Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

CSB094 - RT Planning 4 > Wk2 - Advanced Contouring > Flashcards

Wk2 - Advanced Contouring Flashcards

1
Q

the different contour comparison metrics

A
  • volume
  • centre of volume
  • volume overlap
  • 2D shape and dimension
  • 3D shape and dimension
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

contour comparison metrics - volume + limitations

A
  • the absolute volume (cc)
  • can be used to calculate the % volume different from the reference, mean volume and SD

limitation
- no spatial correlation of volumes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

contour comparison metrics - centre of volume (COV) + limitation

A
  • very easy to work out in TPS
    • autoplace POI in ROI

limitations
- differing volumes can have the same COV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

contour comparison metrics - volume overlap + limitation

A
  • dice similarity coefficient
  • concordance index (CI) = volume of intersection/volume of consensus x 100%

limitation
- do not measure distances between volume edges

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

contour comparison metrics - 2D shape and dimension + limitation

A
  • measure maximum distance in a particular dimension
  • can measure slice by slice
  • can use BEV display with contours displayed

limitations
- can have same maximum in a particular dimension with different volumes and COVs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

contour comparison metrics - 3D shape and dimension + limitation

A
  • hausdorff distance is commonly used
  • mean distance to agreement is also commonly used
  • calculates differences between surfaces for multiple points around the volume

limitation
- maximum distance, average distance and 95% CI measurements only
- no directional information
- irregular surfaces can result in errors
- particularly for radial methods (eg. polar coordinates)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

StructSure

A
  • contour analysis software
  • integrated into ProKnow
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

ProKnow

A
  • contour and plan review software
  • calculates the sensitive and sophisticated StructSure accuracy score as well as simple metrics (dice coefficient, total volume, matching/missing/extra volumes, etc)
  • displays and analyses variability
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

MIM Maestro

A
  • contouring, image registration, plan adaptation software
  • calculates a wide range of metrics
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Matlab

A
  • calculates dice, Hausdorff distance, STAPLE
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

3D Slicer-Slicer RT

A
  • calculates dice and Hausdorff distance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

factors affecting manual contouring outcomes

A
  • windowing
  • image interpretation skills
  • limitations due to image quality
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

deep neural networks (DNNs)

A
  • a type of artificial neural network (ANN)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Describe the rationale for auto-contouring

A

With the advancement of RT techniques came the need for detailed contouring of datasets required to drive optimisation. Manual contouring is time consuming and is prone to intra and inter-observer error.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

How does the threshold auto-contouring tool work?

A

Quick and effective contouring tool where upper and lower CT numbers are selected and only those will be outlined

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is the challenge with fully automatic segmentation methods?

A

To determine how much user interaction is necessary
When is it suitable to implement this into clinical practice
Contours need to be given to build the model - what is the gold standard?

17
Q

Describe the body atlas based method

A

Reference image associated with atlas contours is matched to CT via deformable registration. Atlas contours are then morphed to match patients image.

18
Q

Define AI

A

Models algorithms or computer programs to tackle certain tasks requiring human intelligence

19
Q

Define machine learning

A

Numerical algorithms and models established to analyse data and derive or learn decision-making capabilities to achieve certain tasks

20
Q

Define deep learning

A

Large scale hierarchal models with multi-layer architectures to automatically generate comprehensive representations and learn complicated inherent patterns of data

21
Q

Explain 3 learning styles of DL

A
  1. Supervised - learns relationship between input data and labels (requires labelled data) good for diagnosis, image segmentation
  2. Unsupervised - learns patterns in input data (unlabelled) good for anomaly detection in QA
  3. Reinforcement - learns to perform actions in response to environment to maximise a reward function good for decision making in ART
22
Q

List 4 different contouring tools

A
  1. Manual
  2. Grey scale interrogation
  3. Body atlas based
  4. Statistical shape modelling
23
Q

2 types of greyscale interrogation - CT

A

1 - threshold
2 - model based segmentation

24
Q

body atlas based contouring process

A
  1. reference image associated with atlas contouring is “matched” to the patients’s image (CT or CBCT) via a deformable registration algorithm
  2. the resulting deformation field is used to morph atlas contours to match the patient image
25
Q

manual contouring is

A

time consuming and prone to intra and inter observer error

26
Q

analysis of contouring methods and tools

A
  • manual contours of an expert is used as the gold standard
    • clinical expertise
    • knowledge of spatial relationships, normal anatomy and patterns of disease progression
  • multiple experts preferred (due to intra and inter observer error)
    • consensus contours pooling the expertise of multiple clinicians
    • within a discipline and across disciplines (radiologist, ROs and RTs)
    • assessment of intra and inter observer variability required
27
Q

threshold techniques - contouring CT

A
  • most commonly applied to segment anatomy on individual 2D slices of the 3D data set in radiotherapy treatment planning systems
  • upper and lower limits for the CT numbers are selected, essentially applying thresholds for CT data to be included in the ROI
  • a start point is identified on the image proximal to the edge of the ROI to be outlined. the edge ROI is detected/tracked and the ROI is outlined
  • successful auto-outlining is dependent on image resolution, significant contrast between corresponding structures and a continuous surface
28
Q

threshold technique - PET

A
  • can use count or SUV voxel data
  • very contentious issue
29
Q

emerging solutions

A
  • artificial intelligence
  • machine learning
  • deep learning models
30
Q

common types of DNNs

A
  • convolution neural networks (CNNs)/ fully convolutional network (FCN)
  • widely used to extract image features for classification
  • U-nets commonly used for segmenting/contouring images

CSB094 - RT Planning 4 (9 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions