Method For Detection Of Cancer Research Articles

Integration of feature enhancement technique in Google inception network for breast cancer detection and classification

Breast cancer is a major public health concern, and early detection and classification are essential for improving patient outcomes. However, breast tumors can be difficult to distinguish from benign tumors, leading to high false positive rates in screening. The reason is that both benign and malignant tumors have no consistent shape, are found at the same position, have variable sizes, and have high correlations. The ambiguity of the correlation challenges the computer-aided system, and the inconsistency of morphology challenges an expert in identifying and classifying what is positive and what is negative. Due to this, most of the time, breast cancer screen is prone to false positive rates. This research paper presents the introduction of a feature enhancement method into the Google inception network for breast cancer detection and classification. The proposed model preserves both local and global information, which is important for addressing the variability of breast tumor morphology and their complex correlations. A locally preserving projection transformation function is introduced to retain local information that might be lost in the intermediate output of the inception model. Additionally, transfer learning is used to improve the performance of the proposed model on limited datasets. The proposed model is evaluated on a dataset of ultrasound images and achieves an accuracy of 99.81%, recall of 96.48%, and sensitivity of 93.0%. These results demonstrate the effectiveness of the proposed method for breast cancer detection and classification.

Diagnosis of the Initial Stage of Hepatocellular Carcinoma: A Review.

Hepatocellular carcinoma (HCC) is the third most common cause of cancer-related deaths worldwide. There may be more than a million instances of hepatocellular carcinoma by 2025, making it a persistent concern for global health. The most common form of hepatocellular carcinoma accounts for more than 90% of cases. There is no known cure for hepatocellular carcinoma, which is usually detected late in life. Unlike most other common malignancies, such as lung, prostate, and breast cancers, where mortality rates are declining, rates of death are rising by around 2-3% every year. It is extremely difficult to diagnose hepatocellular carcinoma in its early stages. Alpha-fetoprotein serology studies and ultrasonography (US) monitoring were historically the primary methods for early detection of hepatocellular cancer. However, the sensitivity or specificity of ultrasonography/alpha-fetoprotein (US/AFP) is not high enough to detect hepatocellular carcinoma in its early stages. Alpha-fetoprotein, or AFP, is an amino acid that is normally produced by the liver or yolk sac of an embryonic baby. In adults, AFP levels are typically modest. Adults with high levels of AFP have been associated with several illnesses, the most well-known of which are certain types of cancer. It is still possible to diagnose hepatocellular carcinoma early because of current technological advancements. We address the advancements in the diagnosis of hepatocellular carcinoma in this article, with a focus on new imaging techniques and diagnostic markers for early-stage tumor identification.

Hybrid machine learning-based breast cancer segmentation framework using ultrasound images with optimal weighted features.

One of the most dangerous conditions in clinical practice is breast cancer because it affects the entire life of women in recent days. Nevertheless, the existing techniques for diagnosing breast cancer are complicated, expensive, and inaccurate. Many trans-disciplinary and computerized systems are recently created to prevent human errors in both quantification and diagnosis. Ultrasonography is a crucial imaging technique for cancer detection. Therefore, it is essential to develop a system that enables the healthcare sector to rapidly and effectively detect breast cancer. Due to its benefits in predicting crucial feature identification from complicated breast cancer datasets, machine learning is widely employed in the categorization of breast cancer patterns. The performance of machine learning models is limited by the absence of a successful feature enhancement strategy. There are a few issues that need to be handled with the traditional breast cancer detection method. Thus, a novel breast cancer detection model is designed based on machine learning approaches and employing ultrasonic images. At first, ultrasound images utilized for the analysis is acquired from the benchmark resources and offered as the input to preprocessing phase. The images are preprocessed by utilizing a filtering and contrast enhancement approach and attained the preprocessed image. Then, the preprocessed images are subjected to the segmentation phase. In this phase, segmentation is performed by employing Fuzzy C-Means, active counter, and watershed algorithm and also attained the segmented images. Later, the segmented images are provided to the pixel selection phase. Here, the pixels are selected by the developed hybrid model Conglomerated Aphid with Galactic Swarm Optimization (CAGSO) to attain the final segmented pixels. Then, the selected segmented pixel is fed in to feature extraction phase for attaining the shape features and the textual features. Further, the acquired features are offered to the optimal weighted feature selection phase, and also their weights are tuned tune by the developed CAGSO. Finally, the optimal weighted features are offered to the breast cancer detection phase. Finally, the developed breast cancer detection model secured an enhanced performance rate than the classical approaches throughout the experimental analysis.

