Technical and Clinical Factors Affecting Success Rate of a Deep Learning Method for Pancreas Segmentation on CT

Mohammad Hadi Bagheri; Holger Roth; William Kovacs; Jianhua Yao; Faraz Farhadi; Xiaobai Li; Ronald M Summers

doi:10.1016/j.acra.2019.08.014

Technical and Clinical Factors Affecting Success Rate of a Deep Learning Method for Pancreas Segmentation on CT

Acad Radiol. 2020 May;27(5):689-695. doi: 10.1016/j.acra.2019.08.014. Epub 2019 Sep 16.

Authors

Mohammad Hadi Bagheri¹, Holger Roth², William Kovacs¹, Jianhua Yao¹, Faraz Farhadi³, Xiaobai Li⁴, Ronald M Summers⁵

Affiliations

¹ Clinical Image Processing Service, Radiology and Imaging Sciences Department, Clinical Center, National Institutes of Health, Bethesda, MD 20892-1182, USA.
² Imaging Biomarkers and Computer-aided Diagnosis Laboratory, Radiology and Imaging Sciences Department, Clinical Center, National Institutes of Health, Building 10 Room 1C224D MSC 1182, Bethesda, MD 20892-1182.
³ Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD.
⁴ Biostatistics and Clinical Epidemiology Service (BCES), National Institutes of Health Clinical Center, Bethesda, MD.
⁵ Imaging Biomarkers and Computer-aided Diagnosis Laboratory, Radiology and Imaging Sciences Department, Clinical Center, National Institutes of Health, Building 10 Room 1C224D MSC 1182, Bethesda, MD 20892-1182. Electronic address: rms@nih.gov.

PMID: 31537506
DOI: 10.1016/j.acra.2019.08.014

Abstract

Purpose: Accurate pancreas segmentation has application in surgical planning, assessment of diabetes, and detection and analysis of pancreatic tumors. Factors that affect pancreas segmentation accuracy have not been previously reported. The purpose of this study is to identify technical and clinical factors that adversely affect the accuracy of pancreas segmentation on CT.

Method and materials: In this IRB and HIPAA compliant study, a deep convolutional neural network was used for pancreas segmentation in a publicly available archive of 82 portal-venous phase abdominal CT scans of 53 men and 29 women. The accuracies of the segmentations were evaluated by the Dice similarity coefficient (DSC). The DSC was then correlated with demographic and clinical data (age, gender, height, weight, body mass index), CT technical factors (image pixel size, slice thickness, presence or absence of oral contrast), and CT imaging findings (volume and attenuation of pancreas, visceral abdominal fat, and CT attenuation of the structures within a 5 mm neighborhood of the pancreas).

Results: The average DSC was 78% ± 8%. Factors that were statistically significantly correlated with DSC included body mass index (r = 0.34, p < 0.01), visceral abdominal fat (r = 0.51, p < 0.0001), volume of the pancreas (r = 0.41, p = 0.001), standard deviation of CT attenuation within the pancreas (r = 0.30, p = 0.01), and median and average CT attenuation in the immediate neighborhood of the pancreas (r = -0.53, p < 0.0001 and r = -0.52, p < 0.0001). There were no significant correlations between the DSC and the height, gender, or mean CT attenuation of the pancreas.

Conclusion: Increased visceral abdominal fat and accumulation of fat within or around the pancreas are major factors associated with more accurate segmentation of the pancreas. Potential applications of our findings include assessment of pancreas segmentation difficulty of a particular scan or dataset and identification of methods that work better for more challenging pancreas segmentations.

Keywords: Computed Tomography; Deep Learning; Pancreas; Segmentation.

Publication types

Research Support, N.I.H., Intramural

MeSH terms

Deep Learning*
Female
Humans
Image Processing, Computer-Assisted
Male
Neural Networks, Computer
Pancreas / diagnostic imaging
Tomography, X-Ray Computed

Grants and funding

Z01 CL040004/ImNIH/Intramural NIH HHS/United States