Detection and Localization of Hyperfunctioning Parathyroid Glands on [18F]fluorocholine PET/CT Using Deep Learning – Model Performance and Comparison to Human Experts
Background. In the setting of primary hyperparathyroidism (PHPT), [18F]fluorocholine PET/CT (FCH-PET) has excellent diagnostic performance, with experienced practitioners achieving 97.7% accuracy in localizing hyperfunctioning parathyroid tissue (HPTT). Due to the relative triviality of the task for human readers, we explored the performance of deep learning (DL) methods for HPTT detection and localization on FCH-PET images in the setting of PHPT.
Patients and methods. We used a dataset of 93 subjects with PHPT imaged using FCH-PET, of which 74 subjects had visible HPTT while 19 controls had no visible HPTT on FCH-PET. A conventional Resnet10 as well as a novel mPETResnet10 DL model were trained and tested to detect (present, not present) and localize (upper left, lower left, upper right or lower right) HPTT. Our mPETResnet10 architecture also contained a masking algorithm that we evaluated qualitatively in order to try to explain the model’s decision process.
Results. The models detected the presence of HPTT with an accuracy of 83% and determined the quadrant of HPTT with an accuracy of 74%. The DL methods performed statistically worse (p < 0.001) in both tasks compared to human readers, who localize HPTT with accuracy of 97.7%. The produced mask had no additional value in the qualitative evaluation.
Conclusions. Our experiment is the first reported use of DL analysis of FCH-PET in PHPT. We have shown that it is possible to utilize DL methods with FCH-PET to detect and localize HPTT. Furher research in a larger cohort is warranted to examine apparent inferiority of these methods to human readers.
How to Cite
Copyright (c) 2022 Leon Jarabek, Jan Jamsek, Anka Cuderman, Sebastijan Rep, Marko Hocevar, Tomaz Kocjan, Mojca Jensterle, Luka Ležaič
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
License to Publish
Please read the terms of this agreement, print, initial page 1, sign page 3, scan and send the document as one file attached to an e-mail to email@example.com