Early-stage Detection Research Articles

Deep caries detection using deep learning: from dataset acquisition to detection.

The study aims to address the global burden of dental caries, a highly prevalent disease affecting billions of individuals, including both children and adults. Recognizing the significant health challenges posed by untreated dental caries, particularly in low- and middle-income countries, our goal is to improve early-stage detection. Though effective, traditional diagnostic methods, such as bitewing radiography, have limitations in detecting early lesions. By leveraging Artificial Intelligence (AI), we aim to enhance the accuracy and efficiency of caries detection, offering a transformative approach to dental diagnostics. This study proposes a novel deep learning-based approach for dental caries detection using the latest models, i.e., YOLOv7, YOLOv8, and YOLOv9. Trained on a dataset of over 3,200 images, the models address the shortcomings of existing detection methods and provide an automated solution to improve diagnostic accuracy. The YOLOv7 model achieved a mean Average Precision (mAP) at 0.5 Intersection over Union (IoU) of 0.721, while YOLOv9 attained a mAP@50 IoU of 0.832. Notably, YOLOv8 outperformed both, with a mAP@0.5 of 0.982. This demonstrates robust detection capabilities across multiple categories, including caries," "Deep Caries," and "Exclusion." This high level of accuracy and efficiency highlights the potential of integrating AI-driven systems into clinical workflows, improving diagnostic capabilities, reducing healthcare costs, and contributing to better patient outcomes, especially in resource-constrained environments. Integrating these latest YOLO advanced AI models into dental diagnostics could transform the landscape of caries detection. Enhancing early-stage diagnosis accuracy can lead to more precise and cost-effective treatment strategies, with significant implications for improving patient outcomes, particularly in low-resource settings where traditional diagnostic capabilities are often limited.

Intelligent hybrid approaches utilizing time series forecasting error for enhanced structural health monitoring

Over the past decade, the growing importance of machine learning-based structural health monitoring (SHM) for early-stage damage detection has become evident. Time series forecasting, using deep learning, has emerged as a key focus, significantly contributing to improving damage detection, localization, and quantification processes. Researchers in SHM have conducted numerous studies utilizing neural networks based on time series forecasting, grounded in traditional methods. This study diverges from existing research by directly incorporating neural network prediction errors in time series for detecting, localizing, and quantifying damage. The proposed methods are well-suited for online structural monitoring. They eliminate the need for data classification methods and damage-sensitive feature extraction techniques by relying solely on training the neural network with data from structurally sound conditions. However, the testing process does require data from damaged conditions. To address the non-linear and non-stationary characteristics of the signals, the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) method is applied for signal processing. This method processes response signals (i.e., time series) from three well-known benchmark structures: the University of Central Florida structure, the Qatar University Grandstand Simulator, and the Z24 Bridge. Subsequently, the first intrinsic mode function (IMF) obtained from signal decomposition is independently input into Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks for time series prediction. Optimal parameter values for the LSTM and GRU neural networks are chosen using the Bayesian Optimization (BO) algorithm before the prediction process. By introducing three indices—Statistical Distance Function (SDF), error index, and accuracy index—the evaluation not only emphasizes the accuracy of the methods but also explores the localization and quantification of damage. The results demonstrate that both ICEEMDAN-BO-LSTM-SDF and ICEEMDAN-BO-GRU-SDF methods have successfully achieved accurate detection, localization, and quantification without the need for data classification and damage-sensitive feature extraction methods, and merely by utilizing data from healthy states for neural network training.

Nanoparticle-Assisted Cancer Imaging and Targeted Drug Delivery for Early-Stage Tumor Detection and Combined Diagnosis-Therapy Systems for Improved Cancer Management

Nanoparticle-assisted imaging and targeted drug delivery represent a transformative approach in cancer diagnostics and therapeutics, particularly for early-stage tumor detection and integrated diagnosis- therapy systems. This review explores recent advancements in nanoparticle technology for magnetic resonance imaging (MRI), computed tomography (CT), optical imaging, and ultrasound, emphasizing the efficacy of nanoparticles such as superparamagnetic iron oxide nanoparticles (SPIONs), gold and bismuth nanoparticles, and quantum dots as contrast agents. Nanoparticles offer unique advantages, including enhanced permeability and retention (EPR) effects, ligand-receptor targeting, and microenvironment-responsive drug release, which improve localization and accumulation in tumor tissues. Additionally, dual-function theranostic systems utilizing nanoparticles enable simultaneous diagnostic imaging and therapy, allowing real-time monitoring of therapeutic efficacy and minimizing off-target effects. The integration of nanoparticles for both diagnostic and therapeutic purposes holds significant promise for precision oncology, providing a more personalized, minimally invasive, and effective cancer management strategy. This review also discusses current limitations, including issues of biocompatibility, toxicity, and regulatory challenges, while proposing future directions to overcome these barriers. By presenting a comprehensive analysis of nanoparticle platforms in oncology, this paper aims to underscore their potential in revolutionizing cancer diagnosis and therapy, ultimately contributing to improved patient outcomes and advancing the field of nanomedicine.

