A machine learning-based approach to directly compare the diagnostic accuracy of myocardial perfusion imaging by conventional and cadmium-zinc telluride SPECT.

BACKGROUND: We evaluated the performance of conventional (C) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride (CZT)-SPECT in a large cohort of patients with suspected or known coronary artery disease (CAD) and compared the diagnostic accuracy of the two systems using machine learning (ML) algorithms. METHODS AND RESULTS: A total of 517 consecutive patients underwent stress myocardial perfusion imaging (MPI) by both C-SPECT and CZT-SPECT. In the overall population, an excellent correlation between stress MPI data and left ventricular (LV) functional parameters measured by C-SPECT and by CZT-SPECT was observed (all P < .001). ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (NN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for k-NN) was greater than that of C-SPECT (88% for RF and 53% for k-NN). CONCLUSIONS: MPI data and LV functional parameters obtained by CZT-SPECT are highly reproducible and provide good correlation with those obtained by C-SPECT. ML approach showed that the accuracy and sensitivity of CZT-SPECT is greater than C-SPECT in detecting CAD.

Comparing the Prognostic Value of Stress Myocardial Perfusion Imaging by Conventional and Cadmium-Zinc Telluride Single-Photon Emission Computed Tomography through a Machine Learning Approach.

We compared the prognostic value of myocardial perfusion imaging (MPI) by conventional- (C-) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride- (CZT-) SPECT in a cohort of patients with suspected or known coronary artery disease (CAD) using machine learning (ML) algorithms. A total of 453 consecutive patients underwent stress MPI by both C-SPECT and CZT-SPECT. The outcome was a composite end point of all-cause death, cardiac death, nonfatal myocardial infarction, or coronary revascularization procedures whichever occurred first. ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (KNN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for KNN) was greater than that of C-SPECT (88% for RF and 53% for KNN). A preliminary univariate analysis was performed through Mann-Whitney tests separately on the features of each camera in order to understand which ones could distinguish patients who will experience an adverse event from those who will not. Then, a machine learning analysis was performed by using Matlab (v. 2019b). Tree, KNN, support vector machine (SVM), Naïve Bayes, and RF were implemented twice: first, the analysis was performed on the as-is dataset; then, since the dataset was imbalanced (patients experiencing an adverse event were lower than the others), the analysis was performed again after balancing the classes through the Synthetic Minority Oversampling Technique. According to KNN and SVM with and without balancing the classes, the accuracy (p value = 0.02 and p value = 0.01) and recall (p value = 0.001 and p value = 0.03) of the CZT-SPECT were greater than those obtained by C-SPECT in a statistically significant way. ML approach showed that although the prognostic value of stress MPI by C-SPECT and CZT-SPECT is comparable, CZT-SPECT seems to have higher accuracy and recall.

Outcome of Patients With Differentiated Thyroid Cancer Treated With 131-Iodine on the Basis of a Detectable Serum Thyroglobulin Level After Initial Treatment.

Background: In patients with differentiated thyroid cancer (DTC) and raising serum thyroglobulin (Tg) after total or near-total thyroidectomy and 131I remnant ablation an empiric 131I therapy may be considered. However, outcome data after empiric therapy in did not show a clear evidence of improved survival. We assessed the efficacy of such empiric 131I therapy in patients with DTC and evaluated the long-term outcome. Methods: A total of 100 patients with DTC showing raised Tg level during follow-up after thyroidectomy and 131I ablation were treated with a further 131I therapy (6.1 ± 1.7 GBq). Whole-body scan (WBS) was performed 5-7 days after therapy. Tg value at 12 months after 131I therapy was considered as an indicator of treatment response: ≤1.5 ng/ml complete remission (CR), >50% decrease partial remission (PR), higher than pre-therapy progression disease (PD), all other cases stable disease (SD). Patients were followed-up for 96 ± 75 months. Results: After 12 months, 62% of patients were in CR, 16% in PR, 8% in SD, and 14% in PD. WBS was positive in 41% of patients and negative in 59% (P = NS). Among patients with local recurrences at WBS 89% showed either CR or PR, while 71% of patients with distant metastases were in SD or PD (P < 0.001). Distant metastases at WBS (P < 0.05), CR (P < 0.0001), and CR + PR (P < 0.0001) were predictors of both progression free survival and overall survival. Conclusion: There is a beneficial effect of 131I therapy on outcome of patients with DTC treated on the basis of elevated Tg value. In these patients, survival is affected by achievement of CR or PR at 12 months evaluation after 131I therapy and by the presence of distant metastases at WBS.