The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
HeMIS: Hetero-Modal Image Segmentation
Abstract
We introduce a deep learning image segmentation framework that is extremely robust to missing imaging modalities. Instead of attempting to impute or synthesize missing data, the proposed approach learns, for each modality, an embedding of the input image into a single latent vector space for which arithmetic operations (such as taking the mean) are well defined. Points in that space, which are averaged over modalities available at inference time, can then be further processed to yield the desired segmentation. As such, any combinatorial subset of available modalities can be provided as input, without having to learn a combinatorial number of imputation models. Evaluated on two neurological MRI datasets (brain tumors and MS lesions), the approach yields state-of-the-art segmentation results when provided with all modalities; moreover, its performance degrades remarkably gracefully when modalities are removed, significantly more so than alternative mean-filling or other synthesis approaches.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The current state-of-the-art network architecture which allows for missing modalities is HeMIS [3] and related extensions [12].”
From Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation (2019) · cites this paper as [3]
In the citing paper
“Our model outperforms the current state-of-the-art method for dealing with missing modalities and achieves similar performance to the subset-specific equivalent networks.”
From Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation (2019) · cites this paper as [3]
In the citing paper
“The first, HeMIS is the model described in [3] and is the current state-of-the-art for segmentation with missing modalities.”
From Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation (2019) · cites this paper as [3]
In the citing paper
“In this case, each modality are independently encoded and averaged such as HeMIS.”
From Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation (2019) · cites this paper as [3]
Citations
Cites
(2016) · Cited by 11,679
Self-citationThe multimodal brain tumor image segmentation benchmark (BRATS)
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2377694 · Cited by 6,781 · cited 6×
“There are no ground truth provided for these datasets and thus quantitative evaluation can be achieved via an online evaluation system [13].”
MethodInfluentialFlexible Imputation of Missing Data
van Buuren, S. (2012) · doi:10.1201/b11826 · Cited by 2,022 · cited 1×
“it is common to have one or more modalities to be missing for a given instance. This problem is not new, and the subject of missing data analysis has spawned an immense literature in statistics (e.g. [22]). In medical imaging, a number of approaches have been proposed, some of which require to re-train a specic model…”
BackgroundHofmann, M., Steinke, F., Scheel, V., Charpiat, G., Farquhar, J., Aschoff, P., Brady, M., Schölkopf, B., & Pichler, B. J. (2008) · Journal of Nuclear Medicine · doi:10.2967/jnumed.107.049353 · Cited by 495 · cited 1×
“In medical imaging, a number of approaches have been proposed, some of which require to re-train a specific model with the missing modalities or to synthesize them [9].”
BackgroundTustison, N. J., Shrinidhi, K. L., Wintermark, M., Durst, C. R., Kandel, B. M., Gee, J. C., Grossman, M. C., & Avants, B. B. (2015) · Neuroinformatics · doi:10.1007/s12021-014-9245-2 · Cited by 277 · cited 1×
“[21], the winner of the BRATS 2013 challenge, on most tumor region categories.”
BackgroundDeep Convolutional Encoder Networks for Multiple Sclerosis Lesion Segmentation
Brosch, T., Yoo, Y., Tang, L. Y. W., Li, D. K. B., Traboulsee, A. L., & Tam, R. C. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_1 · Cited by 127
An Automatic Segmentation of T2-FLAIR Multiple Sclerosis Lesions
Souplet, J.-C., Lebrun‐Frénay, C., Ayache, N., & Malandain, G. (2008) · doi:10.54294/6eyg0w · Cited by 115
Why Does Synthesized Data Improve Multi-sequence Classification?
van Tulder, G., & de Bruijne, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24553-9_65 · Cited by 111
Rotation-invariant multi-contrast non-local means for MS lesion segmentation
Guizard, N., Coupé, P., Fonov, V., Manjón, J. V., Arnold, D. L., & Collins, D. L. (2015) · NeuroImage Clinical · doi:10.1016/j.nicl.2015.05.001 · Cited by 85 · cited 1×
“…shown excellent results in structural segmentation when using non-linear registration [11]; when combined with non-local approaches they have proven effective in segmenting diffuse and sparse pathologies (ie. multiple sclerosis (MS) lesions [7]) as well as more complex multi-label pathology (ie.”
