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

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 − 0.72 mL, and a short 95% Hausdorff distance of 9.416 mm (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 40–60 min to < 1 min, 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.