| 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 primary goal is collect the dataset for training other medical diagnostic system and patience privacy data.
|
In the article said that in abstact.
|
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 |
|
These 3 generative Ai according to article utilized VANs,GANs,DDPMs which can produce new data for collect dataset ,however GANs probably cause "MODE COLLAPSE"(generate same images).
|
according to "Image generation trilemma" thast tell some feature that doesn't have in these 3 generatrive AI.
|
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 |
|
Sharing anonymous model weight instead of raw patience data protect privacy.
|
Sharing dataset to train other model that significant in that geography population.
|
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 |
|
These models use physic and biology to ensure generated output in accurate.
|
To calculate in best output.
|
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 |
|
All these 3 generative AI have advantage and disadvantage which are
VANs = speed,diversity but low quality
GANs = speed,high quality but not diversity cause "Mode collapse"
DDPMs = high quality,diversity but slow cause it use "forward diffusion" and "reverse diffusion"
|
All these 3 generative AI have advantage and disadvantage which are
VANs = speed,diversity but low quality
GANs = speed,high quality but not diversity cause "Mode collapse"
DDPMs = high quality,diversity but slow cause it use "forward diffusion" and "reverse diffusion"
|
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 |
|
This method is checked by expert to compare the images from patience and artificial image from generative Ai for find which one is the real one. If expert cannot distinguiish, the image from Ai will validate that the image from generative AI is high quality.
|
This method is checked by expert to compare the images from patience and artificial image from generative Ai for find which one is the real one. If expert cannot distinguiish, the image from Ai will validate that the image from generative AI is high quality.
|
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 |
|
Every choice are potential benefit of synthetic data in healthcare except Eliminating All medical Biases perminently.
|
I had never seen in the article that tell about Eliminating All medical Biases perminently.
|
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 |
|
Actually Ai probably can copying the unique feature from patience. If the data publish to public, someone would spy patience that distruct to patience directly.
|
Actually Ai probably can copying the unique feature from patience. If the data publish to public, someone would spy patience that distruct to patience directly.
|
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 |
|
US agree that image-processing software is just one of tthe method diagnoising it novel modalities.
|
USFDA was agree generate image in health but it has a condition that developed team must shows that while, the medical experts diagnoising image from AI is accurate and equivalrnt diagnostic performance.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 10 |
What is the main purpose of the article?
|
To compare and evaluate ASCVD risk prediction models in East Asia |
|
To compare prevalence of ASCVD and risk factors in China, Japan, South+North Korea.
|
It appear on the abstract of ASCVD article.
|
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 |
|
Framingham risk score is CAC score which is calculate from Western population(non-hispanic white) that is overestimate to Eastern population.
|
The Framingham risk score was developed from the Framingham heart study in USA.
|
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 |
|
their have a lot of factor to other geography to compare and get the output in most likely the same for instance, food climate, etc..
|
their have a lot of factor to other geography to compare and get the output in most likely the same for instance, food climate, etc..
|
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 |
|
|
|
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?
|
Genetic ancestry markers |
|
The major risk prediction include sex,BP,smoking,TC,diabetes.
|
|
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 |
|
|
|
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 |
|
It's improve more accuracy that utilize the models from East population.
|
As a Framingham Risk Score that use USA population.
|
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 |
|
The culture,, type of food like Japan is an island country the major of dish is about fish.
|
As you can seen that east asia population and west population are not equilable statistic for instance, diabetes in east asia is low rate of diabetes while wast is high,.
|
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 |
|
they use their own model such ar China = China_PAR, Japan= Suita score, etc., Korea = KSOLA score.
|
they use their own model such ar China = China_PAR, etc., Japan= Suita score, etc., Korea = KSOLA score etc.
|
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. |
|
VAEs = use real picture input -> encoder -> latent presentation -> decoder ->generate -> output (speed, diverse, low quality)
GAns = it's likely to competition between Generator and discriminator. Generator = generate to best image to avoid discriminator to detect
discrimination = detect the mistake from Generator. Therefore, if generator can avoid discriminator, it will use the same image that was win it cause "Mode collapse:".
DDPMs = it use mathematics to calculate forward diffusion and reverse diffusion to clear to something(I assume that is a tiny pigment) to get the best image.
|
VAEs = use real picture input -> encoder -> latent presentation -> decoder ->generate -> output (speed, diverse, low quality)
GAns = it's likely to competition between Generator and discriminator. Generator = generate to best image to avoid discriminator to detect
discrimination = detect the mistake from Generator. Therefore, if generator can avoid discriminator, it will use the same image that was win it cause "Mode collapse:".
DDPMs = it use mathematics to calculate forward diffusion and reverse diffusion to clear to something(I assume that is a tiny pigment) to get the best image.
|
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. |
|
Despite differences in age structures, Japan maintains low mortality rates in both measures, suggesting effective prevention and healthcare systems.
|
Despite differences in age structures, Japan maintains low mortality rates in both measures, suggesting effective prevention and healthcare systems.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|