Lung-Lobes-Segmentation / Git / Diff of /README.md

Models:

SCallahan/

Lung-Lobes-Segmentation

Downloads: 1

Diff of /README.md [4c12f9] .. [6e07f8]

Switch to unified view


# Lung-Lobes-Segmentation-in-CT-Scans

Python and C++ implementation on vessel and fissure segmentation in Lung CT Scans based on [Bianca's work](https://pdfs.semanticscholar.org/ddd9/8a73eab745841ba41a13633be76ab1f9c8b0.pdf)

## Usage
**For lung and pulmonary vessel segmentation**. 

I create a ipython notebook for this part (in lung_segmentation.ipynb except the last two parts).

**For pulmonary fissure segmentation**. 

Compile the two C++ files for fissure segmentation.
1. cmake .
2. make
3. 
    Use vector-based region growing for fissure segmention. 
    ```Python
    ./vector_region_growing ORIGINAL_CT.mhd FISSURE_EXTRACT.mhd
    ```
    Use intensity-based region growing for removing small regions.
    ```Python
    ./region_growing FISSURE_EXTRACT.mhd FISSURE_EXTRACT_REFINED.mhd
    ```
4. Running the last two sections in the ipython notebook to generate fissure mask and final lung-vessel-fissure mask. 

## Results
The result of lung segmentation:  

![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/lung.png?raw=true)
----

The result of vessel segmentaton:  

![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/vessel.png?raw=true)

And in 3D view:  

![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/vessel3d.png?raw=true)
----

The result of fissure segmentation:   
(From left to right: original, after vector-based region growing, after intensity-based region growing)

![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/fissure.png?raw=true)

The 3D maps of Lung-Vessel-Fissure for 9 cases:  

![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/maps.png?raw=true)

## Dataset
The dataset I used is [LOLA11](https://lola11.grand-challenge.org), which contains 55 CT Scans. 

	a/README.md		b/README.md
1	# Lung-Lobes-Segmentation-in-CT-Scans	1	# Lung-Lobes-Segmentation-in-CT-Scans
2		2
3	Python and C++ implementation on vessel and fissure segmentation in Lung CT Scans based on [Bianca's work](https://pdfs.semanticscholar.org/ddd9/8a73eab745841ba41a13633be76ab1f9c8b0.pdf)	3	Python and C++ implementation on vessel and fissure segmentation in Lung CT Scans based on [Bianca's work](https://pdfs.semanticscholar.org/ddd9/8a73eab745841ba41a13633be76ab1f9c8b0.pdf)
4		4
5	## Usage	5	## Usage
6	For lung and pulmonary vessel segmentation.	6	For lung and pulmonary vessel segmentation.
7		7
8	I create a ipython notebook for this part (in lung_segmentation.ipynb except the last two parts).	8	I create a ipython notebook for this part (in lung_segmentation.ipynb except the last two parts).
9		9
10	For pulmonary fissure segmentation.	10	For pulmonary fissure segmentation.
11		11
12	Compile the two C++ files for fissure segmentation.	12	Compile the two C++ files for fissure segmentation.
13	1. cmake .	13	1. cmake .
14	2. make	14	2. make
15	3.	15	3.
16	Use vector-based region growing for fissure segmention.	16	Use vector-based region growing for fissure segmention.
17	```Python	17	```Python
18	./vector_region_growing ORIGINAL_CT.mhd FISSURE_EXTRACT.mhd	18	./vector_region_growing ORIGINAL_CT.mhd FISSURE_EXTRACT.mhd
19	```	19	```
20	Use intensity-based region growing for removing small regions.	20	Use intensity-based region growing for removing small regions.
21	```Python	21	```Python
22	./region_growing FISSURE_EXTRACT.mhd FISSURE_EXTRACT_REFINED.mhd	22	./region_growing FISSURE_EXTRACT.mhd FISSURE_EXTRACT_REFINED.mhd
23	```	23	```
24	4. Running the last two sections in the ipython notebook to generate fissure mask and final lung-vessel-fissure mask.	24	4. Running the last two sections in the ipython notebook to generate fissure mask and final lung-vessel-fissure mask.
25		25
26	## Results	26	## Results
27	The result of lung segmentation:	27	The result of lung segmentation:
28		28
29	![ ](images/lung.png)	29	![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/lung.png?raw=true)
30	----	30	----
31		31
32	The result of vessel segmentaton:	32	The result of vessel segmentaton:
33		33
34	![ ](images/vessel.png)	34	![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/vessel.png?raw=true)
35		35
36	And in 3D view:	36	And in 3D view:
37		37
38	![ ](images/vessel3d.png)	38	![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/vessel3d.png?raw=true)
39	----	39	----
40		40
41	The result of fissure segmentation:	41	The result of fissure segmentation:
42	(From left to right: original, after vector-based region growing, after intensity-based region growing)	42	(From left to right: original, after vector-based region growing, after intensity-based region growing)
43		43
44	![ ](images/fissure.png)	44	![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/fissure.png?raw=true)
45		45
46	The 3D maps of Lung-Vessel-Fissure for 9 cases:	46	The 3D maps of Lung-Vessel-Fissure for 9 cases:
47		47
48	![ ](images/maps.png)	48	![ ](https://github.com/Connor323/Lung-Lobes-Segmentation-in-CT-Scans/blob/master/images/maps.png?raw=true)
49		49
50	## Dataset	50	## Dataset
51	The dataset I used is [LOLA11](https://lola11.grand-challenge.org), which contains 55 CT Scans.	51	The dataset I used is [LOLA11](https://lola11.grand-challenge.org), which contains 55 CT Scans.