Non-Invasive Detection of Lung Cancer: Integrating Genomic Data with Ensemble Learning for Improved Early Diagnosis

The early and accurate diagnosis of lung cancer, a significant contributor to global cancer-related mortality, remains a paramount challenge in healthcare. Conventional diagnostic methods often lack the sensitivity required for early-stage detection, prompting the exploration of non-invasive alternatives. Leveraging advancements in genomics and bioinformatics, this study investigates the potential of deoxyribonucleic acid (DNA) and ribonucleic acid (RNA) analysis for early-stage lung cancer diagnosis. Two distinct datasets are utilized: GSE4115, comprising gene expression data from bronchial airway epithelial cells of smokers, and GSE33356, focusing on genomic alterations in Taiwanese female non-smoking lung cancer patients. The research employs comprehensive data pre-processing and feature reduction techniques, including normalization and Kernel Principal Component Analysis (KPCA). Subsequently, an ensemble of diverse learners, including Random Forests, AdaBoost, Bagging, Support Vector Machines (SVMs), and Neural Networks, is trained on the original datasets. A novel ensemble stacking approach is proposed, wherein initial predictions from the base learners are combined through logistic regression - the meta-learner to enhance predictive performance. The study aims to contribute to advancements in lung cancer detection by providing a more precise and non-invasive diagnostic method. By integrating DNA and RNA analysis with ensemble learning techniques, the research endeavours to enhance medical outcomes and potentially save lives through early-stage lung cancer detection.

Detecting Collagen by Machine Learning Improved Photoacoustic Spectral Analysis for Breast Cancer Diagnostics: Feasibility Studies With Murine Models.

Collagen, a key structural component of the extracellular matrix, undergoes significant remodeling during carcinogenesis. However, the important role of collagen levels in breast cancer diagnostics still lacks effective invivo detection techniques to provide a deeper understanding. This study presents photoacoustic spectral analysis improved by machine learning as a promising non-invasive diagnostic method, focusing on exploring collagen as a salient biomarker. Murine model experiments revealed more profound associations of collagen with other cancer components than in normal tissues. Moreover, an optimal set of feature wavelengths was identified by a genetic algorithm for enhanced diagnostic performance, among which 75% were from collagen-dominated absorption wavebands. Using optimal spectra, the diagnostic algorithm achieved 72% accuracy, 66% sensitivity, and 78% specificity, surpassing full-range spectra by 6%, 4%, and 8%, respectively. The proposed photoacoustic methods examine the feasibility of offering valuable biochemical insights into existing techniques, showing great potential for early-stage cancer detection.

BREAST CANCER SCREENING IN WOMEN AGED 45-65 IN SAMARKAND REGION, UZBEKISTAN: A CROSS-SECTIONAL ANALYSIS OF DATA FROM 2023

Objective: Breast cancer is a leading cause of cancer-related mortality among women globally, and early detection through screening significantly reduces morbidity and mortality. This study evaluates the outcomes of breast cancer screening programs in the Samarkand region of Uzbekistan in 2023, focusing on participation rates, detection rates, and stage distribution across 17 districts and cities. Methods: Data were collected on women aged 45–65, including annual screening targets, the number of screenings performed, diagnosed cases, and cancer stage distribution (early stages 1–2 vs. late stages 3–4). Statistical analysis was conducted to determine completion and detection rates, as well as regional disparities in screening outcomes. Results: The screening program achieved promising outcomes in participation and early-stage cancer detection, with substantial variability among districts. A higher proportion of cases were detected at stages 1–2, indicating effective early diagnosis in some areas. However, significant regional disparities in screening completion and detection highlight inequitable access to services. Novelty: This study provides a comprehensive regional analysis of breast cancer screening outcomes in Uzbekistan, emphasizing the importance of addressing disparities to improve equitable access to early diagnosis and treatment. These findings underscore the need for targeted public health interventions to enhance program effectiveness and reduce the burden of late-stage breast cancer

