Tumor immune profiles noninvasively estimated by FDG PET with deep learning correlate with immunotherapy response in lung adenocarcinoma
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Rationale: The clinical application of biomarkers reflecting tumor immune microenvironment is hurdled by the invasiveness of obtaining tissues despite its importance in immunotherapy.We developed a deep learning-based biomarker which noninvasively estimates a tumor immune profile with fluorodeoxyglucose positron emission tomography (FDG-PET) in lung adenocarcinoma (LUAD).Methods: A deep learning model to predict cytolytic activity score (CytAct) using semi-automatically segmented tumors on FDG-PET trained by a publicly available dataset paired with tissue RNA sequencing (n = 93).This model was validated in two independent cohorts of LUAD: SNUH (n = 43) and The Cancer Genome Atlas (TCGA) cohort (n = 16).The model was applied to the immune checkpoint blockade (ICB) cohort, which consists of patients with metastatic LUAD who underwent ICB treatment (n = 29).Results: The predicted CytAct showed a positive correlation with CytAct of RNA sequencing in validation cohorts (Spearman rho = 0.32, p = 0.04 in SNUH cohort; spearman rho = 0.47, p = 0.07 in TCGA cohort).In ICB cohort, the higher predicted CytAct of individual lesion was associated with more decrement in tumor size after ICB treatment (Spearman rho = -0.54,p < 0.001).Higher minimum predicted CytAct in each patient associated with significantly prolonged progression free survival and overall survival (Hazard ratio 0.25, p = 0.001 and 0.18, p = 0.004, respectively).In patients with multiple lesions, ICB responders had significantly lower variance of predicted CytActs (p = 0.005). Conclusion:The deep learning model that predicts CytAct using FDG-PET of LUAD was validated in independent cohorts.Our approach may be used to noninvasively assess an immune profile and predict outcomes of LUAD patients treated with ICB.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository
Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., et al. (2013) · Journal of Digital Imaging · doi:10.1007/s10278-013-9622-7 · Cited by 4,599 · cited 3×
“To develop a deep learning model for estimating an immune profile in the TME of LUAD, we used a publicly available dataset, The Cancer Imaging Archive (TCIA) dataset [20], defined in this study as a Stanford cohort [21].”
xCell: digitally portraying the tissue cellular heterogeneity landscape
Aran, D., Hu, Z., & Butte, A. J. (2017) · Genome Biology · doi:10.1186/s13059-017-1349-1 · Cited by 4,397 · cited 3×
“…is known to represent cytotoxic CD8+ T cell activity against tumor [19], we first evaluated whether CytAct would represent the immune profile of TME in the training cohort by analyses on correlations of CytAct with interferon-γ related profile (IFNG score) and Immune score by xCell tool [25,26].”
Tumour heterogeneity and resistance to cancer therapies
Dagogo-Jack, I., & Shaw, A. T. (2018) · Nature Reviews Clinical Oncology · doi:10.1038/nrclinonc.2017.166 · Cited by 3,846 · cited 1×
“In particular, it is controversy whether a single biopsy truly represents all the characteristics of the tumor as genomic, transcriptional and immunologic heterogeneity in metastatic lesions may result in ICB response heterogeneity [12,34].”
Molecular and genetic properties of tumors associated with local immune cytolytic activity
Rooney, M. S., Shukla, S. A., Wu, C. J., Getz, G., & Hacohen, N. (2015) · Cell · doi:10.1016/j.cell.2014.12.033 · Cited by 3,825 · cited 4×
“CytAct is defined by the mean value of the expression of granzyme A ( GZMA ) and perforin 1 ( PRF1 ) normalized by z-score, which is easy to calculate with RNA-seq data [19].”
InfluentialIFN-γ–related mRNA profile predicts clinical response to PD-1 blockade
Ayers, M., Lunceford, J., Nebozhyn, M., Murphy, E., Loboda, A., Kaufman, D. R., Albright, A., Cheng, J. D., Kang, S. P., Shankaran, V., et al. (2017) · Journal of Clinical Investigation · doi:10.1172/jci91190 · Cited by 3,788
Nivolumab plus ipilimumab in lung cancer with a high tumor mutational burden
Hellmann, M. D., Ciuleanu, T.-E., Pluzanski, A., Lee, J. S., Otterson, G. A., Audigier-Valette, C., Minenza, E., Linardou, H., Burgers, S., Salman, P., et al. (2018) · New England Journal of Medicine · doi:10.1056/nejmoa1801946 · Cited by 3,063 · cited 1×
“In this regard, other potential biomarkers, including tumor mutation burden and tumor-infiltrating lymphocytes, have been introduced, and integration of these mechanism-based biomarkers has been suggested to accurately predict the response to ICB [5,6].”
