Predicting cancer outcomes from histology and genomics using convolutional networks
Open accessPublished version of a preprint
The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 4 of the 13 sources its claims cite were checked for support.
Abstract
Significance: Predicting the expected outcome of patients diagnosed with cancer is a critical step in treatment. Advances in genomic and imaging technologies provide physicians with vast amounts of data, yet prognostication remains largely subjective, leading to suboptimal clinical management. We developed a computational approach based on deep learning to predict the overall survival of patients diagnosed with brain tumors from microscopic images of tissue biopsies and genomic biomarkers. This method uses adaptive feedback to simultaneously learn the visual patterns and molecular biomarkers associated with patient outcomes. Our approach surpasses the prognostic accuracy of human experts using the current clinical standard for classifying brain tumors and presents an innovative approach for objective, accurate, and integrated prediction of patient outcomes.
Overview
CoChat Summary
TL;DR
The paper presents survival convolutional neural networks (SCNNs) and genomic SCNNs (GSCNNs) that predict overall survival in diffuse gliomas from histology and genomic biomarkers. SCNN performance was comparable to manual histologic grading or molecular subtyping, and GSCNN integrating IDH and 1p/19q improved median c index to 0.801, outperforming the WHO subtype-grade baseline.
Key findings
- In 769 TCGA gliomas (1,061 H&E whole-slide images), SCNN achieved a median c index of 0.754, comparable to manual histologic grade (0.745, P = 0.307) and molecular subtype (0.746, P = 4.68e-2), but slightly below the combined WHO subtype-plus-grade baseline (0.774, P = 2.61e-3).
- Sampling and risk filtering improved SCNN: without these techniques, median c index dropped to 0.696 (P = 6.55e-4).
- GSCNN using histology plus IDH mutation status and 1p/19q codeletion improved median c index from 0.754 to 0.801 and significantly outperformed the WHO subtype-grade baseline (P = 1.06e-2); superficial integration performed worse (0.785, P = 4.68e-2).
- Multivariable Cox regression found SCNN risk significant (HR 3.05, P = 2.71e-12) and GSCNN risk significant (HR 8.83, P = 9.69e-12); heat maps highlighted microvascular proliferation, cellularity, and nuclear pleomorphism, and also assigned high risk to sparsely infiltrated or edematous regions.
Methods
- Retrospective TCGA Lower-Grade Glioma and Glioblastoma cohort: 769 patients and 1,061 H&E-stained whole-slide images; manually identified regions of interest, 1,024 × 1,024-pixel crops at 20× magnification, and 256 × 256-pixel high-power fields.
- SCNN combined a 19-layer VGG-style convolutional network with a Cox proportional hazards layer; training used random HPF sampling per epoch, image augmentation, minibatches of 14 HPFs, adagrad, and dropout, while testing used nine HPFs per region, median risk per region, second-highest region risk, and model averaging over epochs 96–100.
- Evaluation used Monte Carlo cross-validation with 15 random patient-level 80/20 training/testing splits, Harrell’s c index, Wilcoxon signed rank tests, Cox regression, and Kaplan–Meier analysis.
Limitations
- Stated: only a small portion of each slide was used for training and prediction; ROI selection required expert guidance; risk-category thresholds were subjectively defined; heat map interpretation was subjective; validation in other diseases and larger datasets for enhanced GSCNN models are needed.
- Evident from the text: the study is based on a single retrospective TCGA cohort, with no external independent validation reported, and manual ROI selection may limit scalability and generalizability.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
4 Valid · 0 Not valid · 8 Not checked · 87 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Second, predicted risks are consistent with the published expected overall survivals associated with molecular subtypes (37).”
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Results > SCNN Predictions Correlate with Molecular Subtypes and Manual Histologic Grade.
What the sources say
- Supportedcites [37] Brat DJ Cancer Genome Atlas Research Network 2015 Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas N Engl J Med 372 2481 2498 26061751 PMC4530011 source
The Results section 'Clinical Characteristics and Outcomes Associated with Molecular Subtypes' publishes expected overall survival for each molecular subtype of diffuse lower-grade glioma: median survival 8.0 years with IDH mutation plus 1p/19q codeletion, 6.3 years with IDH mutation and no codeletion, and 1.7 years with wild-type IDH (age-adjusted HR for death 7.4; 95% CI 4.0–13.8). The Discussion restates this ordering and notes that stratification of clinical risk by IDH–1p/19q status is more robust than prediction by histologic class. Thus the cited paper is indeed the published source of the subtype-associated expected survivals against which the citing authors' predicted risks are said to be consistent; the comparison of their own model's predictions is the citing authors' conclusion, not attributed content. (LLM, conf=0.86)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Histologic diagnosis and grading of gliomas have been limited by considerable intra- and interobserver variability (42).”
