Dear TotalSegmentator Team,
Thank you for releasing the updated TotalSegmentator V2 software. I am a Master’s student in medical science, currently focused on the quantitative analysis of micro-CT images in a rabbit model.
I’m wondering if TotalSegmentator V2 is compatible with rabbit micro-CT images, specifically for lung segmentation?
Thank you for your time and assistance.
Best regards
Dear rbumm,
Thank you for your prompt reply. I have also tried LungCTSegmenter for lung segmentation for in micro-CT images, but the results are not satisfactory.
Could you possible have any recommendations or suggestions that might improve the quality of the lung segmentation using micro-CT images?
Best
I would love to be wrong, but my understanding is without retraining or at the minimum finetuning them using your own segmented data, there is not much you can do with models trained on human clinical dataset.
Maybe this link may help:
Thanks dear rbumm. LungCT Segmenter works for the micro-CT images after changing the parameter from 2 to 0.2. but the result is not satisfied.
Is this by manual placement of the segmentation seeds or by AI segmentation? Can you make a CT sample available?
Bot the manual seeds and AI work well for the Chest CT sample. My previous try was segmented by AI. Here is the manual placement seeds. The result still not good. And there is no change after placing more seeds on missing area.
Dear rbumm,
After processing Lung CT Analyzer using the lung segmentation generated, I’ve got some color ball in the image. I don’t think the colour balls affect the statistics results.
I agree with @muratmaga on this:
without retraining or at the minimum finetuning them using your own segmented data, there is not much you can do with models trained on human clinical dataset.
@cong_lu have you considered training an AI model for this task using MONAI Label?
Here I showed how to organize the dataset and train a model: https://youtu.be/-HAryYAO5J4?si=uxJPxrDuTDUE-zHr&t=560
thanks for your suggestion. I’d like to use MONAI Label to train an AI model. I don’t have much experience in programming. I cannot understand the command part in your video. And I got the ERROR from MONAI Label when I start the module. Could you kindly guide me to solve the issue?
Traceback (most recent call last):
File “/Applications/Slicer.app/Contents/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabel.py”, line 1072, in fetchInfo
info = self.logic.info()
File “/Applications/Slicer.app/Contents/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabel.py”, line 2263, in info
return self._client().info()
File “/Applications/Slicer.app/Contents/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabel.py”, line 2239, in _client
if mc.auth_enabled():
File “/Applications/Slicer.app/Contents/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabelLib/client.py”, line 83, in auth_enabled
status, response, _, _ = MONAILabelUtils.http_method(“GET”, self._server_url, selector)
File “/Applications/Slicer.app/Contents/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabelLib/client.py”, line 521, in http_method
conn.request(method, selector, body=body, headers=headers)
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/http/client.py”, line 1285, in request
self._send_request(method, url, body, headers, encode_chunked)
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/http/client.py”, line 1331, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/http/client.py”, line 1280, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/http/client.py”, line 1040, in _send_output
self.send(msg)
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/http/client.py”, line 980, in send
self.connect()
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/http/client.py”, line 946, in connect
self.sock = self._create_connection(
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/socket.py”, line 844, in create_connection
raise err
File “/Applications/Slicer.app/Contents/lib/Python/lib/python3.9/socket.py”, line 832, in create_connection
sock.connect(sa)
ConnectionRefusedError: [Errno 61] Connection refused
Hi @cong_lu,
MONAI Label comprises two parts: a server that hosts the AI models and a viewer part that connects to the server (i.e. 3DSlicer).
The server part can be installed and started following these instructions: GitHub - Project-MONAI/MONAILabel: MONAI Label is an intelligent open source image labeling and learning tool.
Unfortunately, the server part is being tested on Linux and Windows operating systems, not Apple OSs
I hope this helps,
Thank you @diazandr3s for your reply. I’ll find a Windows PC and try to install the server. I’ve no experience with Python, which is a big challenge. I’ll keep you update.
Hello @diazandr3s ,
monailabel-0.8.1 was successfully installed, but I was stuck in downloading sample apps. Could you help me check the message from cmd?
