| 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 introduction summerizes the main focus of this article which explores generative artificial intelligence models and its potential uses in the medical field, particullarly in pathology as well as addressing challenges and flaws with the system.
|
Indroduction of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 artficial intelligence as being capable of creating its own data which is different from discriminative models that are used to interpret data.
|
Indroduction of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
"Model as a dataset" is a term that refers to how generative artificial intelligence learn and store patterns as well as the data it is trained on in their internal parameters, also known as weights.
|
Khosravi B, Li F, Dapamede T, et al. Synthetically enhanced: unveiling synthetic data's potential in medical imaging research.
Pinaya WHL, Tudosiu P-D, Dafflon J, et al, Brain imaging generation with latent difussion models.
|
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 is a model that requires extensive domain expertises. It uses physics principles and is therefore a rule-based model while statistical models learn from data patterns and distrubution.
|
References 14, 15, 16, and 17 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
When a model excel in 2 areas, whether it'd be diversity, quality, and or speed, it often fails in one other aspect.
|
Figure 2 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
The Human Turning Test have experts distinguish between real medical images and synthetic medical images.
|
References 51 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
When a model is trained on data that is biased towards some demographics, pathologies, or imaging protocols, the trained model will be biased as a result.
|
References 25, 72, and 73 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
When a model is able to replicate a specific dataset it is trained on, it might copy and reveal sensitive patient data.
|
References 60, and 61 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
FDA's clearance of synthetic MRI technologies is a framework for evaluating synthetic medical imaging which regulates synthetic data technology as image processing software.
|
Reference 77 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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 |
|
The article illustrates the similarities and differences in the epidemiology, diagnois, and treatment of ASCVD of East Asians immigrates in United States and East Asian Americans when compared with native East Asians.
|
Introduction of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea
|
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 |
|
The PCE was developed by combining 4 U.S. community cohort studies which includes Framingham study, yet it has few Asian subjects.
|
References 18, and 24 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 12 |
Why might Western-based risk prediction models overestimate ASCVD risk in East Asian populations?
|
Data collection standards are weaker in Asia |
|
It has a low discrimination ability and poor calibration for Asian populations.
|
References 27 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
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 |
|
The model is based on China cohort studies.
|
References 27 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
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 |
|
Models usually include sex, race, age, blood pressure, treatment for hypertension, TC, HDL-C, smoking, and diabetes.
|
Reference 18 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
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 picked from 10 distingiushed published risk prediction scores within Japan.
|
Reference 47 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
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 |
|
ASCVD risk assessment is severely overestimated in East Asian populations.
|
References 29, 84, 85 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
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 |
|
East Asians have different engagement levels in physical activities. The can also have different diets when compared to Western people.
|
References 21, 22, 23 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 18 |
What future direction does the article suggest for improving ASCVD risk prediction?
|
Abandoning population-specific models |
|
Standardizations of risk prediction models can help in cross-validation.
|
references 86, and 87 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
Future Directions and Conclusions of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
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 learn to reverse a noising procress to generate data
|
Figure 1 of Exploring the potential of generative artficial intelligence in medical image synthesis: oppotunities, challenges, and future directions
|
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?
|
China’s lower crude mortality rate compared to its age-standardized rate indicates overestimation of CVD prevalence. |
|
Standardized CVD motality rates tends to be overestimated in East Asians.
|
Figure 1 of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
Future Directions and Conclusions of Atherosclerotic Cardiovascular Disease Risk Prediction Models in China, Japan, and Korea.
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|