Deep transfer learning enables lesion tracing of circulating tumor cells

Network properties determine neural network performance

Machine learning influences numerous aspects of modern society, empowers new technologies, from Alphago to ChatGPT, and increasingly materializes in consumer products such as smartphones and self-driving cars. Despite the vital role and broad applications of artificial neural networks, we lack systematic approaches, such as network science, to understand their underlying mechanism. The difficulty is rooted in many possible model configurations, each with different hyper-parameters and weighted architectures determined by noisy data. We bridge the gap by developing a mathematical framework that maps the neural network's performance to the network characters of the line graph governed by the edge dynamics of stochastic gradient descent differential equations. This framework enables us to derive a neural capacitance metric to universally capture a model's generalization capability on a downstream task and predict model performance using only early training results. The numerical results on 17 pre-trained ImageNet models across five benchmark datasets and one NAS benchmark indicate that our neural capacitance metric is a powerful indicator for model selection based only on early training results and is more efficient than state-of-the-art methods.

The Role of Circulating Tumor Cells as a Liquid Biopsy for Cancer: Advances, Biology, Technical Challenges, and Clinical Relevance

Cancer remains a leading cause of mortality worldwide, with metastasis significantly contributing to its lethality. The metastatic spread of tumor cells, primarily through the bloodstream, underscores the importance of circulating tumor cells (CTCs) in oncological research. As a critical component of liquid biopsies, CTCs offer a non-invasive and dynamic window into tumor biology, providing invaluable insights into cancer dissemination, disease progression, and response to treatment. This review article delves into the recent advancements in CTC research, highlighting their emerging role as a biomarker in various cancer types. We explore the latest technologies and methods for CTC isolation and detection, alongside novel approaches to characterizing their biology through genomics, transcriptomics, proteomics, and epigenetic profiling. Additionally, we examine the clinical implementation of these findings, assessing how CTCs are transforming the landscape of cancer diagnosis, prognosis, and management. By offering a comprehensive overview of current developments and potential future directions, this review underscores the significance of CTCs in enhancing our understanding of cancer and in shaping personalized therapeutic strategies, particularly for patients with metastatic disease.

Glowing Octopus-Inspired Nanomachine: A Versatile Aptasensor for Efficient Capture, Imaging, Separation, and NIR-Triggered Release of Cancer Cells

The separation and analysis of circulating tumor cells (CTCs) in liquid biopsy significantly facilitated clinical cancer diagnosis and personalized therapy. However, current methods face challenges in simultaneous efficient capturing, separation, and imaging of CTCs, and most of the devices cannot be reused/regenerated. We present here an innovative glowing octopus-inspired nanomachine (GOIN), capable of capturing, imaging, separating, and controlling the release of cancer cells from whole blood and normal cells. The GOIN comprises an aptamer-decorated magnetic fluorescent covalent organic framework (COF), which exhibits a strong affinity for nucleolin-overexpressed cancer cells through a multivalent binding effect. The captured cancer cells can be directly imaged using the intrinsic stable fluorescence of the COF layer in the GOIN. Employing magnet and NIR laser assistance enables easy separation and mild photothermal release of CTCs from the normal cells and the nanomachine without compromising cell viability. Moreover, the GOIN demonstrates a reusing capability, as the NIR-triggered CTC release is mild and nondestructive, allowing the GOIN to be reused at least three times.

Deciphering the Biology of Circulating Tumor Cells through Single-Cell RNA Sequencing: Implications for Precision Medicine in Cancer

Circulating tumor cells (CTCs) hold unique biological characteristics that directly involve them in hematogenous dissemination. Studying CTCs systematically is technically challenging due to their extreme rarity and heterogeneity and the lack of specific markers to specify metastasis-initiating CTCs. With cutting-edge technology, single-cell RNA sequencing (scRNA-seq) provides insights into the biology of metastatic processes driven by CTCs. Transcriptomics analysis of single CTCs can decipher tumor heterogeneity and phenotypic plasticity for exploring promising novel therapeutic targets. The integrated approach provides a perspective on the mechanisms underlying tumor development and interrogates CTCs interactions with other blood cell types, particularly those of the immune system. This review aims to comprehensively describe the current study on CTC transcriptomic analysis through scRNA-seq technology. We emphasize the workflow for scRNA-seq analysis of CTCs, including enrichment, single cell isolation, and bioinformatic tools applied for this purpose. Furthermore, we elucidated the translational knowledge from the transcriptomic profile of individual CTCs and the biology of cancer metastasis for developing effective therapeutics through targeting key pathways in CTCs.

Tumor Microenvironment-Inspired Glutathione-Responsive Three-Dimensional Fibrous Network for Efficient Trapping and Gentle Release of Circulating Tumor Cells

Detection of circulating tumor cells (CTCs) is important for early cancer diagnosis, prediction of postoperative recurrence, and individualized treatment. However, it is still challenging to achieve efficient capture and gentle release of CTCs from the complex peripheral blood due to their rarity and fragility. Herein, inspired by the three-dimensional (3D) network structure and high glutathione (GSH) level of the tumor microenvironment (TME), a 3D stereo (3D-G@FTP) fibrous network is developed by combining the liquid-assisted electrospinning method, gas foaming technique, and metal-polyphenol coordination interactions to achieve efficient trapping and gentle release of CTCs. Compared with the traditional 2D@FTP fibrous scaffold, the 3D-G@FTP fibrous network could achieve higher capture efficiency (90.4% vs 78.5%) toward cancer cells in a shorter time (30 min vs 90 min). This platform showed superior capture performance toward heterogeneous cancer cells (HepG2, HCT116, HeLa, and A549) in an epithelial cell adhesion molecule (EpCAM)-independent manner. In addition, the captured cells with high cell viability (>90.0%) could be gently released under biologically friendly GSH stimulus. More importantly, the 3D-G@FTP fibrous network could sensitively detect 4-19 CTCs from six kinds of cancer patients' blood samples. We expect this TME-inspired 3D stereo fibrous network integrating efficient trapping, broad-spectrum recognition, and gentle release will promote the development of biomimetic devices for rare cell analysis.

Liquid biopsies and minimal residual disease in myeloid malignancies

Minimal residual disease (MRD) assessment through blood component sampling by liquid biopsies (LBs) is increasingly being investigated in myeloid malignancies. Blood components then undergo molecular analysis by flow cytometry or sequencing techniques and can be used as a powerful tool for prognostic and predictive purposes in myeloid malignancies. There is evidence and more is evolving about the quantification and identification of cell-based and gene-based biomarkers in myeloid malignancies to monitor treatment response. MRD based acute myeloid leukemia protocol and clinical trials are currently incorporating LB testing and preliminary results are encouraging for potential widespread use in clinic in the near future. MRD monitoring using LBs are not standard in myelodysplastic syndrome (MDS) but this is an area of active investigation. In the future, LBs can replace more invasive techniques such as bone marrow biopsies. However, the routine clinical application of these markers continues to be an issue due to lack of standardization and limited number of studies investigating their specificities. Integrating artificial intelligence (AI) could help simplify the complex interpretation of molecular testing and reduce errors related to operator dependency. Though the field is rapidly evolving, the applicability of MRD testing using LB is mostly limited to research setting at this time due to the need for validation, regulatory approval, payer coverage, and cost issues. This review focuses on the types of biomarkers, most recent research exploring MRD and LB in myeloid malignancies, ongoing clinical trials, and the future of LB in the setting of AI.