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

Abstract

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.

Keywords

• Quantification; Single-photon emission computed tomography; Deep-learning; Attenuation correction; Segmentation