Lesiondiff: enhanced breast cancer classification via dynamic lesion amplification using diffusion models

ABSTRACT Breast cancer is a leading cause of mortality among women, underscoring the critical need for accurate and early diagnosis to enhance treatment efficacy. Traditional imaging techniques are limited in their ability to differentiate between benign and malignant lesions, particularly in the early stages, for there are very few images available for the lesion area and the resolution of these images is poor. This paper introduces a novel lesion diffusion model that dynamically amplifies lesion areas, providing a multi-frame analysis to improve classification accuracy. By integrating time-aware motion modeling, the proposed method tracks temporal changes in lesions, Generating a sequence of magnified frames highlighting subtle lesion features. Tested on the BUSI breast ultrasound dataset, our model achieved a 10.269% improvement in classification accuracy over baseline methods, with an average gain of 4.645% across multiple frames. The results demonstrate the model’s ability to enhance the claim and diagnostic utility of breast cancer images after magnification This dynamic lesion amplification approach presents a significant advancement in computer-aided breast cancer diagnostics, offering new possibilities for improving early-stage detection.

A simple colorimetric detection of telomerase exploiting specific cleavage of exonuclease III coupled with telomeric DNA controlled aggregation of nanogold.

Telomerase activity has piqued scientists' interest for the reason that it has the potential to be employed for early-stage cancer detection, anticancer therapy and studies related to cancer progression and metastasis. Several approaches have been developed to detect telomerase activity. However, these approaches were lengthy, challenging to quantify, of limited sensitivity and prone to polymerase chain reaction (PCR)-related artefacts. We herein developed a novel nanoplasmonic sensing platform for colorimetric detection of telomerase activity relying on the telomere elongation of telomerase at the 3' end, structure-specific cleavage activity of exonuclease III that removes mononucleotides from the 3'-hydroxyl termini of double-stranded DNA, and electrostatic interaction of elongated telomeres with plasmonic nanoparticles. Using HeLa cells as a model for colorimetric detection of telomerase activity, this biosensor could detect telomerase activity with a detection limit of ∼100 cells per reaction by visible inspection and ∼5 cells per reaction by spectroscopic measurement and analysis time within about three hours. The proposed sensing method provided a novel tool for simple, rapid, and low-cost detection of telomerase activity, eliminating the necessity for thermal cycling, primers in PCR-based assays, and amplification of telomerase extension products. It exhibits significant potential as a label-free, simple, ultrasensitive strategy for on-site detection of telomerase activity in proteomics and clinical diagnostics.

Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy

This study introduces a novel approach for the early detection of pancreatic cancer through biofluid spectroscopy, leveraging a unique machine learning pipeline comprising class-specific principal component analysis (PCA), linear discriminant analysis (LDA), and support vector machine (SVM) in both real patient and synthetic data. By conducting separate PCA on cancerous and non-cancerous samples and integrating the projections prior to LDA and SVM classification, we demonstrate significantly improved diagnostic accuracy compared to traditional methods. This methodology not only enhances predictive performance but also offers deeper insights into the influence of molecular spectra on model efficacy. Our findings, validated on real patient data, suggest a promising avenue for developing non-invasive, accurate diagnostic tools for early-stage pancreatic cancer detection.

The electronic nose in lung cancer diagnostics: A systematic review and meta-analysis

BackgroundLung cancer remains a leading cause of cancer-related deaths. Early-stage detection is pivotal for curative interventions, yet most cases are diagnosed at advanced stages. Non-invasive point-of-care diagnostic strategies are needed to reduce lung cancer mortality rates. We assess the potential of electronic nose (eNose) devices as a tool for lung cancer detection.Study design and methodsAll online available databases were searched. Following PRISMA guidelines, we reviewed studies utilising eNose forin vivoexhaled air analysis in lung cancer patients. Included patients had pathological confirmed lung cancer, both non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) in various stages. Primary outcomes were sensitivity, specificity, negative predictive value and area under the curve. Secondary outcomes evaluated eNose performance in distinguishing NSCLC subtypes and SCLC. Additionally, a subgroup analysis was conducted to evaluate the efficacy of various commonly used sensors in this differentiation. The QUADAS-2 tool was used for risk-of-bias assessment.ResultsThirty-five studies, comprising 4483 patients, were included. Pooled sensitivity and specificity were 0.90 (CI 0.87–0.93) and 0.89 (0.85–0.93), respectively. Median negative predictive value was 0.93 and median area under the curve was 0.91. Both the likelihood of bias and concerns regarding applicability were minimal.InterpretationeNose devices hold promise as non-invasive, point-of-care tools for lung cancer diagnosis. Due to high sensitivity and negative predictive value, and great ease of use they might be valuable additions to the diagnostic toolbox. Further research and validation efforts are critical to maximise their impact on early lung cancer detection.

