Large-scale Image Region Documentation for Fully Automated Image Biomarker Algorithm Development and Evaluation

Overview

Journal J Med Imaging (Bellingham)

Specialty Radiology

Date 2017 Jun 15

PMID 28612037

Citations 4

Authors

Anthony P Reeves

Yiting Xie

Shuang Liu

Affiliations

Soon will be listed here.

Abstract

With the advent of fully automated image analysis and modern machine learning methods, there is a need for very large image datasets having documented segmentations for both computer algorithm training and evaluation. This paper presents a method and implementation for facilitating such datasets that addresses the critical issue of size scaling for algorithm validation and evaluation; current evaluation methods that are usually used in academic studies do not scale to large datasets. This method includes protocols for the documentation of many regions in very large image datasets; the documentation may be incrementally updated by new image data and by improved algorithm outcomes. This method has been used for 5 years in the context of chest health biomarkers from low-dose chest CT images that are now being used with increasing frequency in lung cancer screening practice. The lung scans are segmented into over 100 different anatomical regions, and the method has been applied to a dataset of over 20,000 chest CT images. Using this framework, the computer algorithms have been developed to achieve over 90% acceptable image segmentation on the complete dataset.

Citing Articles

A Modified LBP Operator-Based Optimized Fuzzy Art Map Medical Image Retrieval System for Disease Diagnosis and Prediction.

Anitha K , S R, C K, Lai W, Srividhya S, K N Biomedicines. 2022; 10(10).

PMID: 36289700 PMC: 9598721. DOI: 10.3390/biomedicines10102438.

Information Hiding in the DICOM Message Service and Upper Layer Service with Entropy-Based Detection.

Mileva A, Velinov A, Dimitrova V, Caviglione L, Wendzel S Entropy (Basel). 2022; 24(2).

PMID: 35205470 PMC: 8871404. DOI: 10.3390/e24020176.

Deep Learning-Based Image Segmentation of Cone-Beam Computed Tomography Images for Oral Lesion Detection.

Wang X, Meng X, Yan S J Healthc Eng. 2021; 2021:4603475.

PMID: 34594482 PMC: 8478545. DOI: 10.1155/2021/4603475.

The Regimen of Computed Tomography Screening for Lung Cancer: Lessons Learned Over 25 Years From the International Early Lung Cancer Action Program.

Henschke C, Yip R, Shaham D, Zulueta J, Aguayo S, Reeves A J Thorac Imaging. 2020; 36(1):6-23.

PMID: 32520848 PMC: 7771636. DOI: 10.1097/RTI.0000000000000538.

References

Jimenez-Del-Toro O, Muller H, Krenn M, Gruenberg K, Taha A, Winterstein M . Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks. IEEE Trans Med Imaging. 2016; 35(11):2459-2475. DOI: 10.1109/TMI.2016.2578680. View

Reeves A, Biancardi A, Apanasovich T, Meyer C, MacMahon H, van Beek E . The Lung Image Database Consortium (LIDC): a comparison of different size metrics for pulmonary nodule measurements. Acad Radiol. 2007; 14(12):1475-85. PMC: 2222556. DOI: 10.1016/j.acra.2007.09.005. View

Zhang L, Hoffman E, Reinhardt J . Atlas-driven lung lobe segmentation in volumetric X-ray CT images. IEEE Trans Med Imaging. 2006; 25(1):1-16. DOI: 10.1109/TMI.2005.859209. View

Gulshan V, Peng L, Coram M, Stumpe M, Wu D, Narayanaswamy A . Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016; 316(22):2402-2410. DOI: 10.1001/jama.2016.17216. View

Liu S, Xie Y, Reeves A . Automated 3D closed surface segmentation: application to vertebral body segmentation in CT images. Int J Comput Assist Radiol Surg. 2015; 11(5):789-801. DOI: 10.1007/s11548-015-1320-0. View

