Comments (27)
VidhiBishnoi
commented on July 30, 2024
1
Thank you the issue is resolved.. Have you extracted the nodule? How to do
that?
…On Tue, Oct 13, 2020 at 7:24 PM notmatthancock ***@***.***> wrote:
path = C:\Users\admin\to\big_external_drive\datasets\LIDC-IDRI
This is a fake path. You need to replace this path with the actual path to
the root folder of the LIDC data.
As this file will itself locate the dataset from the system i think.
I'm sorry, I don't understand what you mean. This file needs to be updated
by you to point to the data. pylidc does not scan your system to discover
the root data location automatically, if that's what you're suggesting.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFC27TSEBZ4QOIWRDSTLSKRLX7ANCNFSM4GXVNEWQ>
.
from pylidc.
VidhiBishnoi
commented on July 30, 2024
1
Please find my python code below:
```
import pylidc as pl
import numpy as np
import matplotlib.pyplot as plt
# Query for all CT scans with desired traits.
scans = pl.query(pl.Scan).filter(pl.Scan.slice_thickness <= 1,
pl.Scan.pixel_spacing <= 0.6)
print(scans.count())
# => 31
pid = 'LIDC-IDRI-0250'
scan = pl.query(pl.Scan).filter(pl.Scan.patient_id == pid).first()
nods = scan.cluster_annotations()
print("%s has %d nodules." % (scan, len(nods)))
for i,nod in enumerate(nods):
print("Nodule %d has %d annotations." % (i+1, len(nods[i])))
vol = scan.to_volume()
scan.visualize(annotation_groups=nods)
annotations = scan.annotations
ann = annotations[0]
mask = ann.boolean_mask()
print(mask.shape, mask.dtype)
bbox = ann.bbox()
print(bbox)
vol = ann.scan.to_volume()
print(vol[bbox].shape)
import pylidc as pl
import matplotlib.pyplot as plt
#ann = pl.query(pl.Annotation).first()
vol = ann.scan.to_volume()
padding = [(30,10), (10,25), (0,0)]
mask = ann.boolean_mask(pad=padding)
bbox = ann.bbox(pad=padding)
fig,ax = plt.subplots(1,2,figsize=(5,3))
ax[0].imshow(vol[bbox][:,:,2], cmap=plt.cm.gray)
ax[0].axis('off')
ax[1].imshow(mask[:,:,2], cmap=plt.cm.gray)
ax[1].axis('off')
plt.tight_layout()
#plt.savefig("../images/mask_bbox.png", bbox_inches="tight")
plt.show()
ann.visualize_in_3d()
ann.visualize_in_scan()
```
The problem is as discussed previously.
…On Thu, Oct 15, 2020 at 5:36 PM Jonas Maison ***@***.***> wrote:
Give us the full code script (and use triple backticks to improve
readability!)
```python
insert code here
```
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFC5NHEBNZMMK2ZTLUIDSK3QS3ANCNFSM4GXVNEWQ>
.
from pylidc.
VidhiBishnoi
commented on July 30, 2024
1
Hello Sir, plz send me the solution of my problem.
On Sat, Oct 17, 2020 at 8:35 PM Vidhi Bishnoi <[email protected]>
wrote:
… Please find my python code below:
```
import pylidc as pl
import numpy as np
import matplotlib.pyplot as plt
# Query for all CT scans with desired traits.
scans = pl.query(pl.Scan).filter(pl.Scan.slice_thickness <= 1,
pl.Scan.pixel_spacing <= 0.6)
print(scans.count())
# => 31
pid = 'LIDC-IDRI-0250'
scan = pl.query(pl.Scan).filter(pl.Scan.patient_id == pid).first()
nods = scan.cluster_annotations()
print("%s has %d nodules." % (scan, len(nods)))
for i,nod in enumerate(nods):
print("Nodule %d has %d annotations." % (i+1, len(nods[i])))
vol = scan.to_volume()
scan.visualize(annotation_groups=nods)
annotations = scan.annotations
ann = annotations[0]
mask = ann.boolean_mask()
print(mask.shape, mask.dtype)
bbox = ann.bbox()
print(bbox)
vol = ann.scan.to_volume()
print(vol[bbox].shape)
import pylidc as pl
import matplotlib.pyplot as plt
#ann = pl.query(pl.Annotation).first()
vol = ann.scan.to_volume()
padding = [(30,10), (10,25), (0,0)]
mask = ann.boolean_mask(pad=padding)
bbox = ann.bbox(pad=padding)
fig,ax = plt.subplots(1,2,figsize=(5,3))
ax[0].imshow(vol[bbox][:,:,2], cmap=plt.cm.gray)
ax[0].axis('off')
ax[1].imshow(mask[:,:,2], cmap=plt.cm.gray)
ax[1].axis('off')
plt.tight_layout()
#plt.savefig("../images/mask_bbox.png", bbox_inches="tight")
plt.show()
ann.visualize_in_3d()
ann.visualize_in_scan()
```
The problem is as discussed previously.