Metamaterial-based Artificial magnetic conductor for efficient breast cancer diagnosis using a low-cost antenna array

Breast cancer is the most common malignancy in women globally, stemming from gene mutations that prompt irregular cellular growth and subsequent tumor development. Early-stage detection of cancer cells results in a remarkable 99% survival rate. This research presents a microwave imaging technique for the non-invasive identification of tumors in the initial stages within the women’s breast. A low-cost antenna array with an Artificial Magnetic Conductor (AMC) is proposed, featuring a compact structure size of 37.2 ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document} 37.2 mm2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{2}$$\\end{document}. The AMC, a metamaterial, acts as a reflective surface to enhance frequency selectivity, specifically at 8.48 GHz. The maximum gains reached 9.35 dBi in simulated results and 10.51 dBi in measured results. The fabricated antenna validates the simulated findings, and its operational efficiency has undergone experimental validation. Moreover, fidelity factors in face-to-face (FtF) and side-by-side (SbS) scenarios are delineated. The antenna, operating as a transceiver, is applied to a modeled breast phantom across five distinct cases for numerical simulations pertaining to cancer cell detection applications. The outcomes of this research bear considerable implications for advancing early-stage breast cancer detection methodologies.

Temperature–amplitude spectrum for early full-field vibration-fatigue-crack identification

A dynamic structure under vibration loading within its natural frequency range can experience failure due to vibration fatigue. Understanding the causes of such failure requires pinpointing the initiation time and location of fatigue cracks, tracking their propagation, and identifying the frequency range of critical stress responses. This research introduces a novel, thermoelasticity-based method – the Temperature–Amplitude Spectrum (TAS) method – for early-stage, full-field, and non-contact crack detection that operates during uninterrupted vibration testing. This method leverages high-speed infrared imaging to analyze the specimen’s temperature–amplitude spectrum, capturing comprehensive crack-related information, including initiation and propagation, in real time. Experimentally validated on both 3D-printed polymer and aluminum specimens, the TAS method accurately identified crack locations and paths without complex adjustments to the experimental setup or data processing. This new approach advances vibration-fatigue testing by enabling reliable, high-resolution crack detection and analysis while remaining computationally efficient.

Exam quality of ultrasound and dynamic contrast-enhanced abbreviated MRI and impact on early-stage HCC detection.

MRI is a potential alternative to ultrasound for hepatocellular carcinoma (HCC) detection. We evaluated the impact of ultrasound and dynamic abbreviated MRI (AMRI) exam quality on early-stage HCC detection. We conducted a multicenter case-control study among patients with cirrhosis (cases with early-stage HCC per Milan Criteria; controls without HCC) who underwent both a liver ultrasound and dynamic contrast-enhanced (DCE) AMRI within 6 months in 2012-2019. Two radiologists performed independent, blinded interpretations of both exams for HCC detection and scored exam quality as no/mild, moderate, or severe limitations. Associations between exam quality, patient characteristics, and HCC detection were assessed by odds ratios (OR). Of 216 cases and 432 controls, severe limitations were reported in 7% and 8% of ultrasounds and DCE-AMRIs, respectively. Severe limitations at ultrasound were associated with obesity (OR 2.08, 95%CI [1.32-3.32]) and metabolic dysfunction-associated steatotic liver disease (MASLD) (OR 1.98 [1.12-3.44]) but not for DCE-AMRI. Decompensated cirrhosis (Child-Pugh C) was associated with severe limitations for both ultrasound (OR 2.54 [1.37-4.58]) and DCE-AMRI (OR 3.96 [2.36-6.58]). Compared to exams with no/mild limitations, exams with severe limitations had lower sensitivity for ultrasound (79.6% vs. 21.7%, P < 0.001) and AMRI (86.1% vs. 50.0%, P = 0.001). In patients in whom ultrasound was severely limited, DCE-AMRI had significantly higher odds of early-stage HCC detection than ultrasound (OR 8.23 [1.25-54.02]). HCC detection by DCE-AMRI may be preferred in patients with severe limitations at ultrasound due to obesity and MASLD. Both modalities remain limited for patients with decompensated cirrhosis, for whom alternative strategies may be needed.

