The DAUH dataset, listed in Table 1, comprises a total of 432 subjects according to the visually assessed criteria of [¹⁸F]Florbetaben PET. An available database was collected from 2015 to 2020 from the Department of Nuclear Medicine at DAUH for a possible population of [¹⁸F]Florbetaben PET. Labeling for Aβ negative and positive was performed according to the decision of a nuclear medicine specialist at DAUH.

PET scans of the possible population were acquired using a Biograph 40 mCT Flow PET/CT Scanner (Siemens Healthcare, Knoxville, TN, USA) and reconstructed via UltraHD-PET (TrueX-TOF) to obtain PET images, and the obtained images were processed with a 3mm FWHM Gaussian filter. All patients underwent a 20 min positron emission scan at 90 min after intravenous injection of 300mBq of [¹⁸F]Florbetaben (NeuraCeq, Piramal, Mumbai, India), and the helical CT scans were acquired with a 0.5 s rotation time at 100 kVp and 228 mAs. The images were finally stored in the DICOM format.

Finally, [¹⁸F]Florbetaben PET images collected from the Alzheimer’s Neuroimaging Initiative (ADNI) database (www.loni.ucla.edu/ADNI) were used as an external dataset in this study. The database includes scans of subjects with normal control, mild cognitive impairment (MCI), and AD. These scans were preprocessed as an ADNI internal protocol and co-registration, averaging, size changing, standardization, and smoothing processes were performed. However, since ADNI does not determine whether the [¹⁸F]Florbetaben scans are Aβ negative or positive, classification was performed by the nuclear medicine specialists at DAUH.

Unlike the DAUH dataset, images from the external dataset were not processed with 3 mm FWHM Gaussian filters. To achieve the same conditions, a 3 mm FWHM Gaussian filter was used to process the statistical parametric mapping (SPM) after the acquisition. An example of Gaussian filter processing is shown in Fig 1.

We performed spatial normalization and count normalization to classify Aβ deposition using brain PET. We used the SPM library [15] based on MATLAB. All dataset groups applied the same preprocessing procedure using the same protocol, even if there were differences in the source and collection times.

Spatial normalization is the registration of the original image to a specific PET template. Subjects with various brain shapes can be compared through image registration by mapping the subject’s PET image to a reference brain template [16].

Meanwhile, we made a reference brain PET template in-house. Co-registration was performed with a PET image and a paired CT image obtained from a subject. The template images are average images of 20 normal brains, 20 Alzheimer’s dementia brains, and 40 left and right inversion images, for a total of 80 images. After image registration, the tissue is stretched or compressed to fit the template brain. We can average the PETs of multiple individuals to reconstruct them into a reference brain space and provide atlas anatomical addresses mapped to the same reference brain space at the data locations in the image. We also performed a cropping process that cuts the empty space around the brain, reducing its size from 400 × 400 × 110 to 95 × 79 × 68.

Count normalization is intended for numerical comparisons between images because the image intensity level varies due to differences in the number of radioactive isotopes administered, individual characteristics, or individual body conditions. This normalization was performed assuming that the absorption of radioactive tracers in a brain region is constant for each person. Count normalization normalizes the entire observation area to the value of the area representing non-specific, lesion-independent absorption, allowing absolute and relative comparisons in specific absorption areas of the patient-patient image [17].

The [¹⁸F]Florbetaben radiotracer exhibits non-specific uptake in the cerebellar region and specific uptake in the gray matter region of the cerebrum; thus, count normalization was performed by using the cerebellar region of the PET template applied in spatial normalization to each patient image.

In addition, the skull, a non-brain tissue, is included in the image because it is spatially normalized with a CT-driven PET template. The presence of these non-brain tissues is considered an obstacle in brain image analysis. Therefore, in brain imaging analysis studies, a preprocessing commonly referred to as skull stripping is required [18].

In the [¹⁸F]Florbetaben amyloid brain PET classification model, spatial normalization, count normalization, and skull stripping are commonly performed for all datasets, and an example of a brain PET scan image that has been preprocessed is shown in Fig 2.

In this study, we apply CNNs of three well-known architectures to the amyloid classification problem in [¹⁸F]Florbetaben brain PET. The architectures considered are Inception [19, 20], ResNet [21], and VGG19 [10]. The reasons for choosing these models were to achieve the best performance in various tasks, use a small kernel (3 × 3) [10] instead of a large kernel, utilize a deep but sparse network structure [19], and provide residual connectivity [21]. We implemented the model ourselves by adopting parts of the primary characteristics of these structures and applying 3D convolution filter. Each representative structure is shown in Fig 3.

To briefly summarize the meaning of each layer:

Recently, 3D CNN research has been actively conducted to extract features of 3D medical images for classification [25]. Moreover, because brain images are volume data, 3D CNNs can be configured for image classification to extract 3D spatial features from 3D PET images. Accordingly, Inception, ResNet, and VGG models are constructed in the form of a 3D CNN and are named Inception3D, ResNet3D, and VGG3D in our experiment.

Eighty percent of the DAUH dataset, as shown in Fig 4, was used for model training and the rest is used for model evaluation. The samples were splitted with Stratified ShuffleSplit cross-validator (https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.StratifiedShuffleSplit.html), which was randomly extracted from each group labeled amyloid positive and negative. Along with the training set, there was also a validation set used to ensure that the model is trained well. This is explained in more detail in Fig 5.