BackgroundSelf-citationSpatially Adaptive Random Forests
Geremia, E., Menze, B. H., & Ayache, N. (2013) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2013.6556781 · Cited by 60 · cited 2×
“(FPR) and the method’s score as in [18]. Method Rater VD (%) SD (mm) TPR (%) FPR (%) Score CHB 86.4 8.4 58.2 70.6 Souplet et al. [16] 80.0 UNC 57.9 7.5 49.1 76.3 CHB 52.4 5.4 59.0 71.5 Geremia et al. [5] 82.1 UNC 45.0 5.7 51.2 76.7 CHB 63.5 7.4 47.1 52.7 Brosch et al. [2] 84.0 UNC 52.0 6.4 56.0 49.8 CHB 127.4 7.5 66.1…”
BackgroundInfluential
Research works printed but not linked: 2
- Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.M., Larochelle, H.: Brain tumor segmentation with deep neural networks. arXiv preprint (2015). arXiv:1505.03540 · arXiv
- Styner, M., Lee, J., Chin, B., Chin, M., Commowick, O., Tran, H., Markovic-Plese, S., Jewells, V., Warfield, S.: 3D segmentation in the clinic: A grand challenge ii: Ms lesion segmentation. MIDAS 2008, 1–6 (2008)
Cited by
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.369 · Cited by 4,616
“Recent notable work includes (but do not limit to) an overview review on the future promise of deep learning [14] and a collection of important medical applications on lymph node and interstitial lung disease detection and classification [36, 42]; cerebral microbleed detection [11]; pulmonary nodule detection in CT im…”
BackgroundBakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R. T., Berger, C., Ha, S. M., Rozycki, M., et al. (2018) · Apollo - University of Cambridge Repository · doi:10.17863/cam.38755 · Cited by 1,441
“Alternative research directions include the enhancement of the flexibility of DL systems that might lack a given set of input images [139], as a transition measure towards worldwide adoption of the standardization initiatives for GBM imaging [140].”
BackgroundBakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R. T., Berger, C., Ha, S. M., Rozycki, M., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.02629 · Cited by 1,441
A review on deep learning in medical image analysis
Suganyadevi, S., Seethalakshmi, V., & Balasamy, K. (2022) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-021-00218-1 · Cited by 653
“The k-nearest neighbours algorithm is a classic example, where the transductive algorithm uses it directly each time a prediction is required, instead of modelling the training data [3, 47, 72].”
Background
Metadata
- Authors
- Havaei, M., Guizard, N., Chapados, N., & Bengio, Y.
- Affiliations
- Université de Montréal (CA)
- Corresponding author
- Havaei, Mohammad
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2016
- Pages
- 469-477
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2502805798
- Semantic Scholar
- 1a07daa88a366c10afa80cbdf63ad1b5d0759d1e
- Cited by
- 332
- References
- 13
- Citations by year
- 2026: 44 · 2025: 51 · 2024: 52 · 2023: 45 · 2022: 20 · 2021: 37 · 2020: 25 · 2019: 25 · 2018: 21 · 2017: 10 · 2016: 2
- FWCI
- 6.83
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Brain Tumor Detection and Classification
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- missing modalities, multimodal MRI, missing data robustness, brain tumor segmentation, multiple sclerosis lesion segmentation
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: HeMIS: Hetero-Modal Image Segmentation. https://app.cochat.ai/papers/10.1007/978-3-319-46723-8_54
- The paper
- Havaei, M., Guizard, N., Chapados, N., & Bengio, Y. (2016). HeMIS: Hetero-Modal Image Segmentation. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-46723-8_54
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.