marek, G, Luna, B, Kubler, A, Dey, B, Foster, B, Papadakis, GZ, Camp, JV, Jonsson, C, Bishai, WR, Jain, S, Udupa, JK & Mollura, DJ 2015, 'Computer-aided pulmonary image analysis in small animal models', Medical Physics, vol. 42, no. 7, pp. 3896-3910. https://doi.org/10.1118/1.4921618
Xu Z, Bagci U, Mansoor A, Kramer-Marek G, Luna B, Kubler A et al. Computer-aided pulmonary image analysis in small animal models. Medical Physics. 2015 Jul 1;42(7):3896-3910. https://doi.org/10.1118/1.4921618
Xu, Ziyue ; Bagci, Ulas ; Mansoor, Awais ; Kramer-Marek, Gabriela ; Luna, Brian ; Kubler, Andre ; Dey, Bappaditya ; Foster, Brent ; Papadakis, Georgios Z. ; Camp, Jeremy V. ; Jonsson, Colleen ; Bishai, William R. ; Jain, Sanjay ; Udupa, Jayaram K. ; Mollura, Daniel J. / Computer-aided pulmonary image analysis in small animal models. In: Medical Physics. 2015 ; Vol. 42, No. 7. pp. 3896-3910.
@article{287d7d65d9c044368476a32011521b01,
title = "Computer-aided pulmonary image analysis in small animal models",
abstract = "Purpose: To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models. Methods: The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters. Results: 133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90{\%} for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT09 data set. Conclusions: The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.",
author = "Ziyue Xu and Ulas Bagci and Awais Mansoor and Gabriela Kramer-Marek and Brian Luna and Andre Kubler and Bappaditya Dey and Brent Foster and Papadakis, {Georgios Z.} and Camp, {Jeremy V.} and Colleen Jonsson and Bishai, {William R.} and Sanjay Jain and Udupa, {Jayaram K.} and Mollura, {Daniel J.}",
year = "2015",
month = "7",
day = "1",
doi = "10.1118/1.4921618",
language = "English (US)",
volume = "42",
pages = "3896--3910",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "7",

}

TY - JOUR

T1 - Computer-aided pulmonary image analysis in small animal models

AU - Xu, Ziyue

AU - Bagci, Ulas

AU - Mansoor, Awais

AU - Kramer-Marek, Gabriela

AU - Luna, Brian

AU - Kubler, Andre

AU - Dey, Bappaditya

AU - Foster, Brent

AU - Papadakis, Georgios Z.

AU - Camp, Jeremy V.

AU - Jonsson, Colleen

AU - Bishai, William R.

AU - Jain, Sanjay

AU - Udupa, Jayaram K.

AU - Mollura, Daniel J.

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Purpose: To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models. Methods: The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters. Results: 133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90% for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT09 data set. Conclusions: The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.

AB - Purpose: To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models. Methods: The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters. Results: 133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90% for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT09 data set. Conclusions: The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.

UR - http://www.scopus.com/inward/record.url?scp=84935038645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84935038645&partnerID=8YFLogxK

U2 - 10.1118/1.4921618

DO - 10.1118/1.4921618

M3 - Article

VL - 42

SP - 3896

EP - 3910

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 7

ER -