Non-invasive Cancer Diagnosis Research Articles

Atomic Force Microscopy-based assessment of multimechanical cellular properties for classification of graded bladder cancer cells and cancer early diagnosis using machine learning analysis.

Cellular mechanical properties (CMPs) have been frequently reported as biomarkers for cell cancerization to assist objective cytology, compared to the current subjective method dependent on cytomorphology. However, single or dual CMPs cannot always successfully distinguish every kind of malignant cell from its benign counterpart. In this work, we extract 4 CMPs of four different graded bladder cancer (BC) cell lines by AFM (atomic force microscopy)-based nanoindentation to generate a CMP database, which is used to train a cancerization-grade classifier by machine learning. The classifier is tested on 4 categories of BC cells at different cancer grades. The classification shows split-independent robustness and an accuracy of 91.25% with an AUC-ROC (ROC stands for receiver operating characteristic, and ROC curve is a graphical plot which illustrates the performance of a binary classifier system as its discrimination threshold is varied) value of 97.98%. Finally, we also compare our proposed method with traditional invasive diagnosis and noninvasive cancer diagnosis relying on cytomorphology, in terms of accuracy, sensitivity and specificity. Unlike former studies focusing on the discrimination between normal and cancerous cells, our study fulfills the classification of 4 graded cell lines at different cancerization stages, and thus provides a potential method for early detection of cancerization. STATEMENT OF SIGNIFICANCE: We measured four cellular mechanical properties (CMPs) of 4 graded bladder cancer (BC) cell lines using AFM (atomic force microscopy). We found that single or dual CMPs cannot fulfill the task of BC cell classification. Instead, we employ MLA (Machine Learning Algorithm)-based analysis whose inputs are BC CMPs. Compared with traditional cytomorphology-based prognoses, the non-invasive method proposed in this study has higher accuracy but with many fewer cellular properties as inputs. The proposed non-invasive prognosis is characterized with high sensitivity and specificity, and thus provides a potential tumor-grading means to identify cancer cells with different metastatic potential. Moreover, our study proposes an objective grading method based on quantitative characteristics desirable for avoiding misdiagnosis induced by ambiguous subjectivity.

Proximity hybridization-regulated CRISPR/Cas12a-based dual signal amplification strategy for sensitive detection of circulating tumor DNA

Circulating tumor DNA (ctDNA) is regarded as an ideal candidate biomarker for the non-invasive diagnosis of cancer. However, the lack of convenient and reliable detection methods for ctDNA restricts its clinical application. Herein, we developed a dual signal amplification strategy for sensitive detection of ctDNA based on hybridization chain reaction (HCR) and proximity hybridization-regulated CRISPR/Cas12a. The ctDNA initiates HCR through the continuous hybridization of two hairpin probes (H1 and H2), yielding long nicked double-stranded DNA nanowires composed of numerous split segments, which are successively connected to activate the trans-cleavage activity of CRISPR/Cas12a. In this case, the doubly labeled single-stranded DNA reporter can be cleaved to produce a strong fluorescent signal. Owing to the dual amplification of HCR and CRISPR/Cas12a, this strategy exhibits high sensitivity toward ctDNA with a low detection limit of 5.43 fM. Moreover, the proposed method was successfully applied for ctDNA detection in serum samples with satisfactory results, which has great potential in the clinical diagnosis of cancer.

