Digital analysis of EUS images: "promising" method, but is it ready for "prime time"?
- Manoop S Bhutani
- Gastrointestinal endoscopy
Background—Quantitative spectral analysis of the radio-frequency (RF) signals that underlie grayscale EUS images can be used to provide additional, objective information about tissue state. Objective—Our purpose was to validate RF spectral analysis as a method to distinguish between (1) benign and malignant lymph nodes and (2) normal pancreas (NP), chronic pancreatitis (CP) and pancreatic cancer (PC). Corresponding author and reprint requests: Ronald E. Kumon, Department of Biomedical Engineering, Department of Biomedical Engineering, University of Michigan, 2200 Bonisteel Boulevard, Ann Arbor, MI 48109–2099, USA, +1 734–763–5448 (voice), +1 734-936-1905 (fax), email@example.com. Participating Institutions: Division of Gastroenterology, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, Ohio, USA, and Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA Conflict of interest disclosures: None Author contributions: (A) Conception and design [A.L.F., A.C., C.X.D., R.E.K., F.T.F., M.P.]; (B) Analysis and interpretation of the data [R.E.K., V.K.C., K.O., F.T.F., M.P., Y.Z., R.C.K.W., G.A.I., M.V.S., A.C., C.X.D.]; (C) Drafting of the article [R.E.K., M.P., F.T.F.]; (D) Critical revision of the article for important intellectual content [all]; (E) Final approval of the article [all] Capsule Summary What is already known on this topic • Identifying pancreatic cancers in the setting of chronic pancreatitis and differentiating benign from malignant lymph nodes can be challenging using conventional grayscale EUS imaging. • Spectral analysis of ultrasound backscatter has been previously demonstrated in both EUS and non-EUS contexts to be an objective, quantitative method for tissue characterization and uses information in the backscattered ultrasound signals otherwise discarded in grayscale EUS imaging. What this study adds to our knowledge • This validation study shows that spectral parameters such as midband fit, intercept, and correlation coefficient of the EUS backscatter spectra can quantitatively discriminate between normal pancreas, pancreatic cancer, and chronic pancreatitis, as well as between benign and malignant lymph nodes. Publisher's Disclaimer: This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. NIH Public Access Author Manuscript Gastrointest Endosc. Author manuscript; available in PMC 2011 January 1. Published in final edited form as: Gastrointest Endosc. 2010 January ; 71(1): 53–63. doi:10.1016/j.gie.2009.08.027. N IH PA Athor M anscript N IH PA Athor M anscript N IH PA Athor M anscript Design & Setting—A prospective validation study of eligible patients was conducted to compare with pilot study RF data. Patients—Forty-three patients underwent EUS of the esophagus, stomach, pancreas, and surrounding intra-abdominal and mediastinal lymph nodes (19 from previous pilot study and 24 additional patients). Main Outcome Measurements—Midband fit, slope, intercept, and correlation coefficient from a linear regression of the calibrated RF power spectra were determined. Results—Discriminant analysis of mean pilot-study parameters was then performed to classify validation-study parameters. For benign vs. malignant lymph nodes, midband-fit and intercept (both with t-test p < 0.058) provided classification with 67% accuracy and area under ROC curve (AUC) of 0.86. For diseased vs. NP, midband-fit and correlation coefficient (both with ANOVA p < 0.001) provided 93% accuracy and AUC of 0.98. For PC vs. CP, the same parameters provided 77% accuracy and AUC of 0.89. Results improved further when classification was performed with all data. Limitations—Moderate sample size and spatial averaging inherent to the technique. Conclusions—This study confirms that mean spectral parameters provide a non-invasive method to quantitatively discriminate benign and malignant lymph nodes as well as normal and diseased pancreas.