The Role of Small-Bowel Endoscopy in the Diagnosis and Management of Small-Bowel Neuroendocrine Tumours.

Neuroendocrine tumours (NETs) are relatively rare neoplasms but represent one of the most frequent types of primary small-bowel tumours. Their incidence is rising, and this is most likely because of their more frequent early-stage detection, physician awareness, and increasing availability and use of imaging and small-bowel endoscopic techniques, such as video capsule endoscopy and device-assisted enteroscopy, which enable the detection, localisation, and histological sampling of previously inaccessible and underdiagnosed small-bowel lesions. This review summarises the role of small-bowel endoscopy in the diagnosis and management of small-bowel NETs to assist clinicians in their practice. Small-bowel endoscopy may play a complementary role in the diagnosis of these tumours alongside other diagnostic tests, such as biomarkers, conventional radiology, and functional imaging. In addition, small-bowel enteroscopy may play a role in the preoperative setting for the identification and marking of these tumours for surgical resection and the management of rare complications, such as small-bowel variceal bleeding, in cases of portal hypertension due to the encasement of mesenteric vessels in fibrotic small-bowel NETs.

Abstract PR013: Highly accurate detection of early-stage colorectal cancer using tumor and immune extracellular vesicles biomarkers

Abstract Introduction: Colorectal cancer (CRC) is one of the most common cancers worldwide, and early detection is critical for successful treatment and improved survival rates. However, precancerous and early-stage CRC present significant diagnostic challenges due to the small size of lesions and the very low expression of tumor-specific biomarkers in the bloodstream. Current genomics-based diagnostic methods struggle to detect these lesions, making it imperative to develop more sensitive and specific approaches. Circulating extracellular vesicles (EVs) are emerging as a promising solution for early-stage CRC detection, since EVs are produced by tumor cells as well as the tumor microenviroment and host immune cells. Thus, EVs may offer the means to detect and monitor small early-stage tumors through both direct detection of tumor- associated biomarkers as well through tumor specific host response and tumor microenvironment biomarkers. Methods: To identify novel early-stage CRC specific biomarkers, we performed proteomics analysis on EVs purified from patient plasma using size exclusion chromatography and a proprietary buffer system that enhances EV and corona protein recovery. TrueDiscovery™ Data-independent acquisition (DIA) mass spectrometry (MS) analysis was conducted on 24 pre- cancer/stage 0 and 25 stage 1 CRC patients and 75 normal patient plasma samples. An in-house developed machine learning pipeline was used to identify differentially expressed proteins and model candidate multiplexes to identify those with extremely high diagnostic accuracy (&amp;gt; 0.99). Results: An average of ∼2,500 proteins were identified per sample and included in bioinformatics analysis. Comparative analysis between control patient EVs and either pre- cancerous/Stage 0, or Stage 1 colon cancer EVs using an in-house Machine Learning pipeline identified 336 and 493 differentially expressed proteins for each group (FDR adjusted p-value &amp;lt; 0.001). Of these, the best 17 pre/stage 0 proteins and 53 stage 1 proteins were trained and tested using Support Vector Machine to assess all potential 3-plexes in order to identify those with mean diagnostic accuracy &amp;gt; 99%. This yielded 5 3-plexes in precancer/stage 0 and 34 3-plexes in stage 1 with near perfect diagnostic accuracy. These plexes are currently being assessed in single analyte and multiplex immunoassays with the goal of translating candidate 3-plexes to the clinical. Conclusions: Key biomarkers from CRC patient EVs indicate the potential to detect and diagnose early-stage and low tumor burden cancers using our methods. Interestingly, the most accurate 3-plexes consist of proteins from immune, inflammatory and metabolic processes, suggesting that for the detection of early stage cancer it may be critical to include both tumor and host specific biomarkers. Citation Format: Poorva Mudgal, Cheryl Bandoski, Zachary Opheim, Martin Mehnert, Valesca Anschau, Issa Isaac, Alan Ezrin, Todd Hembrough. Highly accurate detection of early-stage colorectal cancer using tumor and immune extracellular vesicles biomarkers [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr PR013.

