1,170 Hits in 4.6 sec

A unified computational model for revealing and predicting subtle subtypes of cancers

Xianwen Ren, Yong Wang, Jiguang Wang, Xiang-Sun Zhang
2012 BMC Bioinformatics  
Conclusions: We propose a unified computational framework for class discovery and class prediction to facilitate the discovery and prediction of subtle subtypes of cancers.  ...  Results: We propose a novel convex optimization model to perform class discovery and class prediction in a unified framework.  ...  Acknowledgments The authors thank the members of the ZHANGroup of Academy of Mathematics and Systems Science, Chinese Academy of Science for their valuable discussion and comments.  ... 
doi:10.1186/1471-2105-13-70 pmid:22548981 pmcid:PMC3464623 fatcat:hmpijawfwfb7digmwit22ptbbu

Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography

Kwang-Hyun Uhm, Seung-Won Jung, Moon Hyung Choi, Hong-Kyu Shin, Jae-Ik Yoo, Se Won Oh, Jee Young Kim, Hyun Gi Kim, Young Joon Lee, Seo Yeon Youn, Sung-Hoo Hong, Sung-Jea Ko
2021 npj Precision Oncology  
Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention.  ...  The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes.  ...  Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention.  ... 
doi:10.1038/s41698-021-00195-y pmid:34145374 fatcat:k3pvpu3pgrdshlnvkelhbkqyza

Predicting cancer outcomes from histology and genomics using convolutional networks

Pooya Mobadersany, Safoora Yousefi, Mohamed Amgad, David A. Gutman, Jill S. Barnholtz-Sloan, José E. Velázquez Vega, Daniel J. Brat, Lee A. D. Cooper
2018 Proceedings of the National Academy of Sciences of the United States of America  
Cancer histology reflects underlying molecular processes and disease progression and contains rich phenotypic information that is predictive of patient outcomes.  ...  We illustrate how these survival convolutional neural networks (SCNNs) can integrate information from both histology images and genomic biomarkers into a single unified framework to predict time-to-event  ...  Discussion We developed a deep learning approach for learning survival directly from histological images and created a unified framework for integrating histology and genomic biomarkers for predicting  ... 
doi:10.1073/pnas.1717139115 pmid:29531073 pmcid:PMC5879673 fatcat:oshb7moknbckrogjajqqys3uqm

Signatures of Discriminative Copy Number Aberrations in 31 Cancer Subtypes

Bo Gao, Michael Baudis
2021 Frontiers in Genetics  
Using a hybrid model of neural networks and attention algorithm, we generated the CNA signatures of 31 cancer subtypes, depicting the uniqueness of their respective CNA landscapes.  ...  of source data and derived CNV profiles pose great challenges for data integration and comparative analysis.  ...  The signatures were generated from a computational pipeline (Figure 1) , which unifies heterogeneous data and is powered by a hybrid model of neural networks and attention algorithm.  ... 
doi:10.3389/fgene.2021.654887 pmid:34054918 pmcid:PMC8155688 fatcat:3nebtmrxjvaipml7cvxsfrtate

Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features

Yan Xu, Zhipeng Jia, Liang-Bo Wang, Yuqing Ai, Fang Zhang, Maode Lai, Eric I-Chao Chang
2017 BMC Bioinformatics  
Histopathology image analysis is a gold standard for cancer recognition and diagnosis.  ...  Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists.  ...  Acknowledgements We would like to thank the Department of Pathology, Zhejiang University, China, for providing colon histopathology images and medical consultancy.  ... 
doi:10.1186/s12859-017-1685-x pmid:28549410 pmcid:PMC5446756 fatcat:lnesmctopfb7ppvhiwn2go3gxa

Automated Diagnosis of Lymphoma with Digital Pathology Images Using Deep Learning [article]

Hanadi El Achi, Tatiana Belousova, Lei Chen, Amer Wahed, Iris Wang, Zhihong Hu, Zeyad Kanaan, Adan Rios, Andy N.D. Nguyen
2018 arXiv   pre-print
A total of 2,560 images were obtained from which 1,856 were used for training, 464 for validation and 240 for testing.  ...  For each test set of 5 images, the predicted diagnosis was combined from prediction of 5 images.  ...  Advances in technology revealed multiple subtypes of NHL including DLBCL that accounts for the largest subtype, follicular lymphomas as the second most common, BL and SLL as the relatively common subtype  ... 
arXiv:1811.02668v1 fatcat:omeewzndavfxbf3t543sjfwika

Genomic Copy Number Signatures Based Classifiers for Subtype Identification in Cancer [article]

Bo Gao, Michael Baudis
2020 bioRxiv   pre-print
Using a hybrid model of neural networks and attention algorithm, we generated the CNA signatures of 31 cancer subtypes, depicting the uniqueness of their respective CNA landscapes.  ...  of source data and derived CNV profiles pose great challenges for data integration and comparative analysis.  ...  Acknowledgments We thank Paula Carrio Cordo and Qingyao Huang for support with the data ontologies, and all current and previous members of the Baudis group for contributions to the Progenetix resource  ... 
doi:10.1101/2020.12.18.423278 fatcat:t2gonvbthjc35d72xwbsvrhwpm

Integrative investigation on breast cancer in ER, PR and HER2-defined subgroups using mRNA and miRNA expression profiling

Xiaofeng Dai, Ana Chen, Zhonghu Bai
2014 Scientific Reports  
For this, several layers of information including immunohistochemical markers and a variety of high-throughput genomics approaches have been intensively used.  ...  Exploring the molecular difference among breast cancer subtypes is of crucial importance in understanding its heterogeneity and seeking its effective clinical treatment.  ...  However, this reasoning highly depends on the accuracy of the computational prediction, and needs to be tested in vivo.  ... 
doi:10.1038/srep06566 pmid:25338681 pmcid:PMC4206873 fatcat:nnxmi3qefbhp5nwehurjjoqzxm