Machine Learning in Lung Cancer Radiomics

Lung cancer is the leading cause of cancer-related deaths worldwide. Medical imaging technologies such as computed tomography (CT) and positron emission tomography (PET) are routinely used for non-invasive lung cancer diagnosis. In clinical practice, physicians investigate the characteristics of tumors such as the size, shape and location from CT and PET images to make decisions. Recently, scientists have proposed various computational image features that can capture more information than that directly perceivable by human eyes, which promotes the rise of radiomics. Radiomics is a research field on the conversion of medical images into high-dimensional features with data-driven methods to help subsequent data mining for better clinical decision support. Radiomic analysis has four major steps: image preprocessing, tumor segmentation, feature extraction and clinical prediction. Machine learning, including the high-profile deep learning, facilitates the development and application of radiomic methods. Various radiomic methods have been proposed recently, such as the construction of radiomic signatures, tumor habitat analysis, cluster pattern characterization and end-to-end prediction of tumor properties. These methods have been applied in many studies aiming at lung cancer diagnosis, treatment and monitoring, shedding light on future non-invasive evaluations of the nodule malignancy, histological subtypes, genomic properties and treatment responses. In this review, we summarized and categorized the studies on the general workflow, methods for clinical prediction and clinical applications of machine learning in lung cancer radiomic studies, introduced some commonly-used software tools, and discussed the limitations of current methods and possible future directions.

Expression of Epithelial and Mesenchymal Markers in Plasmatic Extracellular Vesicles as a Diagnostic Tool for Neoplastic Processes.

Tumor-derived extracellular vesicles (TD-EVs) have active roles as cancer hallmark enablers. EVs RNA of epithelial and stromal cells carry information that facilitates the communication processes that contribute to oncological progression, so the objective of this work was to validate by RT-PCR the presence of epithelial (KRT19; CEA) and stromal (COL1A2; COL11A1) markers in RNA of plasmatic EVs in healthy and diverse-malignancy patients for the development of a non-invasive cancer diagnosis system using liquid biopsy. Ten asymptomatic controls and 20 cancer patients were included in the study, and results showed that the isolated plasmatic EVs by scanning transmission electron microscopy (STEM) andBiomedical Research Institute A Coruña nanoparticle tracking analysis (NTA) contained most exosome structures with also a considerable percentage of microvesicles. No differences were found in concentration and size distribution between the two cohorts of patients, but significant gene expression in epithelial and mesenchymal markers between healthy donors and patients with active oncological disease was shown. Results of quantitative RT-PCR are solid and reliable for KRT19, COL1A2, and COL11A1, so the analysis of RNA extracted from TD-EVs could be a correct approach to develop a diagnostic tool in oncological processes.

R.E.A.C.T-Rapid Electro-Analytical graphitic Carbon nitride-based screening Tool for lung cancer – Case study using heptane

Early disease detection and diagnosis through breath-based chemical assessment is broadly studied as a non-invasive tool and used as a cutting-edge opportunity in health care. Breath analytics or Breathomics is based on the recognition of levels of metabolites such as Volatile Organic Compounds (VOCs) and inorganic gases in an exhaled human breath. Lung cancer, one such disease state, alters the concentrations of hydrocarbons released in breath due to oxidative stress and lipid pre-oxidation. Heptane can be utilized as a VOC biomarker for the non-invasive diagnosis of lung cancer. This work outlines the fabrication of a graphitic carbon nitride-based electrochemical sensor platform that possesses increased catalytic activity and can be used for the screening of heptane vapors in the range of 0.45–5 ppm limit of detection of 0.45 ppm with 95% confidence interval. The synthesized material is characterized and validated using various standard analytical methods. Chronoamperometry is employed as an electrochemical technique to examine the diffusion dynamics of the target analyte. We demonstrated the specific sensing responses of the system in the presence of interferants by executing a cross-reactivity study with respect to other commonly found interferants in breath. We effectively established the use of a graphitic carbon nitride-based electrochemical sensor for point-of-care screening (qualitative analysis with p < 0.05) of heptane levels by the development of a prototype device utilizing a commercial microelectronic board. We envision that the in-house fabricated modified electrode platform can aid in early screening for lung cancer, thus leading to a reduction in the mortality rate.

