alexts1980 / covid-ct-mask-net Goto Github PK
View Code? Open in Web Editor NEWSegmentation and Classification models for COVID CT scans (COVID, pneumonia, normal) based on Mask R-CNN.
Home Page: https://github.com/AlexTS1980/COVID-CT-Mask-Net
Segmentation and Classification models for COVID CT scans (COVID, pneumonia, normal) based on Mask R-CNN.
Home Page: https://github.com/AlexTS1980/COVID-CT-Mask-Net
is the VOC style mask work with overlapped instance ground truth? (lungs and lesion)
I want to inquire about the dataset usage mentioned in your GitHub statement. In your statement, you mentioned, "We trained it on the CNCB CT images with masks ((http://ncov-ai.big.ac.cn/download, Experiment data files): 500 training and 150 for testing taken from COVID-positive patients, but some slices have no lesions."
I would like to know which specific dataset from the website was used for training. Is it from the COVID19-1.zip to COVID19-31.zip dataset? As shown in the figure below.
Thank you for your time and consideration.
Hi, thanks a lot for your nice work. I followed your instruction and repeated your great results.
However, with my DICOM files, I tried a few conversions but none of them worked. The result is very poor. Do you have an idea of how to read the DICOM file to have a meaningful result?
Question 1: I would like to try to run the reference_segmentation.py file, but the following error occurs "RuntimeError: Can't call numpy() on Tensor that requires grad. use tensor.detach(). numpy() instead.". As shown in the image below.
Then I modified ax.add_patch(rect) to ax.add_patch(rect.detach().numpy()). But new error "AttributeError: 'Rectangle' object has no attribute 'detach'" appears.
I would like to ask how to solve this problem. The image format I am using is png.
Question 2: While segmenting the CT images, I found that there is a corresponding tasks file in both test and train datasets. How is that masks file obtained?
I would like to ask if the data name of the test set will be announced
can the model work with conventional X-rays?
Hello,
May I ask, how you generated mask results? I think the dataset annotation does not provide a mask? Thanks.
Hello, I would like to reproduce the segmentation capabilities of your work, do you have available weights to run your prediction exactly with the result of your training you published? Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.