OpenNDD: Open Set Recognition for Neurodevelopmental Disorders Detection

TL;DR

This paper introduces OpenNDD, a novel open set recognition framework combining autoencoder and adversarial learning to improve autism spectrum disorder diagnosis amidst similar neurodevelopmental disorders, effectively distinguishing known and unknown classes.

Contribution

The paper proposes a new open set recognition method for NDD diagnosis that enhances class distinction using joint scaling and adversarial reciprocal points learning.

Findings

Achieves 77.38% accuracy in ASD detection

Attains 75.53% AUROC, indicating strong discriminative ability

Reaches 59.43% open set classification rate, effectively identifying unknown NDDs

Abstract

Since the strong comorbid similarity in NDDs, such as attention-deficit hyperactivity disorder, can interfere with the accurate diagnosis of autism spectrum disorder (ASD), identifying unknown classes is extremely crucial and challenging from NDDs. We design a novel open set recognition framework for ASD-aided diagnosis (OpenNDD), which trains a model by combining autoencoder and adversarial reciprocal points learning to distinguish in-distribution and out-of-distribution categories as well as identify ASD accurately. Considering the strong similarities between NDDs, we present a joint scaling method by Min-Max scaling combined with Standardization (MMS) to increase the differences between classes for better distinguishing unknown NDDs. We conduct the experiments in the hybrid datasets from Autism Brain Imaging Data Exchange I (ABIDE I) and THE ADHD-200 SAMPLE (ADHD-200) with 791 samples from four sites and the results demonstrate the superiority on various metrics. Our OpenNDD achieves promising performance, where the accuracy is 77.38%, AUROC is 75.53% and the open set classification rate is as high as 59.43%.