Deciphering Machine Learning Decisions to Distinguish between Posterior Fossa Tumor Types Using MRI Features: What Do the Data Tell Us?

ABSTRACT:

Simple Summary

This paper focuses on interpreting machine learning (ML) models’ decisions in medical diagnoses, specifically for four types of posterior fossa tumors in pediatric patients. The proposed methodology involves using kernel density estimations with Gaussian distributions to analyze individual MRI features, assess their relationships, and comprehensively study ML model behavior. The study demonstrates that employing a simplified approach in the absence of large datasets can lead to more pronounced and explainable outcomes. Furthermore, the pre-analysis results consistently align with the outputs of ML models and existing clinical findings. By bridging the knowledge gap between ML and medical outcomes, this research contributes to a better understanding of ML-based diagn

SUBMITTER: Tanyel T 

PROVIDER: S-EPMC10452543 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature