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.

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.

Case Report of Kidney Paired Donation (KPD) with Desensitization: the Strategy and Experience of 3-Way KPD in Samsung Medical Center

As the need for the organ donation increases, strategies to increase kidney transplantation (KT) through expanded living donation have become essential. These include kidney paired donation (KPD) programs and desensitization in incompatible transplantations. KPD enables kidney transplant candidates with incompatible living donors to join a registry with other incompatible pairs in order to find potentially compatible living donor. Positive cross match and ABO incompatible transplantation has been successfully accomplished in selective cases with several pre-conditionings. Patients who are both difficult-to-match due to broad sensitization and hard-to-desensitize because of donor conditions can often be successfully transplanted through a combination of KPD and desensitization. According to the existing data, KPD can increase the number of KTs from living donors with excellent clinical results. This is also a cost-effective treatment as compared with dialysis and desensitization protocols. We carried out 3-way KPD transplantation with one highly sensitized, positive cross match pair and with two ABO incompatible pairs. Herein we report our first successful 3-way KPD transplantation in a single center. To maximize donor-recipient matching and minimize immunologic risk, KPD programs should use proper algorithms with desensitization to identify optimal donor with simultaneous two-, three- or more complex multi-way exchanges.