From a5fbe1e7a819e2e802a07a4b9de8898893b338b6 Mon Sep 17 00:00:00 2001 From: neuronflow Date: Tue, 26 Nov 2024 15:04:43 +0100 Subject: [PATCH] rdme updates Signed-off-by: neuronflow --- README.md | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 3e54ad2..0e59e27 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) -Quality prediction for brain tumor segmentation on scale ranging from 1 ⭐ to 6 stars ⭐⭐⭐⭐⭐⭐. +Quality prediction for brain tumor segmentation on scale ranging from 1 ⭐ to 6 stars ⭐⭐⭐⭐⭐⭐ inspyred by the paper [**Deep Quality Estimation: Creating Surrogate Models for Human Quality Ratings**](https://arxiv.org/abs/2205.10355). Can be used to estimate the quality of a segmentation for evaluation purposes or as e.g. as part of a loss function during model training. > [!NOTE] @@ -16,6 +16,11 @@ Can be used to estimate the quality of a segmentation for evaluation purposes or > - `label 2` is the peritumoral edema > - `label 3` is the GD-enhancing tumor (used to be `label 4` in older data, both are supported) + +> [!NOTE] +The model here is not the original model presented in the paper. Instead it is trained on the individual radiologists' ratings. This way the model has a chance to learn the variance between radioligsts' estimates. It outperforms the model presented in the paper on the test set. + + ## Installation With a Python 3.9+ environment, you can install `deep_quality_estimation` directly from [PyPI](https://pypi.org/project/deep_quality_estimation/):