Novel Deep Learning Methodology for Automated Classification of Adamantinomatous Craniopharyngioma Using a Small Radiographic Dataset

Abstract

Modern Deep Learning (DL) networks routinely achieve classification accuracy superior to human experts, leveraging scenarios with vast amounts of training data. Community focus has now seen a shift towards the design of accurate classifiers for scenarios with limited training data. Such an example is the uncommon pediatric brain tumor, Adamantinomatous Craniopharyngioma (ACP). Recent work has demonstrated the efficacy of Transfer Learning (TL) and novel loss functions for the training of DL networks in limited data scenarios. This work describes a DL approach utilizing TL and a state-of-the-art custom loss function for predicting ACP diagnosis from radiographic data, achieving performance (CT AUPR=0.99+/-0.01, MRI AUPR=0.99+/-0.02) superior to reported human performance (0.87).

Application of Artificial Intelligence in Diagnosis of Craniopharyngioma

“…(4) Prince et al ( 29 ) tried adopting deep learning to identify craniopharyngiomas. The imaging data were obtained via Children's Hospital in Colorado.…”

“…Baid et al ( 92 ) segmented glioma images with a 3D-UNET network. Prince et al ( 29 ) adopted the long short-term memory (LSTM) network to realize the non-invasive diagnosis of adamantinomatous craniopharyngioma.…”