Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma

HIGHLIGHTS

SUMMARY

In this paper, a DL model 3D ResNet was used to perform binary OS classification of patients with PCNSL. The authors investigated the power of DL models in OS classification of patients with PCNSL from MRI. From the performance results, the authors can say that T1Gd under TL learns better representation of PCNSL, while compared with ML-based models on clinical data and radiomics data, respectively. The authors obtained the largest AUC 0.81(0.03) from T1Gd under TL, meaning that T1Gd under TL is stable for different threshold and the model ranks . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or E-mail:

If you don't have an account, you can create one here.