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Discussion
What the sources say
- Partly supportedcites [42] van den Bent MJ 2010 Interobserver variation of the histopathological diagnosis in clinical trials on glioma: a clinician’s perspective Acta Neuropathol 120 297 304 20644945 PMC2910894 sourceExperimental — accuracy not yet measured
The Abstract states 'ample evidence of a clinically significant interobserver variation of the histological diagnosis of glioma' with 'an effect on both the typing and grading of glial tumors', and the Introduction/Pathology review sections document 20-30% reclassification on independent review, so the interobserver half of the claim (limiting both diagnosis and grading) is well supported. However, the intraobserver component is not: in 'Pathology review and conclusions derived from clinical trials' the paper says there are 'very little data on intraobserver variation', assuming only that it is less than interobserver variation. Attributing considerable intra- and interobserver variability to this source therefore overstates it on the intraobserver point. (LLM, conf=0.80)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“IDH mutant astrocytomas are another subtype with considerably better overall survival ranging from 3 to 8 y”
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Results > SCNN Predictions Correlate with Molecular Subtypes and Manual Histologic Grade.
What the sources say
- Partly supportedcites [37] Brat DJ Cancer Genome Atlas Research Network 2015 Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas N Engl J Med 372 2481 2498 26061751 PMC4530011 sourceExperimental — accuracy not yet measured
The RESULTS section 'Clinical characteristics and outcomes associated with molecular subtypes' supports the direction of the claim — both IDH-mutant subgroups had substantially longer overall survival than IDH wild-type lower-grade gliomas (median 6.3 years for IDH mutation without codeletion, 8.0 years with codeletion, versus 1.7 years for wild-type; DISCUSSION repeats this). What the source does not support is the magnitude given: it reports no 3-to-8-year range for IDH-mutant astrocytomas (its only range statement is the general introduction's 'survival ranges widely, from 1 to 15 years' for lower-grade gliomas as a whole), and it does not treat 'IDH mutant astrocytoma' as a survival-bearing subtype — the HISTOLOGIC AND MOLECULAR SUBTYPES section states that IDH-1p/19q status correlated only modestly with astrocytoma and oligoastrocytoma, with the IDH-mutant/no-codeletion group being a mixture of histologic classes enriched for astrocytomas and oligoastrocytomas. (LLM, conf=0.78)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“IDH WT astrocytomas are, for the most part, highly aggressive, having a median survival of 18 mo”
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Results > SCNN Predictions Correlate with Molecular Subtypes and Manual Histologic Grade.
What the sources say
- Partly supportedcites [37] Brat DJ Cancer Genome Atlas Research Network 2015 Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas N Engl J Med 372 2481 2498 26061751 PMC4530011 sourceExperimental — accuracy not yet measured
Our copy supports the aggressiveness: the Discussion calls wild-type IDH lower-grade glioma 'a clinically aggressive form of lower-grade glioma,' and the Results (Clinical Characteristics and Outcomes Associated with Molecular Subtypes) report a median survival of 1.7 years (~20 months) with an age-adjusted hazard ratio for death of 7.4 versus IDH-mutated tumors. However, the 18-month figure attributed here is not stated in our copy, and the survival figure is given for the whole IDH-wild-type lower-grade glioma group, not for astrocytomas specifically — that group was 'mostly astrocytomas (31 of 55 samples)' but included all three histologic classes and grades (Histologic and Molecular Subtypes). The paper also qualifies the 'for the most part' framing by noting that the rare grade II wild-type IDH tumors in the M1 methylation cluster lacked TERT promoter mutations and 'potentially ... are distinct pathologic entities.' (LLM, conf=0.78)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and that SCNN predictions suggest prognostic relevance for histologic patterns with significance that is not currently appreciated by neuropathologists.”
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Discussion
hedgedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
52 more claims
Create a free account to see all 99 claims and to verify the 9 references still open.
- It may state two separate claims as one. 26
- Probably not a substantial claim. 21
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These datasets can be correlated to molecular tumor characteristics and can be used to quantitatively characterize tissue at multiple spatial scales to create biomarkers that predict outcome and treatment response [150], [152]–[154].”
From AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020) · cites this paper as [150]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, Mobadersanya et al. [77] showed that imbalance does not necessarily lead to poor performance if the input features of the lower dimensional modality are chosen with prior knowledge.”
