دورية أكاديمية
Channel Embedding for Informative Protein Identification from Highly Multiplexed Images.
العنوان: | Channel Embedding for Informative Protein Identification from Highly Multiplexed Images. |
---|---|
المؤلفون: | Magid SA; School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA., Jang WD; School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA., Schapiro D; Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, USA.; Klarman Cell Observatory, Broad Institute of MIT and Harvard, Cambridge, MA, USA., Wei D; School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA., Tompkin J; Department of Computer Science, Brown University, Providence, RI, USA., Sorger PK; Department of Systems Biology, Harvard Medical School, Boston, MA, USA., Pfister H; School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA. |
المصدر: | Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention [Med Image Comput Comput Assist Interv] 2020 Oct; Vol. 12265, pp. 3-13. Date of Electronic Publication: 2020 Sep 29. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: Springer Country of Publication: Germany NLM ID: 101249582 Publication Model: Print-Electronic Cited Medium: Print NLM ISO Abbreviation: Med Image Comput Comput Assist Interv Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Berlin ; New York : Springer, c1998- |
مستخلص: | Interest is growing rapidly in using deep learning to classify biomedical images, and interpreting these deep-learned models is necessary for life-critical decisions and scientific discovery. Effective interpretation techniques accelerate biomarker discovery and provide new insights into the etiology, diagnosis, and treatment of disease. Most interpretation techniques aim to discover spatially-salient regions within images, but few techniques consider imagery with multiple channels of information. For instance, highly multiplexed tumor and tissue images have 30-100 channels and require interpretation methods that work across many channels to provide deep molecular insights. We propose a novel channel embedding method that extracts features from each channel. We then use these features to train a classifier for prediction. Using this channel embedding, we apply an interpretation method to rank the most discriminative channels. To validate our approach, we conduct an ablation study on a synthetic dataset. Moreover, we demonstrate that our method aligns with biological findings on highly multiplexed images of breast cancer cells while outperforming baseline pipelines. Code is available at https://sabdelmagid.github.io/miccai2020-project/. |
References: | Curr Protoc Chem Biol. 2016 Dec 7;8(4):251-264. (PMID: 27925668) Cell. 2018 Aug 9;174(4):968-981.e15. (PMID: 30078711) Cell. 2018 Sep 6;174(6):1373-1387.e19. (PMID: 30193111) Nature. 2020 Feb;578(7796):615-620. (PMID: 31959985) |
معلومات مُعتمدة: | U54 CA225088 United States CA NCI NIH HHS |
فهرسة مساهمة: | Keywords: Deep learning; Highly multiplexed imaging; Interpretability |
تواريخ الأحداث: | Date Created: 20201207 Latest Revision: 20201209 |
رمز التحديث: | 20221213 |
مُعرف محوري في PubMed: | PMC7713713 |
DOI: | 10.1007/978-3-030-59722-1_1 |
PMID: | 33283211 |
قاعدة البيانات: | MEDLINE |
DOI: | 10.1007/978-3-030-59722-1_1 |
---|