DeepFEL: Deep Fastfood Ensemble Learning for Histopathology Image Analysis

TL;DR

DeepFEL introduces a rapid ensemble learning method that combines deep features from various CNN models using random projections, effectively addressing challenges in histopathology image analysis with fast training and high accuracy.

Contribution

The paper proposes Deep Fastfood Ensembles, a novel method that efficiently combines deep features via random projections for improved histopathology image analysis.

Findings

Outperforms state-of-the-art methods in three histopathology tasks

Offers fast training times suitable for domain-specific applications

Effective with limited and uncertain annotations

Abstract

Computational pathology tasks have some unique characterises such as multi-gigapixel images, tedious and frequently uncertain annotations, and unavailability of large number of cases [13]. To address some of these issues, we present Deep Fastfood Ensembles - a simple, fast and yet effective method for combining deep features pooled from popular CNN models pre-trained on totally different source domains (e.g., natural image objects) and projected onto diverse dimensions using random projections, the so-called Fastfood [11]. The final ensemble output is obtained by a consensus of simple individual classifiers, each of which is trained on a different collection of random basis vectors. This offers extremely fast and yet effective solution, especially when training times and domain labels are of the essence. We demonstrate the effectiveness of the proposed deep fastfood ensemble learning as compared to the state-of-the-art methods for three different tasks in histopathology image analysis.