AIEgen-deep: Deep learning of single AIEgen-imaging pattern for cancer cell discrimination and preclinical diagnosis

Hua，Haojun1; Deng，Yanlin1; Zhang，Jing5; Zhou，Xiang1,2; Zhang，Tianfu4; Khoo，Bee Luan1,3,6

2024-06-01

10.1016/j.bios.2024.116086

Biosensors and Bioelectronics   影响因子和分区

0956-5663

1873-4235

This study introduces AIEgen-Deep, an innovative classification program combining AIEgen fluorescent dyes, deep learning algorithms, and the Segment Anything Model (SAM) for accurate cancer cell identification. Our approach significantly reduces manual annotation efforts by 80%–90%. AIEgen-Deep demonstrates remarkable accuracy in recognizing cancer cell morphology, achieving a 75.9% accuracy rate across 26,693 images of eight different cell types. In binary classifications of healthy versus cancerous cells, it shows enhanced performance with an accuracy of 88.3% and a recall rate of 79.9%. The model effectively distinguishes between healthy cells (fibroblast and WBC) and various cancer cells (breast, bladder, and mesothelial), with accuracies of 89.0%, 88.6%, and 83.1%, respectively. Our method's broad applicability across different cancer types is anticipated to significantly contribute to early cancer detection and improve patient survival rates.

Aggregation-induced emission Automated classification systems Cancer cell detection Deep learning Early diagnosis techniques Image analysis

SCI ; EI

英语

其他

CHEMISTRY

2-s2.0-85186491135

Scopus

1.City University of Hong Kong,Kowloon,83 Tat Chee Avenue, Hong Kong,999077,China
2.Department of Biomedical Engineering,Southern University of Science and Technology,Shenzhen,518055,China
3.Hong Kong Center for Cerebro-Cardiovascular Health Engineering (COCHE),Hong Kong SAR,China
4.School of Biomedical Engineering,Guangzhou Medical University,Guangzhou,China
5.College of Basic Medicine,Hebei University,Baoding,342 Yuhua West Road, Lianchi District,071000,China
6.Department of Precision Diagnostic and Therapeutic Technology,City University of Hong Kong,Futian-Shenzhen Research Institute,Shenzhen,518057,China

Hua，Haojun,Deng，Yanlin,Zhang，Jing,et al. AIEgen-deep: Deep learning of single AIEgen-imaging pattern for cancer cell discrimination and preclinical diagnosis[J]. Biosensors and Bioelectronics,2024,253.

Hua，Haojun,Deng，Yanlin,Zhang，Jing,Zhou，Xiang,Zhang，Tianfu,&Khoo，Bee Luan.(2024).AIEgen-deep: Deep learning of single AIEgen-imaging pattern for cancer cell discrimination and preclinical diagnosis.Biosensors and Bioelectronics,253.

Hua，Haojun,et al."AIEgen-deep: Deep learning of single AIEgen-imaging pattern for cancer cell discrimination and preclinical diagnosis".Biosensors and Bioelectronics 253(2024).