On Thu, Oct 15, 2020 at 5:36 PM Jonas Maison ***@***.***>
wrote:
> Give us the full code script (and use triple backticks to improve
> readability!)
>
> ```python
> insert code here
> ```
>
> —
> You are receiving this because you were mentioned.
> Reply to this email directly, view it on GitHub
> <#25 (comment)>,
> or unsubscribe
> <https://github.com/notifications/unsubscribe-auth/AKLHFC5NHEBNZMMK2ZTLUIDSK3QS3ANCNFSM4GXVNEWQ>
> .
>
from pylidc.
notmatthancock
commented on July 30, 2024
.pylidcrc is plain text. Edit the path to point to the root folder of where the dicom data is stored on your particular machine.
from pylidc.
chinnujacob
commented on July 30, 2024
hii
this i s how i did in .pylidcrc .stil i get the same error.
[dicom]
path = /home/user/LIDC-IDRI
warn = True
can u suggest a solution
from pylidc.
notmatthancock
commented on July 30, 2024
The path that you have specified is not a real path. You have to update that to point to the root directory of where the LIDC data actually resides on your specific machine.
from pylidc.
chinnujacob
commented on July 30, 2024
hii
i have created a folder LIDC-IDRI in /home/user .and data s stored here.so isn't this the real path.what should i do now .please help
from pylidc.
chinnujacob
commented on July 30, 2024
hii
i have created a folder LIDC-IDRI in /home/user .and data s stored here.so isn't this the real path.what should i do now .please help
from pylidc.
notmatthancock
commented on July 30, 2024
Usually “user” should be your actual user account name. Are you on Linux? What’s the output of “ls /home/user/LIDC-IDRI”?
from pylidc.
chinnujacob
commented on July 30, 2024
hii
thank you so much.my problem is resolved.i got path correct
from pylidc.
notmatthancock
commented on July 30, 2024
ok...
from pylidc.
VidhiBishnoi
commented on July 30, 2024
Hello, Please help me out in the same issue above for the error:
RuntimeError: Could not establish path to dicom files. Have you specified the path option in the configuration file C:\Users\admin\pylidc.conf?
Iam using this code:
[dicom]
path = "C:/Users/admin/to/big_external_drive/datasets/LIDC-IDRI"
warn = True
from pylidc.
Jonas1312
commented on July 30, 2024
this pylidc.conf works for me:
[dicom]
path = D:\PhD Thesis\LIDC\LIDC-IDRItry with backslash and remove quotes
from pylidc.
VidhiBishnoi
commented on July 30, 2024
Hello,
I have mentioned the path in my pylidc.conf file :
path = C:\Users\admin\pylidc.conf
But now new error comes after running
vol = scan.to_volume()
print(vol.shape)
i.e:
RuntimeError: Couldn't find DICOM files for
Scan(id=1,patient_id=LIDC-IDRI-0078) in
C:\Users\admin\pylidc.conf\LIDC-IDRI-0078
plz help to findout
…On Tue, Oct 13, 2020 at 5:08 PM Jonas Maison ***@***.***> wrote:
this pylidc.conf works for me:
[dicom]
path = D:\PhD Thesis\LIDC\LIDC-IDRI
try with backslash and remove quotes
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFCYOGFX5TL7CQEJ2LWLSKQ33TANCNFSM4GXVNEWQ>
.
from pylidc.
Jonas1312
commented on July 30, 2024
[dicom]
path = C:\Users\admin\to\big_external_drive\datasets\LIDC-IDRI
put that in your pylidc.conf
from pylidc.
VidhiBishnoi
commented on July 30, 2024
Thank you..
