mlsanityData to 14 Oct 2026

Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone-beam CT

arXiv 2210.14297 ↗First posted 25 Oct 2022eess.IV cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Method: ProRSeg was trained using 5-fold cross-validation with 110 T2-weighted MRI acquired at 5 treatment fractions from 10 different patients, taking care that same patient scans were not placed in training and testing folds. Segmentation accuracy was measured using Dice similarity coefficient (DSC) and Hausdorff distance at 95th percentile (HD95). Registration consistency was measured using coefficient of variation (CV) in displacement of OARs. Ablation tests and accuracy comparisons against multiple methods were done. Finally, applicability of ProRSeg to segment cone-beam CT (CBCT) scans was evaluated on 80 scans using 5-fold cross-validation. Results: ProRSeg processed 3D volumes (128 × 192 × 128) in 3 secs on a NVIDIA Tesla V100 GPU. It's segmentations were significantly more accurate (p<0.001) than compared methods, achieving a DSC of 0.94 ±0.02 for liver, 0.88±0.04 for large bowel, 0.78±0.03 for small bowel and 0.82±0.04 for stomach-duodenum from MRI. ProRSeg achieved a DSC of 0.72±0.01 for small bowel and 0.76±0.03 for stomach-duodenum from CBCT. ProRSeg registrations resulted in the lowest CV in displacement (stomach-duodenum CVx: 0.75%, CVy: 0.73%, and CVz: 0.81%; small bowel CVx: 0.80%, CVy: 0.80%, and CVz: 0.68%; large bowel CVx: 0.71%, CVy : 0.81%, and CVz: 0.75%). ProRSeg based dose accumulation accounting for intra-fraction (pre-treatment to post-treatment MRI scan) and inter-fraction motion showed that the organ dose constraints were violated in 4 patients for stomach-duodenum and for 3 patients for small bowel. Study limitations include lack of independent testing and ground truth phantom datasets to measure dose accumulation accuracy.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 25 Oct 2022.

Builds on

18 of 43 references.

References · 18

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  3. 2015Spatial Transformer Networkscited by 1,429
  4. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  5. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  6. 2019Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfacescited by 186
  7. 2018A Deep Learning Framework for Unsupervised Affine and Deformable Image Registrationcited by 160
  8. 2020Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networkscited by 107
  9. 2019Recursive Cascaded Networks for Unsupervised Medical Image Registrationcited by 105
  10. 2019DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentationcited by 66
  11. 2022Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)cited by 35
  12. 2018Multi-Scale Coarse-to-Fine Segmentation for Screening Pancreatic Ductal Adenocarcinomacited by 24
6 more
  1. 2020Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Imagescited by 17
  2. 2019Recurrent Registration Neural Networks for Deformable Image Registrationcited by 11
  3. 2019Fully Automated Multi-Organ Segmentation in Abdominal Magnetic Resonance Imaging with Deep Neural Networkscited by 8
  4. 2021Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registrationcited by 8
  5. 2022One shot PACS: Patient specific Anatomic Context and Shape prior aware recurrent registration-segmentation of longitudinal thoracic cone beam CTscited by 8
  6. 2020A Cross-Stitch Architecture for Joint Registration and Segmentation in Adaptive Radiotherapycited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 2; 2026: 1.

5 papers.

  1. 2023SegReg: Segmenting OARs by Registering MR Images and CT Annotationscited by 16
  2. 2024Deep Learning for Pancreas Segmentation: a Systematic Reviewcited by 4
  3. 2025Modality-agnostic, patient-specific digital twins modeling temporally varying digestive motioncited by 0
  4. 2025Segmentation Regularized Training for Multi-Domain Deep Learning Registration applied to MR-Guided Prostate Cancer Radiotherapycited by 0
  5. 2026Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopycited by 0