RESUMO
Background: Worldwide, coronary artery disease (CAD) is a leading cause of mortality and morbidity and remains to be a top health priority in many countries. A non-invasive imaging modality for diagnosis of CAD such as single photon emission computed tomography-myocardial perfusion imaging (SPECT-MPI) is usually requested by cardiologists as it displays radiotracer distribution in the heart reflecting myocardial perfusion. The interpretation of SPECT-MPI is done visually by a nuclear medicine physician and is largely dependent on his clinical experience and showing significant inter-observer variability. Objective: The aim of the study is to apply a deep learning approach in the classification of SPECT-MPI for perfusion abnormalities using convolutional neural networks (CNN). Methods: A publicly available anonymized SPECT-MPI from a machine learning repository (https://www.kaggle.com/selcankaplan/spect-mpi) was used in this study involving 192 patients who underwent stress-test-rest Tc99m MPI. An exploratory approach of CNN hyperparameter selection to search for optimum neural network model was utilized with particular focus on various dropouts (0.2, 0.5, 0.7), batch sizes (8, 16, 32, 64), and number of dense nodes (32, 64, 128, 256). The base CNN model was also compared with the commonly used pre-trained CNNs in medical images such as VGG16, InceptionV3, DenseNet121 and ResNet50. All simulations experiments were performed in Kaggle using TensorFlow 2.6.0., Keras 2.6.0, and Python language 3.7.10. Results: The best performing base CNN model with parameters consisting of 0.7 dropout, batch size 8, and 32 dense nodes generated the highest normalized Matthews Correlation Coefficient at 0.909 and obtained 93.75% accuracy, 96.00% sensitivity, 96.00% precision, and 96.00% F1-score. It also obtained higher classification performance as compared to the pre-trained architectures. Conclusions: The results suggest that deep learning approaches through the use of CNN models can be deployed by nuclear medicine physicians in their clinical practice to further augment their decision skills in the interpretation of SPECT-MPI tests. These CNN models can also be used as a dependable and valid second opinion that can aid physicians as a decision-support tool as well as serve as teaching or learning materials for the less-experienced physicians particularly those still in their training career. These highlights the clinical utility of deep learning approaches through CNN models in the practice of nuclear cardiology.
RESUMO
OBJECTIVES: This study sought to establish worldwide and regional diagnostic reference levels (DRLs) and achievable administered activities (AAAs) for single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). BACKGROUND: Reference levels serve as radiation dose benchmarks to compare individual laboratories against aggregated data, helping to identify sites in greatest need of dose reduction interventions. DRLs for SPECT MPI have previously been derived from national or regional registries. To date there have been no multiregional reports of DRLs for SPECT MPI from a single standardized dataset. METHODS: Data were submitted voluntarily to the INCAPS (International Atomic Energy Agency Nuclear Cardiology Protocols Study), a cross-sectional, multinational registry of MPI protocols. A total of 7,103 studies were included. DRLs and AAAs were calculated by protocol for each world region and for aggregated worldwide data. RESULTS: The aggregated worldwide DRLs for rest-stress or stress-rest studies employing technetium Tc 99m-labeled radiopharmaceuticals were 11.2 mCi (first dose) and 32.0 mCi (second dose) for 1-day protocols, and 23.0 mCi (first dose) and 24.0 mCi (second dose) for multiday protocols. Corresponding AAAs were 10.1 mCi (first dose) and 28.0 mCi (second dose) for 1-day protocols, and 17.8 mCi (first dose) and 18.7 mCi (second dose) for multiday protocols. For stress-only technetium Tc 99m studies, the worldwide DRL and AAA were 18.0 mCi and 12.5 mCi, respectively. Stress-first imaging was used in 26% to 92% of regional studies except in North America where it was used in just 7% of cases. Significant differences in DRLs and AAAs were observed between regions. CONCLUSIONS: This study reports reference levels for SPECT MPI for each major world region from one of the largest international registries of clinical MPI studies. Regional DRLs may be useful in establishing or revising guidelines or simply comparing individual laboratory protocols to regional trends. Organizations should continue to focus on establishing standardized reporting methods to improve the validity and comparability of regional DRLs.