P M Gordaliza1,2, A Muñoz-Barrutia3,4, L E Via5, S Sharpe6, M Desco1,2,7,8, J J Vaquero1,2. 1. Dpto. Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Leganés, Spain. 2. Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain. 3. Dpto. Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Leganés, Spain. mamunozb@ing.uc3m.es. 4. Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain. mamunozb@ing.uc3m.es. 5. Tuberculosis Research Section, LCIM, and Tuberculosis Imaging Program, DIR, NIAID, NIH, Bethesda, MD, USA. 6. National Infections Service, Public Health England, Porton Down, England. 7. Centro Nacional de Investigaciones Cardiovasculares Carlos III, Madrid, Spain. 8. Centro de Investigación Biomédica en Red de Salud Mental, Madrid, Spain.
Abstract
PURPOSE: Computed tomography (CT) images enable capturing specific manifestations of tuberculosis (TB) that are undetectable using common diagnostic tests, which suffer from limited specificity. In this study, we aimed to automatically quantify the burden of Mycobacterium tuberculosis (Mtb) using biomarkers extracted from x-ray CT images. PROCEDURES: Nine macaques were aerosol-infected with Mtb and treated with various antibiotic cocktails. Chest CT scans were acquired in all animals at specific times independently of disease progression. First, a fully automatic segmentation of the healthy lungs from the acquired chest CT volumes was performed and air-like structures were extracted. Next, unsegmented pulmonary regions corresponding to damaged parenchymal tissue and TB lesions were included. CT biomarkers were extracted by classification of the probability distribution of the intensity of the segmented images into three tissue types: (1) Healthy tissue, parenchyma free from infection; (2) soft diseased tissue, and (3) hard diseased tissue. The probability distribution of tissue intensities was assumed to follow a Gaussian mixture model. The thresholds identifying each region were automatically computed using an expectation-maximization algorithm. RESULTS: The estimated longitudinal course of TB infection shows that subjects that have followed the same antibiotic treatment present a similar response (relative change in the diseased volume) with respect to baseline. More interestingly, the correlation between the diseased volume (soft tissue + hard tissue), which was manually delineated by an expert, and the automatically extracted volume with the proposed method was very strong (R2 ≈ 0.8). CONCLUSIONS: We present a methodology that is suitable for automatic extraction of a radiological biomarker from CT images for TB disease burden. The method could be used to describe the longitudinal evolution of Mtb infection in a clinical trial devoted to the design of new drugs.
PURPOSE: Computed tomography (CT) images enable capturing specific manifestations of tuberculosis (TB) that are undetectable using common diagnostic tests, which suffer from limited specificity. In this study, we aimed to automatically quantify the burden of Mycobacterium tuberculosis (Mtb) using biomarkers extracted from x-ray CT images. PROCEDURES: Nine macaques were aerosol-infected with Mtb and treated with various antibiotic cocktails. Chest CT scans were acquired in all animals at specific times independently of disease progression. First, a fully automatic segmentation of the healthy lungs from the acquired chest CT volumes was performed and air-like structures were extracted. Next, unsegmented pulmonary regions corresponding to damaged parenchymal tissue and TB lesions were included. CT biomarkers were extracted by classification of the probability distribution of the intensity of the segmented images into three tissue types: (1) Healthy tissue, parenchyma free from infection; (2) soft diseased tissue, and (3) hard diseased tissue. The probability distribution of tissue intensities was assumed to follow a Gaussian mixture model. The thresholds identifying each region were automatically computed using an expectation-maximization algorithm. RESULTS: The estimated longitudinal course of TB infection shows that subjects that have followed the same antibiotic treatment present a similar response (relative change in the diseased volume) with respect to baseline. More interestingly, the correlation between the diseased volume (soft tissue + hard tissue), which was manually delineated by an expert, and the automatically extracted volume with the proposed method was very strong (R2 ≈ 0.8). CONCLUSIONS: We present a methodology that is suitable for automatic extraction of a radiological biomarker from CT images for TB disease burden. The method could be used to describe the longitudinal evolution of Mtb infection in a clinical trial devoted to the design of new drugs.
Authors: Arun C Nachiappan; Kasra Rahbar; Xiao Shi; Elizabeth S Guy; Eduardo J Mortani Barbosa; Girish S Shroff; Daniel Ocazionez; Alan E Schlesinger; Sharyn I Katz; Mark M Hammer Journal: Radiographics Date: 2017 Jan-Feb Impact factor: 5.333
Authors: Laura E Via; Kathleen England; Danielle M Weiner; Daniel Schimel; Matthew D Zimmerman; Emmanuel Dayao; Ray Y Chen; Lori E Dodd; Mike Richardson; Katherine K Robbins; Ying Cai; Dima Hammoud; Peter Herscovitch; Véronique Dartois; JoAnne L Flynn; Clifton E Barry Journal: Antimicrob Agents Chemother Date: 2015-05-04 Impact factor: 5.191
Authors: Laura E Via; Dan Schimel; Danielle M Weiner; Veronique Dartois; Emmanuel Dayao; Ying Cai; Young-Soon Yoon; Matthew R Dreher; Robin J Kastenmayer; Charles M Laymon; J Eoin Carny; Joanne L Flynn; Peter Herscovitch; Clifton E Barry Journal: Antimicrob Agents Chemother Date: 2012-06-11 Impact factor: 5.191
Authors: Ray Y Chen; Lori E Dodd; Myungsun Lee; Praveen Paripati; Dima A Hammoud; James M Mountz; Doosoo Jeon; Nadeem Zia; Homeira Zahiri; M Teresa Coleman; Matthew W Carroll; Jong Doo Lee; Yeon Joo Jeong; Peter Herscovitch; Saher Lahouar; Michael Tartakovsky; Alexander Rosenthal; Sandeep Somaiyya; Soyoung Lee; Lisa C Goldfeder; Ying Cai; Laura E Via; Seung-Kyu Park; Sang-Nae Cho; Clifton E Barry Journal: Sci Transl Med Date: 2014-12-03 Impact factor: 17.956
Authors: Robert S Wallis; Peter Kim; Stewart Cole; Debra Hanna; Bruno B Andrade; Markus Maeurer; Marco Schito; Alimuddin Zumla Journal: Lancet Infect Dis Date: 2013-03-24 Impact factor: 25.071
Authors: Laura E Via; Danielle M Weiner; Daniel Schimel; Philana Ling Lin; Emmanuel Dayao; Sarah L Tankersley; Ying Cai; M Teresa Coleman; Jaime Tomko; Praveen Paripati; Marlene Orandle; Robin J Kastenmayer; Michael Tartakovsky; Alexander Rosenthal; Damien Portevin; Seok Yong Eum; Saher Lahouar; Sebastien Gagneux; Douglas B Young; Joanne L Flynn; Clifton E Barry Journal: Infect Immun Date: 2013-05-28 Impact factor: 3.441
Authors: Craig J Galbán; Meilan K Han; Jennifer L Boes; Komal A Chughtai; Charles R Meyer; Timothy D Johnson; Stefanie Galbán; Alnawaz Rehemtulla; Ella A Kazerooni; Fernando J Martinez; Brian D Ross Journal: Nat Med Date: 2012-10-07 Impact factor: 53.440
Authors: Hee-Jeong Yang; Decheng Wang; Xin Wen; Danielle M Weiner; Laura E Via Journal: Front Cell Infect Microbiol Date: 2021-03-16 Impact factor: 5.293