Wait times and breast cancer survival: a population-based retrospective cohort study using CanIMPACT data.

The time from breast cancer surgery to chemotherapy has been shown to affect survival outcomes; however, the effect of time from first breast cancer-related healthcare contact to first cancer specialist consultation, or the time from first breast cancer-related healthcare contact to adjuvant chemotherapy on survival has not been well explored. We aimed to determine whether various wait times along the breast cancer treatment pathway (contact-to-consultation, contact-to-chemotherapy, surgery-to-chemotherapy) were associated with overall survival in women within the Canadian province of Ontario. We performed a population-based retrospective cohort study of women diagnosed with stage I-III breast cancer in Ontario between 2007 and 2011 who received surgery and adjuvant chemotherapy. This was the Ontario cohort of a larger, nationwide study (the Canadian Team to improve Community-Based Cancer Care along the Continuum - CanIMPACT). We used Cox-proportional hazards regression to determine the association between the contact-to-consultation, contact-to-chemotherapy, and surgery-to-chemotherapy intervals and overall survival while adjusting for cancer stage, age, comorbidity, neighborhood income, immigration status, surgery type, and method of cancer detection. Among 12,782 breast cancer patients, longer surgery-to-chemotherapy intervals (HR 1.13, 95% CI 1.03-1.18 per 30-day increase), but not the contact-to-consultation (HR 0.979, 95% CI 0.95-1.01 per 30-day increase), nor the more comprehensive contact-to-chemotherapy intervals (HR 1.00, 95% CI 0.98-1.02 per 30-day increase) were associated with decreased survival in our adjusted analyses. Our findings emphasize the prognostic importance of a shorter surgery-to-chemotherapy interval, whereas the contact-to-consultation and contact-to-chemotherapy intervals have less impact on survival outcomes.

T2-weighted imaging-based deep-learning method for noninvasive prostate cancer detection and Gleason grade prediction: a multicenter study.

To noninvasively detect prostate cancer and predict the Gleason grade using single-modality T2-weighted imaging with a deep-learning approach. Patients with prostate cancer, confirmed by histopathology, who underwent magnetic resonance imaging examinations at our hospital during September 2015-June 2022 were retrospectively included in an internal dataset. An external dataset from another medical center and a public challenge dataset were used for external validation. A deep-learning approach was designed for prostate cancer detection and Gleason grade prediction. The area under the curve (AUC) was calculated to compare the model performance. For prostate cancer detection, the internal datasets comprised data from 195 healthy individuals (age: 57.27 ± 14.45 years) and 302 patients (age: 72.20 ± 8.34 years) diagnosed with prostate cancer. The AUC of our model for prostate cancer detection in the validation set (n = 96, 19.7%) was 0.918. For Gleason grade prediction, datasets comprising data from 283 of 302 patients with prostate cancer were used, with 227 (age: 72.06 ± 7.98 years) and 56 (age: 72.78 ± 9.49 years) patients being used for training and testing, respectively. The external and public challenge datasets comprised data from 48 (age: 72.19 ± 7.81 years) and 91 patients (unavailable information on age), respectively. The AUC of our model for Gleason grade prediction in the training set (n = 227) was 0.902, whereas those of the validation (n = 56), external validation (n = 48), and public challenge validation sets (n = 91) were 0.854, 0.776, and 0.838, respectively. Through multicenter dataset validation, our proposed deep-learning method could detect prostate cancer and predict the Gleason grade better than human experts. Precise prostate cancer detection and Gleason grade prediction have great significance for clinical treatment and decision making. Prostate segmentation is easier to annotate than prostate cancer lesions for radiologists. Our deep-learning method detected prostate cancer and predicted the Gleason grade, outperforming human experts. Non-invasive Gleason grade prediction can reduce the number of unnecessary biopsies.