Mechanistic Modeling of Gene Regulation and Metabolism Identifies Potential Targets for Hepatocellular Carcinoma

Renliang Sun, Yizhou Xu, Hang Zhang, Qiangzhen Yang, Ke Wang, Yongyong Shi, Zhuo Wang
2020 Frontiers in Genetics  
using a unified model.  ...  Comprehensive personalized metabolic analysis based on models generated from data of liver HCC in The Cancer Genome Atlas revealed 18 genes essential for tumorigenesis in all three subtypes of patients  ...  using a unified model.  ... 
doi:10.3389/fgene.2020.595242 pmid:33424926 pmcid:PMC7786279 fatcat:dzj2o5erzrca3fbyflntuycjaq

Value of the Application of CE-MRI Radiomics and Machine Learning in Preoperative Prediction of Sentinel Lymph Node Metastasis in Breast Cancer

Yadi Zhu, Ling Yang, Hailin Shen
2021 Frontiers in Oncology  
of machine learning models established based on CE-MRI radiomic features, providing a highly accurate, non-invasive, and convenient method for preoperative prediction of SLNM in breast cancer patients  ...  Meanwhile, the combined model showed better performance in sentinel lymph node metastasis (SLNM) prediction and achieved a higher AUC (0.88) in the validation set.ConclusionsWe revealed the clinical value  ...  The combined model established in this study is simpler than the model established by Yu et al. and has high predictive performance, providing a more convenient and feasible prediction model for clinical  ... 
doi:10.3389/fonc.2021.757111 pmid:34868967 pmcid:PMC8640128 fatcat:sgblnkswazae5aeeipqkdhb4mu

Artificial intelligence radiogenomics for advancing precision and effectiveness in oncologic care (Review)

Eleftherios Trivizakis, Georgios Papadakis, Ioannis Souglakos, Nikolaos Papanikolaou, Lefteris Koumakis, Demetrios Spandidos, Aristidis Tsatsakis, Apostolos Karantanas, Kostas Marias
2020 International Journal of Oncology  
The main deep learning radiogenomics architectures, together with the clinical questions addressed, and the achieved genetic or molecular correlations are presented, while a performance comparison of the  ...  These advances have created unprecedented momentum in computational medical imaging applications and have given rise to new precision medicine research areas.  ...  Technologies in the Preservation of Cultural Heritage and the Tackling of Societal Challenges').  ... 
doi:10.3892/ijo.2020.5063 pmid:32467997 pmcid:PMC7252460 fatcat:dwgljcnhfzhllbfmb2p4ujtb3e

Microenvironmental niche divergence shapes BRCA1-dysregulated ovarian cancer morphological plasticity

Andreas Heindl, Adnan Mujahid Khan, Daniel Nava Rodrigues, Katherine Eason, Anguraj Sadanandam, Cecilia Orbegoso, Marco Punta, Andrea Sottoriva, Stefano Lise, Susana Banerjee, Yinyin Yuan
2018 Nature Communications  
Our findings support a model whereby a subpopulation of morphologically plastic cancer cells with dysregulated DNA repair promotes ovarian cancer progression through positive selection by immune evasion  ...  Integration of this spatially explicit analysis with omics and clinical data reveals a relationship between morphological diversification and the dysregulation of DNA repair, loss of nuclear integrity,  ...  Unbiased, large-scale analysis of cancer morphology within the spatial context of the local microenvironment has the potential to generate more powerful predictive models and identify new targets for this  ... 
doi:10.1038/s41467-018-06130-3 fatcat:v43e3rqhjvag7iusxhubnlhxjm

An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning

Chi-Long Chen, Chi-Chung Chen, Wei-Hsiang Yu, Szu-Hua Chen, Yu-Chan Chang, Tai-I Hsu, Michael Hsiao, Chao-Yuan Yeh, Cheng-Yu Chen
2021 Nature Communications  
Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and  ...  Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators.  ...  Trees-Juen Chuang for careful reading and giving advice on this manuscript. We are grateful to the National Center for High-performance Computing for providing computing resources.  ... 
doi:10.1038/s41467-021-21467-y pmid:33608558 fatcat:thkwoy5xvbcc5jcnv6hd5nohv4

Deep Learning and Its Applications in Computational Pathology

Runyu Hong, David Fenyö
2022 BioMedInformatics  
Deep learning techniques, such as convolutional neural networks (CNNs), generative adversarial networks (GANs), and graph neural networks (GNNs) have, over the past decade, changed the accuracy of prediction  ...  In recent years, the application of deep learning techniques in computer vision tasks in pathology has demonstrated extraordinary potential in assisting clinicians, automating diagnoses, and reducing costs  ...  Acknowledgments: We would like to thank all members of the Fenyö laboratory and the administration team of ISG at NYU. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/biomedinformatics2010010 fatcat:bagnt7eqgnelhnkj5dq7i4bjdu

Cancer classification in the genomic era: five contemporary problems

Qingxuan Song, Sofia D. Merajver, Jun Z. Li
2015 Human Genomics  
Here, we discuss the classification of cancer and the process of categorizing cancer subtypes based on their observed clinical and biological features.  ...  Exploration of these problems is essential for data-driven refinement of cancer classification and the successful application of these concepts in precision medicine.  ...  We thank two anonymous reviewers for their insightful comments.  ... 
doi:10.1186/s40246-015-0049-8 pmid:26481255 pmcid:PMC4612488 fatcat:wq6ehlw5rvfkln4m5qdyzugqce
« Previous Showing results 1 — 15 out of 1,170 results