Early-Stage Lung Cancer Diagnosis by Deep Learning-Based Spectroscopic Analysis of Circulating Exosomes

Abstract

Lung cancer has a high mortality rate, but an early diagnosis can contribute to a favorable prognosis. A liquid biopsy that captures and detects tumor-related biomarkers in body fluids has great potential for early-stage diagnosis. Exosomes, nanosized extracellular vesicles found in blood, have been proposed as promising biomarkers for liquid biopsy. Here, we demonstrate an accurate diagnosis of early-stage lung cancer, using deep learning-based surface-enhanced Raman spectroscopy (SERS) of the exosomes. Our approach was to explore the features of cell exosomes through deep learning and figure out the similarity in human plasma exosomes, without learning insufficient human data. The deep learning model was trained with SERS signals of exosomes derived from normal and lung cancer cell lines and could classify them with an accuracy of 95%. In 43 patients, including stage I and II cancer patients, the deep learning model predicted that plasma exosomes of 90.7% patients had higher similarity to lung cancer cell exosomes than the average of the healthy controls. Such similarity was proportional to the progression of cancer. Notably, the model predicted lung cancer with an area under the curve (AUC) of 0.912 for the whole cohort and stage I patients with an AUC of 0.910. These results suggest the great potential of the combination of exosome analysis and deep learning as a method for early-stage liquid biopsy of lung cancer.

WITHDRAWN: GCC2 is a New Biomarker for Diagnosis of Early Non-Small Cell Lung Cancer and A Potential Target to Reverse Epithelial to Mesenchymal Transition

“…These results suggest that the use of GCC2 as a biomarker may provide accurate information for detecting early-stage NSCLC. Recently, we reported that early-stage lung cancer could be diagnosed through deep-learning-based surfaced-enhanced Raman spectroscopy analysis of the circulating exosomes (30).…”

“…High-quality exosome puri cation is crucial for basic research and applications, such as the diagnostics of various diseases using exosomes. Exosomes were isolated from precleared cell culture media and plasma samples by centrifugation and SEC, as reported in our previous studies (29)(30)(31). NTA was performed to determine the size and concentration of exosomes in the eluted fractions.…”

Immunoassay-aptasensor for the determination of tumor-derived exosomes based on the combination of magnetic nanoparticles and hybridization chain reaction

“…16 A series of novel technologies have been developed for the determination of exosomes, including uorescence detection, 17 electrochemical biosensors, 5,14,18,19 immunosensors, 13,20 surface plasmon resonance (SPR), [21][22][23] microuidic devices, 21 electrochemiluminescence, 24 aptasensors, 25 and spectroscopic analysis. 26 However, these established exosome assays usually involve labour-intensive steps and require extended quantitative protocols and expensive laboratory infrastructures. They suffer from low sensitivity and high-cost and thus are impractical for wide use.…”

The role of exosomes in liquid biopsy for cancer diagnosis and prognosis prediction

“…Importantly, by switching other recognition elements, the SERS probe can also be employed for detecting other biological samples including toxin and bacterial 41 . Intriguingly, the combination of SERS and deep learning model achieved the superb performance for detecting early‐stage NSCLC with the area under the curve (AUC) of 0.912 47 …”