Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
120 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation (2207.06799v4)

Published 14 Jul 2022 in cs.CV

Abstract: Ovarian cancer is one of the most harmful gynecological diseases. Detecting ovarian tumors in early stage with computer-aided techniques can efficiently decrease the mortality rate. With the improvement of medical treatment standard, ultrasound images are widely applied in clinical treatment. However, recent notable methods mainly focus on single-modality ultrasound ovarian tumor segmentation or recognition, which means there still lacks researches on exploring the representation capability of multi-modality ultrasound ovarian tumor images. To solve this problem, we propose a Multi-Modality Ovarian Tumor Ultrasound (MMOTU) image dataset containing 1469 2d ultrasound images and 170 contrast enhanced ultrasonography (CEUS) images with pixel-wise and global-wise annotations. Based on MMOTU, we mainly focus on unsupervised cross-domain semantic segmentation task. To solve the domain shift problem, we propose a feature alignment based architecture named Dual-Scheme Domain-Selected Network (DS2Net). Specifically, we first design source-encoder and target-encoder to extract two-style features of source and target images. Then, we propose Domain-Distinct Selected Module (DDSM) and Domain-Universal Selected Module (DUSM) to extract the distinct and universal features in two styles (source-style or target-style). Finally, we fuse these two kinds of features and feed them into the source-decoder and target-decoder to generate final predictions. Extensive comparison experiments and analysis on MMOTU image dataset show that DS2Net can boost the segmentation performance for bidirectional cross-domain adaptation of 2d ultrasound images and CEUS images. Our proposed dataset and code are all available at https://github.com/cv516Buaa/MMOTU_DS2Net.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Skip-scse multi-scale attention and co-learning method for oropharyngeal tumor segmentation on multi-modal PET-CT images, in: HECKTOR 2021, Held in Conjunction with MICCAI 2021, pp. 109–120.
  2. Swin-unet: Unet-like pure transformer for medical image segmentation. CoRR abs/2105.05537.
  3. Disentangle, align and fuse for multimodal and semi-supervised image segmentation. IEEE Trans. Medical Imaging 40, 781–792.
  4. Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation. IEEE Trans. Medical Imaging 39, 2494–2505.
  5. Robust multimodal brain tumor segmentation via feature disentanglement and gated fusion, in: Medical Image Computing and Computer Assisted Intervention, pp. 447–456.
  6. Transunet: Transformers make strong encoders for medical image segmentation. CoRR abs/2102.04306. URL: https://arxiv.org/abs/2102.04306.
  7. Feature fusion encoder decoder network for automatic liver lesion segmentation, in: International Symposium on Biomedical Imaging, pp. 430–433.
  8. Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J. Digit. Imaging 30, 477–486.
  9. Imagenet: A large-scale hierarchical image database, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255.
  10. An image is worth 16x16 words: Transformers for image recognition at scale, in: International Conference on Learning Representations.
  11. Pnp-adanet: Plug-and-play adversarial domain adaptation network at unpaired cross-modality cardiac segmentation. IEEE Access 7, 99065–99076.
  12. SSF-DAN: separated semantic feature based domain adaptation network for semantic segmentation, in: IEEE International Conference on Computer Vision, pp. 982–991.
  13. Dual attention network for scene segmentation, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146–3154.
  14. Deep residual learning for image recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778.
  15. Multi-modal retinal image classification with modality-specific attention network. IEEE Trans. Medical Imaging 40, 1591–1602.
  16. Cycada: Cycle-consistent adversarial domain adaptation, in: International Conference on Machine Learning, pp. 1994–2003.
  17. Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation, in: IEEE Conference on Computer Vision and Pattern Recognition, IEEE. pp. 9914–9925.
  18. Densely connected convolutional networks, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261–2269.
  19. Image-to-image translation with conditional adversarial networks, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5967–5976.
  20. Focusnet: An attention-based fully convolutional network for medical image segmentation, in: International Symposium on Biomedical Imaging, pp. 455–458.
  21. Unsupervised deep consistency learning adaptation network for cardiac cross-modality structural segmentation. Medical & biological engineering & computing .
  22. Cr-unet: A composite network for ovary and follicle segmentation in ultrasound images. IEEE J. Biomed. Health Informatics 24, 974–983.
  23. Medical image segmentation using squeeze-and-expansion transformers, in: International Joint Conference on Artificial Intelligence, pp. 807–815.
  24. Maxformer: Enhanced transformer for medical image segmentation with multi-attention and multi-scale features fusion. Knowledge-Based Systems 280, 110987.
  25. Swin transformer: Hierarchical vision transformer using shifted windows, in: IEEE International Conference on Computer Vision, pp. 9992–10002.
  26. Deep learning based quantification of ovary and follicles using 3d transvaginal ultrasound in assisted reproduction, in: International Conference of the Engineering in Medicine & Biology Society, pp. 2109–2112.
  27. Automated ovarian volume quantification in transvaginal ultrasound, in: International Symposium on Biomedical Imaging, pp. 1513–1516.