Abstract B058: Novel machine learning lung cancer classifier shows significant correlation with cancer-specific fragmentomics features

Abstract Lung cancer is the second most prevalent cancer, and the leading cause of cancer-related deaths, in the US. Since the survival rate of patients diagnosed with lung cancer at earlier stages is dramatically higher than those diagnosed at later stages, technologies that shift lung cancer diagnosis to an earlier stage would be expected to improve survival rates. Fragmentomics, the study of short circulating cell-free DNA (cfDNA) fragments in the blood, is an emerging field in cancer diagnostics that has the potential to catalyze such a shift. Studies have shown that fragmentomics features, such as fragment sizes and end motifs, can be used to discriminate normal cfDNA from circulating tumor DNA (ctDNA) generated through tumor necrosis and apoptosis. Using this knowledge, machine learning tools, trained to identify ctDNA-specific features, are being leveraged in novel liquid biopsy assays to improve early-stage lung cancer detection. To create a machine learning classifier that detects discrete signals of ctDNA in individuals with lung cancer, Genece Health utilized low pass (∼3x coverage) whole genome sequencing (Illumina) of plasma extracted cfDNA from &amp;gt;400 lung cancer samples and &amp;gt;1,000 negative controls. This data was used to generate our novel FEMS (Fragment End Motifs and Sizes) dataframe, containing &amp;gt;30,000 features, by combining fragment lengths with their corresponding 5’ 4bp end motifs. The FEMS dataframe was then used to train a neural network machine learning classifier. To evaluate the performance of our machine learning classifier, we investigated whether the classifier scores correlated with well-known hallmarks of ctDNA. First, consistent with published ctDNA characteristics, we observed significant (p&amp;lt;0.01) enrichment of fragment sizes ≤167bp in lung cancer samples. Concordantly, our classifier scores are significantly correlated with this fragment size enrichment. Also, both fragment size enrichment and our classifier scores are correlated with lung cancer stage, with higher enrichment and higher scores observed in later stages. Next, we show that our classifier scores are correlated with specific end motif enrichments or depletions in lung cancer samples. For example, in lung cancer samples, CCCA end motifs were significantly enriched (p&amp;lt;0.01) in fragment sizes 120-140bp (max at 128bp), while significantly depleted in fragment sizes 190-210bp (min at 204bp). Once again, our classifier scores were significantly correlated with both the enrichment of this end motif in short fragments and its depletion in long fragments. Last, we assessed the classifier’s performance in an independent cohort (46 lung cancer and 132 non-cancer samples) and show 89.2% sensitivity with 90.4% specificity (auROC=0.957). The correlation observed between our classifier scores and published ctDNA characteristics, combined with the strong performance in an independent cohort, suggests that Genece’s novel machine learning classifier is effectively leveraging ctDNA-specific fragmentomics features for the identification of lung cancer in patient samples. Citation Format: Carlos Guzman, Michael L Salmans, Mengchi Wang, Byung In Lee, Andrew R Carson. Novel machine learning lung cancer classifier shows significant correlation with cancer-specific fragmentomics features [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr B058.

Abstract A020: Enhanced cell-free RNA (cfRNA) recovery for liquid biopsy applications: Comparative analysis using controlled RNA samples for early and advanced cancer detection

Abstract Introduction: Extracting cfRNA from biological samples is crucial in liquid biopsy applications, particularly for detecting low-frequency mutations like KRAS G12V, essential for early cancer diagnosis and minimal residual disease (MRD) monitoring. Traditional cfRNA extraction methods involve multiple transfer steps, aliquoting, and pooling, leading to cfRNA loss and affecting mutation detection sensitivity and accuracy. The nRichDX Revolution cfTNA Max 20 kit, with its innovative nRicher cartridge, simplifies the extraction process by eliminating these extra steps, potentially enhancing yield and efficiency. This study evaluates the cfRNA recovery efficiency of the nRichDX kit compared to the Qiagen Circulating Total Nucleic Acid kit. Methods: Plasma samples (5 mL each) were spiked with RNA containing KRAS G12V mutation at concentrations ranging from 100 to 2 million copies, mimicking early-stage cancer detection and MRD monitoring, where low copy numbers represent early disease and high copy numbers reflect advanced cancer stages. cfRNA was extracted using the nRichDX and Qiagen kits, with each condition tested in triplicate. cfRNA recovery efficiency was assessed using quantitative reverse transcription PCR (qRT-PCR) to quantify KRAS G12V RNA copies recovered. High-sensitivity RNA ScreenTape Analysis was also used to evaluate cfRNA profile quality. Results: The nRichDX kit recovered significantly higher cfRNA yields than Qiagen across all concentrations. Recovery rates were consistent and reproducible, with over 70% of input RNA recovered, even at lower inputs (100 to 100,000 copies), where recovery rates were approximately 70-85%. High Sensitivity RNA ScreenTape Analysis showed a linear increase in 18S and 28S ribosomal peaks and high RNA Integrity Number (RIN) scores in nRichDX profiles. The ability to robustly recover low copy numbers is significant for early cancer detection and MRD monitoring. In contrast, the kit’s effectiveness in high copy number samples reflects its ability to monitor advanced cancer stages accurately. Conclusion: The nRichDX cfTNA kit demonstrates exceptional efficiency in cfRNA extraction from plasma samples across a broad dynamic range, from as few as 100 copies to as many as 2 million copies of the KRAS G12V mutation. Its versatility makes it suitable for various cancer detection and monitoring applications. The streamlined process offered by the nRicher cartridge minimizes sample handling and reduces cfRNA loss, enhancing performance. This translates to more accurate and sensitive detection of early-stage and high-burden mutations associated with advanced cancer. The high-quality profiles indicated by RNA ScreenTape Analysis further validate the reliability of the nRichDX kit, making it a valuable tool for liquid biopsy applications, with significant advantages in early cancer detection and monitoring disease progression. Citation Format: Nafiseh Jafari, Mayer Saidian, Jason Saenz, Andrew Dunnigan, Carlos Hernandez, Leila Aghili. Enhanced cell-free RNA (cfRNA) recovery for liquid biopsy applications: Comparative analysis using controlled RNA samples for early and advanced cancer detection [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A020.

