Prediction of Lymph Node Maximum Standardized Uptake Value in Patients With Cancer Using a 3D Convolutional Neural Network: A Proof-of-Concept Study.

Authors

Hiram Shaish
Simukayi Mutasa MD, Lehigh Valley Health NetworkFollow
Jasnit Makkar
Peter Chang
Lawrence Schwartz
Firas Ahmed

Publication/Presentation Date

2-1-2019

Abstract

OBJECTIVE: The purpose of this study is to determine whether a convolutional neural network (CNN) can predict the maximum standardized uptake value (SUV

MATERIALS AND METHODS: Consecutive initial staging PET/CT scans obtained in 2017 for patients with pathologically proven malignancy were collected. Two blinded radiologists selected one to 10 lymph nodes from the unenhanced CT portion of each PET/CT examination. The SUV

RESULTS: A total of 400 lymph nodes (median SUV

CONCLUSION: A CNN is able to predict with moderate accuracy the SUV

Volume

212

Issue

2

First Page

238

Last Page

244

ISSN

1546-3141

Published In/Presented At

Shaish, H., Mutasa, S., Makkar, J., Chang, P., Schwartz, L., & Ahmed, F. (2019). Prediction of Lymph Node Maximum Standardized Uptake Value in Patients With Cancer Using a 3D Convolutional Neural Network: A Proof-of-Concept Study. AJR. American journal of roentgenology, 212(2), 238–244. https://doi.org/10.2214/AJR.18.20094

Disciplines

Diagnosis | Medicine and Health Sciences | Other Analytical, Diagnostic and Therapeutic Techniques and Equipment | Radiology

PubMedID

30540209

Department(s)

Department of Radiology and Diagnostic Medical Imaging

Document Type

Article