A multicenter proof-of-concept study on deep learning-based intraoperative discrimination of primary central nervous system lymphoma

Xinke Zhang, Zihan Zhao, Ruixuan Wang, Haohua Chen, Xueyi Zheng, Lili Liu, Lilong Lan, Peng Li, Shuyang Wu, Qinghua Cao, Rongzhen Luo, Wanming Hu, Shanshan Lyu, Zhengyu Zhang, Dan Xie (), Yaping Ye (), Yu Wang () and Muyan Cai ()
Additional contact information
Xinke Zhang: Sun Yat-sen University Cancer Center
Zihan Zhao: Sun Yat-sen University Cancer Center
Ruixuan Wang: Sun Yat-sen University
Haohua Chen: Sun Yat-sen University Cancer Center
Xueyi Zheng: Sun Yat-sen University Cancer Center
Lili Liu: Sun Yat-sen University Cancer Center
Lilong Lan: Sun Yat-sen University Cancer Center
Peng Li: Sun Yat-sen University Cancer Center
Shuyang Wu: Sun Yat-sen University Cancer Center
Qinghua Cao: Sun Yat-sen University
Rongzhen Luo: Sun Yat-sen University Cancer Center
Wanming Hu: Sun Yat-sen University Cancer Center
Shanshan Lyu: Guangdong Provincial People’s Hospital
Zhengyu Zhang: Soutern Medical University
Dan Xie: Sun Yat-sen University Cancer Center
Yaping Ye: Soutern Medical University
Yu Wang: Soutern Medical University
Muyan Cai: Sun Yat-sen University Cancer Center

Nature Communications, 2024, vol. 15, issue 1, 1-15

Abstract: Abstract Accurate intraoperative differentiation of primary central nervous system lymphoma (PCNSL) remains pivotal in guiding neurosurgical decisions. However, distinguishing PCNSL from other lesions, notably glioma, through frozen sections challenges pathologists. Here we sought to develop and validate a deep learning model capable of precisely distinguishing PCNSL from non-PCNSL lesions, especially glioma, using hematoxylin and eosin (H&E)-stained frozen whole-slide images. Also, we compared its performance against pathologists of varying expertise. Additionally, a human-machine fusion approach integrated both model and pathologic diagnostics. In external cohorts, LGNet achieved AUROCs of 0.965 and 0.972 in distinguishing PCNSL from glioma and AUROCs of 0.981 and 0.993 in differentiating PCNSL from non-PCNSL lesions. Outperforming several pathologists, LGNet significantly improved diagnostic performance, further augmented to some extent by fusion approach. LGNet’s proficiency in frozen section analysis and its synergy with pathologists indicate its valuable role in intraoperative diagnosis, particularly in discriminating PCNSL from glioma, alongside other lesions.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-48171-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-48171-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-48171-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().