Publications

Detailed Information

CT-free quantitative SPECT for automatic evaluation of %thyroid uptake based on deep-learning

Cited 0 time in Web of Science Cited 0 time in Scopus
Authors

Kwon, Kyounghyoun; Hwang, Donghwi; Oh, Dongkyu; Kim, Ji Hye; Yoo, Jihyung; Lee, Jae Sung; Lee, Won Woo

Issue Date
2023-03-22
Publisher
Springer
Citation
EJNMMI Physics, 10(1):20
Keywords
QuantificationSingle-photon emission computed tomographyDeep-learningAttenuation correctionSegmentation
Abstract
Purpose
Quantitative thyroid single-photon emission computed tomography/computed tomography (SPECT/CT) requires computed tomography (CT)-based attenuation correction and manual thyroid segmentation on CT for %thyroid uptake measurements. Here, we aimed to develop a deep-learning-based CT-free quantitative thyroid SPECT that can generate an attenuation map (μ-map) and automatically segment the thyroid.
Methods
Quantitative thyroid SPECT/CT data (n = 650) were retrospectively analyzed. Typical 3D U-Nets were used for the μ-map generation and automatic thyroid segmentation. Primary emission and scattering SPECTs were inputted to generate a μ-map, and the original μ-map from CT was labeled (268 and 30 for training and validation, respectively). The generated μ-map and primary emission SPECT were inputted for the automatic thyroid segmentation, and the manual thyroid segmentation was labeled (280 and 36 for training and validation, respectively). Other thyroid SPECT/CT (n = 36) and salivary SPECT/CT (n = 29) were employed for verification.
Results
The synthetic μ-map demonstrated a strong correlation (R2 = 0.972) and minimum error (mean square error = 0.936 × 10−4, %normalized mean absolute error = 0.999%) of attenuation coefficients when compared to the ground truth (n = 30). Compared to manual segmentation, the automatic thyroid segmentation was excellent with a Dice similarity coefficient of 0.767, minimal thyroid volume difference of − 0.72mL, and a short 95% Hausdorff distance of 9.416mm (n = 36). Additionally, %thyroid uptake by synthetic μ-map and automatic thyroid segmentation (CT-free SPECT) was similar to that by the original μ-map and manual thyroid segmentation (SPECT/CT) (3.772 ± 5.735% vs. 3.682 ± 5.516%, p = 0.1090) (n = 36). Furthermore, the synthetic μ-map generation and automatic thyroid segmentation were successfully performed in the salivary SPECT/CT using the deep-learning algorithms trained by thyroid SPECT/CT (n = 29).
Conclusion
CT-free quantitative SPECT for automatic evaluation of %thyroid uptake can be realized by deep-learning.
Key points
Question 1: Can CT-free attenuation correction be realized for SPECT?
Pertinent findings: The first deep-learning algorithm produced μ-map similar to CT-derived μ-map.
Implications for patient care: Quantitative SPECT can be performed without CT. Therefore, patients can be protected from redundant radiation exposure of CT.
Question 2: Can the thyroid be segmented without high-resolution images like CT?
Pertinent findings: The second deep-learning algorithm successfully generated the thyroid segmentation map using low-resolution images such as the generated μ-map and SPECT.
Implications for patient care: The thyroid segmentation process was dramatically reduced from 40–60min to < 1min, facilitating rapid patient care.
Question 3: Can quantitative SPECT/CT be possible without CT?
Pertinent findings: The two deep-learning algorithms deprived the quantitative thyroid SPECT/CT of CT.
Implications for patient care: Repetitive CT acquisitions may be excluded in multiple SPECT/CT-based nuclear imaging studies, such as dosimetry.
ISSN
2197-7364
Language
English
URI
https://hdl.handle.net/10371/192392
DOI
https://doi.org/10.1186/s40658-023-00536-9
Files in This Item:
Appears in Collections:

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share