From Multimodal deep learning for biomedical data fusion: a review (2022) · cites this paper as [77]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“there are increasing efforts of using digital pathology images to guide treatment selection by predicting patient prognosis (73)(74)(75) and/or existing treatment biomarkers (76-79) using AI.”
From Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions (2024) · cites this paper as [73]
The cited source says what the claim attributes to it.
In the citing paper
“Studies have validated and shown the value of digitized tissue slides in biomedical research [148]–[152].”
From AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020) · cites this paper as [150]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Results > Assessing the Prognostic Accuracy of SCNN.
“The risks predicted by the SCNN models correlate with both histologic grade and molecular subtype, decreasing with grade and generally trending with the clinical aggressiveness of genomic subtypes.”
§ Predicting cancer outcomes from histology and genomics using convolutional networks > Results > SCNN Predictions Correlate with Molecular Subtypes and Manual Histologic Grade.
“First, within each molecular subtype, the risks predicted by SCNN increase with histologic grade.”
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Nishimura, R., Osako, T., Nishiyama, Y., Tashima, R., Nakano, M., Fujisue, M., Toyozumi, Y., & Arima, N. (2013) · Oncology · doi:10.1159/000353099 · Cited by 13,166
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
(2010) · Cited by 8,261
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
2013 IEEE International Conference on Computer Vision
(2013) · doi:10.1109/iccv19984.2013 · Cited by 4,183
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.10.004 · Cited by 3,498
Cited by
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
Campanella, G., Hanna, M. G., Geneslaw, L., Miraflor, A., Werneck Krauss Silva, V., Busam, K. J., Brogi, E., Reuter, V. E., Klimstra, D. S., & Fuchs, T. J. (2019) · Nature Medicine · doi:10.1038/s41591-019-0508-1 · Cited by 2,799
Data-efficient and weakly supervised computational pathology on whole-slide images
Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Chen, R. J., Barbieri, M., & Mahmood, F. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-020-00682-w · Cited by 2,282
Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology
Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V., & Madabhushi, A. (2019) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-019-0252-y · Cited by 1,698
Towards a general-purpose foundation model for computational pathology
Chen, R. J., Ding, T., Lu, M. Y., Williamson, D. F. K., Jaume, G., Song, A. H., Chen, B., Zhang, A., Shao, D., Shaban, M., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-02857-3 · Cited by 1,560
Kather, J. N., Pearson, A. T., Halama, N., Jäger, D., Krause, J., Loosen, S. H., Marx, A., Boor, P., Tacke, F., Neumann, U. P., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0462-y · Cited by 1,458
Metadata
- Authors
- Mobadersany, P., Yousefi, S., Amgad, M., Gutman, D. A., Barnholtz-Sloan, J. S., Velázquez Vega, J. E., Brat, D. J., & Cooper, L. A. D.
- Affiliations
- Emory University (US)
- Case Comprehensive Cancer Center, Case Western Reserve University School of Medicine, Cleveland, OH 44106;
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA 30322;
- Northwestern University (US)
- Georgia Institute of Technology (US)
- Corresponding author
- Cooper, Lee A. D.
- ORCID
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2018-03-12
- Volume
- 115
- Issue
- 13
- Pages
- E2970-E2979
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC5879673
- OpenAlex
- W2761668583
- Semantic Scholar
- 7b05161938f4e5f89ddd7ab7f432de8ecab1566e
- Cited by
- 1,084
- References
- 52
- Citations by year
- 2026: 120 · 2025: 126 · 2024: 157 · 2023: 124 · 2022: 172 · 2021: 157 · 2020: 130 · 2019: 84 · 2018: 13
- FWCI
- 54.74
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Funders
- HHS | NIH | U.S. National Library of Medicine (K22LM011576)
- HHS | NIH | National Cancer Institute (U24CA194362)
- National Brain Tumor Society (Not issued)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- cancer prognosis, digital pathology, glioma, histological images, genomic biomarkers, time-to-event prediction, overall survival, tumor heterogeneity, microvascular proliferation, heat map visualization, precision medicine
- MeSH terms
- Algorithms, Brain Neoplasms, Glioma, Histological Techniques, Humans, Image Processing, Computer-Assisted, Prognosis, Neural Networks, Computer, Genomics, Precision Medicine
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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: Predicting cancer outcomes from histology and genomics using convolutional networks. https://app.cochat.ai/papers/10.1073/pnas.1717139115
- The paper
- Mobadersany, P., Yousefi, S., Amgad, M., Gutman, D. A., Barnholtz-Sloan, J. S., Velázquez Vega, J. E., Brat, D. J., & Cooper, L. A. D. (2018). Predicting cancer outcomes from histology and genomics using convolutional networks. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.1717139115
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.