CoChat
Sign Up
Cited by 107Radiomics and Machine Learning in Medical ImagingGlioma Diagnosis and TreatmentMachine Learning in Healthcare

Deep Orthogonal Fusion: Multimodal Prognostic Biomarker Discovery Integrating Radiology, Pathology, Genomic, and Clinical Data

Open access
Braman, Nathaniel, Gordon, Jacob W. H., Goossens, Emery T., Willis, Caleb, Stumpe, Martin C., Venkataraman, Jagadish·2021·Lecture Notes in Computer Science
DOI 10.1007/978-3-030-87240-3_64
Open this paper in CoChat — free accountOpen PDF

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-030-87240-3_64

Cites

5 of 5 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • When datasets encompass as many as four distinct modalities, this allows extensive investigations on the effects of missing data, model uncertainty, and model explainability with various data modalities.

    “When datasets encompass as many as four distinct modalities (i.e. CT imaging, pathology slides, genomic data and text data), as seen in the TCGA-GBM dataset (The Cancer Genome Atlas Glioblastoma Multiforme Collection), this allows extensive investigations on the effects of missing data, model uncertainty, and model explainability with various data modalities (Cui et al., 2022b; Braman et al., 2021”

    From Navigating the landscape of multimodal AI in medicine: A scoping review on technical challenges and clinical applications (2025) · cites this paper as Braman et al., 2021

    The Introduction (p. 2) describes a framework combining four modalities, and Experimental Details (p. 6) identifies TCGA-GBM as one source of imaging data. But the modalities are MRI, histology, genomics, and clinical data—not CT and text—and the paper also uses TCGA-LGG. The cited passages do not establish the claimed investigations of missing data, model uncertainty, or explainability. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 18

  1. [3][3] Luca Saba et al. 'The present and future of deep learning in radiology'. In: European Journal of Radiology 114 (May 1, 2019), pp. 14-24. -
  2. [4][4] Ole-Johan Skrede et al. 'Deep learning for prediction of colorectal cancer outcome: a discovery and validation study'. In: Lancet (London, England) 395.10221 (Feb. 1, 2020), pp. 350-360. -
  3. [5][5] David N. Louis et al. 'The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary'. In: Acta Neuropathologica 131.6 (June 2016), pp. 803-820. -
  4. [7][7] Adriana Olar and Kenneth D. Aldape. 'Using the molecular classification of glioblastoma to inform personalized treatment'. In: The Journal of Pathology 232.2 (Jan. 2014), pp. 165-177. -
  5. [8][8] Roger Stupp et al. 'Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma'. In: The New England Journal of Medicine 352.10 (Mar. 10, 2005), pp. 987-996. -
  6. [10][10] Sohi Bae et al. 'Radiomic MRI Phenotyping of Glioblastoma: Improving Survival Prediction'. In: Radiology 289.3 (Oct. 2, 2018). Publisher: Radiological Society of North America, pp. 797-806. -
  7. [11][11] Prateek Prasanna et al. 'Radiomic features from the peritumoral brain parenchyma on treatment-na¨ ıve multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: Preliminary findings'. In: European Radiology 27.10 (Oct. 2017), pp. 4188-4197. -
  8. [12][12] Niha Beig et al. 'Radiogenomic-Based Survival Risk Stratification of Tumor Habitat on Gd-T1w MRI Is Associated with Biological Processes in Glioblastoma'. In: Clinical Cancer Research 26.8 (Apr. 15, 2020). Publisher: American Association for Cancer Research Section: Precision Medicine and Imaging, pp. 1866-1876. -
  9. [13][13] Niha Beig et al. 'Sexually dimorphic radiogenomic models identify distinct imaging and biological pathways that are prognostic of overall survival in glioblastoma'. In: Neuro-Oncology 23.2 (Feb. 1, 2021), pp. 251-263. -
  10. [14][14] Richard J. Chen et al. 'Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosis'. In: arXiv:1912.08937 [cs, q-bio] (Dec. 18, 2019). version: 1. - · arXiv
  11. [15][15] Pooya Mobadersany et al. 'Predicting cancer outcomes from histology and genomics using convolutional networks'. In: Proceedings of the National Academy of Sciences 115.13 (Mar. 27, 2018), E2970-E2979. -
  12. [17][17] Pranjal Vaidya et al. 'RaPtomics: integrating radiomic and pathomic features for predicting recurrence in early stage lung cancer'. In: Medical Imaging 2018: Digital Pathology . Medical Imaging 2018: Digital Pathology. Vol. 10581. International Society for Optics and Photonics, Mar. 6, 2018, p. 105810M. -
  13. [18][18] Vaishnavi Subramanian, Minh N. Do, and Tanveer Syeda-Mahmood. 'Multimodal fusion of imaging and genomics for lung cancer recurrence prediction'. In: arXiv:2002.01982 [cs, eess, q-bio] (Feb. 5, 2020). - · arXiv
  14. [19][19] Amir Zadeh et al. 'Tensor Fusion Network for Multimodal Sentiment Analysis'. In: arXiv:1707.07250 [cs] (July 23, 2017). - · arXiv
  15. [20][20] Jos´ e Lezama et al. 'OL \ 'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning'. In: arXiv:1712.01727 [cs, stat] (Dec. 5, 2017). - · arXiv
  16. [21][21] Karen Simonyan and Andrew Zisserman. 'Very Deep Convolutional Networks for Large-Scale Image Recognition'. In: arXiv:1409.1556 [cs] (Apr. 10, 2015). - · arXiv
  17. [22][22] Jia Deng et al. 'ImageNet: A large-scale hierarchical image database'. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition . 2009 IEEE Conference on Computer Vision and Pattern Recognition. ISSN: 1063-6919. June 2009, pp. 248-255. -
  18. [26][26] H. B. Mann and D. R. Whitney. 'On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other'. In: The Annals of Mathematical Statistics 18.1 (Mar. 1947). Publisher: Institute of Mathematical Statistics, pp. 50-60. -

Cited by

Sorted by citations

Authors
Braman, N., Gordon, J. W. H., Goossens, E. T., Willis, C., Stumpe, M. C., & Venkataraman, J.
Affiliations
Tempus Labs (United States) (US)
Corresponding author
Braman, Nathaniel
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Published
2021
Pages
667-677
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-030-87240-3_64
OpenAlex
W3173461800
Cited by
107
References
5
Citations by year
2026: 17 · 2025: 29 · 2024: 19 · 2023: 29 · 2022: 11 · 2021: 2
FWCI
18.93
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Health Sciences › Medicine › Genetics › Glioma Diagnosis and Treatment
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
glioma, overall survival prediction, multimodal fusion, multiparametric MRI, histopathology image analysis, DNA sequencing, prognostic factors, risk score, molecular subtyping, clinical grading

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