TriadNet: Sampling-free predictive intervals for lesional volume in 3D brain MR images
This addresses the need for reliable uncertainty quantification in clinical lesion volume segmentation, though it is incremental as it builds on existing CNN methods.
The paper tackled the problem of providing predictive intervals for brain lesion volume estimation from 3D MRI images, proposing TriadNet, which delivers both volume and intervals in under a second and demonstrated superiority on the BraTS 2021 dataset.
The volume of a brain lesion (e.g. infarct or tumor) is a powerful indicator of patient prognosis and can be used to guide the therapeutic strategy. Lesional volume estimation is usually performed by segmentation with deep convolutional neural networks (CNN), currently the state-of-the-art approach. However, to date, few work has been done to equip volume segmentation tools with adequate quantitative predictive intervals, which can hinder their usefulness and acceptation in clinical practice. In this work, we propose TriadNet, a segmentation approach relying on a multi-head CNN architecture, which provides both the lesion volumes and the associated predictive intervals simultaneously, in less than a second. We demonstrate its superiority over other solutions on BraTS 2021, a large-scale MRI glioblastoma image database.