<abstract xmlns="http://www.w3.org/1999/xhtml">

<sec id="j_raon-2022-0037_s_006"><h3>Background</h3>
<p>In the setting of primary hyperparathyroidism (PHPT), [<sup>18</sup>F]fluorocholine PET/CT (FCH-PET) has excellent diagnostic performance, with experienced practitioners achieving 97.7% accuracy in localising 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 localisation on FCH-PET images in the setting of PHPT.</p></sec>
<sec id="j_raon-2022-0037_s_007"><h3>Patients and methods</h3>
<p>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 localise (upper left, lower left, upper right or lower right) HPTT. Our mPETResnet10 architecture also contained a region-of-interest masking algorithm that we evaluated qualitatively in order to try to explain the model’s decision process.</p></sec>
<sec id="j_raon-2022-0037_s_008"><h3>Results</h3>
<p>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 &lt; 0.001) in both tasks compared to human readers, who localise HPTT with the accuracy of 97.7%. The produced region-of-interest mask, while not showing a consistent added value in the qualitative evaluation of model’s decision process, had correctly identified the foreground PET signal.</p></sec>
<sec id="j_raon-2022-0037_s_009"><h3>Conclusions</h3>
<p>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. Given our small dataset of 93 subjects, results are nevertheless promising for further research.</p></sec>
</abstract>

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 localising 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 localisation 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 localise (upper left, lower left, upper right or lower right) HPTT. Our mPETResnet10 architecture also contained a region-of-interest 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 localise HPTT with the accuracy of 97.7%. The produced region-of-interest mask, while not showing a consistent added value in the qualitative evaluation of model’s decision process, had correctly identified the foreground PET signal.
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. Given our small dataset of 93 subjects, results are nevertheless promising for further research.

Detection and localization of hyperfunctioning parathyroid glands on [<sup>18</sup>F]fluorocholine PET/ CT using deep learning – model performance and comparison to human experts

Radiology and Oncology

This work is licensed under the Creative Commons Attribution 4.0 International License.

Detection and localization of hyperfunctioning parathyroid glands on [F]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...

Detection and localization of hyperfunctioning parathyroid glands on [¹⁸F]fluorocholine PET/ CT using deep learning – model performance and comparison to human experts

Article Category: Research Article

Data publikacji: 13 gru 2022

Zakres stron: 440 - 452

Otrzymano: 21 kwi 2022

Przyjęty: 22 sie 2022

DOI: https://doi.org/10.2478/raon-2022-0037

© 2022 Leon Jarabek, Jan Jamsek, Anka Cuderman, Sebastijan Rep, Marko Hocevar, Tomaz Kocjan, Mojca Jensterle, Ziga Spiclin, Ziga Macek Lezaic, Filip Cvetko, Luka Lezaic, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Detection and localization of hyperfunctioning parathyroid glands on [18F]fluorocholine PET/ CT using deep learning – model performance and comparison to human experts

Article Category: Research Article

Data publikacji: 13 gru 2022

Zakres stron: 440 - 452

Otrzymano: 21 kwi 2022

Przyjęty: 22 sie 2022

DOI: https://doi.org/10.2478/raon-2022-0037

© 2022 Leon Jarabek, Jan Jamsek, Anka Cuderman, Sebastijan Rep, Marko Hocevar, Tomaz Kocjan, Mojca Jensterle, Ziga Spiclin, Ziga Macek Lezaic, Filip Cvetko, Luka Lezaic, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Detection and localization of hyperfunctioning parathyroid glands on [¹⁸F]fluorocholine PET/ CT using deep learning – model performance and comparison to human experts