Modality-Independent Explainable Detection of Inaccurate Organ Segmentations Using Denoising Autoencoders
This addresses the risk of suboptimal treatment delivery in radiation therapy by providing explainable detection of segmentation errors, though it is incremental as it builds on existing autoencoder techniques.
The paper tackled the problem of detecting inaccurate organ segmentations in radiation therapy planning by developing a denoising autoencoder-based method, which achieved superior performance for most organs compared to existing approaches.
In radiation therapy planning, inaccurate segmentations of organs at risk can result in suboptimal treatment delivery, if left undetected by the clinician. To address this challenge, we developed a denoising autoencoder-based method to detect inaccurate organ segmentations. We applied noise to ground truth organ segmentations, and the autoencoders were tasked to denoise them. Through the application of our method to organ segmentations generated on both MR and CT scans, we demonstrated that the method is independent of imaging modality. By providing reconstructions, our method offers visual information about inaccurate regions of the organ segmentations, leading to more explainable detection of suboptimal segmentations. We compared our method to existing approaches in the literature and demonstrated that it achieved superior performance for the majority of organs.