Abstract B073: Leveraging micronuclei DNA from erythrocytes for early detection of hepatocellular carcinoma

Abstract Background: Hepatocellular carcinoma (HCC) is the most common form of liver cancer and accounts for ∼90% of cases globally. Detection of early-stage HCC is vital as it allows for potentially curative treatment, yet remains a significant challenge. Micronuclei (MN) are a hallmark of genomic instability. An increased frequency of MN is commonly observed in tumor cells as well as other somatic cells, including erythrocytes, in cancer patients. Here, we have established a technique (WO2021/228246 A1), for the isolation and analysis of micronuclei DNA (MN-DNA) in erythrocytes from peripheral blood. Significant changes in read densities at specific genomic locations within MN-DNA were identified in patients, termed as tumor- associated MN-DNA (taMN-DNA) features. This study evaluates the potential of these taMN- DNA features for early-stage HCC detection across human and murine model. Methods: To explore the potential of MN-DNA in cancer detection, we first collected 1-2 mL of whole blood from HDs (N = 53) and HCC patients (N = 53). MN-DNA was isolated and purified from erythrocytes, followed by whole-genome sequencing. Participants were randomly divided into training, test cohorts in an 8:2 ratio. We applied machine learning algorithms to leverage these features for cancer detection in the human model. Additionally, to investigate the formation of taMN-DNA features, we employed a well-established mouse model that mimics HCC development. Mice were injected with the genotoxic agent diethylnitrosamine (DEN) 2 weeks after birth, and developed malignant macroscopic liver nodules at approximately 40 weeks of age. Results: In the human cohort, we enrolled 106 participants, with more than half of the HCC cases were diagnosed at early-stage (stage 0-II). The cancer detection model utilizing taMN- DNA features achieved an overall accuracy of 86.3%, with a sensitivity of 81.8% and specificity of 90.9%. For early-stage, the model demonstrated sensitivities of 54.5% at a specificity of 90.9%. In the DEN-induced HCC mouse model, unsupervised hierarchical clustering based on these selected taMN-DNA features clearly separated WT and tumor mice into two distinct groups. Notably, mice that were not tumorigenic at 36 weeks post-treatment in the DEN-treated group fell into the WT group when classified by the same taMN-DNA features, indicating that the formation of taMN-DNA signatures is associated with the presence of tumors specifically. Conclusions: This pilot study highlights the potential of MN-DNA as a promising tool for early HCC detection. Leveraging these taMN-DNA features can accurately distinguish early-stage HCC patients from HDs with high sensitivity. In both human and murine models, there is a significant relationship between these signatures and tumor presence, suggesting that taMN- DNA features might reflect the diseased state across mammalian species. Research sponsor: Timing Biotech. Citation Format: Hui Lin, Haobo Sun, Xingyun Yao, Xiaoxiao Fan, Fei Meng, Honghao Liang, Xiaofei Gao. Leveraging micronuclei DNA from erythrocytes for early detection of hepatocellular carcinoma [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr B073.