Multiscale and multiperception feature learning for pancreatic lesion detection based on noncontrast CT

Background. Pancreatic cancer is one of the most malignant tumours, demonstrating a poor prognosis and nearly identically high mortality and morbidity, mainly because of the difficulty of early diagnosis and timely treatment for localized stages. Objective. To develop a noncontrast CT (NCCT)-based pancreatic lesion detection model that could serve as an intelligent tool for diagnosing pancreatic cancer early, overcoming the challenges associated with low contrast intensities and complex anatomical structures present in NCCT images. Approach. We design a multiscale and multiperception (MSMP) feature learning network with ResNet50 coupled with a feature pyramid network as the backbone for strengthening feature expressions. We added multiscale atrous convolutions to expand different receptive fields, contextual attention to perceive contextual information, and channel and spatial attention to focus on important channels and spatial regions, respectively. The MSMP network then acts as a feature extractor for proposing an NCCT-based pancreatic lesion detection model with image patches covering the pancreas as its input; Faster R-CNN is employed as the detection method for accurately detecting pancreatic lesions. Main results. By using the new MSMP network as a feature extractor, our model outperforms the conventional object detection algorithms in terms of the recall (75.40% and 90.95%), precision (40.84% and 68.21%), F1 score (52.98% and 77.96%), F2 score (64.48% and 85.26%) and Ap50 metrics (53.53% and 70.14%) at the image and patient levels, respectively. Significance.The good performance of our new model implies that MSMP can mine NCCT imaging features for detecting pancreatic lesions from complex backgrounds well. The proposed detection model is expected to be further developed as an intelligent method for the early detection of pancreatic cancer.

Detection of uterine cancer biomarker EGFR through an aptasensor utilizing a carbon electrode modified with silver nanowires

Treatment options and survival chances are enhanced with early detection of uterine cancer. In this work, an electrochemical paper analytical device (ePAD) for detecting Epidermal growth factor receptor (EGFR), a biomarker for uterine cancer, was demonstrated. The objective of this study is to develop a rapid nano-biosensing method for early detection of fatal uterine cancer. The proposed ePAD is inexpensive, disposable, easy, and repeatable, among other advantageous qualities. The ePAD's Working electrode comprises of silver nanowires. In addition, the use of aptamers has enhanced the performance of the biosensor. The silver nanowires' morphological, optical, elemental content, and phase characteristics were assessed by employing several analytical techniques: transmission electron microscopy (TEM), Fourier transform infrared (FTIR), Scanning electron microscopy (SEM), X-ray diffraction (XRD), and UV–vis spectroscopy. This aptamer-modified ePAD assists in amplifying the signal of the developed platform to identify EGFR. The biosensor utilized the voltametric detection of EGFR in a solution of 0.5 mM potassium ferro/ferri cyanide, which acts as a redox pair by applying a potential of 50 mV/s at the working electrode yielded the highest performance. The designed sensor demonstrated an optimum response broad linearity of 0.01 ng/ml – 1 μg/ml for EGFR, with limit of detection (LOD) of 0.01ng/ml.

Advancements in Precision Oncology: Investigating the Function of Circulating DNA in the Advancement of Liquid Biopsy Technologies

While the traditional method is a biopsy of the potential tumor tissue, more non-invasive methods have been developed such as the liquid biopsy. It is an emerging, powerful cancer detection method that is used for molecular profiling of tumors apart from tissue-specific biopsy. It involves the analysis of free, circulating tumor genetic material and circulating tumor cells (CTCs) that are found in the fluids of the patient. This analysis helps to detect the abnormal genetic anomalies associated with the various forms of cancer as well as identify mutations corresponding to specific tumors. It is an upcoming method of diagnostics applied in the field of precision oncology that helps overcome the limitations of the traditional biopsy. It can interrogate and look through difficult-to-biopsy tumors and also aid in early cancer detection. Sequencing techniques help in building databases with different information on mutations in the genetic as well as epigenetic levels. In this review, we understand the role of liquid biopsy as not only a diagnostic tool but its role in therapeutics and its potential in the future.

