BackgroundDetection of circulating tumor cells (CTCs) is a promising technology in tumor management; however, the slow development of CTC identification methods hinders their clinical utility. Moreover, CTC detection is currently challenging owing to major issues such as isolation and correct identification. To improve the identification efficiency of glioma CTCs, we developed a karyoplasmic ratio (KR)-based identification method and constructed an automatic recognition algorithm. We also intended to determine the correlation between high-KR CTC and patients’ clinical characteristics.MethodsCTCs were isolated from the peripheral blood samples of 68 glioma patients and analyzed using DNA-seq and immunofluorescence staining. Subsequently, the clinical information of both glioma patients and matched individuals was collected for analyses. ROC curve was performed to evaluate the efficiency of the KR-based identification method. Finally, CTC images were captured and used for developing a CTC recognition algorithm.ResultsKR was a better parameter than cell size for identifying glioma CTCs. We demonstrated that low CTC counts were independently associated with isocitrate dehydrogenase (IDH) mutations (p = 0.024) and 1p19q co-deletion status (p = 0.05), highlighting its utility in predicting oligodendroglioma (area under the curve = 0.770). The accuracy, sensitivity, and specificity of our algorithm were 93.4%, 81.0%, and 97.4%, respectively, whereas the precision and F1 score were 90.9% and 85.7%, respectively.ConclusionOur findings remarkably increased the efficiency of detecting glioma CTCs and revealed a correlation between CTC counts and patients’ clinical characteristics. This will allow researchers to further investigate the clinical utility of CTCs. Moreover, our automatic recognition algorithm can maintain high precision in the CTC identification process, shorten the time and cost, and significantly reduce the burden on clinicians.

Background2021 World Health Organization (WHO) Central Nervous System (CNS) tumor classification increasingly emphasizes the important role of molecular markers in glioma diagnoses. Preoperatively non-invasive “integrated diagnosis” will bring great benefits to the treatment and prognosis of these patients with special tumor locations that cannot receive craniotomy or needle biopsy. Magnetic resonance imaging (MRI) radiomics and liquid biopsy (LB) have great potential for non-invasive diagnosis of molecular markers and grading since they are both easy to perform. This study aims to build a novel multi-task deep learning (DL) radiomic model to achieve preoperative non-invasive “integrated diagnosis” of glioma based on the 2021 WHO-CNS classification and explore whether the DL model with LB parameters can improve the performance of glioma diagnosis.MethodsThis is a double-center, ambispective, diagnostical observational study. One public database named the 2019 Brain Tumor Segmentation challenge dataset (BraTS) and two original datasets, including the Second Affiliated Hospital of Nanchang University, and Renmin Hospital of Wuhan University, will be used to develop the multi-task DL radiomic model. As one of the LB techniques, circulating tumor cell (CTC) parameters will be additionally applied in the DL radiomic model for assisting the “integrated diagnosis” of glioma. The segmentation model will be evaluated with the Dice index, and the performance of the DL model for WHO grading and all molecular subtype will be evaluated with the indicators of accuracy, precision, and recall.DiscussionSimply relying on radiomics features to find the correlation with the molecular subtypes of gliomas can no longer meet the need for “precisely integrated prediction.” CTC features are a promising biomarker that may provide new directions in the exploration of “precision integrated prediction” based on the radiomics, and this is the first original study that combination of radiomics and LB technology for glioma diagnosis. We firmly believe that this innovative work will surely lay a good foundation for the “precisely integrated prediction” of glioma and point out further directions for future research.Clinical trail registrationThis study was registered on ClinicalTrails.gov on 09/10/2022 with Identifier NCT05536024.