Nanotechnology and machine learning enable circulating tumor cells as a reliable biomarker for radiotherapy responses of gastrointestinal cancer patients

Inhalable DNase I@Au hybrid nanoparticles for radiation sensitization and metastasis inhibition by elimination of neutrophil extracellular traps

High-dose radiation therapy is a widely used clinical strategy to inhibit tumor growth. However, the rapid generation of excessive reactive oxygen species (ROS) triggers the formation of neutrophil extracellular traps (NETs), which capture free tumor cells in the bloodstream, promoting metastasis. In this study, we developed a hybrid nanoparticle composed of DNase I and gold (DNase I@Au) to enhance radiotherapy efficacy while mitigating metastasis by precisely eliminating NETs. The DNase I@Au nanoparticles, administered via aerosol inhalation, are efficiently delivered to lung tumor tissue, improving radiosensitization and reducing tumor size. Crucially, the nanoparticles could gradually release DNase I, effectively degrading ROS-induced NETs and preventing the interaction of free malignant cells with tumor sites or vasculature, thereby inhibiting metastasis. Therefore, we provide an enzyme and sensitizer co-loaded strategy that offers a promising approach to improve the therapeutic outcome of radiotherapy and reduce the risk of lung cancer metastasis under ROS stimulation.

Postoperative circulating tumor cells predict the benefits of tyrosine kinase inhibitor for hepatocellular carcinoma after transplantation

AIM

Circulating tumor cells (CTC) have shown promise in predicting the outcomes of adjuvant treatments for several malignancies. The clinical significance of CTC in predicting the efficacy of tyrosine kinase inhibitor (TKI) administration in patients with hepatocellular carcinoma (HCC) was unclear.

METHODS

A total of 429 patients who underwent liver transplantation for HCC had provided 335 preoperative and 373 postoperative blood samples that could be used for CTC detection (pre-CTC and post-CTC). The association of the pre-CTC and post-CTC findings with the efficacy of TKI administration was assessed. Additionally, CTC surveillance was performed in 27 patients during TKI administration.

RESULTS

Patients with detectable post-CTC, instead of pre-CTC, showed a significantly longer time to recurrence when receiving a TKI after liver transplantation for HCC (hazard ratio 0.57; P = 0.042). Whereas patients without detectable post-CTC did not benefit from the TKI administration (P = 0.270). Furthermore, we also found that patients who persistently harbored CTC during TKI administration showed significantly higher early recurrence rates (≤1 year; 40% vs. 5.9%, P < 0.001) and a shorter time to recurrence (HR 7.03; P < 0.001) than those whose CTC status switched from positive to negative. In addition, longitudinal CTC monitoring demonstrated that CTC tended to reflect drug resistance during TKI administration.

CONCLUSIONS

The postoperative CTC level could predict the efficacy of TKI treatment for HCC patients after liver transplantation. Dynamic monitoring for CTC during treatment could sensitively reflect the response to the TKI, the development of drug resistance, and foresee tumor recurrence.

Advanced NLP-driven predictive modeling for tailored treatment strategies in gastrointestinal cancer

Gastrointestinal cancer represents a significant health burden, necessitating innovative approaches for personalized treatment. This study aims to develop an advanced natural language processing (NLP)-driven predictive modeling framework for tailored treatment strategies in gastrointestinal cancer, leveraging the capabilities of deep learning. The Resilient Adam Algorithm-driven Versatile Long-Short Term Memory (RAA-VLSTM) model is proposed to analyze comprehensive clinical data. The dataset comprises extensive electronic health records (EHRs) from multiple healthcare centers, focusing on patient demographics, clinical history, treatment outcomes, and genetic factors. Data preprocessing employs techniques such as tokenization, normalization, and stop-word removal to ensure effective representation of textual data. For feature extraction, state-of-the-art word embeddings are utilized to enhance model performance. The proposed framework outlines a comprehensive process: data collection from EHRs, preprocessing to prepare the data for analysis, and employing NLP techniques to extract meaningful features. The RAA optimization algorithm significantly improves training efficiency by adapting learning rates for each parameter, addressing common issues in gradient descent. This optimization enhances feature learning from sequential clinical data, enabling accurate predictions of treatment responses and outcomes. The overall performance in terms of F1-score (89.4%), accuracy (92.5%), recall (88.7%), and precision (90.1%). Preliminary results demonstrate the model's strong predictive capabilities, achieving high accuracy in predicting treatment outcomes, thereby suggesting its potential to improve individualized care. In conclusion, this study establishes a robust foundation for employing advanced NLP and machine learning techniques in the management of gastrointestinal cancer, paving the way for future research and clinical applications.

Dual Biomarker Strategies for Liquid Biopsy: Integrating Circulating Tumor Cells and Circulating Tumor DNA for Enhanced Tumor Monitoring

The liquid biopsy has gained significant attention in cancer diagnostics, with circulating tumor cells (CTCs) and circulating tumor DNA (ctDNA) being recognized as key biomarkers for tumor detection and monitoring. However, each biomarker possesses inherent limitations that restrict its standalone clinical utility, such as the rarity and heterogeneity of CTCs and the variable sensitivity and specificity of ctDNA assays. This highlights the necessity of integrating both biomarkers to maximize diagnostic and prognostic potential, offering a more comprehensive understanding of the tumor biology and therapeutic response. In this review, we summarize clinical studies that have explored the combined analysis of CTCs and ctDNA as biomarkers, providing insights into their synergistic value in diverse tumor types. Specifically, this paper examines the individual advantages and limitations of CTCs and ctDNA, details the findings of combined biomarker studies across various cancers, highlights the benefits of dual biomarker approaches over single-biomarker strategies, and discusses future prospects for advancing personalized oncology through liquid biopsies. By offering a comprehensive overview of clinical studies combining CTCs and ctDNA, this review serves as a guideline for researchers and clinicians aiming to enhance biomarker-based strategies in oncology and informs biosensor design for improved biomarker detection.

