Update README.md
Browse files
README.md
CHANGED
|
@@ -7,22 +7,20 @@ tags:
|
|
| 7 |
library_name: fastMONAI
|
| 8 |
---
|
| 9 |
# Endometrial cancer segmentation
|
| 10 |
-
|
| 11 |
This repository contains weights and exported learner (encapsulates both the model architecture and its trained parameters) for a deep learning model designed to automate the segmentation of endometrial cancer on MR images.
|
| 12 |
Our VIBE model utilizes a Residual U-Net architecture, trained on data derived from the study [Automated segmentation of endometrial cancer on MR images using deep learning](https://link.springer.com/content/pdf/10.1038/s41598-020-80068-9.pdf).
|
| 13 |
The primary objective of this repository is to reproduce the results reported in the study. In addition, we have looked at improving the segmentation performance using multi-sequence MR images (T2w, VIBE, and ADC) as reported in the study [Automatic segmentation of uterine endometrial cancer on multi-sequence MRI using a convolutional neural network](https://www.nature.com/articles/s41598-021-93792-7).
|
| 14 |
|
| 15 |
## Requirements
|
| 16 |
-
|
| 17 |
Last checked and validated with fastMONAI version 0.3.9. Please ensure that you have the correct version of fastMONAI installed to guarantee the correct operation of the model.
|
| 18 |
|
| 19 |
## Usage
|
| 20 |
-
|
| 21 |
The source code for training the model and running inference on your own data is available at: https://github.com/MMIV-ML/fastMONAI/tree/master/research/endometrial_cancer.
|
|
|
|
| 22 |
|
| 23 |
## Results for VIBE
|
| 24 |
The box plot of the predictions on the validation set:
|
| 25 |
-
|
| 26 |
|
| 27 |
The results from the validation set are also presented in the table below:
|
| 28 |
|
|
@@ -64,7 +62,7 @@ The results from the validation set are also presented in the table below:
|
|
| 64 |
|
| 65 |
## Results for multi-sequence (T2, VIBE, and ADC)
|
| 66 |
The box plot of the predictions on the validation set:
|
| 67 |
-
 for a deep learning model designed to automate the segmentation of endometrial cancer on MR images.
|
| 11 |
Our VIBE model utilizes a Residual U-Net architecture, trained on data derived from the study [Automated segmentation of endometrial cancer on MR images using deep learning](https://link.springer.com/content/pdf/10.1038/s41598-020-80068-9.pdf).
|
| 12 |
The primary objective of this repository is to reproduce the results reported in the study. In addition, we have looked at improving the segmentation performance using multi-sequence MR images (T2w, VIBE, and ADC) as reported in the study [Automatic segmentation of uterine endometrial cancer on multi-sequence MRI using a convolutional neural network](https://www.nature.com/articles/s41598-021-93792-7).
|
| 13 |
|
| 14 |
## Requirements
|
|
|
|
| 15 |
Last checked and validated with fastMONAI version 0.3.9. Please ensure that you have the correct version of fastMONAI installed to guarantee the correct operation of the model.
|
| 16 |
|
| 17 |
## Usage
|
|
|
|
| 18 |
The source code for training the model and running inference on your own data is available at: https://github.com/MMIV-ML/fastMONAI/tree/master/research/endometrial_cancer.
|
| 19 |
+
Test our model live with the Gradio app for VIBE on [Hugging Face Spaces](https://skaliy-endometrial-cancer-segmentation-app.hf.space).
|
| 20 |
|
| 21 |
## Results for VIBE
|
| 22 |
The box plot of the predictions on the validation set:
|
| 23 |
+
|
| 24 |
|
| 25 |
The results from the validation set are also presented in the table below:
|
| 26 |
|
|
|
|
| 62 |
|
| 63 |
## Results for multi-sequence (T2, VIBE, and ADC)
|
| 64 |
The box plot of the predictions on the validation set:
|
| 65 |
+
|
| 66 |
|
| 67 |
The results from the validation set are also presented in the table below:
|
| 68 |
|