A novel bidirectional perfusion-like administered system for NIR-II fluorescence imaging precision diagnosis of bladder cancer

Intravesical instillation has been considered an efficient route for detecting bladder cancer. However, only a small fraction of administered dose permeates into tumor tissues, and insufficient retention time limits their application. In this work, a novel intravesical bidirectional perfusion-like administered mode was developed to improve diagnostic accuracy of bladder tumor imaging. Specifically, the ultrasmall AuPd-P-FA Nanoprobe exhibit excellent NIR-II FL imaging performance due to electronic structure perturbation. Benefiting from the size advantage for kidney metabolism and FA targeting specificity, AuPd-P-FA could effectively administration to bladder tumor. When AuPd-P-FA reached maximum enrichment at 1 h post-injection, the localized and mild thermal energy produced upon laser irradiation activated a phase transition. This thermo-sensitive characteristic could prolong the retention time in bladder and the fluorescence signal could be clearly observed at 6 h post-injection with high accuracy. This novel intravesical bidirectional perfusion-like administered mode is expected to achieve a non-invasive diagnosis of early bladder cancer.

Progress in the Application of Energy-spectrum CT Imaging and Radiomics for the Diagnosis of Lung Cancer and Subtype Differentiation

Lung cancer is the most prevalent malignancy and a serious threat to human health, and the early non-invasive diagnosis of lung cancer has been a hot topic of research in recent years. Lung cancer is subtyped into small cell lung cancer and non-small cell lung cancer, which is closely related to long-term smoking exposure history and chronic lung diseases, and its subtypes are inseparable from the diagnosis and prognosis of lung cancer. With the iterative development of CT technology, energy spectrum CT has been applied. Energy spectral CT of lung cancer can reduce artifacts, improve signal-to-noise ratio and clarity of images, and provide more information for CT diagnosis of lung cancer by combining multi-parameter energy spectral data at the same time. Radiomics refers to the acquisition of a large number of imaging histological features from other imaging images such as CT, ultrasound and MR, and the selection of valuable imaging histological clinical data for analysis. The exploration of disease by energy-spectrum CT combined with radiomics is a hot spot and trend in current research, and this paper will review the research progress of both on lung cancer subtypes.

Poly(ethylene oxide) Concentration Gradient-Based Microfluidic Isolation of Circulating Tumor Cells

Circulating tumor cells (CTCs) have emerged as promising circulating biomarkers for non-invasive cancer diagnosis and management. Isolation and detection of CTCs in clinical samples are challenging due to the extreme rarity and high heterogeneity of CTCs. Here, we describe a poly(ethylene oxide) (PEO) concentration gradient-based microfluidic method for rapid, label-free, highly efficient isolation of CTCs directly from whole blood samples. Stable concentration gradients of PEO were formed within the microchannel by co-injecting the side fluid (blood sample spiked with 0.025% PEO) and center fluid (0.075% PEO solution). The competition between the elastic lift force and the inertial lift force enabled size-based separation of large CTCs and small blood cells based on their distinct migration patterns. The microfluidic device could process 1 mL of blood sample in 30 min, with a separation efficiency of >90% and an enrichment ratio of >700 for tumor cells. The isolated CTCs from blood samples were enumerated by immunofluorescence staining, allowing for discrimination of breast cancer patients from healthy donors with an accuracy of 84.2%. The concentration gradient-based microfluidic separation provides a powerful tool for label-free isolation of CTCs for a wide range of clinical applications.

Cervical Fluids Are a Source of Protein Biomarkers for Early, Non-Invasive Endometrial Cancer Diagnosis.

Abnormal uterine bleeding is the main symptom of endometrial cancer (EC), but it is highly nonspecific. This represents a huge burden for women's health since all women presenting with bleeding will undergo sequential invasive tests, which are avoidable for 90-95% of those women who do not have EC. This study aimed to evaluate the potential of cervical samples collected with five different devices as a source of protein biomarkers to diagnose EC. We evaluated the protein quantity and the proteome composition of five cervical sampling methods. Samples collected with a Rovers Cervex Brush® and the HC2 DNA collection device, Digene, were the most suitable samples for EC proteomic studies. Most proteins found in uterine fluids were also detected in both cervical samples. We then conducted a clinical retrospective study to assess the expression of 52 EC-related proteins in 41 patients (22 EC; 19 non-EC), using targeted proteomics. We identified SERPINH1, VIM, TAGLN, PPIA, CSE1L, and CTNNB1 as potential protein biomarkers to discriminate between EC and symptomatic non-EC women with abnormal uterine bleeding in cervical fluids (AUC > 0.8). This study opens an avenue for developing non-invasive protein-based EC diagnostic tests, which will improve the standard of care for gynecological patients.