Gastrointestinal cancer resistance to treatment: the role of microbiota

The most common illnesses that adversely influence human health globally are gastrointestinal malignancies. The prevalence of gastrointestinal cancers (GICs) is relatively high, and the majority of patients receive ineffective care since they are discovered at an advanced stage of the disease. A major component of the human body is thought to be the microbiota of the gastrointestinal tract and the genes that make up the microbiome. The gut microbiota includes more than 3000 diverse species and billions of microbes. Each of them has benefits and drawbacks and been demonstrated to alter anticancer medication efficacy. Treatment of GIC with the help of the gut bacteria is effective while changes in the gut microbiome which is linked to resistance immunotherapy or chemotherapy. Despite significant studies and findings in this field, more research on the interactions between microbiota and response to treatment in GIC are needed to help researchers provide more effective therapeutic strategies with fewer treatment complication. In this review, we examine the effect of the human microbiota on anti-cancer management, including chemotherapy, immunotherapy, and radiotherapy.

Quantitative image analysis pipeline for detecting circulating hybrid cells in immunofluorescence images with human-level accuracy

Circulating hybrid cells (CHCs) are a newly discovered, tumor-derived cell population found in the peripheral blood of cancer patients and are thought to contribute to tumor metastasis. However, identifying CHCs by immunofluorescence (IF) imaging of patient peripheral blood mononuclear cells (PBMCs) is a time-consuming and subjective process that currently relies on manual annotation by laboratory technicians. Additionally, while IF is relatively easy to apply to tissue sections, its application to PBMC smears presents challenges due to the presence of biological and technical artifacts. To address these challenges, we present a robust image analysis pipeline to automate the detection and analysis of CHCs in IF images. The pipeline incorporates quality control to optimize specimen preparation protocols and remove unwanted artifacts, leverages a β-variational autoencoder (VAE) to learn meaningful latent representations of single-cell images, and employs a support vector machine (SVM) classifier to achieve human-level CHC detection. We created a rigorously labeled IF CHC data set including nine patients and two disease sites with the assistance of 10 annotators to evaluate the pipeline. We examined annotator variation and bias in CHC detection and provided guidelines to optimize the accuracy of CHC annotation. We found that all annotators agreed on CHC identification for only 65% of the cells in the data set and had a tendency to underestimate CHC counts for regions of interest (ROIs) containing relatively large amounts of cells (>50,000) when using the conventional enumeration method. On the other hand, our proposed approach is unbiased to ROI size. The SVM classifier trained on the β-VAE embeddings achieved an F1 score of 0.80, matching the average performance of human annotators. Our pipeline enables researchers to explore the role of CHCs in cancer progression and assess their potential as a clinical biomarker for metastasis. Further, we demonstrate that the pipeline can identify discrete cellular phenotypes among PBMCs, highlighting its utility beyond CHCs.

Advancing Healthcare: Synergizing Biosensors and Machine Learning for Early Cancer Diagnosis

Cancer is a fatal disease and a significant cause of millions of deaths. Traditional methods for cancer detection often have limitations in identifying the disease in its early stages, and they can be expensive and time-consuming. Since cancer typically lacks symptoms and is often only detected at advanced stages, it is crucial to use affordable technologies that can provide quick results at the point of care for early diagnosis. Biosensors that target specific biomarkers associated with different types of cancer offer an alternative diagnostic approach at the point of care. Recent advancements in manufacturing and design technologies have enabled the miniaturization and cost reduction of point-of-care devices, making them practical for diagnosing various cancer diseases. Furthermore, machine learning (ML) algorithms have been employed to analyze sensor data and extract valuable information through the use of statistical techniques. In this review paper, we provide details on how various machine learning algorithms contribute to the ongoing development of advanced data processing techniques for biosensors, which are continually emerging. We also provide information on the various technologies used in point-of-care cancer diagnostic biosensors, along with a comparison of the performance of different ML algorithms and sensing modalities in terms of classification accuracy.

Circulating tumor cell abundance in head and neck squamous cell carcinoma decreases with successful chemoradiation and cetuximab treatment

Head and neck squamous cell carcinoma (HNSCC) is a common and deadly cancer. Circulating tumor cell (CTC) abundance may a valuable, prognostic biomarker in low- and intermediate-risk patients. However, few technologies have demonstrated success in detecting CTCs in these populations. We prospectively collected longitudinal CTC counts from two cohorts of patients receiving treatments at our institution using a highly sensitive device that purifies CTCs using biomimetic cell rolling and dendrimer-conjugated antibodies. In patients with intermediate risk human papillomavirus (HPV)-positive HNSCC, elevated CTC counts were detected in 13 of 14 subjects at screening with a median of 17 CTC/ml (range 0.2-2986.5). A second cohort of non-metastatic, HPV- HNSCC subjects received cetuximab monotherapy followed by surgical resection. In this cohort, all subjects had elevated baseline CTC counts median of 73 CTC/ml (range 5.4-332.9) with statistically significant declines during treatment. Interestingly, two patients with recurrent disease had elevated CTC counts during and following treatment, which also correlated with growth of size and ki67 expression in the primary tumor. The results suggest that our device may be a valuable tool for evaluating the success of less intensive treatment regimens.