Artificial Intelligence in Radiology Practice Questions

Q: A deep learning algorithm for detecting pneumonia on chest X-rays performs excellently on the validation set but poorly on external testing. Analysis reveals the algorithm learned to recognize the hospital logo and text on images from ICU patients (who more likely had pneumonia). What type of bias does this represent?

Confounding bias. ***Confounding bias*** - In machine learning, this occurs when an algorithm learns a **spurious correlation** between a feature (like a hospital logo) and the outcome (pneumonia) because that feature is non-causally associated with the disease. - The **hospital logo** acts as a **confounding variable** that provides a shortcut for the model, leading to high internal accuracy but poor **generalizability** to external datasets without that logo. *Selection bias* - This involves errors in the **recruitment or retention** of study participants, leading to a sample that does not accurately represent the target population. - While the ICU population represents a specific subset, the core issue here is the algorithm identifying **irrelevant visual markers**, not just the patient selection process. *Information bias* - This refers to errors in how data is **measured, collected, or recorded**, such as recall bias or measurement error. - In this scenario, the images themselves were recorded correctly, but the model's **interpretation logic** was flawed due to external markers rather than an error in the data collection tool. *Spectrum bias* - This occurs when the study population does not reflect the **full range** of disease severity seen in clinical practice, often using only very sick patients and healthy controls. - While using ICU patients could contribute to this, the specific problem of identifying **hospital-specific text or logos** is a hallmark of confounding, not just a narrow disease spectrum.

Q: A hospital implements an AI algorithm for detecting intracranial hemorrhage on CT scans. The algorithm was trained on data from a different population with different CT scanner protocols. The algorithm shows decreased performance. Which concept explains this phenomenon?

Dataset shift and lack of generalizability. ***Dataset shift and lack of generalizability*** - **Dataset shift** occurs when the distribution of data used during training differs significantly from the data encountered in clinical practice, such as different **scanner protocols**. - This leads to a lack of **generalizability**, where the AI performs poorly in new environments because it cannot adapt to variations in **population demographics** or imaging hardware. *Overfitting of the training data* - **Overfitting** happens when a model learns the noise and specific details of the training set too well, failing to predict outcomes on any new data. - While it affects generalizability, the specific issue of switching **scanner protocols** and **populations** is more accurately described as a shift in data domains. *Insufficient neural network layers* - Insufficient layers or **lack of depth** typically results in **underfitting**, where the model is too simple to capture the underlying patterns in the training data. - This is a structural limitation of the model architecture rather than an issue related to the **external validation** or the source of the data. *Poor image preprocessing* - **Preprocessing** involves cleaning or standardizing images before feeding them into the model; errors here would affect consistency across all datasets. - While standardized preprocessing helps mitigate differences, the root cause of decreased performance across different **institutional protocols** is the mismatch in the data distribution itself.

Q: Which convolutional neural network architecture won the ImageNet competition in 2012 and revolutionized medical image analysis?

AlexNet. ***AlexNet*** - Developed by **Alex Krizhevsky**, this architecture won the **2012 ImageNet** competition and is credited with initiating the modern **deep learning** era. - It utilized **GPUs** for training and deep **Convolutional Neural Networks (CNNs)**, leading to its widespread adoption for tasks like **radiological image classification**. *VGGNet* - This architecture was introduced later in **2014** and is known for its simplicity, using a uniform architecture of **3x3 convolutional filters**. - While influential in medical imaging, it did not win the 2012 competition that originally sparked the **AI revolution**. *ResNet* - Introduced in **2015**, **ResNet** (Residual Network) solved the vanishing gradient problem using **skip connections** or residual blocks. - It allowed for much deeper networks (e.g., **152 layers**), but its development followed years after the 2012 milestone. *GoogleNet* - Also known as **Inception-v1**, this architecture won the ImageNet competition in **2014**, not 2012. - It introduced the **Inception module**, which uses multiple filter sizes at the same level to capture features at different **spatial scales**.

Q: What is the term used for AI systems that can perform narrow, specific tasks in radiology such as detecting lung nodules?

Artificial Narrow Intelligence (ANI). ***Artificial Narrow Intelligence (ANI)*** - Also known as **Weak AI**, this refers to systems trained to perform **specific, specialized tasks** like identifying lung nodules or bone fractures. - **Current radiology applications** are exclusively ANI because they lack the ability to transfer skills across unrelated domains or generalize beyond their training. *Artificial General Intelligence (AGI)* - Describes a theoretical AI that possesses the ability to **reason and perform any intellectual task** that a human can do. - Unlike specialized medical imaging tools, **AGI** would be able to adapt to diverse clinical scenarios without being specifically pre-programmed for each. *Artificial Super Intelligence (ASI)* - Refers to a future, hypothetical level of AI that **surpasses human intelligence** across all fields, including creativity and social skills. - This level of intelligence is significantly more advanced than the **task-specific algorithms** currently used in diagnostic workflows. *Deep Reinforcement Learning* - A specific **machine learning technique** where an agent learns to make decisions by receiving rewards or penalties based on its actions. - While it is a method used to train models, it is not the categorical term for AI systems defined by their **specialized or narrow scope**.

