Machine learning-based pathomics signature of histology slides as a novel prognostic indicator in primary central nervous system lymphoma

1

Primary central nervous system lymphoma (PCNSL) is a rare and aggressive lymphoma affecting the brain and spinal cord, with a poor overall survival rate.
2

Current prognostic models for PCNSL, such as IELSG and MSKCC, have limitations and do not adequately predict survival outcomes.
3

A novel pathomics score (Path-score) was developed using machine learning to analyze histological features from H&E-stained slides in PCNSL patients.
4

The Path-score demonstrated a significant correlation with initial treatment response and outperformed existing prognostic models.
5

A nomogram combining the Path-score and clinical characteristics was constructed to enhance outcome prediction for PCNSL patients.

Journal Of Neuro-Oncology

by Ling Duan, Yongqi He, Wenhui Guo, Yanru Du, Shuo Yin, Shoubo Yang, Gehong Dong, Wenbin Li, Feng Chen
April 1, 2024

1