A simple and sensitive electrochemical biosensor for circulating tumor cell determination based on dual-toehold accelerated catalytic hairpin assembly

Tumor cells in blood circulation (CTCs) are vital biomarkers for noninvasive cancer diagnosis. We developed a simple and sensitive electrochemical biosensor based on dual-toehold accelerated catalytic hairpin assembly (DCHA) to distinguish CTCs from blood cells. In the presence of CTCs, the aptamer probe initiates the DCHA process, which produces amplified electrochemical signals. Compared with conventional catalytic hairpin assembly (CHA), the proposed DCHA showed high sensitivity, which led to a broader workingrange of 10-1000 cells mL-1 with a limit of detection of 4 cells mL-1. Furthermore, our method exhibited an excellent capability of distinguishing malignant breast cancers from healthy people, with a sensitivity of 97.4%. In summary, we have established an enzyme-free, easy-to-operate, and nondisruptive method for detecting circulating tumor cells in blood circulation based on the DCHA strategy. Its versatility and simplicity will make it more widely used in clinical diagnosis and biomedical research.

1H NMR-based metabolomics of paired tissue, serum and urine samples reveals an optimized panel of biofluids metabolic biomarkers for esophageal cancer.

The goal of this study was to establish an optimized metabolic panel by combining serum and urine biomarkers that could reflect the malignancy of cancer tissues to improve the non-invasive diagnosis of esophageal squamous cell cancer (ESCC). Urine and serum specimens representing the healthy and ESCC individuals, together with the paralleled ESCC cancer tissues and corresponding distant non-cancerous tissues were investigated in this study using the high-resolution 600 MHz 1H-NMR technique. We identified distinct 1H NMR-based serum and urine metabolic signatures respectively, which were linked to the metabolic profiles of esophageal-cancerous tissues. Creatine and glycine in both serum and urine were selected as the optimal biofluids biomarker panel for ESCC detection, as they were the overlapping discriminative metabolites across serum, urine and cancer tissues in ESCC patients. Also, the were the major metabolites involved in the perturbation of "glycine, serine, and threonine metabolism", the significant pathway alteration associated with ESCC progression. Then a visual predictive nomogram was constructed by combining creatine and glycine in both serum and urine, which exhibited superior diagnostic efficiency (with an AUC of 0.930) than any diagnostic model constructed by a single urine or serum metabolic biomarkers. Overall, this study highlighted that NMR-based biofluids metabolomics fingerprinting, as a non-invasive predictor, has the potential utility for ESCC detection. Further studies based on a lager number size and in combination with other omics or molecular biological approaches are needed to validate the metabolic pathway disturbances in ESCC patients.

The non-invasive diagnosis of colorectal cancer via a SOX9-based gene panel.

Colorectal cancer (CRC) threatens human health seriously. Early diagnosis of CRC is critical to improving patient survival. Meanwhile, non-invasive detection through tumor-circulating markers can be an important auxiliary diagnosis. In this study, we performed targeted RNA sequencing in paired tumor and adjacent normal fresh frozen tissues from 68 patients, and we also measured circulating mRNA levels in 4 time-point plasma samples collected before and after operation or chemotherapy. Our results showed that SOX9 (6.73-fold with adjusted p value < 1 × 10-45), MYC (20.59-fold with adjusted p value < 1 × 10-57), and MMP7 (131.94-fold with adjusted p value < 1 × 10-78) highly expressed in tumor compared with adjacent normal tissues. Besides, the circulating mRNA of SOX9 (41.14-fold with adjusted p value < 1 × 10-13) in CRC was significantly higher than in the normal control as well. Moreover, a SOX9-based 9-gene panel (SOX9, GSK3A, FZD4, LEF1, DVL1, FZD7, NFATC1, KRT19, and RUVBL1) showed the non-invasive diagnostic value of CRC (AUC: 0.863 (0.766-0.960), TPR: 0.92, TNR: 0.87). In summary, SOX9 expression consistently increases in tumor and plasma samples from CRC patients, which indicates the important role of SOX9 in CRC progression and its potential in non-invasive diagnosis of CRC.

