Papers
Topics
Authors
Recent
Search
2000 character limit reached

CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations

Published 1 Dec 2023 in cs.CV and cs.LG | (2312.00671v1)

Abstract: In recent years, several unsupervised cell segmentation methods have been presented, trying to omit the requirement of laborious pixel-level annotations for the training of a cell segmentation model. Most if not all of these methods handle the instance segmentation task by focusing on the detection of different cell instances ignoring their type. While such models prove adequate for certain tasks, like cell counting, other applications require the identification of each cell's type. In this paper, we present CellMixer, an innovative annotation-free approach for the semantic segmentation of heterogeneous cell populations. Our augmentation-based method enables the training of a segmentation model from image-level labels of homogeneous cell populations. Our results show that CellMixer can achieve competitive segmentation performance across multiple cell types and imaging modalities, demonstrating the method's scalability and potential for broader applications in medical imaging, cellular biology, and diagnostics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (8)
  1. Saliency and ballness driven deep learning framework for cell segmentation in bright field microscopic images. Engineering Applications of Artificial Intelligence, 118:105704, 2023. ISSN 0952-1976. doi: https://doi.org/10.1016/j.engappai.2022.105704. URL https://www.sciencedirect.com/science/article/pii/S0952197622006947.
  2. U-net: deep learning for cell counting, detection, and morphometry. Nature Methods, 16(1):67–70, Jan 2019. ISSN 1548-7105. doi: 10.1038/s41592-018-0261-2. URL https://doi.org/10.1038/s41592-018-0261-2.
  3. Unsupervised network learning for cell segmentation. In Marleen de Bruijne, Philippe C. Cattin, Stéphane Cotin, Nicolas Padoy, Stefanie Speidel, Yefeng Zheng, and Caroline Essert, editors, Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, pages 282–292, Cham, 2021. Springer International Publishing. ISBN 978-3-030-87193-2.
  4. Unsupervised cell segmentation in fluorescence microscopy images via self-supervised learning. In Mounîm El Yacoubi, Eric Granger, Pong Chi Yuen, Umapada Pal, and Nicole Vincent, editors, Pattern Recognition and Artificial Intelligence, pages 236–247, Cham, 2022. Springer International Publishing. ISBN 978-3-031-09037-0.
  5. Automated training of deep convolutional neural networks for cell segmentation. Scientific Reports, 7(1):7860, Aug 2017. ISSN 2045-2322. doi: 10.1038/s41598-017-07599-6. URL https://doi.org/10.1038/s41598-017-07599-6.
  6. A deep network designed for segmentation and classification of leukemia using fusion of the transfer learning models. Complex & Intelligent Systems, 8(4):3105–3120, Aug 2022. ISSN 2198-6053. doi: 10.1007/s40747-021-00473-z. URL https://doi.org/10.1007/s40747-021-00473-z.
  7. Segmenter: Transformer for semantic segmentation. In ICCV, pages 7242–7252. IEEE, 2021.
  8. mixup: Beyond empirical risk minimization. In ICLR (Poster). OpenReview.net, 2018.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.