  28. Attention u-net: Learning where to look for the pancreas. CoRR abs/1804.03999.
  29. Data efficient unsupervised domain adaptation for cross-modality image segmentation, in: Medical Image Computing and Computer Assisted Intervention, pp. 669–677.
  30. 3dq: Compact quantized neural networks for volumetric whole brain segmentation, in: Medical Image Computing and Computer Assisted Intervention, pp. 438–446.
  31. Disentangle domain features for cross-modality cardiac image segmentation. Medical Image Anal. 71, 102078.
  32. HASA: hybrid architecture search with aggregation strategy for echinococcosis classification and ovary segmentation in ultrasound images. CoRR abs/2204.06697.
  33. U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention, pp. 234–241.
  34. Mobilenetv2: Inverted residuals and linear bottlenecks, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520.
  35. Cancer statistics, 2021. CA: A Cancer Journal for Clinicians 71.
  36. Very deep convolutional networks for large-scale image recognition, in: International Conference on Learning Representations.
  37. Efficientnet: Rethinking model scaling for convolutional neural networks, in: International Conference on Machine Learning, pp. 6105–6114.
  38. Efficientnetv2: Smaller models and faster training, in: International Conference on Machine Learning, pp. 6105–6114.
  39. Learning to adapt structured output space for semantic segmentation, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7472–7481.
  40. Multi-modal learning from unpaired images: Application to multi-organ segmentation in CT and MRI, in: IEEE Winter Conference on Applications of Computer Vision, pp. 547–556.
  41. End-to-end ovarian structures segmentation, in: Progress in Pattern Recognition, Image Analysis, Computer Vision and Applications, pp. 681–689.
  42. Application of deep convolutional neural networks for discriminating benign, borderline, and malignant serous ovarian tumors from ultrasound images. Frontiers in Oncology 11.
  43. Edrl: Entropy-guided disentangled representation learning for unsupervised domain adaptation in semantic segmentation. Computer methods and programs in biomedicine 240, 107729.
  44. Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans. Medical Imaging 38, 2485–2495.
  45. Ovarian tumor texture classification based on sparse auto-encoder network combined with multi-feature fusion and random forest in ultrasound image. J. Medical Imaging Health Informatics 11, 424–431.
  46. Non-local u-nets for biomedical image segmentation, in: AAAI Conference on Artificial Intelligence, pp. 6315–6322.
  47. Deep learning for ovarian tumor classification with ultrasound images, in: Advances in Multimedia Information Processing PCM, pp. 395–406.
  48. CF distance: A new domain discrepancy metric and application to explicit domain adaptation for cross-modality cardiac image segmentation. IEEE Trans. Medical Imaging 39, 4274–4285.
  49. Ctranscnn: Combining transformer and cnn in multilabel medical image classification. Knowledge-Based Systems 281, 111030.
  50. Segformer: Simple and efficient design for semantic segmentation with transformers, in: Advances in Neural Information Processing Systems, pp. 12077–12090.
  51. Unsupervised domain adaptation via disentangled representations: Application to cross-modality liver segmentation, in: Medical Image Computing and Computer Assisted Intervention, pp. 255–263.
  52. Ucunet: A lightweight and precise medical image segmentation network based on efficient large kernel u-shaped convolutional module design. Knowledge-Based Systems 278, 110868.
  53. Contrastive rendering with semi-supervised learning for ovary and follicle segmentation from 3d ultrasound. Medical Image Anal. 73, 102134.
  54. Bisenet V2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vis. 129, 3051–3068.
  55. Free-form image inpainting with gated convolution, in: IEEE International Conference on Computer Vision, pp. 4471–4480.
  56. Semantic consistent unsupervised domain adaptation for cross-modality medical image segmentation, in: Medical Image Computing and Computer Assisted Intervention, pp. 201–210.
  57. Entropy guided unsupervised domain adaptation for cross-center hip cartilage segmentation from MRI, in: Medical Image Computing and Computer Assisted Intervention, pp. 447–456.
  58. Segmenting medical images via explicit–implicit attention aggregation. Knowledge-Based Systems 279, 110932.
  59. From whole slide imaging to microscopy: Deep microscopy adaptation network for histopathology cancer image classification, in: Medical Image Computing and Computer Assisted Intervention, pp. 360–368.
  60. Transfuse: Fusing transformers and cnns for medical image segmentation, in: Medical Image Computing and Computer Assisted Intervention, pp. 14–24.
  61. Pyramid scene parsing network, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6230–6239.
  62. Unet++: A nested u-net architecture for medical image segmentation, in: Deep Learning in Medical Image Analysis - and - Multimodal Learning for Clinical Decision Support, pp. 3–11.
  63. Unpaired image-to-image translation using cycle-consistent adversarial networks, in: IEEE International Conference on Computer Vision, pp. 2242–2251.
  64. Dsi-net: Deep synergistic interaction network for joint classification and segmentation with endoscope images. IEEE Trans. Medical Imaging 40, 3315–3325.
  65. Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Medical Image Anal. 31, 77–87.
  66. Unsupervised domain adaptation with dual-scheme fusion network for medical image segmentation, in: International Joint Conference on Artificial Intelligence, pp. 3291–3298.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - cv516Buaa/MMOTU_DS2Net (25 stars)