Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images

TL;DR

The paper introduces SISSI, a semi-supervised method that iteratively corrects imperfect labels in microscopy image object detection, improving accuracy without manual annotation.

Contribution

SISSI is a novel semi-supervised approach that corrects noisy labels iteratively and uses synthetic-like images to enhance object detection in microscopy images.

Findings

Achieves >15% AP improvement over standard semi-supervised methods.

Achieves >20% AR improvement across three different readers.

Effective in correcting imperfect labels without manual annotation.

Abstract

In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Detecting cells as a first step, a cell expert evaluates the growth of cells according to cytotoxicity grade under the microscope. Thus, human fatigue plays a role in error making, making the use of deep learning appealing. Due to the high cost of training data annotation, an approach without manual annotation is needed. We propose Seamless Iterative Semi-Supervised correction of Imperfect labels (SISSI), a new method for training object detection models with noisy and missing annotations in a semi-supervised fashion. Our network learns from noisy labels generated with simple image processing algorithms, which are iteratively corrected during self-training. Due to the nature of missing bounding boxes in the pseudo labels, which would negatively affect the training, we propose to train on dynamically generated synthetic-like images using seamless cloning. Our method successfully provides an adaptive early learning correction technique for object detection. The combination of early learning correction that has been applied in classification and semantic segmentation before and synthetic-like image generation proves to be more effective than the usual semi-supervised approach by > 15% AP and > 20% AR across three different readers. Our code is available at https://github.com/marwankefah/SISSI.