Classification of Melanoma Skin Cancer using Transfer Learning

Abstract: Melanoma, a fatal variety of skin cancer, is a significant public health issue on a global scale. For patients to have better results, melanoma must be detected accurately and early. In this study, transfer learning techniques are used in deep learning to provide a novel method of melanoma cancer detection. By using pre-trained convolutional neural networks (CNNs), such as VGG, MobileNet, and EfficientNet, as feature extractors, the research takes advantage of the capability of transfer learning. These networks, which were first created for tasks involving generic image identification, are refined using a large dataset of dermoscopic images of skin lesions in order to adapt them to the particular needs of melanoma detection. Essential preprocessing techniques, including image resizing, image normalization, and lesion segmentation using the Otsu segmentation method, are used to improve the dataset's quality and consistency. Image normalization has been used to reduce the complexity and processing time of the image. Skin lesions have been segmented using Otsu segmentation. These procedures increase the robustness of the melanoma detection model and help to prepare the images for efficient training. The findings of this study highlight the possibility for an earlier and more precise diagnosis and provide encouraging insights into the viability of transfer learning as a formidable tool for melanoma detection. The overall objective of this work is to improve the diagnosis and patient care for melanoma cancer. This work contributes to ongoing efforts to provide practical and effective tools for dermatologists and healthcare professionals.

Lung Cancer Detection Using CNN VGG19 + Model

In the last many years, lung cancer has become a major public health concern. To examine cell breakdown in the lungs in its starting stages, doctors often use imaging modalities such as X-ray chest films, CT scans, MRIs, etc. The timing of diagnosis determines the course of therapy. Artificial intelligence (AI) is a hotspot for developing computational models of human intellect. In this research, we aim to enhance the detection and classification of lung nodules from CT images using a novel deep learning approach. Our study builds upon an extensive review of existing lung cancer detection methods, highlighting their strengths and weaknesses. This LIDC/IDRI dataset has been used in over half of the most recent research on lung cancer diagnosis. While several Convolutional Neural Networks (CNNs) architecture are adequate to process medical field data using technology solutions to discover and diagnose Lung cancer, here we proposed model VGG-19+ model. It is known for its strong feature extraction capabilities. It outflanks the ongoing model on a few exhibition measures, including exactness, accuracy, responsiveness/review, and f1-score.This research using VGG-19+ model could lead to more widespread utilization in cancer diagnosis by enhancing early lung cancer detection and developing the field of medical image analysis.

Early automated detection system for skin cancer diagnosis using artificial intelligent techniques

Recently, skin cancer is one of the spread and dangerous cancers around the world. Early detection of skin cancer can reduce mortality. Traditional methods for skin cancer detection are painful, time-consuming, expensive, and may cause the disease to spread out. Dermoscopy is used for noninvasive diagnosis of skin cancer. Artificial Intelligence (AI) plays a vital role in diseases’ diagnosis especially in biomedical engineering field. The automated detection systems based on AI reduce the complications in the traditional methods and can improve skin cancer’s diagnosis rate. In this paper, automated early detection system for skin cancer dermoscopic images using artificial intelligent is presented. Adaptive snake (AS) and region growing (RG) algorithms are used for automated segmentation and compared with each other. The results show that AS is accurate and efficient (accuracy = 96%) more than RG algorithm (accuracy = 90%). Artificial Neural networks (ANN) and support vector machine (SVM) algorithms are used for automated classification compared with each other. The proposed system with ANN algorithm shows high accuracy (94%), precision (96%), specificity (95.83%), sensitivity (recall) (92.30%), and F1-score (0.94). The proposed system is easy to use, time consuming, enables patients to make early detection for skin cancer and has high efficiency.

Cervical Cancer Detection Using Gabor Featured Convolutional Neural Networks

Cervical cancer is identified as the most killing disease in women patients from past two decades. Even though various medical treatments are available at present, its death rate is not reduced. Hence, various computational and automated methods are proposed to improve the medical treatments as early as possible at an earlier stage. From the past decades, machine and deep learning methods are used for detecting the cervical cancer images. The deep learning algorithms provide superior results for the cervical cancer detection system. Therefore, Gabor Featured Convolutional Neural Networks (GFCNN) is proposed to detect the cancer regions in cervical images. It proposes Cervical Cancer Detection System (CCDS) is significantly analyzed by applying the methodologies on the cervical images which are available in Guanacaste Dataset. The proposed CCDS is constructed with the following modules Gabor transforms, Feature computations, Classification and Segmentation. The Gabor transform transforms the pixel coordinates and then intrinsic variation features are determined. These features are classified by the GFCNN classifier. The GFCNN method is tested on the set of cervical images in Guanacaste Dataset and its performance is analyzed with respect to precision, recall and cancer accuracy rate. The proposed CCDs method achieved 98.42% of PN, 98.54% of RL and 98.45% of AY. The results of GFCNN method for cervical cancer detection and segmentation system are compared with other state-of-the-art methods.

