Rapid and sensitive acute leukemia classification and diagnosis platform using deep learning-assisted SERS detection.

Cell Rep Med

Center for Biomedical-photonics and Molecular Imaging, Advanced Diagnostic-Therapy Technology and Equipment Key Laboratory of Higher Education Institutions in Shaanxi Province, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China; Engineering Research Center of Mole

Published: August 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Rapid identification and accurate diagnosis are critical for individuals with acute leukemia (AL). Here, we propose a combined deep learning and surface-enhanced Raman scattering (DL-SERS) classification strategy to achieve rapid and sensitive identification of AL with various subtypes and genetic abnormalities. More than 390 of cerebrospinal fluid (CSF) samples are collected as targets, encompassing healthy control, AL patients, and individuals with other diseases. Sensitive SERS detection could be achieved within 5 min, using only 0.5 μL volume of CSF. Through integrated feature fusion (1D spectra and 2D image) with a transformer model, the classification method is developed to screen and diagnose AL patients, demonstrating exceptional classification performances of accuracy, sensitivity, specificity, or reliability. Also, this approach demonstrates remarkable versatility and could be extended to the classifications of meningitis diseases. The sensitive DL-SERS classification platform has the potential to be a powerful auxiliary in vitro diagnostic tool.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.xcrm.2025.102320DOI Listing

Publication Analysis

Top Keywords

rapid sensitive
8
acute leukemia
8
sers detection
8
dl-sers classification
8
diseases sensitive
8
classification
5
sensitive acute
4
leukemia classification
4
classification diagnosis
4
diagnosis platform
4

Similar Publications

Objectives In Japan, clinical diagnosis based solely on symptoms, without the use of test kits, has been adopted to enable the rapid identification of individuals infected with coronavirus disease 2019 (COVID-19). A history of close contact with COVID-19 patients is a prerequisite for such symptom-based diagnosis. However, the current diagnostic criteria lack objectivity.

View Article and Find Full Text PDF

Background And Aim: Bovine babesiosis, caused by , poses significant economic challenges to Kazakhstan's cattle industry. Early and accurate detection is crucial for interrupting transmission cycles, particularly in regions lacking advanced diagnostic infrastructure. This study aimed to develop a rapid lateral flow immunoassay (LFIA) using a recombinant C-terminal fragment of the recombinant rhoptry-associated protein 1 (rRap1) antigen for the serodiagnosis of bovine babesiosis.

View Article and Find Full Text PDF

Abnormal glycosylation is widespread in cancer, and the overexpression of glycoantigens is a manifestation of glycosylation abnormalities. Tn antigen, sTn antigen, and T antigen are known as tumor-associated glycoantigens, and their expression varies in different tumors or subtypes of the same tumor. Therefore, simultaneous detection of these three glycoantigens is of great significance for the diagnosis of tumors.

View Article and Find Full Text PDF

A directional self-priming continuous-driven compartmentalized microfluidic chip for multiplexed pathogen detection.

Analyst

September 2025

Research Centre for Analytical Instrumentation, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, P. R. China.

Rapid and efficient screening of foodborne pathogens is crucial for preventing bacterial spread and food poisoning. However, developing a multi-detection method that is easy to operate, offers good stability, and achieves high efficiency remains an enormous challenge. Existing multiplexed nucleic acid detection methods suffer from complex designs, leading to complicated operations, and non-robust sample introduction, causing primer/probe crosstalk and false-positive results.

View Article and Find Full Text PDF

Nucleic acid-based therapeutics, such as oncolytic virotherapy or gene therapy, would benefit greatly from a reporter gene that induces endogenous production of a protein biomarker to noninvasively track the delivery, persistence, and spread with imaging. Several chemical exchange saturation transfer (CEST) reporter proteins detectable by magnetic resonance imaging (MRI) have been demonstrated to have high sensitivity. However, to date none can provide strong CEST contrast at a distinct resonance from that of endogenous proteins, limiting their specificity.

View Article and Find Full Text PDF