Task Fingerprinting for Meta Learning in Biomedical Image Analysis

TL;DR

This paper introduces task fingerprinting, a method to quantify task similarity in biomedical image analysis, facilitating meta learning by enabling better task selection and transfer learning across diverse datasets.

Contribution

The paper proposes a novel task fingerprinting approach that converts tasks into fixed-length vectors, allowing direct comparison regardless of dataset size or label type, advancing meta learning in biomedical imaging.

Findings

Feasibility demonstrated with 26 classification tasks in surgical data science

Task fingerprinting aids in dataset selection for pretraining

Task fingerprinting helps in choosing suitable architectures for new tasks

Abstract

Shortage of annotated data is one of the greatest bottlenecks in biomedical image analysis. Meta learning studies how learning systems can increase in efficiency through experience and could thus evolve as an important concept to overcome data sparsity. However, the core capability of meta learning-based approaches is the identification of similar previous tasks given a new task - a challenge largely unexplored in the biomedical imaging domain. In this paper, we address the problem of quantifying task similarity with a concept that we refer to as task fingerprinting. The concept involves converting a given task, represented by imaging data and corresponding labels, to a fixed-length vector representation. In fingerprint space, different tasks can be directly compared irrespective of their data set sizes, types of labels or specific resolutions. An initial feasibility study in the field of surgical data science (SDS) with 26 classification tasks from various medical and non-medical domains suggests that task fingerprinting could be leveraged for both (1) selecting appropriate data sets for pretraining and (2) selecting appropriate architectures for a new task. Task fingerprinting could thus become an important tool for meta learning in SDS and other fields of biomedical image analysis.