Chemical Biopsy for GNMT as Noninvasive and Tumorigenesis-Relevant Diagnosis of Liver Cancer.

Early diagnosis of hepatocellular carcinoma (HCC) is difficult; the lack of convenient biomarker-based diagnostic modalities renders high-risk HCC patients burdened by life-long periodical examinations. Here, a new chemical biopsy approach was developed for noninvasive diagnosis of HCC using urine samples. Bioinformatic screening for tumor suppressors yielded glycine N-methyltransferase (GNMT) as a biomarker with clinical relevance to HCC tumorigenesis. A liquid chromatography-mass spectrometry (LC-MS)-based chemical biopsy detecting nonradioactive 13C-sarcosine from 13C-glycine was designed to noninvasively assess liver GNMT activity extrahepatically. 13C-Sarcosine showed a strong correlation with GNMT in normal and cancerous liver cells. In an autochthonous animal model developing visible cancer nodules at 17 weeks, the urinary 13C-sarcosine chemical biopsy exhibited notable changes as early as 8 weeks, showing significant correlations with liver GNMT and molecular pathological changes. Our chemical biopsy approach should facilitate early and noninvasive diagnosis of HCC, with direct relevance to tumorigenesis, which can be straightforwardly applied to other diseases.

Electrochemical Micro-Immunosensor of Cubic AuPt Dendritic Nanocrystals/Ti3C2-MXenes for Exosomes Detection.

Exosomes are extracellular vesicles that exist in body circulation as intercellular message transmitters. Although the potential of tumor-derived exosomes for non-invasive cancer diagnosis is promising, the rapid detection and effective capture of exosomes remains challenging. Herein, a portable electrochemical aptasensor of cubic AuPt dendritic nanocrystals (AuPt DNs)/Ti3C2 assisted in signal amplification, and aptamer CD63 modified graphene oxide (GO) was immobilized on a screen-printed carbon electrode (SPCE) as the substrate materials for the direct capture and detection of colorectal carcinoma exosomes. Cubic AuPt DNs/Ti3C2 was synthesized according to a simple hydrothermal procedure, and the AuPt DNs/Ti3C2-Apt hybrid demonstrated an efficient recognition of exosomes. Under optimal conditions, a detection limit of down to 20 exosomes µL-1 was achieved with the linear range from 100 exosomes μL-1 to 5.0 × 105 exosomes μL-1. The proposed immunosensor could be suitable for the analysis of exosomes and has clinical value in the early diagnosis of cancer.

Accurate and noninvasive diagnosis of epithelial cancers through AND gate photoluminescence on tumor-derived small extracellular vesicles.

Noninvasive detection of small extracellular vesicles (sEVs) has become one of the most promising liquid biopsy methodologies for effective and timely cancer diagnosis and prognostic monitoring. Currently, accurate and sensitive detection of tumor-derived sEVs is compromised by their heterogeneous nature, and the tissue origin and parent cell cycle change may significantly affect the tumor-associated information (e.g., phenotypic proteins) of sEVs. Accordingly, many of the single-marker dependent detections on sEVs may not provide comprehensive information about the tumor, and their reliability and clinical applicability cannot be guaranteed. Herein, a strategy for constructing AND gate photoluminescence on tumor-derived sEVs is proposed. Briefly, only after co-recognition of the two epithelial phenotypic proteins (EpCAM and MUC1) on tumor-derived sEVs simultaneously, can our designed lanthanide luminescence probe precursors then assemble to form the AND gate for photoluminescence detection. Consequently, the generated AND gate photoluminescence provided time-resolved luminescence for a wide cancerous sEV linear detection range of 6.0 × 104-6.0 × 109 particles per mL, with a calculated detection limitation of 1.42 × 102 particles per mL. Furthermore, the AND gate photoluminescence can significantly distinguish epithelial cancer patients from healthy controls, displaying its great potential for accurate and noninvasive cancer diagnosis.

