1
00:00:04,500 --> 00:00:06,670
In this recitation,
we will see how

2
00:00:06,670 --> 00:00:10,150
to apply clustering
techniques to segment images,

3
00:00:10,150 --> 00:00:13,190
with the main application being
geared towards medical image

4
00:00:13,190 --> 00:00:14,770
segmentation.

5
00:00:14,770 --> 00:00:16,900
At the end of this
recitation, you

6
00:00:16,900 --> 00:00:20,370
will get a head start on
how to cluster an MRI brain

7
00:00:20,370 --> 00:00:25,440
image by tissue substances and
locate pathological anatomies.

8
00:00:25,440 --> 00:00:27,500
Image segmentation
is the process

9
00:00:27,500 --> 00:00:31,200
of partitioning digital images
into regions, or segments,

10
00:00:31,200 --> 00:00:34,750
that share the same visual
characteristics, such as color,

11
00:00:34,750 --> 00:00:36,890
intensity, or texture.

12
00:00:36,890 --> 00:00:39,250
The segments should
also be meaningful,

13
00:00:39,250 --> 00:00:43,040
as in they should correspond to
particular surfaces, objects,

14
00:00:43,040 --> 00:00:45,430
or even parts of an object.

15
00:00:45,430 --> 00:00:47,490
Think of having an
image of a water pond,

16
00:00:47,490 --> 00:00:50,290
a mountain chain in the
backdrop, and the sky.

17
00:00:50,290 --> 00:00:52,430
Segmenting this
image should ideally

18
00:00:52,430 --> 00:00:54,690
detect the three
different objects

19
00:00:54,690 --> 00:00:56,600
and assign their
corresponding pixels

20
00:00:56,600 --> 00:00:59,000
to three different regions.

21
00:00:59,000 --> 00:01:01,830
In few words, the goal
of image segmentation

22
00:01:01,830 --> 00:01:05,810
is to modify the representation
of an image from pixel data

23
00:01:05,810 --> 00:01:09,980
into something meaningful
to us and easier to analyze.

24
00:01:09,980 --> 00:01:13,110
Image segmentation has
a wide applicability.

25
00:01:13,110 --> 00:01:15,590
A major practical
application is in the field

26
00:01:15,590 --> 00:01:18,670
of medical imaging, where
image segments often

27
00:01:18,670 --> 00:01:23,140
correspond to different tissues,
organs, pathologies, or tumors.

28
00:01:23,140 --> 00:01:26,530
Image segmentation helps locate
these geometrically complex

29
00:01:26,530 --> 00:01:29,530
objects and measure
their volume.

30
00:01:29,530 --> 00:01:31,950
Another application
is detecting instances

31
00:01:31,950 --> 00:01:36,110
of semantic objects such as
humans, buildings, and others.

32
00:01:36,110 --> 00:01:38,850
The two major domains that
have seen much attention

33
00:01:38,850 --> 00:01:42,560
recently include face
and pedestrian detection.

34
00:01:42,560 --> 00:01:44,870
The main uses of facial
detection, for instance,

35
00:01:44,870 --> 00:01:48,640
include the development of the
auto-focus in digital cameras

36
00:01:48,640 --> 00:01:53,150
and face recognition commonly
used in video surveillance.

37
00:01:53,150 --> 00:01:56,289
Other important applications
are fingerprint and iris

38
00:01:56,289 --> 00:01:57,470
recognition.

39
00:01:57,470 --> 00:01:59,800
For instance,
fingerprint recognition

40
00:01:59,800 --> 00:02:02,450
tries to identify print
patterns, including

41
00:02:02,450 --> 00:02:06,520
aggregate characteristics of
ridges and minutiae points.

42
00:02:06,520 --> 00:02:09,270
In this recitation, we
will look in particular

43
00:02:09,270 --> 00:02:12,960
at the medical
imaging application.

44
00:02:12,960 --> 00:02:15,860
Various methods have been
proposed to segment images.

45
00:02:15,860 --> 00:02:18,160
Clustering methods are
used to group the points

46
00:02:18,160 --> 00:02:21,520
into clusters according to
their characteristic features,

47
00:02:21,520 --> 00:02:23,910
for instance, intensity values.

48
00:02:23,910 --> 00:02:25,930
These clusters are
then mapped back

49
00:02:25,930 --> 00:02:28,740
to the original spatial
domain to produce

50
00:02:28,740 --> 00:02:31,380
a segmentation of the image.

51
00:02:31,380 --> 00:02:33,960
Another technique
is edge detection,

52
00:02:33,960 --> 00:02:38,020
which is based on detecting
discontinuities or boundaries.

53
00:02:38,020 --> 00:02:40,230
For instance, in a
gray-scale image,

54
00:02:40,230 --> 00:02:42,600
a boundary would correspond
to an abrupt change

55
00:02:42,600 --> 00:02:45,180
in the gray level.

56
00:02:45,180 --> 00:02:47,570
Instead of finding boundaries
of regions in the image,

57
00:02:47,570 --> 00:02:49,560
there are other
techniques called region

58
00:02:49,560 --> 00:02:51,760
growing methods,
which start dividing

59
00:02:51,760 --> 00:02:54,180
the image into small regions.

60
00:02:54,180 --> 00:02:57,540
Then, they sequentially
merge these regions together

61
00:02:57,540 --> 00:03:00,340
if they are
sufficiently similar.

62
00:03:00,340 --> 00:03:04,350
In this recitation, our focus
is on clustering methods.

63
00:03:04,350 --> 00:03:07,560
In particular, we will review
hierarchical and k-means

64
00:03:07,560 --> 00:03:11,160
clustering techniques
and how to use them in R.

65
00:03:11,160 --> 00:03:14,530
We will restrict ourselves
to gray-scale images.

66
00:03:14,530 --> 00:03:17,890
Our first example is a
low-resolution flower image

67
00:03:17,890 --> 00:03:19,920
whose pixel
intensity information

68
00:03:19,920 --> 00:03:23,360
is given the data
set flower.csv.

69
00:03:23,360 --> 00:03:27,240
Our second and major example
involves two weighted MRI

70
00:03:27,240 --> 00:03:28,810
images of the brain.

71
00:03:28,810 --> 00:03:31,590
One image corresponds
to a healthy patient,

72
00:03:31,590 --> 00:03:34,610
and the other one corresponds
to a patient with a tumor

73
00:03:34,610 --> 00:03:36,950
called oligodendroglioma.

74
00:03:36,950 --> 00:03:39,990
The pixel intensity
information of these two images

75
00:03:39,990 --> 00:03:44,410
are given in the data sets
healthy and tumor.csv.

76
00:03:44,410 --> 00:03:47,370
The last video will
compare the use, pros,

77
00:03:47,370 --> 00:03:51,430
and cons of all the analytics
tools that we have seen so far.

78
00:03:51,430 --> 00:03:54,160
I hope that this will
help you synthesize all

79
00:03:54,160 --> 00:03:56,460
that you've learned to give
you an edge in the class

80
00:03:56,460 --> 00:03:59,590
competition that
is coming up soon.