Now how to call this .conf file in the main file? As iam coding as given in
pylidc documentation. Starting my code with:
import pylidc as pl
# Query for all CT scans with desired traits.
scans = pl.query(pl.Scan).filter(pl.Scan.slice_thickness <= 1,
pl.Scan.pixel_spacing <= 0.6)
print(scans.count())
# => 31
pid = 'LIDC-IDRI-0078'
scan = pl.query(pl.Scan).filter(pl.Scan.patient_id == pid).first()
till:
vol = scan.to_volume()
print(vol.shape)
but now the error is:
RuntimeError: Could not establish path to dicom files. Have you
specified the `path` option in the configuration file
C:\Users\admin\pylidc.conf?
Iam not able to find it? plz tell
…On Tue, Oct 13, 2020 at 5:42 PM Jonas Maison ***@***.***> wrote:
[dicom]
path = C:\Users\admin\to\big_external_drive\datasets\LIDC-IDRI
put that in your pylidc.conf
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFC6H5Z22QHYGV67R6JTSKQ72BANCNFSM4GXVNEWQ>
.
from pylidc.
notmatthancock
commented on July 30, 2024
This error means that the configuration file pylidc.conf exists, but the path to the DICOM data that you've specified in that file does not exist. It would be helpful if you posted the contents of your pylidc.conf file.
from pylidc.
VidhiBishnoi
commented on July 30, 2024
[dicom]
path = C:\Users\admin\to\big_external_drive\datasets\LIDC-IDRI
warn = True
These r the contents in my pylidc.conf file. My dataset is downloaded in E:
drive. As this file will itself locate the dataset from the system i think.
…On Tue, Oct 13, 2020 at 7:06 PM notmatthancock ***@***.***> wrote:
This error means that the pylidc.conf, but the path to the DICOM data
that you've specified in that file does not exist. It would be helpful if
you posted the contents of your pylidc.conf file.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFCY2FKALVK3NFQOHIMLSKRJWZANCNFSM4GXVNEWQ>
.
from pylidc.
notmatthancock
commented on July 30, 2024
path = C:\Users\admin\to\big_external_drive\datasets\LIDC-IDRI
This is a fake path. You need to replace this path with the actual path to the root folder of the LIDC data.
As this file will itself locate the dataset from the system i think.
I'm sorry, I don't understand what you mean. This file needs to be updated by you to point to the data. pylidc does not scan your system to discover the root data location automatically, if that's what you're suggesting.
from pylidc.
notmatthancock
commented on July 30, 2024
@VidhiBishnoi please read the guides here: https://pylidc.github.io/ If you still have questions about topics related to general usage (i.e., not related to this issue), then feel free to email me.
from pylidc.
VidhiBishnoi
commented on July 30, 2024
Thank you for helping..
Actually Iam trying to extract the nodule for other images today but got
stuck in a problem, hope you can help.
I followed the tutorial and achieved the same results for pid LIDC-Idri
0078 patient id. Now i changed the patient id to 0090 or other then iam
achieving the annotation image but after this when iam running the code
from :
ann = pl.query(pl.Annotation)\
.filter(pl.Annotation.malignancy == 5).first()
Iam getting the results of 0078 id that was taken as an example in tutorial.
kindly help me in this regard. Also how can we extract the nodule for
complete dataset?
regards
Vidhi Bishnoi
…On Tue, Oct 13, 2020 at 11:58 PM notmatthancock ***@***.***> wrote:
@VidhiBishnoi <https://github.com/VidhiBishnoi> please read the guides
here: https://pylidc.github.io/ If you still have questions about topics
related to general usage (i.e., not related to this issue), then feel free
to email me.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFC7Q5L44OLEDZKDKOYLSKSL4DANCNFSM4GXVNEWQ>
.
from pylidc.
Jonas1312
commented on July 30, 2024
scan = pl.query(pl.Scan).filter(pl.Scan.patient_id == "LIDC-IDRI-0090").first()
annotations = scan.annotations
ann = annotations[0]
mask_cropped = ann.boolean_mask()
bbox=ann.bbox()
mask = np.zeros(scan.to_volume().shape, dtype=np.bool)
mask[bbox] = mask_croppedfrom pylidc.
