Alexandra Cunliffe1, Samuel G Armato1, Richard Castillo2, Ngoc Pham3, Thomas Guerrero4, Hania A Al-Hallaq5. 1. Department of Radiology, The University of Chicago, Chicago, Illinois. 2. Department of Radiation Oncology, The University of Texas Medical Branch, Galveston, Texas. 3. Baylor College of Medicine, Houston, Texas. 4. Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 5. Department of Radiation and Cellular Oncology, The University of Chicago, Chicago, Illinois. Electronic address: hal-hallaq@radonc.uchicago.edu.
Abstract
PURPOSE: To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). METHODS AND MATERIALS: A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. RESULTS: For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). CONCLUSIONS: A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.
PURPOSE: To assess the relationship between radiation dose and change in a set of mathematical intensity- and texture-based features and to determine the ability of texture analysis to identify patients who develop radiation pneumonitis (RP). METHODS AND MATERIALS: A total of 106 patients who received radiation therapy (RT) for esophageal cancer were retrospectively identified under institutional review board approval. For each patient, diagnostic computed tomography (CT) scans were acquired before (0-168 days) and after (5-120 days) RT, and a treatment planning CT scan with an associated dose map was obtained. 32- × 32-pixel regions of interest (ROIs) were randomly identified in the lungs of each pre-RT scan. ROIs were subsequently mapped to the post-RT scan and the planning scan dose map by using deformable image registration. The changes in 20 feature values (ΔFV) between pre- and post-RT scan ROIs were calculated. Regression modeling and analysis of variance were used to test the relationships between ΔFV, mean ROI dose, and development of grade ≥2 RP. Area under the receiver operating characteristic curve (AUC) was calculated to determine each feature's ability to distinguish between patients with and those without RP. A classifier was constructed to determine whether 2- or 3-feature combinations could improve RP distinction. RESULTS: For all 20 features, a significant ΔFV was observed with increasing radiation dose. Twelve features changed significantly for patients with RP. Individual texture features could discriminate between patients with and those without RP with moderate performance (AUCs from 0.49 to 0.78). Using multiple features in a classifier, AUC increased significantly (0.59-0.84). CONCLUSIONS: A relationship between dose and change in a set of image-based features was observed. For 12 features, ΔFV was significantly related to RP development. This study demonstrated the ability of radiomics to provide a quantitative, individualized measurement of patient lung tissue reaction to RT and assess RP development.
Authors: Zafer Kocak; Elizabeth S Evans; Su-Min Zhou; Keith L Miller; Rodney J Folz; Timothy D Shafman; Lawrence B Marks Journal: Int J Radiat Oncol Biol Phys Date: 2005-07-01 Impact factor: 7.038
Authors: Ellen D Yorke; Andrew Jackson; Kenneth E Rosenzweig; Scott A Merrick; Dorota Gabrys; Ennapadam S Venkatraman; Chandra M Burman; Steven A Leibel; C Clifton Ling Journal: Int J Radiat Oncol Biol Phys Date: 2002-10-01 Impact factor: 7.038
Authors: R Uppaluri; E A Hoffman; M Sonka; P G Hartley; G W Hunninghake; G McLennan Journal: Am J Respir Crit Care Med Date: 1999-08 Impact factor: 21.405
Authors: Matthew R McCurdy; Richard Castillo; Josue Martinez; Mohammad Najeeb Al Hallack; Jessica Lichter; Nicolas Zouain; Thomas Guerrero Journal: Radiother Oncol Date: 2012-05-10 Impact factor: 6.280
Authors: Sarah A Mattonen; Shyama Tetar; David A Palma; Alexander V Louie; Suresh Senan; Aaron D Ward Journal: J Med Imaging (Bellingham) Date: 2015-11-12
Authors: Gregory J Anthony; Alexandra Cunliffe; Richard Castillo; Ngoc Pham; Thomas Guerrero; Samuel G Armato; Hania A Al-Hallaq Journal: Med Phys Date: 2017-05-22 Impact factor: 4.071
Authors: Michael MacManus; Sarah Everitt; Tanja Schimek-Jasch; X Allen Li; Ursula Nestle; Feng-Ming Spring Kong Journal: Transl Lung Cancer Res Date: 2017-12