Continual Multiple Instance Learning for Hematologic Disease Diagnosis

TL;DR

This paper introduces the first continual learning method tailored for multiple instance learning, specifically designed for hematologic disease diagnosis, effectively adapting models to evolving data streams in clinical settings.

Contribution

It presents a novel rehearsal-based continual learning approach for MIL, addressing catastrophic forgetting in leukemia diagnosis models using real-world data.

Findings

Outperforms existing continual learning methods in leukemia diagnosis tasks

Successfully adapts to shifting data distributions over time

Preserves data diversity through selective sample and instance retention

Abstract

The dynamic environment of laboratories and clinics, with streams of data arriving on a daily basis, requires regular updates of trained machine learning models for consistent performance. Continual learning is supposed to help train models without catastrophic forgetting. However, state-of-the-art methods are ineffective for multiple instance learning (MIL), which is often used in single-cell-based hematologic disease diagnosis (e.g., leukemia detection). Here, we propose the first continual learning method tailored specifically to MIL. Our method is rehearsal-based over a selection of single instances from various bags. We use a combination of the instance attention score and distance from the bag mean and class mean vectors to carefully select which samples and instances to store in exemplary sets from previous tasks, preserving the diversity of the data. Using the real-world input of one month of data from a leukemia laboratory, we study the effectiveness of our approach in a class incremental scenario, comparing it to well-known continual learning methods. We show that our method considerably outperforms state-of-the-art methods, providing the first continual learning approach for MIL. This enables the adaptation of models to shifting data distributions over time, such as those caused by changes in disease occurrence or underlying genetic alterations.