mlsanityData to 7 Oct 2026

OARnet: Automated organs-at-risk delineation in Head and Neck CT images

arXiv 2108.13987 ↗First posted 31 Aug 2021eess.IV cs.CV physics.med-phcited by 0

Not on the map. Why?

Abstract (arXiv)

A 3D deep learning model (OARnet) is developed and used to delineate 28 H&N OARs on CT images. OARnet utilizes a densely connected network to detect the OAR bounding-box, then delineates the OAR within the box. It reuses information from any layer to subsequent layers and uses skip connections to combine information from different dense block levels to progressively improve delineation accuracy. Training uses up to 28 expert manual delineated (MD) OARs from 165 CTs. Dice similarity coefficient (DSC) and the 95th percentile Hausdorff distance (HD95) with respect to MD is assessed for 70 other CTs. Mean, maximum, and root-mean-square dose differences with respect to MD are assessed for 56 of the 70 CTs. OARnet is compared with UaNet, AnatomyNet, and Multi-Atlas Segmentation (MAS). Wilcoxon signed-rank tests using 95% confidence intervals are used to assess significance. Wilcoxon signed ranked tests show that, compared with UaNet, OARnet improves (p<0.05) the DSC (23/28 OARs) and HD95 (17/28). OARnet outperforms both AnatomyNet and MAS for DSC (28/28) and HD95 (27/28). Compared with UaNet, OARnet improves median DSC up to 0.05 and HD95 up to 1.5mm. Compared with AnatomyNet and MAS, OARnet improves median (DSC, HD95) by up to (0.08, 2.7mm) and (0.17, 6.3mm). Dosimetrically, OARnet outperforms UaNet (Dmax 7/28; Dmean 10/28), AnatomyNet (Dmax 21/28; Dmean 24/28), and MAS (Dmax 22/28; Dmean 21/28). The DenseNet architecture is optimized using a hybrid approach that performs OAR-specific bounding box detection followed by feature recognition. Compared with other auto-delineation methods, OARnet is better than or equal to UaNet for all but one geometric (Temporal Lobe L, HD95) and one dosimetric (Eye L, mean dose) endpoint for the 28 H&N OARs, and is better than or equal to both AnatomyNet and MAS for all OARs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 60 references that are in the map. First posted on arXiv 31 Aug 2021.

Builds on

11 of 60 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2015Fast R-CNNcited by 2,930
  6. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  7. 2018AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomycited by 54
  8. 2018An application of cascaded 3D fully convolutional networks for medical image segmentationcited by 34
  9. 2017Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNetscited by 32
  10. 20173D Densely Convolutional Networks for Volumetric Segmentationcited by 9
  11. 2018Organ at Risk Segmentation in Head and Neck CT Images by Using a Two-Stage Segmentation Framework Based on 3D U-Netcited by 9

Built on by

Not cited yet.