Identification of faecalextracellular vesicles as novel biomarkers for the non-invasive diagnosis and prognosis of colorectal cancer.

Colorectal cancer (CRC) is one of the most common malignancies that is usually detected late in the clinic. The currently available diagnostic tools for CRC are either invasive or insensitive to early lesions due to the dearth of reliable biomarkers. In this study, we discovered that the extracellular vesicles (EVs) in the faecesof CRC patients can act as a potent biomarker for the non-invasive diagnosis and prognosis of CRC. This finding is based on the identification of two transmembrane proteins-CD147 and A33-on faeces-derived EVs (fEVs) that are intrinsically associated with CRC. The detection results show that the levels of CD147 and A33 on fEVs were upregulated in the CRC patients (n=48), dramatically distinguishing them from the healthy donors (n=16). The CD147/A33-enriched EVs offer a clinical sensitivity of 89%, much higher than that (40%) of carcinoembryonic antigen (CEA), a clinically-established serum biomarker for CRC diagnosis. In addition, the analysis of longitudinal faecessamples (n=29) demonstrated that the CD147/A33-enriched fEVs can be utilized to track the prognosis of CRC. Due to the high compliance of faeces-based detection, the CD147/A33-enriched fEVs could serve as new-generation CRC biomarkers for large-scale, non-invasive CRC screening as well as real-time monitoring of patient outcomes during clinical interventions.

Diagnostic accuracy and added value of blood-based protein biomarkers for pancreatic cancer: A meta-analysis of aggregate and individual participant data.

Novel blood-based protein biomarkers may be of value for efficient, accurate, and non-invasive diagnosis of pancreatic cancer. This study assesses the diagnostic accuracy of newly recognized blood-based protein biomarkers for detecting pancreatic cancer, and investigates their added value to CA19-9, the common blood-based biomarker in clinical use for pancreatic cancer. PubMed, Embase, Web of Science, and the Wiley/Cochrane Library were systematically searched from inception until June 2022. A meta-analysis of aggregate and individual participant data was conducted using frequentist and Bayesian hierarchical random-effects models. The added clinical utility of protein biomarkers was investigated using bootstrap bias-corrected decision curve analyses. Aggregate data from 28 primary studies (6127 participants) were included, of which 8 studies (1790 participants) provided individual participant data. CA19-9 was significantly more accurate than MIC-1 for distinguishing pancreatic cancer from benign disease (AUC, 0.83 vs 0.74; relative diagnostic odds ratio [rDOR], 2.10 [95% CI, 0.98-4.48]; p=0.002), THBS2 (AUC, 0.87 vs 0.69; rDOR, 4.53 [2.16-9.39]; p<0.0001), TIMP-1 (AUC, 0.91 vs 0.70; rDOR, 8.00 [3.81-16.9]; p<0.0001), OPN (AUC, 0.89 vs 0.74; rDOR, 4.22 [1.13-15.6]; p<0.0001), ICAM-1 (AUC, 0.91 vs 0.68; rDOR 9.30 [0.87-99.5]; p<0.0001), and IGFBP2 (AUC, 0.91 vs 0.68; rDOR, 4.48 [0.78-24.3]; p<0.0001). The addition of these novel protein biomarkers to CA19-9 did not significantly improve the AUC, and resulted in minor increases or limited decreases in clinical utility. Novel protein biomarkers have moderate diagnostic accuracy, do not outperform CA19-9 in differentiating pancreatic cancer from benign disease, and show limited added clinical value to CA19-9. We propose recommendations to aid the development of minimally invasive diagnostic tests with sufficient clinical utility to improve the management of patients with suspected pancreatic cancer. Bennink Foundation, Dutch Cancer Foundation (KWF Kankerbestrijding), and AIRC.

Nanomaterials: a promising multimodal theranostics platform for thyroid cancer.

