We apply deep learning to the detection of mental illness with meaningful results, using SPECT (Single Photon Emission Computed Tomography) images of the brain. The data consists in scans from patients with attention deficit hyperactivity disorder (ADHD), major depressive disorder (MDD) and obsessive compulsive disorder (OCD), plus scans of healthy brains. We focus here on the application of a deep convolutional neural network (CNN). The main challenge in using CNN models for medical diagnosis is often the number of samples not being sufficiently large to ensure high accuracy. We propose a soft classifier for using the machine. Instead of a binary output “yes/no” for each condition, we add an intermediate outcome, which says that the machine yields a weak result. The “Red Zone” corresponds to a positive result (condition is present) and the “Green Zone” corresponds to a negative, each with a preassigned statistical confidence level; the “Amber Zone” is an ambiguous outcome, where the scan is assigned a likelihood of having the condition. This information is then passed to the doctors for further analysis of patients.

1. 1.

   Watson is a system developed by International Business Machines Corporation.

This work was partially supported by the CUNY Institute for Computer Simulation, Stochastic Modeling and Optimization.

Authors and Affiliations

1. Department of Computer Science, Hunter College CUNY, New York City, USA

   Felisa J. Vázquez-Abad & Silvano Bernabel

2. School of Computing and Information Systems, University of Melbourne, Melbourne, Australia

   Felisa J. Vázquez-Abad & Silvano Bernabel

3. Department of Mathematics and Statistics, Concordia University, Montreal, Canada

   Daniel Dufresne

4. Amen Clinics, New York, NY, USA

   Rishi Sood & Thomas Ward

5. Amen Clinics, Costa Mesa, CA, USA

   Daniel Amen

Corresponding author

Correspondence toDaniel Dufresne.

Editors and Affiliations

1. Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China

   Ruidan Su

2. Cardiff University, Cardiff, UK

   Han Liu

Reprints and permissions

© 2020 Springer Nature Singapore Pte Ltd.

Policies and ethics