Anatomically consistent CNN-based segmentation of organs-at-risk in cranial radiotherapy

Abstract

Planning of radiotherapy involves accurate segmentation of a large number of organs at risk, i.e. organs for which irradiation doses should be minimized to avoid important side effects of the therapy. We propose a deep learning method for segmentation of organs at risk inside the brain region, from Magnetic Resonance (MR) images. Our system performs segmentation of eight structures: eye, lens, optic nerve, optic chiasm, pituitary gland, hippocampus, brainstem and brain. We propose an efficient algorithm to train neural networks for an end-to-end segmentation of multiple and nonexclusive classes, addressing problems related to computational costs and missing ground truth segmentations for a subset of classes. We enforce anatomical consistency of the result in a postprocessing step, in particular we introduce a graph-based algorithm for segmentation of the optic nerves, enforcing the connectivity between the eyes and the optic chiasm. We report cross-validated quantitative results on a database of 44 contrast-enhanced T1-weighted MRIs with provided segmentations of the considered organs at risk, which were originally used for radiotherapy planning. In addition, the segmentations produced by our model on an independent test set of 50 MRIs are evaluated by an experienced radiotherapist in order to qualitatively assess their accuracy. The mean distances between produced segmentations and the ground truth ranged from 0.1 mm to 0.7 mm across different organs. A vast majority (96 %) of the produced segmentations were found acceptable for radiotherapy planning.

Generating High-Quality Lymph Node Clinical Target Volumes for Head and Neck Cancer Radiation Therapy Using a Fully Automated Deep Learning-Based Approach

“…19,20 Researchers have used these networks to autosegment many anatomic sites using computed tomography, magnetic resonance imaging, positron emission tomography, x-rays, and ultrasound images resulting in rapid development and quick translation to the field of radiation oncology. Several studies have focused on normal tissue [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36] and CTV [37][38][39][40] autosegmentation for HNC radiation therapy. In previous deep learning-based CTV autosegmentation work, researchers developed algorithms to autodelineate targets based on their risk (high-risk 37,38 or low-risk 37,39,40 CTVs) but lacked the ability to autodelineate individual lymph node levels.…”

Head and neck multi‐organ auto‐segmentation on CT images aided by synthetic MRI

“…Several planning studies have underlined the benefit of incorporating MR images in the planning process to delineate tumor and OARs, by significantly improving the imaging contrast compared to CT 21–24 . In the domain of MRI‐based HN organ automatic segmentation, there have been several studies on the single organ segmentation such as parotid 25 and multi‐organs including brainstem, eyes, lens, optic nerves, chiasm, and brain 26 . Promising segmentation results in terms of DSC can be found in the MRI‐based organ segmentation.…”

A Fully Automated Deep Learning-based Network For Detecting COVID-19 from a New And Large Lung CT Scan Dataset

“…Machine Vision has been a superior method for advancing many fields like Agriculture [21], biomedical engineering [23,19], industry [13] and others. Implementation of machine vision methods on the deep neural networks, especially using the convolution layers, has resulted in extremely accurate performing.…”