EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images

Yi Li, Xiaomin Xiong iD, Xiaohua Liu, Yihan Wu, Xiaoju Li, Bo Liu, Bo Lin, Yu Li, Bo Xu

PeerJ · 2024

DOI: 10.7717/peerj.18098 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ, 2024. Verfasst von Yi Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, Chongqing University, Chongqing, China. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning, Eosine Yellowish-(YS), Hematoxylin. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chongqing Natural Science Foundation, Chongqing University Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Determining the status of breast cancer susceptibility genes ( BRCA ) is crucial for guiding breast cancer treatment. Nevertheless, the need for BRCA genetic testing among breast cancer patients remains unmet due to high costs and limited resources. This study aimed to develop a Bi-directional Self-Attention Multiple Instance Learning (BiAMIL) algorithm to detect BRCA status from hematoxylin and eosin (H&E) pathological images.

Methods

A total of 319 histopathological slides from 254 breast cancer patients were included, comprising two dependent cohorts. Following image pre-processing, 633,484 tumor tiles from the training dataset were employed to train the self-developed deep-learning model. The performance of the network was evaluated in the internal and external test sets.

Results

BiAMIL achieved AUC values of 0.819 (95% CI [0.673–0.965]) in the internal test set, and 0.817 (95% CI [0.712–0.923]) in the external test set. To explore the relationship between BRCA status and interpretable morphological features in pathological images, we utilized Class Activation Mapping (CAM) technique and cluster analysis to investigate the connections between BRCA gene mutation status and tissue and cell features. Significantly, we observed that tumor-infiltrating lymphocytes and the morphological characteristics of tumor cells appeared to be potential features associated with BRCA status.

Conclusions

An interpretable deep neural network model based on the attention mechanism was developed to predict the BRCA status in breast cancer. Keywords: Breast cancer, BRCA , deep learning, self-attention, interpretability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsDeep LearningEosine Yellowish-(YS)HematoxylinHumansFemaleGenetic Predisposition to DiseaseMiddle AgedAlgorithmsAdultMutation

Stichwörter der Autor:innen

BRCABreast cancerDeep learningInterpretabilitySelf-attention

Substanzen

Eosine Yellowish-(YS)Hematoxylin

Autor:innen und Institutionen

  • School of Medicine, Chongqing University, Chongqing, China.
  • Chongqing Key Laboratory for Intelligent Oncology in Breast Cancer, Chongqing University Cancer Hospital, Chongqing, China.
  • Bioengineering College of Chongqing University, Chongqing, China.
  • Department of Pathology, Chongqing University Cancer Hospital, School of Medicine, Chongqing University, Chongqing, China.

ORCID-Profile: Xiaomin Xiong

Förderung

  • National Natural Science Foundation of China
  • Chongqing Natural Science Foundation
  • Chongqing University Research
  • Chongqing Technology Innovation and Application Development

Zitieren

APA

Li, Y., Xiong, X., Liu, X., Wu, Y., Li, X., Liu, B., Lin, B., Li, Y., & Xu, B. (2024). An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images. PeerJ. https://doi.org/10.7717/peerj.18098

Vancouver

Li Y, Xiong X, Liu X, Wu Y, Li X, Liu B, et al. An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images. PeerJ. 2024. doi:10.7717/peerj.18098

BibTeX
@article{Li2024,
  author = {Li, Yi and Xiong, Xiaomin and Liu, Xiaohua and Wu, Yihan and Li, Xiaoju and Liu, Bo and Lin, Bo and Li, Yu and Xu, Bo},
  title = {An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images},
  journal = {PeerJ},
  year = {2024},
  doi = {10.7717/peerj.18098}
}
Kostenlos starten →