Reducing Annotation Need in Self-Explanatory Models for Lung Nodule Diagnosis
This addresses the annotation burden for medical imaging researchers and clinicians, though it is incremental as it builds on existing self-explanatory methods.
The paper tackles the problem of high annotation costs in self-explanatory models for lung nodule diagnosis by proposing cRedAnno, which reduces annotation need to 1% while achieving competitive malignancy prediction accuracy and surpassing previous works in predicting nodule attributes.
Feature-based self-explanatory methods explain their classification in terms of human-understandable features. In the medical imaging community, this semantic matching of clinical knowledge adds significantly to the trustworthiness of the AI. However, the cost of additional annotation of features remains a pressing issue. We address this problem by proposing cRedAnno, a data-/annotation-efficient self-explanatory approach for lung nodule diagnosis. cRedAnno considerably reduces the annotation need by introducing self-supervised contrastive learning to alleviate the burden of learning most parameters from annotation, replacing end-to-end training with two-stage training. When training with hundreds of nodule samples and only 1% of their annotations, cRedAnno achieves competitive accuracy in predicting malignancy, meanwhile significantly surpassing most previous works in predicting nodule attributes. Visualisation of the learned space further indicates that the correlation between the clustering of malignancy and nodule attributes coincides with clinical knowledge. Our complete code is open-source available: https://github.com/diku-dk/credanno.