SpotNet - Learned iterations for cell detection in image-based immunoassays

TL;DR

SpotNet is a learned iterative method for cell detection in immunoassay images that outperforms traditional CNNs in accuracy and training ease by capturing underlying physical process patterns.

Contribution

The paper introduces SpotNet, a parameterized computation graph that learns iteration patterns for improved cell detection in immunoassays, outperforming CNNs.

Findings

SpotNet achieves higher detection accuracy than CNNs.

SpotNet is easier to train than traditional iterative methods.

Both methods outperform human experts on synthetic data.

Abstract

Accurate cell detection and counting in the image-based ELISpot and FluoroSpot immunoassays is a challenging task. Recently proposed methodology matches human accuracy by leveraging knowledge of the underlying physical process of these assays and using proximal optimization methods to solve an inverse problem. Nonetheless, thousands of computationally expensive iterations are often needed to reach a near-optimal solution. In this paper, we exploit the structure of the iterations to design a parameterized computation graph, SpotNet, that learns the patterns embedded within several training images and their respective cell information. Further, we compare SpotNet to a convolutional neural network layout customized for cell detection. We show empirical evidence that, while both designs obtain a detection performance on synthetic data far beyond that of a human expert, SpotNet is easier to train and obtains better estimates of particle secretion for each cell.