# Improving Pediatric Low-Grade Neuroepithelial Tumors Molecular Subtype Identification Using a Novel AUROC Loss Function for Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2402.03547 · HTML: https://mlsanity.com/paper/2402.03547/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 4 of 4)

- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [A Modified AUC for Training Convolutional Neural Networks: Taking Confidence into Account](https://mlsanity.com/paper/2006.04836/) (2020)
- [Evolution-based Fine-tuning of CNNs for Prostate Cancer Detection](https://mlsanity.com/paper/1911.01477/) (2019)
- [Improving Deep Learning Models for Pediatric Low-Grade Glioma Tumors Molecular Subtype Identification Using 3D Probability Distributions of Tumor Location](https://mlsanity.com/paper/2210.07287/) (2022)

## Built on by (most cited first, 1 of 1)

- [Tumor Location-weighted MRI-Report Contrastive Learning: A Framework for Improving the Explainability of Pediatric Brain Tumor Diagnosis](https://mlsanity.com/paper/2411.00609/) (2024)

## Abstract (arXiv)

Pediatric Low-Grade Neuroepithelial Tumors (PLGNT) are the most common pediatric cancer type, accounting for 40% of brain tumors in children, and identifying PLGNT molecular subtype is crucial for treatment planning. However, the gold standard to determine the PLGNT subtype is biopsy, which can be impractical or dangerous for patients. This research improves the performance of Convolutional Neural Networks (CNNs) in classifying PLGNT subtypes through MRI scans by introducing a loss function that specifically improves the model's Area Under the Receiver Operating Characteristic (ROC) Curve (AUROC), offering a non-invasive diagnostic alternative. In this study, a retrospective dataset of 339 children with PLGNT (143 BRAF fusion, 71 with BRAF V600E mutation, and 125 non-BRAF) was curated. We employed a CNN model with Monte Carlo random data splitting. The baseline model was trained using binary cross entropy (BCE), and achieved an AUROC of 86.11% for differentiating BRAF fusion and BRAF V600E mutations, which was improved to 87.71% using our proposed AUROC loss function (p-value 0.045). With multiclass classification, the AUROC improved from 74.42% to 76. 59% (p-value 0.0016).