mlsanityData to 14 Oct 2026

Improving Prostate Gland Segmentation Using Transformer based Architectures

arXiv 2506.14844 ↗First posted 16 Jun 2025eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Inter reader variability and cross site domain shift challenge the automatic segmentation of prostate anatomy using T2 weighted MRI images. This study investigates whether transformer models can retain precision amid such heterogeneity. We compare the performance of UNETR and SwinUNETR in prostate gland segmentation against our previous 3D UNet model [1], based on 546 MRI (T2weighted) volumes annotated by two independent experts. Three training strategies were analyzed: single cohort dataset, 5 fold cross validated mixed cohort, and gland size based dataset. Hyperparameters were tuned by Optuna. The test set, from an independent population of readers, served as the evaluation endpoint (Dice Similarity Coefficient). In single reader training, SwinUNETR achieved an average dice score of 0.816 for Reader#1 and 0.860 for Reader#2, while UNETR scored 0.8 and 0.833 for Readers #1 and #2, respectively, compared to the baseline UNets 0.825 for Reader #1 and 0.851 for Reader #2. SwinUNETR had an average dice score of 0.8583 for Reader#1 and 0.867 for Reader#2 in cross-validated mixed training. For the gland size-based dataset, SwinUNETR achieved an average dice score of 0.902 for Reader#1 subset and 0.894 for Reader#2, using the five-fold mixed training strategy (Reader#1, n=53; Reader#2, n=87) at larger gland size-based subsets, where UNETR performed poorly. Our findings demonstrate that global and shifted-window self-attention effectively reduces label noise and class imbalance sensitivity, resulting in improvements in the Dice score over CNNs by up to five points while maintaining computational efficiency. This contributes to the high robustness of SwinUNETR for clinical deployment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

18 of 44 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  4. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  5. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  6. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  7. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
  8. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  9. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  10. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  11. 2022UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentationcited by 112
  12. 2025Your ViT is Secretly an Image Segmentation Modelcited by 63
6 more
  1. 2024A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentationscited by 40
  2. 2022TFCNs: A CNN-Transformer Hybrid Network for Medical Image Segmentationcited by 18
  3. 2024BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentationcited by 11
  4. 2022ConvFormer: Combining CNN and Transformer for Medical Image Segmentationcited by 10
  5. 2018Fully Automated Organ Segmentation in Male Pelvic CT Imagescited by 6
  6. 2024D-TrAttUnet: Toward Hybrid CNN-Transformer Architecture for Generic and Subtle Segmentation in Medical Imagescited by 2

Built on by

Not cited yet.