MLOps for Scarce Image Data: A Use Case in Microscopic Image Analysis

TL;DR

This paper explores applying MLOps to microscopic image analysis with scarce data, proposing a holistic approach that includes fingerprinting, automation, and continuous monitoring to improve model robustness and adaptability.

Contribution

It introduces a comprehensive MLOps framework tailored for scarce biomedical image data, integrating fingerprinting, automation, and continuous learning strategies.

Findings

Proof of concept for fingerprinting in microscopic datasets

Enhanced model selection for scarce data scenarios

Initial validation of continuous deployment in biomedical imaging

Abstract

Nowadays, Machine Learning (ML) is experiencing tremendous popularity that has never been seen before. The operationalization of ML models is governed by a set of concepts and methods referred to as Machine Learning Operations (MLOps). Nevertheless, researchers, as well as professionals, often focus more on the automation aspect and neglect the continuous deployment and monitoring aspects of MLOps. As a result, there is a lack of continuous learning through the flow of feedback from production to development, causing unexpected model deterioration over time due to concept drifts, particularly when dealing with scarce data. This work explores the complete application of MLOps in the context of scarce data analysis. The paper proposes a new holistic approach to enhance biomedical image analysis. Our method includes: a fingerprinting process that enables selecting the best models, datasets, and model development strategy relative to the image analysis task at hand; an automated model development stage; and a continuous deployment and monitoring process to ensure continuous learning. For preliminary results, we perform a proof of concept for fingerprinting in microscopic image datasets.