SSI-GAN: Semi-Supervised Swin-Inspired Generative Adversarial Networks for Neuronal Spike Classification

TL;DR

This paper introduces SSI-GAN, a semi-supervised GAN architecture inspired by Swin transformers, capable of classifying neuronal spike patterns with minimal labeled data, achieving high accuracy in detecting viral infections.

Contribution

The paper presents a novel semi-supervised GAN with a Swin-inspired discriminator and transformer generator for neuronal spike classification, reducing labeling effort significantly.

Findings

Achieved 99.93% accuracy with only 3% labeled data on infection classification.

Reduced manual labeling effort by 97-99% compared to supervised methods.

Outperformed all baseline models with a new state-of-the-art in spike-based infection detection.

Abstract

Mosquitos are the main transmissive agents of arboviral diseases. Manual classification of their neuronal spike patterns is very labor-intensive and expensive. Most available deep learning solutions require fully labeled spike datasets and highly preprocessed neuronal signals. This reduces the feasibility of mass adoption in actual field scenarios. To address the scarcity of labeled data problems, we propose a new Generative Adversarial Network (GAN) architecture that we call the Semi-supervised Swin-Inspired GAN (SSI-GAN). The Swin-inspired, shifted-window discriminator, together with a transformer-based generator, is used to classify neuronal spike trains and, consequently, detect viral neurotropism. We use a multi-head self-attention model in a flat, window-based transformer discriminator that learns to capture sparser high-frequency spike features. Using just 1 to 3% labeled data, SSI-GAN was trained with more than 15 million spike samples collected at five-time post-infection and recording classification into Zika-infected, dengue-infected, or uninfected categories. Hyperparameters were optimized using the Bayesian Optuna framework, and performance for robustness was validated under fivefold Monte Carlo cross-validation. SSI-GAN reached 99.93% classification accuracy on the third day post-infection with only 3% labeled data. It maintained high accuracy across all stages of infection with just 1% supervision. This shows a 97-99% reduction in manual labeling effort relative to standard supervised approaches at the same performance level. The shifted-window transformer design proposed here beat all baselines by a wide margin and set new best marks in spike-based neuronal infection classification.