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
Perez, L., & Wang, J. (2017) · arXiv · doi:10.48550/arxiv.1712.04621 · Cited by 2,499
iRECIST: guidelines for response criteria for use in trials testing immunotherapeutics
Seymour, L., Bogaerts, J., Perrone, A., Ford, R., Schwartz, L. H., Mandrekar, S., Lin, N. U., Litière, S., Dancey, J., Chen, A., et al. (2017) · The Lancet Oncology · doi:10.1016/s1470-2045(17)30074-8 · Cited by 2,472 · cited 5×
“Lesions were measured according to RECIST 1.1, and response evaluation was done according to iRECIST criteria [13,24].”
InfluentialA comprehensive map of molecular drug targets
Santos, R., Ursu, O., Gaulton, A., Bento, A. P., Donadi, R. S., Bologa, C. G., Karlsson, A., Al-Lazikani, B., Hersey, A., Oprea, T. I., et al. (2017) · Nature Reviews Drug Discovery · doi:10.1038/nrd.2016.230 · Cited by 2,427
The evolving landscape of biomarkers for checkpoint inhibitor immunotherapy
Havel, J. J., Chowell, D., & Chan, T. A. (2019) · Nature Reviews Cancer · doi:10.1038/s41568-019-0116-x · Cited by 2,286 · cited 1×
“Although the higher PD-L1 IHC expression level is associated with better response rates, the level alone is unsatisfactory for clinicians to refer to as a sole biomarker [4].”
Sun, R., Limkin, E. J., Vakalopoulou, M., Dercle, L., Champiat, S., Han, S. R., Verlingue, L., Brandao, D., Lancia, A., Ammari, S., et al. (2018) · The Lancet Oncology · doi:10.1016/s1470-2045(18)30413-3 · Cited by 1,236 · cited 2×
“A few studies that attempted to predict responders to ICB by machine learning algorithms trained by comparing responding and nonresponding lesions [36,37] also had such an issue.”
Unintended consequences of machine learning in medicine
Cabitza, F., Rasoini, R., & Gensini, G. F. (2017) · JAMA · doi:10.1001/jama.2017.7797 · Cited by 1,066
Saltz, J., Gupta, R., Hou, L., Kurc, T., Singh, P., Nguyen, V., Samaras, D., Shroyer, K. R., Zhao, T., Batiste, R., et al. (2018) · Cell Reports · doi:10.1016/j.celrep.2018.03.086 · Cited by 1,027
Self-citationTraining cnns for image registration from few samples with model-based data augmentation
Uzunova, H., Wilms, M., Handels, H., & Ehrhardt, J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-66182-7_26 · Cited by 110 · cited 1×
“Such type of image augmentation is commonly used in the training of deep learning for natural images as well as medical images [31,32].”
Allison, K. E., Coomber, B. L., & Bridle, B. W. (2017) · Immunology · doi:10.1111/imm.12777 · Cited by 109
Cited by
Artificial Intelligence for Predictive Biomarker Discovery in Immuno-Oncology: A Systematic Review
Prelaj, A., Miskovic, V., Zanitti, M., Trovo, F., Genova, C., Viscardi, G., Rebuzzi, S. E., Mazzeo, L., Provenzano, L., Kosta, S., et al. (2024) · Annals of Oncology · doi:10.1016/j.annonc.2023.10.125 · Cited by 340
Xu, Y., Su, G.-H., Ma, D., Xiao, Y., Shao, Z.-M., & Jiang, Y.-Z. (2021) · Signal Transduction and Targeted Therapy · doi:10.1038/s41392-021-00729-7 · Cited by 163
“First, radiomics provides a non-invasive method to estimate immune-related biomarkers, such as the cytolytic activity score (CytAct) predicted by the deep learning of fl uorodeoxyglucose positron emission tomography (FDG-PET) 186 and the Immuno-Score of gastric cancer predicted by radiomic features.”
MethodArtificial intelligence in thoracic surgery: a narrative review
Bellini, V., Valente, M., Del Rio, P., & Bignami, E. (2021) · Journal of Thoracic Disease · doi:10.21037/jtd-21-761 · Cited by 49
Metadata
- Authors
- Park, C., Na, K. J., Choi, H., Ock, C.-Y., Ha, S., Kim, M., Park, S., Keam, B., Kim, T. M., Paeng, J. C., Park, I. K., Kang, C. H., Kim, D.-W., Cheon, G.-J., Kang, K. W., Kim, Y. T., & Heo, D. S.
- Venue
- Theranostics
- Publisher
- Ivyspring International Publisher
- Published
- 2020
- Volume
- 10
- Issue
- 23
- Pages
- 10838-10848
- ISSN
- 1838-7640 (ISSN-L)
- OpenAlex
- W3083982834
- Cited by
- 71
- References
- 15
- FWCI
- 3.92
- Type
- journal article
- Language
- en
- Open access
- gold
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
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.