Abstract A041: Detection of early-stage gastrointestinal cancers using micronuclei DNA from erythrocytes

Abstract Background: Gastrointestinal (GI) cancers account for over a third of cancer deaths. However, their early detection remains a challenge. Micronuclei (MN) are cytoplasm-resident subcellular structures, containing damaged chromosome segments that indicative of genomic instability. Increased MN frequency in hematopoietic cells is observed in patients with solid tumors. Our developed technique (WO2021/228246 A1) enables the purification and characterization of micronuclei DNA in erythrocytes from peripheral blood. By comparing MN-DNA from healthy donors (HDs) and GI cancer patients, we identified significant changes in read densities at specific genomic locations in patients, which were termed as tumor-associated MN-DNA (taMN- DNA) features. Here, we evaluated the potential of these features for early-stage GI cancer detection, including colorectal (CC), gastric (GC) and esophageal (EC) cancers. Methods: Peripheral blood (1-2 mL) was collected from healthy donors (HD) and cancer patients MN-DNA isolation and purification from erythrocytes. Participants were randomly divided into training, validation and independent test cohorts in a 7:2:1 ratio, maintaining similar cancer types, gender and age distribution. Distinct MN-DNA features between cancer patients and HDs were identified using sequencing data. Machine learning algorithms were applied using these features for cancer detection. Results: The study enrolled 1753 participants, including 987 HDs, 420 CC, 282 GC and 64 EC cases. Of these, over half were diagnosed with early-stage diseases; TNM stage 0-I accounted for 40.57%, stage II for 23.32%, stage III for 29.25% and stage IV for 6.87%. The pan-cancer model achieved 88.2% sensitivity with an overall specificity of 95.4%. Patients in individual caner types were detected from the tissue of origin classification with an overall accuracy of 91.9% based on pan-cancer at 95.4% specificity. Sensitivity was 90.8% for CC, 91.7% for GC and 100% for EC. For early- stage (stage 0-II) CC, GC and EC, the model demonstrated sensitivities of 97.4%, 94.7% and 100.00%, respectively, at 95.4% specificity. Conclusions: Unlike cell-free DNA, MN-DNA are chromosomal fragments in the cytoplasm. The abundance of erythrocytes in peripheral blood provides an easily accessible source for MN-DNA enrichment. This pilot study illustrates the potential of MN-DNA as a tool for early GI cancer detection, contributing to large-scale efforts towards developing an effective GI cancer screening test. Research sponsor: Timing Biotech. Citation Format: Haobo Sun, Xingyun Yao, Yuehua Han, Yurong Jiao, Xiangxing Kong, Chengcheng Liu, Qingqu Guo, Fei Meng, Honghao Liang, Hongbo Li, Xiuqin Fan, Jun Li, Xiaofei Gao. Detection of early-stage gastrointestinal cancers using micronuclei DNA from erythrocytes [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A041.

Photothermally Active Quantum Dots in Cancer Imaging and Therapeutics: Nanotheranostics Perspective.

Cancer is becoming a global threat, as the cancerous cells manipulate themselves frequently, resulting in mutants and more abnormalities. Early-stage and real-time detection of cancer biomarkers can provide insight into designing cost-effective diagnostic and therapeutic modalities. Nanoparticle and quantum dot (QD)-based approaches have been recognized as clinically relevant methods to detect disease biomarkers at the molecular level. Over decades, as an emergent noninvasive approach, photothermal therapy has evolved to eradicate cancer. Moreover, various structures, viz., nanoparticles, clusters, quantum dots, etc., have been tested as bioimaging and photothermal agents to identify tumor cells selectively. Among them, QDs have been recognized as versatile probes. They have attracted enormous attention for imaging and therapeutic applications due to their unique colloidal stability, optical and physicochemical properties, biocompatibility, easy surface conjugation, scalable production, etc. However, a few critical concerns of QDs, viz., precise engineering for molecular imaging and sensing, selective interaction with the biological system, and their associated toxicity, restrict their potential intervention in curing cancer and are yet to be explored. According to the U.S. Food and Drug Administration (FDA), there is no specific regulation for the approval of nanomedicines. Therefore, these nanomedicines undergo the traditional drug, biological, and device approval process. However, the market survey of QDs is increasing, and their prospects in translational nanomedicine are very promising. From this perspective, we discuss the importance of QDs for imaging, sensing, and therapeutic usage pertinent to cancer, especially in its early stages. Moreover, we also discuss the rapidly growing translational view of QDs. The long-term safety studies and cellular interaction of these QDs could enhance their visibility and bring photothermally active QDs to the clinical stage and concurrently to FDA approval.