EUVIMEDEUVIMED entdecken
Crossref

A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations

Bangwei Guo, Xingyu Li, Miaomiao Yang, Hong Zhang, Xu Steven Xu

Computerized Medical Imaging and Graphics · 2023-04 · 105 · 102189

DOI: 10.1016/j.compmedimag.2023.102189 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2023-04. Verfasst von Bangwei Guo und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Data Science, University of Science and Technology of China, Hefei, Anhui, China. Hauptthemen laut MEDLINE: Algorithms, Machine Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 42 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-attention mechanism-based algorithms are attractive in digital pathology due to their interpretability, but suffer from computation complexity. This paper presents a novel, lightweight Attention-based Multiple Instance Mutation Learning (AMIML) model to allow small-scale attention operations for predicting gene mutations. Compared to the standard self-attention model, AMIML reduces the number of model parameters by approximately 70%. Using data for 24 clinically relevant genes from four cancer cohorts in TCGA studies (UCEC, BRCA, GBM, and KIRC), we compare AMIML with a standard self-attention model, five other deep learning models, and four traditional machine learning models. The results show that AMIML has excellent robustness and outperforms all the baseline algorithms in the vast majority of the tested genes. Conversely, the performance of the reference deep learning and machine learning models vary across different genes, and produce suboptimal prediction for certain genes. Furthermore, with the flexible and interpretable attention-based pooling mechanism, AMIML can further zero in and detect predictive image patches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsMachine Learning

Stichwörter der Autor:innen

Attention mechanismDeep learningGene MutationMutiple Instance LearningWhole slide images

Autor:innen und Institutionen

  • School of Data Science, University of Science and Technology of China, Hefei, Anhui, China.
  • Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei, Anhui, China.
  • Clinical Pathology Center, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, China.
  • Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei, Anhui, China. Electronic address: zhangh@ustc.edu.cn.
  • Clinical Pharmacology and Quantitative Science, Genmab Inc., Princeton, NJ, USA. Electronic address: sxu@genmab.com.

Zitieren

APA

Guo, B., Li, X., Yang, M., Zhang, H., & Xu, X. S. (2023). A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations. Computerized Medical Imaging and Graphics, 105, 102189. https://doi.org/10.1016/j.compmedimag.2023.102189

Vancouver

Guo B, Li X, Yang M, Zhang H, Xu XS. A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations. Computerized Medical Imaging and Graphics. 2023;105:102189. doi:10.1016/j.compmedimag.2023.102189

BibTeX
@article{Guo2023,
  author = {Guo, Bangwei and Li, Xingyu and Yang, Miaomiao and Zhang, Hong and Xu, Xu Steven},
  title = {A robust and lightweight deep attention multiple instance learning algorithm for predicting genetic alterations},
  journal = {Computerized Medical Imaging and Graphics},
  year = {2023},
  volume = {105},
  pages = {102189},
  doi = {10.1016/j.compmedimag.2023.102189}
}
Kostenlos starten →