| 1 |
What is the primary goal of the article according to its introduction?
|
To explore advancements, applications, and challenges of generative AI in medical imaging |
|
The abstract of the study discusses the advancements of artificial intelligence image generation paradigms as the advancements, specific implications usuing synthetic data, and the challenges and ethical considerations such as patient privacy.
|
The abstract of the study focuses on the aspects of synthetic data based on its advancements, applications, and challenges in medical imaging, and explores their potential in the medical field. This was from the first paragraph of the paper that highlights the advancements, applications, and challenges in medical imaging.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 2 |
How do generative AI models differ from traditional discriminative models in healthcare applications?
|
Generative models produce new data rather than only classify or interpret |
|
Generative artificial intelligence models use deep learning capabilities to create new content, unlike traditional discriminative models that interpret presented data for decision making purposes.
|
The introduction of the paper, exploring the potential of generative artificial intelligence in medical imaging, compares it to traditional discriminative models.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 3 |
What is meant by the term “model as a dataset”?
|
Sharing trained model weights instead of raw data |
|
generative models learn to store patterns and characteristics of the original data
|
In the synthetic data sets part, the study refers to the "model as a dataset, then proceeds to explain this concept.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 4 |
Which statement correctly distinguishes physics-informed and statistical models?
|
Physics-informed models incorporate biological or physical principles |
|
Physics-informed models uses domain-specific knowledge and physics principles through mathematical equations to generate data, whereas statistical models learn from patterns from datas.
|
The synthetic datasets compare two broad categories of generative models provide the ability to generate synthetic datasets: physics-informed and statistical models.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 5 |
According to the article, what does the “image generation trilemma” describe?
|
Trade-offs among image diversity, quality, and speed |
|
Figure 2 presents a triangular image that highlights the trade-off between diversity, quality, and speed, explaining how improving each aspects sacrifices the other 2/
|
Searching the paper with image generation trilemma shows a figure of image generation trilemma with an explanation of what it is.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 6 |
What is the Human Turing Test used for in medical image synthesis?
|
To assess realism of synthetic medical images by experts |
|
Human evaluations such as the human Turing Test involve experts distinguishing real images from synthetic ones, offering insights into the perceptual quality that is important for medical use.
|
It was stated in the perceptual quality assessment, and realism evaluation that Human Turing test: medical experts discern between real and derived images
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 7 |
Which of the following is NOT mentioned as a potential benefit of synthetic data in healthcare?
|
Eliminating all medical biases permanently |
|
There could be potential biases in the source datasets in the generated data, leading to skewed research findings or discriminatory applications.
|
The model does not eliminate all medical biases permanently as there could still be some, as proposed in the challenges and ethical considerations.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 8 |
What is one major ethical concern associated with generative AI in medical imaging?
|
Data copying and patient reidentification |
|
There are still concerns regarding potential data copying still exist
|
This was presented in the challenges and considerations section.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 9 |
What regulatory precedent did the article cite for synthetic data technologies?
|
FDA clearance of synthetic MRI as image-processing software |
|
The article mentions the frameworls for evaluating synthetic medical imaging, evidenced by the FDA's clearance of synthetic MRI technologies.
|
This regulatory precedent was presented in the future directions section.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 10 |
What is the main purpose of the article?
|
To create a universal ASCVD model for Western countries |
|
The article highlights the similarities and
differences in the epidemiology, diagnosis, and
treatment of ASCVD for individuals of East Asian
origin who immigrated to the United States and their offspring (“East Asian Americans”) compared with those living in East Asia (“East Asian natives”).
|
The main purpose was stated in the abstract or the introduction part.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 11 |
Which of the following models was originally developed for a Western population?
|
Framingham Risk Score |
|
A recalibration of the Framingham Risk Score (FRS) equation was performed
|
The article mentions the Framingham Risk Score (FRS).
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 12 |
Why might Western-based risk prediction models overestimate ASCVD risk in East Asian populations?
|
East Asians have lower baseline incidence of ASCVD |
|
Differences in risk fator patterns and baseline diseases rates overestimate the ASCVD rates in east asian populations.
|
It was mentioned when comparing the rates of cerebrovascular disease relative to CHD in the
region, standardization of these risk calculators may promote better opportunities for cross-validation.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 13 |
What is the key advantage of the China-PAR model compared to Western-based models?
|
It was calibrated using national data representing diverse regions in China |
|
It was developed using large cohorts in China to estimate.
|
Searching the word China-PAR
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 14 |
Which of the following variables is not typically included in ASCVD risk prediction models discussed in the article?
|
Serum cholesterol |
|
Serum cholesterol was not mention in the article
|
The model includes all the other factors.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 15 |
What is a major difference between the Suita Score and the Framingham Risk Score?
|
Suita Score was designed for a Japanese population using local epidemiological data |
|
The Suita score was chosen from 10 different published risk prediction scores in Japan where internal validation was carefully performed
|
Finding the suita score and Framingham Risk Score in the text
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 16 |
According to the article, what is a potential benefit of developing East Asia–specific risk models?
|
They improve accuracy and reduce overestimation of risk |
|
People from different regions have different factor and rates that affects the disease
|
This was mentioned several times in the article where different models are different for the population and one may overestimate more then the other.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 17 |
Which factor was highlighted as influencing ASCVD risk differences among East Asian countries?
|
Cultural and dietary variations, such as salt intake and lifestyle |
|
there is different cultural eating habits in different region
|
other choices does not describe how different they are, but rather the similarities which are not presented in the article
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 18 |
What future direction does the article suggest for improving ASCVD risk prediction?
|
Using multimodal AI-based prediction integrated with regional data |
|
It provides a more refined model without overlooking other factors.
|
by comparing with other factors
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 19 |
Which statement best explains the key difference in how VAEs, GANs, and DDPMs generate medical images according to the figure?
|
DDPMs iteratively remove noise through reverse diffusion rather than using encoder–decoder or discriminator structures. |
|
DDPMs start with noise and slowly remove them
|
they also do not use the name model as the other 2
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 20 |
Which of the following best explains the trend shown in Figure comparing age-standardized and crude CVD mortality rates among East Asian countries?
|
Despite differences in age structures, Japan maintains low mortality rates in both measures, suggesting effective prevention and healthcare systems. |
|
the age standardised rates are adjusted
|
by comparing the graph with other countries and the rates
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|