Keller B, Reeves A, Henschke C, Yankelevitz D . Multivariate compensation of quantitative pulmonary emphysema metric variation from low-dose, whole-lung CT scans. AJR Am J Roentgenol. 2011; 197(3):W495-502. DOI: 10.2214/AJR.11.6444. View

Kostis W, Reeves A, Yankelevitz D, Henschke C . Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images. IEEE Trans Med Imaging. 2003; 22(10):1259-74. DOI: 10.1109/TMI.2003.817785. View

Reeves A, Biancardi A, Yankelevitz D, Fotin S, Keller B, Jirapatnakul A . A public image database to support research in computer aided diagnosis. Annu Int Conf IEEE Eng Med Biol Soc. 2009; 2009:3715-8. DOI: 10.1109/IEMBS.2009.5334807. View

Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C . Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal. 2009; 13(3):471-82. DOI: 10.1016/j.media.2009.02.004. View

10.

Enquobahrie A, Reeves A, Yankelevitz D, Henschke C . Automated detection of small pulmonary nodules in whole lung CT scans. Acad Radiol. 2007; 14(5):579-93. DOI: 10.1016/j.acra.2007.01.029. View

11.

Chu C, Oda M, Kitasaka T, Misawa K, Fujiwara M, Hayashi Y . Multi-organ segmentation based on spatially-divided probabilistic atlas from 3D abdominal CT images. Med Image Comput Comput Assist Interv. 2014; 16(Pt 2):165-72. DOI: 10.1007/978-3-642-40763-5_21. View

12.

Padgett J, Biancardi A, Henschke C, Yankelevitz D, Reeves A . Local noise estimation in low-dose chest CT images. Int J Comput Assist Radiol Surg. 2013; 9(2):221-9. DOI: 10.1007/s11548-013-0930-7. View

13.

Takx R, de Jong P, Leiner T, Oudkerk M, de Koning H, Mol C . Automated coronary artery calcification scoring in non-gated chest CT: agreement and reliability. PLoS One. 2014; 9(3):e91239. PMC: 3953377. DOI: 10.1371/journal.pone.0091239. View

14.

Leader J, Zheng B, Rogers R, Sciurba F, Perez A, Chapman B . Automated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme. Acad Radiol. 2003; 10(11):1224-36. DOI: 10.1016/s1076-6332(03)00380-5. View

15.

Xu Z, Bagci U, Jonsson C, Jain S, Mollura D . Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach. Annu Int Conf IEEE Eng Med Biol Soc. 2015; 2014:6036-9. PMC: 4486059. DOI: 10.1109/EMBC.2014.6945005. View

16.

Armato 3rd S, McLennan G, Bidaut L, McNitt-Gray M, Meyer C, Reeves A . The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys. 2011; 38(2):915-31. PMC: 3041807. DOI: 10.1118/1.3528204. View

17.

Gill G, Bauer C, Beichel R . A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes. Med Phys. 2014; 41(10):101908. PMC: 4965110. DOI: 10.1118/1.4894817. View

18.

Kim Y, Kim D . A fully automatic vertebra segmentation method using 3D deformable fences. Comput Med Imaging Graph. 2009; 33(5):343-52. DOI: 10.1016/j.compmedimag.2009.02.006. View

19.

Heimann T, van Ginneken B, Styner M, Arzhaeva Y, Aurich V, Bauer C . Comparison and evaluation of methods for liver segmentation from CT datasets. IEEE Trans Med Imaging. 2009; 28(8):1251-65. DOI: 10.1109/TMI.2009.2013851. View

20.

Altorki N, Lane M, Bauer T, Lee P, Guarino M, Pass H . Phase II proof-of-concept study of pazopanib monotherapy in treatment-naive patients with stage I/II resectable non-small-cell lung cancer. J Clin Oncol. 2010; 28(19):3131-7. DOI: 10.1200/JCO.2009.23.9749. View