Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer

Vanguri, R.; Luo, Jia; Aukerman, Andrew; Egger, Jacklynn V.; Fong, Christopher J.; Horvat, Natally; Pagano, Andrew; Araújo-Filho, José de Arimateia Batista; Geneslaw, Luke; Rizvi, Hira; Sosa, Ramon E.; Boehm, Kevin M.; Yang, Soo‐Ryum; Bodd, Francis M.; Ventura, Katia; Hollmann, Travis J.; Ginsberg, Michelle S.; Gao, Jianjiong; Hellmann, Matthew D.; Sauter, Jennifer L.; Shah, Sohrab P.

doi:10.1038/s43018-022-00416-8

Cited by 129 publications

(85 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18,21,22 Indeed, the multimodal integration of radiology and pathology has increasingly been seen as a promising predictive tool for guiding immunotherapies in NSCLC. 23 Due to its retrospective and single-center nature, this study has some limitations that might bias the results and conclusions. The lack of an independent validation cohort further evaluating the 18 F-FDG PET/CT cutoffs for high or low glycolytic profiles may limit the drawing of definitive conclusions.…”

Section: Discussionmentioning

confidence: 94%

See 1 more Smart Citation

Tumor glycolytic profiling through ¹⁸F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

et al. 2022

View full text Add to dashboard Cite

Background: A significant proportion of patients with non-small-cell lung cancer (NSCLC) do not respond to immune checkpoint inhibitors (ICIs). Since metabolic reprogramming with increased glycolysis is a hallmark of cancer and is involved in immune evasion, we used 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET/CT) to evaluate the baseline glycolytic parameters of patients with advanced NSCLC submitted to ICIs, and assessed their predictive value. Methods: 18F-FDG PET/CT results in the 3 months before ICIs treatment were included. Maximum standardized uptake values, whole metabolic tumor volume (wMTV), and whole-body total lesion glycolysis (wTLG) were evaluated. Cutoff values for high or low glycolytic categories were determined using receiver-operating characteristic curves. Progression-free survival (PFS) and overall survival (OS) were evaluated. Patients with a complete response and a matching group with resistance to ICIs underwent immunohistochemistry analysis. An unsupervised k-means clustering model integrating programmed cell death ligand 1 (PD-L1) expression, glycolytic parameters, and ICIs therapy was performed. Results: In all, 98 patients were included. Lower baseline 18F-FDG PET/CT parameters were associated with responses to ICIs. Patients with low wMTV or wTLG had improved PFS and OS. High wTLG, strong tumor expression of glucose transporter-1, and lack of responses were significantly associated. Patients with low glycolytic parameters benefited from ICIs, regardless of chemotherapy. Conversely, those with high parameters benefited from the addition of chemotherapy. Patients with higher wTLG and lower PD-L1 were associated with progression and worse survival to ICIs monotherapy. Conclusions: Glycolytic metabolic profiles established through baseline 18F-FDG PET/CT are useful biomarkers for evaluating ICI therapy in advanced NSCLC.

show abstract

Section: Discussionmentioning

confidence: 94%

“… 18 , 21 , 22 Indeed, the multimodal integration of radiology and pathology has increasingly been seen as a promising predictive tool for guiding immunotherapies in NSCLC. 23 …”

Section: Discussionmentioning

confidence: 99%

Tumor glycolytic profiling through ¹⁸F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

et al. 2022

View full text Add to dashboard Cite

show abstract

“…While a vast amount of gene expression datasets are publicly available, most of these datasets do not provide matching WSIs. This limits their use in multimodal classification models [13, 15, 20, 52]. With our model, WSI tiles can be imputed from the gene expression, which opens new possibilities in publicly available datasets.…”

Section: Discussionmentioning

confidence: 99%

Synthetic whole-slide image tile generation with gene expression profiles infused deep generative models

