Constrained deep weak supervision for histopathology image segmentation
Open accessAbstract
In this paper, we develop a new weakly supervised learning algorithm to learn to segment cancerous regions in histopathology images. This paper is under a multiple instance learning (MIL) framework with a new formulation, deep weak supervision (DWS); we also propose an effective way to introduce constraints to our neural networks to assist the learning process. The contributions of our algorithm are threefold: 1) we build an end-to-end learning system that segments cancerous regions with fully convolutional networks (FCNs) in which image-to-image weakly-supervised learning is performed; 2) we develop a DWS formulation to exploit multi-scale learning under weak supervision within FCNs; and 3) constraints about positive instances are introduced in our approach to effectively explore additional weakly supervised information that is easy to obtain and enjoy a significant boost to the learning process. The proposed algorithm, abbreviated as DWS-MIL, is easy to implement and can be trained efficiently. Our system demonstrates the state-of-the-art results on large-scale histopathology image data sets and can be applied to various applications in medical imaging beyond histopathology images, such as MRI, CT, and ultrasound images.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Jia et al.'s method achieves a 6% improvement in F-measure around boundaries and 2% overall over the baseline without area constraints and multiple-level predictions.
“The improvement in F-measure over the baseline (without area constraints and multiple-level predictions) is 6% around the boundaries and 2% overall.”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Jia et al. (2017)
Jia et al. (2017) use a multiple instance learning approach to generate pixel-level predictions given only image-level cancer labels for histopathology images.
“Jia et al. (2017) use a multiple instance learning approach to generate pixel-level predictions given only image-level cancer labels for histopathology images.”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Jia et al. (2017)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 48 · Cited by 242
Research works printed but not linked: 14
- [11][11] Z. Tu, 'Auto-context and its application to high-level vision tasks,' in CVPR , 2008, pp. 1-8. -
- [14][14] C. Zhang, J. C. Platt, and P. A. Viola, 'Multiple instance boosting for object detection,' in NIPS , 2005, pp. 1417-1424. -
- [15][15] O. Maron and A. L. Ratan, 'Multiple-instance learning for natural scene classification,' in ICML , 1998, pp. 341-349. -
- [19][19] Y. Xu, J. Zhu, E. Chang, and Z. Tu, 'Multiple clustered instance learning for histopathology cancer image classification, segmentation and clustering,' in CVPR , 2012, pp. 964-971. -
- [20][20] Y. Xu, J. Zhang, E. Chang, M. Lai, and Z. Tu, 'Contexts-constrained multiple instance learning for histopathology image analysis,' in MICCAI , 2012, pp. 623-630. -
- [21][21] S. Andrews, I. Tsochantaridis, and T. Hofmann, 'Support vector machines for multiple-instance learning,' in NIPS , 2002, pp. 561-568. -
- [22][22] O. Maron and T. Lozano-P´ erez, 'A framework for multiple-instance learning,' in NIPS , 1998, pp. 570-576. -
- [24][24] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, 'Semantic image segmentation with deep convolutional nets and fully connected crfs,' in ICLR , 2015. -
- [26][26] D. Pathak, E. Shelhamer, J. Long, and T. Darrell, 'Fully convolutional multi-class multiple instance learning,' in ICLR , 2014. -
- [27][27] C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, 'Deeply-supervised nets,' in AISTATS , 2015. -
- [32][32] X. Wang, B. Wang, X. Bai, W. Liu, and Z. Tu, 'Max-margin multiple instance dictionary learning,' in ICML , 2013, pp. 846-854. -
- [37][37] A. Diba, V. Sharma, A. Pazandeh, H. Pirsiavash, and L. Van Gool, 'Weakly supervised cascaded convolutional networks,' arXiv preprint arXiv:1611.08258 , 2016. - · arXiv
- [40][40] K. Simonyan and A. Zisserman, 'Very deep convolutional networks for large-scale image recognition,' in ICLR , 2015. -
- [44][44] D. Kingma and J. Ba, 'Adam: A method for stochastic optimization,' in ICLR , 2015.
- Authors
- Jia, Z., Huang, X., Chang, E. I.-C., & Xu, Y.
- Affiliations
- Microsoft Research Asia (China) (CN)
- State Key Laboratory of Software Development Environment (CN)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2017-11
- Volume
- 36
- Issue
- 11
- Pages
- 2376-2388
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2583578793
- Cited by
- 242
- References
- 48
- Citations by year
- 2026: 8 · 2025: 17 · 2024: 20 · 2023: 37 · 2022: 40 · 2021: 38 · 2020: 40 · 2019: 29 · 2018: 11 · 2017: 2
- FWCI
- 13.38
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Microsoft Research through the eHealth Program
- Beijing National Science Foundation in China (4152033)
- Technology and Innovation Commission of Shenzhen in China (shenfagai2016-627)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- histopathology image segmentation, multiple instance learning, fully convolutional network, multi-scale learning, constraint learning, weakly supervised learning, medical image segmentation
- MeSH terms
- Supervised Machine Learning, Algorithms, Colon, Colonic Neoplasms, Histocytochemistry, Humans, Image Processing, Computer-Assisted, Databases, Factual, Neural Networks, Computer, Tissue Array Analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
