Amyloid PET Quantification Via End-to-End Training of a Deep Learning / 대한핵의학회잡지

PURPOSE@#Although quantification of amyloid positron emission tomography (PET) is important for evaluating patients with cognitive impairment, its routine clinical use is hampered by complicated preprocessing steps and required MRI. Here, we suggested a one-step quantification based on deep learning using native-space amyloid PET images of different radiotracers acquired from multiple centers.@*METHODS@#Amyloid PET data of the Alzheimer Disease Neuroimaging Initiative (ADNI) were used for this study. A training/validation consists of 850 florbetapir PET images. Three hundred sixty-six florbetapir and 89 florbetaben PET images were used as test sets to evaluate the model. Native-space amyloid PET images were used as inputs, and the outputs were standardized uptake value ratios (SUVRs) calculated by the conventional MR-based method.@*RESULTS@#The mean absolute errors (MAEs) of the composite SUVR were 0.040, 0.060, and 0.050 of training/validation and test sets for florbetapir PETand a test set for florbetaben PET, respectively. The agreement of amyloid positivity measured by Cohen's kappa for test sets of florbetapir and florbetaben PET were 0.87 and 0.89, respectively.@*CONCLUSION@#We suggest a one-step quantification method for amyloid PET via a deep learning model. The model is highly reliable to quantify the amyloid PET regardless of multicenter images and various radiotracers.

Comparative Analysis of Lung Perfusion Scan and SPECT/CT for the Evaluation of Functional Lung Capacity / 대한핵의학회잡지

PURPOSE@#This study aimed to compare lung perfusion scan with single photon emission computed tomography/computed tomography (SPECT/CT) for the evaluation of lung function and to elucidate the most appropriate modality for the prediction of postoperative lung function in patients with lung cancer.@*METHODS@#A total of 181 patients underwent Tc-99m macroaggregated albumin lung perfusion scan and SPECT/CT to examine the ratio of diseased lung and diseased lobe. Forty-one patients with lung cancer underwent both preoperative and postoperative pulmonary function tests within 1 month to predict postoperative pulmonary function. Predicted postoperative forced expiratory volume in 1 s (ppoFEV₁) was calculated by the % radioactivity of lung perfusion scan and SPECT, and the % volume of the residual lung, assessed on CT.@*RESULTS@#The ratios of diseased lung as seen on lung perfusion scan and SPECT showed significant correlation, but neither modality correlated with CT. The ratios of the diseased lung and diseased lobe based on CT were higher than the ratios based on either perfusion scan or SPECT, because CT overestimated the function of the diseased area. The lobar ratio of both upper lobes was lower based on the perfusion scan than on SPECT but was higher for both lower lobes. Actual postoperative FEV₁ showed significant correlation with ppoFEV₁ based on lung perfusion SPECT and perfusion scan.@*CONCLUSIONS@#We suggest SPECT/CT as the primary modality of choice for the assessment of the ratio of diseased lung area. Both perfusion scan and SPECT/CT can be used for the prediction of postoperative lung function.

Comparative Analysis of Lung Perfusion Scan and SPECT/CT for the Evaluation of Functional Lung Capacity / 대한핵의학회잡지

PURPOSE: This study aimed to compare lung perfusion scan with single photon emission computed tomography/computed tomography (SPECT/CT) for the evaluation of lung function and to elucidate the most appropriate modality for the prediction of postoperative lung function in patients with lung cancer.METHODS: A total of 181 patients underwent Tc-99m macroaggregated albumin lung perfusion scan and SPECT/CT to examine the ratio of diseased lung and diseased lobe. Forty-one patients with lung cancer underwent both preoperative and postoperative pulmonary function tests within 1 month to predict postoperative pulmonary function. Predicted postoperative forced expiratory volume in 1 s (ppoFEV₁) was calculated by the % radioactivity of lung perfusion scan and SPECT, and the % volume of the residual lung, assessed on CT.RESULTS: The ratios of diseased lung as seen on lung perfusion scan and SPECT showed significant correlation, but neither modality correlated with CT. The ratios of the diseased lung and diseased lobe based on CT were higher than the ratios based on either perfusion scan or SPECT, because CT overestimated the function of the diseased area. The lobar ratio of both upper lobes was lower based on the perfusion scan than on SPECT but was higher for both lower lobes. Actual postoperative FEV₁ showed significant correlation with ppoFEV₁ based on lung perfusion SPECT and perfusion scan.CONCLUSIONS: We suggest SPECT/CT as the primary modality of choice for the assessment of the ratio of diseased lung area. Both perfusion scan and SPECT/CT can be used for the prediction of postoperative lung function.

Amyloid PET Quantification Via End-to-End Training of a Deep Learning / 대한핵의학회잡지

PURPOSE: Although quantification of amyloid positron emission tomography (PET) is important for evaluating patients with cognitive impairment, its routine clinical use is hampered by complicated preprocessing steps and required MRI. Here, we suggested a one-step quantification based on deep learning using native-space amyloid PET images of different radiotracers acquired from multiple centers.METHODS: Amyloid PET data of the Alzheimer Disease Neuroimaging Initiative (ADNI) were used for this study. A training/validation consists of 850 florbetapir PET images. Three hundred sixty-six florbetapir and 89 florbetaben PET images were used as test sets to evaluate the model. Native-space amyloid PET images were used as inputs, and the outputs were standardized uptake value ratios (SUVRs) calculated by the conventional MR-based method.RESULTS: The mean absolute errors (MAEs) of the composite SUVR were 0.040, 0.060, and 0.050 of training/validation and test sets for florbetapir PETand a test set for florbetaben PET, respectively. The agreement of amyloid positivity measured by Cohen's kappa for test sets of florbetapir and florbetaben PET were 0.87 and 0.89, respectively.CONCLUSION: We suggest a one-step quantification method for amyloid PET via a deep learning model. The model is highly reliable to quantify the amyloid PET regardless of multicenter images and various radiotracers.