Harnessing multimodal data integration to advance precision oncology

Boehm, Kevin M.; Khosravi, Pegah; Vanguri, R.; Gao, Jianjiong; Shah, Sohrab P.

doi:10.1038/s41568-021-00408-3

Cited by 270 publications

(160 citation statements)

References 153 publications

Supporting

Mentioning

157

Contrasting

Unclassified

Order By: Relevance

“…In addition, the capacity of AI systems to learn pathophysiologically relevant patterns from non-annotated images shows that AI could enable mechanistic scientific insight in addition to yielding tools of potential clinical usefulness. Future approaches could also be used to predict clinical features as well as genomic findings and predict risk of malignancy in conjunction with other data elements such as clinical, radiology, and whole slide images 31 . Our study provides a blueprint as well as the algorithms and open-source implementation for future multicentric studies required to implement weakly supervised AI systems as diagnostic support tools in endoscopy.…”

Section: Discussionmentioning

confidence: 99%

Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy

Buendgens

Cifci

Laleh

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Artificial intelligence (AI) is widely used to analyze gastrointestinal (GI) endoscopy image data. AI has led to several clinically approved algorithms for polyp detection, but application of AI beyond this specific task is limited by the high cost of manual annotations. Here, we show that a weakly supervised AI can be trained on data from a clinical routine database to learn visual patterns of GI diseases without any manual labeling or annotation. We trained a deep neural network on a dataset of N = 29,506 gastroscopy and N = 18,942 colonoscopy examinations from a large endoscopy unit serving patients in Germany, the Netherlands and Belgium, using only routine diagnosis data for the 42 most common diseases. Despite a high data heterogeneity, the AI system reached a high performance for diagnosis of multiple diseases, including inflammatory, degenerative, infectious and neoplastic diseases. Specifically, a cross-validated area under the receiver operating curve (AUROC) of above 0.70 was reached for 13 diseases, and an AUROC of above 0.80 was reached for two diseases in the primary data set. In an external validation set including six disease categories, the AI system was able to significantly predict the presence of diverticulosis, candidiasis, colon and rectal cancer with AUROCs above 0.76. Reverse engineering the predictions demonstrated that plausible patterns were learned on the level of images and within images and potential confounders were identified. In summary, our study demonstrates the potential of weakly supervised AI to generate high-performing classifiers and identify clinically relevant visual patterns based on non-annotated routine image data in GI endoscopy and potentially other clinical imaging modalities.

show abstract

Section: Discussionmentioning

confidence: 99%

Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy

Buendgens

Cifci

Laleh

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…However, at present, even when these data are available, they are rarely integrated. Artificial intelligence and deep learning provide an opportunity for multimodal data integration ( 116 ). One example is that, by integrating PET-CT imaging, RNA-sequencing, and histology, differential immuno-metabolic crosstalk in lung squamous cell carcinoma and adenocarcinoma was observed ( 117 ).…”

Section: Challenges and Perspectivesmentioning

confidence: 99%

Navigate Towards the Immunotherapy Era: Value of Immune Checkpoint Inhibitors in Non-Small Cell Lung Cancer Patients With Brain Metastases

2022

View full text Add to dashboard Cite

Brain metastases (BMs) in non-small-cell lung cancer (NSCLC) patients are associated with significant morbidity and poor prognosis. Immune checkpoint inhibitors (ICIs) have resulted in a paradigm shift in the management of advanced NSCLC. However, the value of ICIs in NSCLC patients with BMs remains unclear because patients with BMs are routinely excluded in numerous prospective trials on ICIs. Here, starting from the mechanisms of ICIs for BMs, we will reveal the value of ICIs by reviewing the efficacy and adverse effects of ICIs monotherapy as well as promising combination strategies, such as combinations with chemotherapy, radiotherapy, and anti-angiogenic drugs, etc. In addition, the methods of patient selection and response assessment will be summarized to assist clinical practice and further studies.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Artificial intelligence methods have recently been applied to improve prediction accuracy [ 29 , 30 , 31 , 32 , 33 ]. Among them, artificial deep learning neural networks (NNs) have been applied to cancer research and diagnosis [ 29 , 30 , 31 , 32 , 33 ]. NNs mimic brain neurons to learn patterns of objects defined by features (e.g., biomarkers) and then predicts known objects.…”

Section: Introductionmentioning

confidence: 99%

Noncoding RNAs and Deep Learning Neural Network Discriminate Multi-Cancer Types

Wang

Hai

Rider

et al. 2022

Cancers

View full text Add to dashboard Cite

Detecting cancers at early stages can dramatically reduce mortality rates. Therefore, practical cancer screening at the population level is needed. To develop a comprehensive detection system to classify multiple cancer types. We integrated an artificial intelligence deep learning neural network and noncoding RNA biomarkers selected from massive data. Our system can accurately detect cancer vs. healthy objects with 96.3% of AUC of ROC (Area Under Curve of a Receiver Operating Characteristic curve), and it surprisingly reaches 78.77% of AUC when validated by real-world raw data from a completely independent data set. Even validating with raw exosome data from blood, our system can reach 72% of AUC. Moreover, our system significantly outperforms conventional machine learning models, such as random forest. Intriguingly, with no more than six biomarkers, our approach can easily discriminate any individual cancer type vs. normal with 99% to 100% AUC. Furthermore, a comprehensive marker panel can simultaneously multi-classify common cancers with a stable 82.15% accuracy rate for heterogeneous cancerous tissues and conditions.: This detection system provides a promising practical framework for automatic cancer screening at population level. Key points: (1) We developed a practical cancer screening system, which is simple, accurate, affordable, and easy to operate. (2) Our system binarily classify cancers vs. normal with >96% AUC. (3) In total, 26 individual cancer types can be easily detected by our system with 99 to 100% AUC. (4) The system can detect multiple cancer types simultaneously with >82% accuracy.

show abstract

Harnessing multimodal data integration to advance precision oncology

Cited by 270 publications

References 153 publications

Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy

Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy

Navigate Towards the Immunotherapy Era: Value of Immune Checkpoint Inhibitors in Non-Small Cell Lung Cancer Patients With Brain Metastases

Noncoding RNAs and Deep Learning Neural Network Discriminate Multi-Cancer Types

Contact Info

Product

Resources

About