VidhiBishnoi
commented on July 30, 2024
Hello , Yes i have done it already and i can see the output of applied scan
by the code:
scan.visualize(annotation_groups=nods)
After this i need to extract the nodule for which iam using the following
code:
import pylidc as pl
import matplotlib.pyplot as plt
#ann = pl.query(pl.Annotation).first()
vol = ann.scan.to_volume()
padding = [(30,10), (10,25), (0,0)]
mask = ann.boolean_mask(pad=padding)
bbox = ann.bbox(pad=padding)
fig,ax = plt.subplots(1,2,figsize=(5,3))
ax[0].imshow(vol[bbox][:,:,2], cmap=plt.cm.gray)
ax[0].axis('off')
ax[1].imshow(mask[:,:,2], cmap=plt.cm.gray)
ax[1].axis('off')
plt.tight_layout()
#plt.savefig("../images/mask_bbox.png", bbox_inches="tight")
plt.show()
after running this iam getting the same output as of 0078 i.e the example
taken in tutorial and also the output of 0078 is coming after running code:
ann.visualize_in_scan() to visualize annotations.
I dont knw how its happening even if i have given different patient id as
scan.
plz help
…On Wed, Oct 14, 2020 at 6:30 PM Jonas Maison ***@***.***> wrote:
scan = pl.query(pl.Scan).filter(pl.Scan.patient_id == "LIDC-IDRI-0090").first()annotations = scan.annotationsann = annotations[0]mask_cropped = ann.boolean_mask()bbox=ann.bbox()mask = np.zeros(scan.to_volume().shape, dtype=np.bool)mask[bbox] = mask_cropped
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFC3D4OR7DD6NSGPKBMDSKWOG3ANCNFSM4GXVNEWQ>
.
from pylidc.
Jonas1312
commented on July 30, 2024
Give us the full code script (and use triple backticks to improve readability!)
```python
insert code here
```
from pylidc.
VidhiBishnoi
commented on July 30, 2024
kindly help me out..
from pylidc.
notmatthancock
commented on July 30, 2024
Hi @VidhiBishnoi like I mentioned already, a closed issue on an unrelated topic is not the avenue for this discussion.
If you are having a problem, then please open a separate issue that contains minimal steps to reproduce the issue you are experiencing, documenting the actual vs. expected results.
from pylidc.
VidhiBishnoi
commented on July 30, 2024
This issue iam getting while extracting nodule as I need to apply certain
machine learning techniques on the nodules extracted from this
dataset... that's why i asked..
Thank you
…On Wed, Oct 21, 2020 at 6:24 PM notmatthancock ***@***.***> wrote:
Hi @VidhiBishnoi <https://github.com/VidhiBishnoi> like I mentioned
already, a closed issue on an unrelated topic is not the avenue for this
discussion.
If you are having a problem, then please open a separate issue that
contains minimal steps to reproduce the issue you are experiencing,
documenting the actual vs. expected results.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKLHFCY6INCGMGYCJ5GQVC3SL3KXDANCNFSM4GXVNEWQ>
.
from pylidc.
Related Issues (20)
- How to access NBIA via pylidc HOT 1
- ValueError: The length of the pixel data in the dataset (524285 bytes) doesn't match the expected length (524288 bytes). HOT 5
- how to obtain the physical bbox? HOT 5
- Where to find pylidc.conf file in Google Colab? HOT 1
- Not able to do path configuration for pylidc on mac HOT 1
- RuntimeError: Could not establish path to dicom files. Have you specified the `path` option in the configuration file C:\Users\user\pylidc.conf? HOT 1
- marching_cubes_lewiner HOT 1
- Pylidc Annotation Class HOT 3
- 3D Annotation HOT 9
- OSError: Couldn't find DICOM files for Scan(id=12,patient_id=LIDC-IDRI-0001). HOT 6
- Showing patients with multiple nodules HOT 9
- module 'cmap_d' error
- RuntimeError: Could not establish path to dicom files in MacOS HOT 6
- Mismatching SeriesInstanceUID and StudyInstanceUID HOT 2
- Using populate.py
- AssertionError: Internal structure score out of bounds in Annotation(id=3761,scan_id=516)
- Annotation slice number HOT 2
- centroid to physical coordinates HOT 1
- Majorly slow dataloader using pylidc HOT 2
- Fix deprecated numpy dtype
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pylidc.