The model training was conducted by four-fold cross-validation with 192 amyloid positive subjects and 153 amyloid negative subjects from the DAUH dataset. If the dataset is small, the reliability of the performance evaluation is reduced. If the performance varies depending on how the validation set is held, the effect of the match will bias the model evaluation performance. To solve this, cross-validation ensures that all data are used as a validation set at least once.

As shown in Fig 6, the entire dataset can be divided into four subsets; the first subset is used as the validation set in the first iteration, and the remaining subsets are used as the training set. In the second iteration, the second subset is used as the validation set, and the remaining subsets are used as the training set. By repeating the number of subsets in this manner, we could select the lowest loss model out of the four performances.

All models of each structure were selected through four-fold cross-validation [26] and evaluated with the model evaluation set of the DAUH dataset specified in Fig 4.

In the external dataset, some samples were randomly extracted using the same sample extraction method. If the accuracy was significantly different between the model evaluation and the external validation, it is possible that a part of the external dataset could be included in the training set to acquire generalization performance. In that case, only a portion of the dataset was composed of the external validation set.

To confirm the data distribution of the preprocessed DAUH and external datasets before CNN-based analysis, as shown in Fig 7, t-SNE (Stochastic Neighbor Embedding) [27] visualization, which is widely used for visualization after a data dimension reduction, was performed. Although the sources of the datasets are different, the same groups have a similar distribution. In other words, data similarity was observed between the same groups.

The model evaluation results of the Inception3D, ResNet3D, and VGG3D models after training the models with the DAUH training dataset are summarized in Table 3. To evaluate the performance of each model, three metrics were considered: sensitivity, specificity, and accuracy.

Sensitivity is the proportion of subjects who are inferred to be positive among all Aβ-positive subjects and is defined as follows: S e n s i t i v i t y = T P T P + F N where TP represents the number of true positives and FN represents the number of false negatives.

Specificity is the proportion of subjects who are inferred to be negative among all Aβ-negative subjects and is defined as follows: S p e c i f i c i t y = T N T N + F P where TN represents the number of true negatives and FP indicates the number of false positives.

PPV(Positive Predictive Value) is the probability that those that come out Aβ positive actually have Aβ positive according to the ground truth. NPV(Negative Predictive Value) is the probability that those that come out Aβ negative actually have Aβ negative according to the ground truth. P P V = T P T P + F P N P V = T N F N + T N

Accuracy is the degree of closeness between the predicted value and the actual value of the subjects. It is calculated as the number of true positives and negatives among all accurate and evaluated subjects as follows: A c c u r a c y = T P + T N T P + F N + T N + F P

We plotted the receiver operating characteristic (ROC) curve of our method for Aβ positivity, as shown in Fig 8, and calculated the area under the curve (AUC). The AUC value was close to 1 for all three models.

Table 4 summarizes the pairwise comparison results of ROC curves obtained from the Inception3D, ResNet3D, and VGG3D inferences that performed model evaluation. At the 95% significance level, since both p-values are greater than 0.05, the corresponding two comparison areas are not significantly different.

With respect to accuracy and AUC, VGG3D showed the best classification performance. As summarized in Table 3, the AUC of the external validations was lower than that of the model evaluation, and a comparison of the p-values summarized in Table 4 indicates that Inception3D and ResNet3D were below the significance level; thus, there were significant differences in the performance evaluation. However, there was no significant difference between the model evaluation and the external validation for the VGG model, as shown by the significance level, p = 0.1950. The ROC curves of the comparison are plotted in Fig 9.

This is a method of redefining the model to create a generalized model by additionally retraining a part of the external dataset to the model trained with the DAUH training set. In this part, excluding the external validation set shown in Fig 4, the 38 Aβ positives and 50 Aβ negatives were configured as a retraining set for fine tuning. the pre-trained model was imported as it is, and all layers were retrained.

As summarized in Table 5, when the external validation was performed, the classification performance was improved compared to before retraining. The evaluation performance of the models trained with DAUH was compared with that of models additionally retrained with the residue of the external datasets by independent ROC. Both evaluation performances were within the 95% confidence level (Inception3D: 0.5124, ResNet3D: 0.3247), as shown in Table 6. No significant difference was observed between the two evaluations for each model, and the ROC curves are shown in Fig 10.

Our CNN-based [¹⁸F]Florbetaben amyloid brain PET classification studies have a limitation in that only the DAUH dataset and ADNI have been utilized. Therefore, a medical imaging artificial intelligence (AI) research platform that enables doctors with medical knowledge and medical data to perform medical AI research without programming is needed. DEEP:PHI is one such open platform (https://www.deepphi.ai). It is a research platform developed by DEEPNOID, a Korean medical AI startup company that is currently being serviced in the form of a closed beta, and a number of doctors are using this platform to conduct artificial intelligence research.

As shown in Fig 11, DEEP:PHI comprises a GUI, and it is possible to perform image preprocessing, neural network model generation, and neural network training results verification within the DEEP:PHI platform from the workflow window. In addition, the server provides a high-end research environment without a GPU and hard disk drive in the local environment. As it operates on the web, the platform allows doctors and developers of various organizations to collect data and perform collaborative research directly on the web. The models from our research can also be uploaded to the DEEP:PHI platform and used for various AI research. If necessary, it is possible to modify and create modules specialized for specific research through the code editor.