Keywords: dental deep learning, multiple instance learning, interpretability, interactive learning
TL;DR: An interpretable deep multiple instance learning architecture shows competitive caries classification and localization performance on a large-scale bitewing dataset.
Abstract: We propose a simple and efficient image classification architecture based on deep multiple instance learning, and apply it to the challenging task of caries detection in dental radiographs. Technically, our approach contributes in two ways: First, it outputs a heatmap of local patch classification probabilities despite being trained with weak image-level labels. Second, it is amenable to learning from segmentation labels to guide training. In contrast to existing methods, the human user can faithfully interpret predictions and interact with the model to decide which regions to attend to. Experiments are conducted on a large clinical dataset of $\sim$38k bitewings ($\sim$316k teeth), where we achieve competitive performance compared to various baselines. When guided by an external caries segmentation model, a significant improvement in classification and localization performance is observed.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: both
Primary Subject Area: Detection and Diagnosis
Secondary Subject Area: Interpretability and Explainable AI
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
Code And Data: The code of the EMIL architecture can be found here: https://github.com/benbergner/emil Due to legal and data protection obligations the data cannot be made available.