Variability in Heart-to-Mediastinum Ratio from Planar 123I-MIBG Images of a Thorax Phantom for 6 Common γ-Camera Models

Absolute quantitation of sympathetic nerve activity using [123I] metaiodobenzylguanidine SPECT-CT in neurology

BACKGROUND AND PURPOSE

The ability of [123I]metaiodobenzylguanidine (MIBG) sympathetic nerve imaging with three-dimensional (3D) quantitation to clinically diagnose neurological disorders has not been evaluated. This study compared absolute heart counts calculated as mean standardized uptake values (SUVmean) using conventional planar imaging and assessed the contribution of [123I]MIBG single-photon emission computed tomography (SPECT)-CT to the diagnosis of neurological diseases.

METHODS

Seventy-two patients with neurological diseases were consecutively assessed using early and delayed [123I]MIBG SPECT-CT and planar imaging. Left ventricles were manually segmented in early and delayed SPECT-CT images, then the SUVmean and washout rates (WRs) were calculated. Heart-to-mediastinum ratios (HMRs) and WRs on planar images were conventionally computed. We investigated correlations between planar HMRs and SPECT-CT SUVmeans and between WRs obtained from planar and SPECT-CT images. The cutoff for SPECT-CT WRs defined by linear regression and that of normal planar WRs derived from a database were compared with neurological diagnoses of the patients. We assigned the patients to groups according to clinical diagnoses as controls (n = 6), multiple system atrophy (MSA, n = 7), progressive supranuclear palsy (PSP, n = 17), and Parkinson's disease or dementia with Lewy bodies (PD/DLB, n = 19), then compared SPECT-CT and planar image parameters.

RESULTS

We found significant correlations between SPECT-CT SUVmean and planar HMR on early and delayed images (R2 = 0.69 and 0.82, p < 0.0001) and between SPECT-CT and planar WRs (R2 = 0.79, p < 0.0001). A threshold of 31% for SPECT-CT WR based on linear regression resulted in agreement between planar and SPECT-CT WR in 67 (93.1%) of 72 patients. Compared with controls, early and delayed SUVmean in patients with PSP and MSA tended more towards significance than planar HMR. This trend was similar for SPECT-CT WRs in patients with PSP.

CONCLUSIONS

Absolute heart counts and SUVmean determined using [123I]MIBG SPECT-CT correlated with findings of conventional planar images in patients with neurological diseases. Three-dimensional quantitation with [123I]MIBG SPECT-CT imaging might differentiate patients with PSP and MSA from controls.

Convolutional neural network-based automatic heart segmentation and quantitation in 123I-metaiodobenzylguanidine SPECT imaging

Background

Since three-dimensional segmentation of cardiac region in ¹²³I-metaiodobenzylguanidine (MIBG) study has not been established, this study aimed to achieve organ segmentation using a convolutional neural network (CNN) with ¹²³I-MIBG single photon emission computed tomography (SPECT) imaging, to calculate heart counts and washout rates (WR) automatically and to compare with conventional quantitation based on planar imaging.

Methods

We assessed 48 patients (aged 68.4 ± 11.7 years) with heart and neurological diseases, including chronic heart failure, dementia with Lewy bodies, and Parkinson's disease. All patients were assessed by early and late ¹²³I-MIBG planar and SPECT imaging. The CNN was initially trained to individually segment the lungs and liver on early and late SPECT images. The segmentation masks were aligned, and then, the CNN was trained to directly segment the heart, and all models were evaluated using fourfold cross-validation. The CNN-based average heart counts and WR were calculated and compared with those determined using planar parameters. The CNN-based SPECT and conventional planar heart counts were corrected by physical time decay, injected dose of ¹²³I-MIBG, and body weight. We also divided WR into normal and abnormal groups from linear regression lines determined by the relationship between planar WR and CNN-based WR and then analyzed agreement between them.

Results

The CNN segmented the cardiac region in patients with normal and reduced uptake. The CNN-based SPECT heart counts significantly correlated with conventional planar heart counts with and without background correction and a planar heart-to-mediastinum ratio (R² = 0.862, 0.827, and 0.729, p < 0.0001, respectively). The CNN-based and planar WRs also correlated with and without background correction and WR based on heart-to-mediastinum ratios of R² = 0.584, 0.568 and 0.507, respectively (p < 0.0001). Contingency table findings of high and low WR (cutoffs: 34% and 30% for planar and SPECT studies, respectively) showed 87.2% agreement between CNN-based and planar methods.

Conclusions

The CNN could create segmentation from SPECT images, and average heart counts and WR were reliably calculated three-dimensionally, which might be a novel approach to quantifying SPECT images of innervation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13550-021-00847-x.