wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

BME_lecture2

Total questions: 10

Worksheet time: 5mins

Name
Class
Date
1.

What is NOT one of the challenges in AI medical images?

a)

Doctors can easily make annotation for large scale dataset

b)

Noisy labels from multiple experts

c)

Privacy and legal issues

d)

Class imbalance

2.

What is NOT the classic medical imaging problem?

a)

Registration

b)

Classification

c)

Segmentation

d)

Federated learning

3.

Example of uni-modal registration?

a)

Cardiac MRI

b)

T1w-T2w MRI

c)

CT-MRI

d)

MRI-Ultrasound

4.

One of the SOTA networks for medical image segmentation?

a)

SE-ResNet

b)

U-Net (and its variants)

c)

Inception-Net

d)

Mobile-Net

5.

A technique to transfer knowledge from pre-trained model (from large scale natural images) to be used for medical images

a)

Curriculum learning

b)

Federated learning

c)

Transfer learning

d)

Multi-modal learning

6.

What is the benefit of domain adaptation in medical images?

a)

Increase the domain shift

b)

Reducing the domain generalization

c)

Transfer knowledge from pre-trained model from large scale natural images

d)

Improve the performance of a target model with insufficient or lack of annotated data

7.

Which one does NOT require manually annotated labels?

a)

Ensemble learning

b)

Supervised learning

c)

Self-supervised learning

d)

Multi-modal learning

8.

What is PACS?

a)

picture archiving and communications systems

b)

picture asynchronous constellation systems

c)

patient archive and communication system

d)

patient as synced and computer system

9.

What is the benefit of federated learning?

a)

Send all patients details to the central system

b)

Share the privacy protocols

c)

Train the data without actually sending data to the central node.

d)

Heavy computing process

10.

which one is not biomedical image?

a)

Whole Slide Images

b)

Fundus image

c)

SPECT image

d)

Depth image