Thyroid cancer is the most prevalent malignant neoplasm of the cervical region and endocrine system, characterized by a discernible upward trend in incidence over recent years. Ultrasound-guided fine needle aspiration is the current standard for preoperative diagnosis of thyroid cancer, albeit with limitations and a certain degree of false-negative outcomes. Although differentiated thyroid carcinoma generally exhibits a favorable prognosis, dedifferentiation is associated with an unfavorable clinical course. Anaplastic thyroid cancer, characterized by high malignancy and aggressiveness, remains an unmet clinical need with no effective treatments available. The emergence of nanomedicine has opened new avenues for cancer theranostics. The unique features of nanomaterials, including multifunctionality, modifiability, and various detection modes, enable non-invasive and convenient thyroid cancer diagnosis through multimodal imaging. For thyroid cancer treatment, nanomaterial-based photothermal therapy or photodynamic therapy, combined with chemotherapy, radiotherapy, or gene therapy, holds promise in reducing invasiveness and prolonging patient survival or alleviating pain in individuals with anaplastic thyroid carcinoma. Furthermore, nanomaterials enable simultaneous diagnosis and treatment of thyroid cancer. This review aims to provide a comprehensive survey of the latest developments in nanomaterials for thyroid cancer diagnosis and treatment and encourage further research in developing innovative and effective theranostic approaches for thyroid cancer.

Developing a weakly supervised deep learning framework for breast cancer diagnosis with HR status based on mammography images

The status of hormone receptors (HR) at the molecular level is crucial for accurate diagnosis and effective treatment of breast cancer. Meanwhile, mammography is an effective screening method for detecting breast cancer, which significantly improve survival. However, diagnosing the molecular status of breast cancer involves a pathological biopsy, which can affect the accuracy of the diagnosis. To non-invasively diagnose the hormone receptor (HR) status of breast cancer and reduced manual annotation, we proposed a weakly supervised deep learning framework BSNet which detected breast cancer with HR status and benign tumors. BSNet was trained on 2321 multi-view mammography cases from female undergoing digital mammography for the general population at Harbin Medical University Cancer Hospital in Heilongjiang Province during the period 2017–2018 and was validated on the external cohort. The average AUCs of BSNet on the test set and the external validation set were 0.89 and 0.92, respectively. BSNet demonstrated excellent performance in non-invasive breast cancer diagnosis with HR status, using multiple mammography views without pixel annotation. Furthermore, we developed a web server (http://bsnet.edbc.org) for easy use. BSNet described high-dimensional mammography of breast cancer subtypes, which helped inform early management options.

A rapid and highly sensitive ctDNA detection platform based on locked nucleic acid-assisted catalytic hairpin assembly circuits.

As a promising biomarker of liquid biopsy, circulating tumor DNA (ctDNA) plays a paramount role in the early diagnosis of noninvasive cancer. The isothermal catalytic hairpin assembly (CHA) strategy has great potential for in vitro detection of ctDNA in low abundance. However, a traditional CHA strategy for ctDNA detection at the earlier stages of cancer remains extremely challenging, as annoying signal leakage from the 'breathing' phenomenon and nuclease degradation occur. Herein, we report a locked nucleic acid (LNA)-incorporated CHA circuit for the rapid and sensitive detection of target ctDNA. The target ctDNA intelligently catalyzed LNA-modified hairpins H1 and H2via a range of toehold-mediated strand displacement processes, leading to the continuous generation of an H1-H2 hybrid for the amplified fluorescence signal. In comparison to conventional CHA circuits, the stronger binding affinity of LNA-DNA bases greatly inhibited the breathing effect, which endowed it with greater thermodynamic stability and resistance to nuclease degradation in the LNA-assisted CHA system, thus achieving a high signal gain. The developed CHA circuit demonstrated excellent performance during target ctDNA detection, with a linear range from 10 pM to 5 nM, and its target detection limit was reached at 3.3 pM. Moreover, this LNA-assisted CHA system was successfully applied to the analysis of target ctDNA in clinical serum samples of breast cancer patients. This updated CHA system provides a general and robust platform for the sensitive detection of biomarkers of interest, thus facilitating the accurate identification and diagnosis of cancers.