![Page 1: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/1.jpg)
MODULE II
Semi-Automatic Segmentation
RSNA 2016 ITK-SNAP Course
![Page 2: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/2.jpg)
Semi-Automatic Segmentation
Segmentation Algorithm
User: quickly identifies structure of interest and sets parameters
![Page 3: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/3.jpg)
Semi-Automatic Segmentation
Segmentation Algorithm
User: quickly identifies structure of interest and sets parameters
![Page 4: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/4.jpg)
Semi-Automatic Segmentation
Segmentation Algorithm
User: quickly identifies structure of interest and sets parameters
![Page 5: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/5.jpg)
Semi-Automatic Segmentation
Segmentation Algorithm
User: quickly identifies structure of interest and sets parameters
![Page 6: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/6.jpg)
How does it work?
• Pre-segmentation Phase
• Identify parts of image as foreground and background
• Active Contour Phase
• Place seeds inside the structure of interest
• Grow the seeds to fill the structure of interest
![Page 7: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/7.jpg)
Pre-segmentation Phase
Images Region of Interest
Pre-segmentation
Speed Image
Foreg
round
Backg
round
Uncert
ain
![Page 8: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/8.jpg)
Pre-segmentation Modes
Thresholding
Classification
![Page 9: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/9.jpg)
Pre-segmentation Modes
Thresholding
Classificationsets t
hresholds
![Page 10: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/10.jpg)
Pre-segmentation Modes
Thresholding
Classificationsets t
hresholds
![Page 11: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/11.jpg)
Pre-segmentation Modes
Thresholding
Classificationsets t
hresholds
paints examples
![Page 12: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/12.jpg)
Pre-segmentation Modes
Thresholding
Classificationsets t
hresholds
paints examples
![Page 13: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/13.jpg)
Active Contour Evolution driven by Forces
Image Force: outward over foreground, inward over background
Smoothing Force: strongest in places of high curvature
![Page 14: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/14.jpg)
Active Contour Evolution
![Page 15: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/15.jpg)
Active Contour Evolution
![Page 16: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/16.jpg)
Active Contour Evolution
![Page 17: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/17.jpg)
Active Contour Evolution
places seeds
![Page 18: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/18.jpg)
Live demo of semi-automatic segmentation
![Page 19: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/19.jpg)
Newest ITK-SNAP Functionality (late 2016)
Manual and automatic registrationMorphological interpolation
2
1 Introduction
Proliferation of automatic segmentation algorithms is on the rise, but their performance is measured againsta manually created ‘gold standard’ segmentation. Additionally, manual segmentation is sometimes requiredfor other purposes.
As anyone who has ever done manual image segmentation can tell you, it becomes monotonous very quickly.This is especially true for high-resolution 3D images, i.e. for 3D images with thin ‘slices’ (because thereare many of them). The classic ‘cure’ for this is inter-slice interpolation (Fig. 1). Namely, in regions wherethe anatomy is slowly changing and adjacent slices are quite similar, some slices can be skipped by a humansegmenter and then interpolated by an algorithm.
Figure 1: Examples of inputs (left) and outputs (right). First row: two labels, manual segmentation on coronal slices
only. Second row: four labels, manual segmentation along all three principal axes of the body.
Latest version available at the Insight Journal [ http://hdl.handle.net/10380/1338]Distributed under Creative Commons Attribution License
2
1 Introduction
Proliferation of automatic segmentation algorithms is on the rise, but their performance is measured againsta manually created ‘gold standard’ segmentation. Additionally, manual segmentation is sometimes requiredfor other purposes.
As anyone who has ever done manual image segmentation can tell you, it becomes monotonous very quickly.This is especially true for high-resolution 3D images, i.e. for 3D images with thin ‘slices’ (because thereare many of them). The classic ‘cure’ for this is inter-slice interpolation (Fig. 1). Namely, in regions wherethe anatomy is slowly changing and adjacent slices are quite similar, some slices can be skipped by a humansegmenter and then interpolated by an algorithm.
Figure 1: Examples of inputs (left) and outputs (right). First row: two labels, manual segmentation on coronal slices
only. Second row: four labels, manual segmentation along all three principal axes of the body.
Latest version available at the Insight Journal [ http://hdl.handle.net/10380/1338]Distributed under Creative Commons Attribution License
![Page 20: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/20.jpg)
Newest ITK-SNAP Functionality (late 2016)
Manual and automatic registrationMorphological interpolation
2
1 Introduction
Proliferation of automatic segmentation algorithms is on the rise, but their performance is measured againsta manually created ‘gold standard’ segmentation. Additionally, manual segmentation is sometimes requiredfor other purposes.
As anyone who has ever done manual image segmentation can tell you, it becomes monotonous very quickly.This is especially true for high-resolution 3D images, i.e. for 3D images with thin ‘slices’ (because thereare many of them). The classic ‘cure’ for this is inter-slice interpolation (Fig. 1). Namely, in regions wherethe anatomy is slowly changing and adjacent slices are quite similar, some slices can be skipped by a humansegmenter and then interpolated by an algorithm.
Figure 1: Examples of inputs (left) and outputs (right). First row: two labels, manual segmentation on coronal slices
only. Second row: four labels, manual segmentation along all three principal axes of the body.
Latest version available at the Insight Journal [ http://hdl.handle.net/10380/1338]Distributed under Creative Commons Attribution License
2
1 Introduction
Proliferation of automatic segmentation algorithms is on the rise, but their performance is measured againsta manually created ‘gold standard’ segmentation. Additionally, manual segmentation is sometimes requiredfor other purposes.
As anyone who has ever done manual image segmentation can tell you, it becomes monotonous very quickly.This is especially true for high-resolution 3D images, i.e. for 3D images with thin ‘slices’ (because thereare many of them). The classic ‘cure’ for this is inter-slice interpolation (Fig. 1). Namely, in regions wherethe anatomy is slowly changing and adjacent slices are quite similar, some slices can be skipped by a humansegmenter and then interpolated by an algorithm.
Figure 1: Examples of inputs (left) and outputs (right). First row: two labels, manual segmentation on coronal slices
only. Second row: four labels, manual segmentation along all three principal axes of the body.
Latest version available at the Insight Journal [ http://hdl.handle.net/10380/1338]Distributed under Creative Commons Attribution License
![Page 21: MODULE II - ITK-SNAP · Newest ITK-SNAP Functionality (late 2016) Morphological interpolation Manual and automatic registration 2 1 Introduction Proliferation of automatic segmentation](https://reader033.vdocument.in/reader033/viewer/2022042709/5f4295ae9e71c21883560af4/html5/thumbnails/21.jpg)
Please work on exercises 3 and 4