Question 1

A research team develops an AI algorithm using 100,000 CT scans from multiple institutions. The algorithm shows excellent performance (AUC 0.96) but requires extensive computational resources. To deploy it in resource-limited settings, they propose model compression techniques. Evaluate the potential trade-offs and propose the most balanced approach.

Accepted Answer

Use knowledge distillation to train a smaller model that mimics the larger model while accepting minimal performance decrease

Answer

Model compression always maintains performance while reducing size

Answer

Avoid compression as any performance loss is unacceptable in medical AI

Answer

Random pruning of neural network connections is sufficient

Question 2

A radiology department is evaluating two AI algorithms for fracture detection. Algorithm A has AUC-ROC of 0.95, while Algorithm B has AUC-ROC of 0.92 but provides explainable results showing which image regions influenced its decision. Considering clinical implementation and medicolegal aspects, which statement best evaluates the choice?

Accepted Answer

Algorithm B may be preferred despite lower AUC due to interpretability and accountability

Answer

Algorithm A should always be chosen due to superior performance metrics

Answer

AUC-ROC is the only relevant metric for clinical decision making

Answer

The difference in AUC is clinically insignificant so both are equivalent

Question 3

A deep learning algorithm for detecting pneumonia on chest X-rays performs excellently on the validation set but poorly on external testing. Analysis reveals the algorithm learned to recognize the hospital logo and text on images from ICU patients (who more likely had pneumonia). What type of bias does this represent?

Accepted Answer

Confounding bias

Answer

Selection bias

Answer

Information bias

Answer

Spectrum bias

Question 4

An AI model for detecting breast cancer on mammography shows sensitivity of 95% and specificity of 85% in a screening population with 1% disease prevalence. A study claims the AI outperforms radiologists who have 90% sensitivity and 90% specificity. Analyze why this comparison may be misleading.

Accepted Answer

The AI has lower positive predictive value despite higher sensitivity

Answer

The AI has higher negative predictive value in all cases

Answer

Specificity is more important than sensitivity in screening

Answer

The prevalence is too high for meaningful comparison

Question 5

A hospital implements an AI algorithm for detecting intracranial hemorrhage on CT scans. The algorithm was trained on data from a different population with different CT scanner protocols. The algorithm shows decreased performance. Which concept explains this phenomenon?

Accepted Answer

Dataset shift and lack of generalizability

Answer

Overfitting of the training data

Answer

Insufficient neural network layers

Answer

Poor image preprocessing

Question 6

A 55-year-old male presents with chronic cough. A chest X-ray is analyzed by an AI algorithm that reports a 4mm lung nodule in the right upper lobe with 85% confidence. The human radiologist reviews the image but cannot identify the nodule. What is the most appropriate next step?

Accepted Answer

Obtain a second opinion from another radiologist and correlate with clinical findings

Answer

Accept the AI finding and proceed to CT scan immediately

Answer

Reject the AI finding as a false positive without further action

Answer

Report only what the radiologist can see and discard AI output

Question 7

How does a Generative Adversarial Network (GAN) work in the context of medical image synthesis?

Accepted Answer

Through a generator creating images and a discriminator distinguishing real from fake

Answer

By comparing two identical neural networks

Answer

By using regression algorithms to predict image quality

Answer

Through supervised learning with labeled datasets only

Question 8

What is the primary advantage of using transfer learning in developing AI models for radiology?

Accepted Answer

It allows using pre-trained models on large datasets and fine-tuning for medical images

Answer

It eliminates the need for labeled medical images

Answer

It automatically annotates all pathological findings

Answer

It reduces radiation dose in imaging

Question 9

Which convolutional neural network architecture won the ImageNet competition in 2012 and revolutionized medical image analysis?

Accepted Answer

AlexNet

Answer

VGGNet

Answer

ResNet

Answer

GoogleNet

Question 10

What is the term used for AI systems that can perform narrow, specific tasks in radiology such as detecting lung nodules?

Accepted Answer

Artificial Narrow Intelligence (ANI)

Answer

Artificial General Intelligence (AGI)

Answer

Artificial Super Intelligence (ASI)

Answer

Deep Reinforcement Learning

Artificial Intelligence in Radiology — MCQs

Artificial Intelligence in Radiology — MCQs

On this page

Practice by Chapter

Want unlimited practice?