Carrillo-Pérez

Pizurica

Ozawa

et al. 2022

Preprint

View full text Add to dashboard Cite

The acquisition of multi-modal biological data for the same sample, such as RNA sequencing and whole slide imaging (WSI), has increased in recent years, enabling studying human biology from multiple angles. However, despite these emerging multi-modal efforts, for the majority of studies only one modality is typically available, mostly due to financial or logistical constraints. Given these difficulties, multi-modal data imputation and multi-modal synthetic data generation are appealing as a solution for the multi-modal data scarcity problem. Currently, most studies focus on generating a single modality (e.g. WSI), without leveraging the information provided by additional data modalities (e.g. gene expression profiles). In this work, we propose an approach to generate WSI tiles by using deep generative models infused with matched gene expression profiles. First, we train a variational autoencoder (VAE) that learns a latent, lower dimensional representation of multi-tissue gene expression profiles. Then, we use this representation to infuse generative adversarial networks (GAN) that generate lung and brain cortex tissue tiles, resulting in a new model that we call RNA-GAN. Tiles generated by RNA-GAN were preferred by expert pathologists in comparison to tiles generated using traditional GANs and in addition, RNA-GAN needs fewer training epochs to generate high-quality tiles. Finally, RNA-GAN was able to generalize to gene expression profiles outside of the training set, showing imputation capabilities. A web-based quiz is available for users to play a game distinguishing real and synthetic tiles: https://rna-gan.stanford.edu/ and the code for RNA-GAN is available here: https://github.com/gevaertlab/RNA-GAN.

show abstract

“…Ongoing efforts are being evaluated for incorporating radiomics in the development of multimodal biomarkers for HGSOC, and a variety of other malignancies [ 159 – 163 ]. Radiomics quantifies images, usually derived from computed tomography (CT) that are routinely used to monitor disease progression [ 164 ].…”

Section: Hgsoc Heterogeneitymentioning

confidence: 99%

Multiparameter single-cell proteomic technologies give new insights into the biology of ovarian tumors

et al. 2023

View full text Add to dashboard Cite

High-grade serous ovarian cancer (HGSOC) is the most lethal gynecological malignancy. Its diagnosis at advanced stage compounded with its excessive genomic and cellular heterogeneity make curative treatment challenging. Two critical therapeutic challenges to overcome are carboplatin resistance and lack of response to immunotherapy. Carboplatin resistance results from diverse cell autonomous mechanisms which operate in different combinations within and across tumors. The lack of response to immunotherapy is highly likely to be related to an immunosuppressive HGSOC tumor microenvironment which overrides any clinical benefit. Results from a number of studies, mainly using transcriptomics, indicate that the immune tumor microenvironment (iTME) plays a role in carboplatin response. However, in patients receiving treatment, the exact mechanistic details are unclear. During the past decade, multiplex single-cell proteomic technologies have come to the forefront of biomedical research. Mass cytometry or cytometry by time-of-flight, measures up to 60 parameters in single cells that are in suspension. Multiplex cellular imaging technologies allow simultaneous measurement of up to 60 proteins in single cells with spatial resolution and interrogation of cell–cell interactions. This review suggests that functional interplay between cell autonomous responses to carboplatin and the HGSOC immune tumor microenvironment could be clarified through the application of multiplex single-cell proteomic technologies. We conclude that for better clinical care, multiplex single-cell proteomic technologies could be an integral component of multimodal biomarker development that also includes genomics and radiomics. Collection of matched samples from patients before and on treatment will be critical to the success of these efforts.

show abstract

Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer

Cited by 129 publications

References 52 publications

Tumor glycolytic profiling through ¹⁸F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

Tumor glycolytic profiling through ¹⁸F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

Synthetic whole-slide image tile generation with gene expression profiles infused deep generative models

Multiparameter single-cell proteomic technologies give new insights into the biology of ovarian tumors

Contact Info

Product

Resources

About

Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer

Cited by 129 publications

References 52 publications

Tumor glycolytic profiling through 18F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

Tumor glycolytic profiling through 18F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

Synthetic whole-slide image tile generation with gene expression profiles infused deep generative models

Multiparameter single-cell proteomic technologies give new insights into the biology of ovarian tumors

Contact Info

Product

Resources

About

Tumor glycolytic profiling through ¹⁸F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC

Tumor glycolytic profiling through ¹⁸F-FDG PET/CT predicts immune checkpoint inhibitor efficacy in advanced NSCLC