Brain Tumor Segmentation with Uncertainty Estimation and Overall Survival Prediction

Feng, Xue; Quan, Dou; Tustison, Nicholas J.; Meyer, Craig H.

doi:10.1007/978-3-030-46640-4_29

“…We have used four predictors and parameter tuning. These are (1) Artificial Neural Network (ANN) [9,10], (2) Linear Regressor (LR) [7,8], (3) Gradient Boosting Regressor (GBR) [10], and (4) Random Forest Regressor (RFR) [6,15,10]. All these predictors were used by the top performing models in all recent BraTS challenges.…”

Section: Predictors and Parameter Tuningmentioning

confidence: 99%

“…Image-based features [8,9] Shape features extracted from the segmentation were used in the OS prediction. These features were volume of the WT, TC, and ET, surface area of the WT, TC, and ET, age.…”

Section: Prognosis Using Featuresmentioning

confidence: 99%

“…The proposed paper aims to establish the correlation between handcrafted features and overall survival prediction. Unlike the existing state-of-the-art methods used for survival prediction [6], [7], [8], [9], the paper uses four predictors and two feature sets to establish their correlation with overall survival prediction of High Grade Glioma (HGG) patients. Shape features and gradient boosting regressors achieve better survival prediction accuracy than state-of-the-art methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Glioblastoma Multiforme Patient Survival Prediction

Rajput¹,

Agravat²,

Roy³

et al. 2021

Preprint

2

1

0

View full text Add to dashboard Cite

Glioblastoma Multiforme is a very aggressive type of brain tumor. Due to spatial and temporal intra-tissue inhomogeneity, location and the extent of the cancer tissue, it is difficult to detect and dissect the tumor regions. In this paper, we propose survival prognosis models using four regressors operating on handcrafted image-based and radiomics features. We hypothesize that the radiomics shape features have the highest correlation with survival prediction. The proposed approaches were assessed on the Brain Tumor Segmentation (BraTS-2020) challenge dataset. The highest accuracy of image features with random forest regressor approach was 51.5\% for the training and 51.7\% for the validation dataset. The gradient boosting regressor with shape features gave an accuracy of 91.5\% and 62.1\% on training and validation datasets respectively. It is better than the BraTS 2020 survival prediction challenge winners on the training and validation datasets. Our work shows that handcrafted features exhibit a strong correlation with survival prediction. The consensus based regressor with gradient boosting and radiomics shape features is the best combination for survival prediction.

show abstract

“…Recent methods [2,3,4,5,6] employed for OS time prediction follow a pre-hoc pipeline [7] that consists of two stages. In the first stage, tumors are segmented into the following tissues: necrotic, edema tumor or enhancing tumor.…”

Section: Introductionmentioning

confidence: 99%

Post-Hoc Overall Survival Time Prediction From Brain MRI

Hermoza

¹

,

Maicas

²

,

Nascimento

³

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Overall survival (OS) time prediction is one of the most common estimates of the prognosis of gliomas and is used to design an appropriate treatment planning. State-of-the-art (SOTA) methods for OS time prediction follow a pre-hoc approach that require computing the segmentation map of the glioma tumor sub-regions (necrotic, edema tumor, enhancing tumor) for estimating OS time. However, the training of the segmentation methods require ground truth segmentation labels which are tedious and expensive to obtain. Given that most of the large-scale data sets available from hospitals are unlikely to contain such precise segmentation, those SOTA methods have limited applicability. In this paper, we introduce a new post-hoc method for OS time prediction that does not require segmentation map annotation for training. Our model uses medical image and patient demographics (represented by age) as inputs to estimate the OS time and to estimate a saliency map that localizes the tumor as a way to explain the OS time prediction in a post-hoc manner. It is worth emphasizing that although our model can localize tumors, it uses only the ground truth OS time as training signal, i.e., no segmentation labels are needed. We evaluate our post-hoc method on the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019 data set and show that it achieves competitive results compared to prehoc methods with the advantage of not requiring segmentation labels for training. We make our code available at https://github.com/renato145/posthocOS.

show abstract

“…The accuracy for survival prediction was 0.59 and 0.56 for BraTS-2019 validation and test dataset respectively. Feng et al [8] used an ensemble of U-Net models. The models were trained on patches having brain pixels.…”

Section: Introductionmentioning

confidence: 99%

Glioblastoma Multiforme Patient Survival Prediction

Rajput¹,

Agravat²,

Roy³

et al. 2021

Preprint

View full text Add to dashboard Cite

Glioblastoma Multiforme is a very aggressive type of brain tumor. Due to spatial and temporal intra-tissue inhomogeneity, location and the extent of the cancer tissue, it is difficult to detect and dissect the tumor regions. In this paper, we propose survival prognosis models using four regressors operating on handcrafted image-based and radiomics features. We hypothesize that the radiomics shape features have the highest correlation with survival prediction. The proposed approaches were assessed on the Brain Tumor Segmentation (BraTS-2020) challenge dataset. The highest accuracy of image features with random forest regressor approach was 51.5\% for the training and 51.7\% for the validation dataset. The gradient boosting regressor with shape features gave an accuracy of 91.5\% and 62.1\% on training and validation datasets respectively. It is better than the BraTS 2020 survival prediction challenge winners on the training and validation datasets. Our work shows that handcrafted features exhibit a strong correlation with survival prediction. The consensus based regressor with gradient boosting and radiomics shape features is the best combination for survival prediction.

show abstract

Brain Tumor Segmentation with Uncertainty Estimation and Overall Survival Prediction

Cited by 18 publications

References 10 publications

Glioblastoma Multiforme Patient Survival Prediction

Glioblastoma Multiforme Patient Survival Prediction

Post-Hoc Overall Survival Time Prediction From Brain MRI

Glioblastoma Multiforme Patient Survival Prediction

Contact Info

Product

Resources

About