An Explainable Method for Lung Cancer Detection and Localisation from Tissue Images through Convolutional Neural Networks

Lung cancer, a prevalent and life-threatening condition, necessitates early detection for effective intervention. Considering the recent advancements in deep learning techniques, particularly in medical image analysis, which offer unparalleled accuracy and efficiency, in this paper, we propose a method for the automated identification of cancerous cells in lung tissue images. We explore various deep learning architectures with the objective of identifying the most effective one based on both quantitative and qualitative assessments. In particular, we assess qualitative outcomes by incorporating the concept of prediction explainability, enabling the visualization of areas within tissue images deemed relevant to the presence of lung cancer by the model. The experimental analysis, conducted on a dataset comprising 15,000 lung tissue images, demonstrates the effectiveness of our proposed method, yielding an accuracy rate of 0.99.

A serial image analysis architecture with positron emission tomography using machine learning combined for the detection of lung cancer

Introduction and objectivesLung cancer is the second type of cancer with the second highest incidence rate and the first with the highest mortality rate in the world. Machine learning through the analysis of imaging tests such as positron emission tomography/computed tomography (PET/CT) has become a fundamental tool for the early and accurate detection of cancer. The objective of this study was to propose an image analysis architecture (PET/CT) ordered in phases through the application of ensemble or combined machine learning methods for the early detection of lung cancer by analyzing PET/CT images. Material and methodsA retrospective observational study was conducted utilizing a public dataset entitled “A large-scale CT and PET/CT dataset for lung cancer diagnosis.” Various imaging modalities, including CT, PET, and fused PET/CT images, were employed. The architecture or framework of this study comprised the following phases: 1. Image loading or collection, 2. Image selection, 3. Image transformation, and 4. Balancing the frequency distribution of image classes. Predictive models for lung cancer detection using PET/CT images included: a) the Stacking model, which used Random Forest and Support Vector Machine (SVM) as base models and complemented them with a logistic regression model, and b) the Boosting model, which employed the Adaptive Boosting (AdaBoost) model for comparison with the Stacking model. Quality metrics used for evaluation included accuracy, precision, recall, and F1-score. ResultsThis study showed a general performance of 94% with the Stacking method and a general performance of 77% with the Boosting method. ConclusionsThe Stacking method proved to be a model with high performance and quality for lung cancer detection when analyzing PET/CT images.

A Review of Brain Tumor Detection Techniques Using YOLOv8

Abstract: Brain tumors, whether benign or malignant, pose significant risks, especially in children and young adults, impacting both life expectancy and quality of life. This review addresses the critical importance of early detection and treatment of brain tumors. With a focus on artificial intelligence, particularly object detection using the YOLOv8 model, the paper explores the potential for accurate and efficient brain tumor detection from magnetic resonance images (MRI). The YOLOv8 model is known for its real-time performance, efficiency, and high accuracy, making it a promising tool in the field of medical image analysis. The paper presents a method for brain cancer detection and localization, discusses experimental results, reviews the state-of-theart literature, and outlines future research directions.[1-22]

Signal-On Fluorescence Biosensor for Detection of miRNA-21 Based on ROX labeled Specific Stem-Loop Probe

Background: The abnormal expression of microRNA (miRNA) influences RNA transcription and protein translation, leading to tumor progression and metastasis. Today, reliably identifying aberrant miRNA expression remains challenging, especially when employing quick, simple, and portable detection methods. Objectives: This study aimed to diagnose and detect the miR-21 biomarker with high sensitivity and specificity. Methods: Our detection approach involves immobilizing ROX dye-labeled single-stranded DNA probes (ROX-labeled ssDNA) onto MWCNTs to detect target miRNA-21. Initially, adsorbing ROX-labeled ssDNA onto MWCNTs causes fluorescence quenching of ROX. Subsequently, introducing its complementary DNA (cDNA) forms double-stranded DNA (dsDNA), which results in the desorption and release from MWCNTs, thus restoring ROX fluorescence. Results: The study examined changes in fluorescence intensities before and after hybridization with miRNA-21. The fluorescence emission intensities responded linearly to increases in miR-21 concentration from 10-9 to 3.2 × 10-6 M. The developed fluorescence sensor exhibited a detection limit of 1.12 × 10-9 M. Conclusions: This work demonstrates that using a nano-biosensor based on carbon nanotubes offers a highly sensitive method for the early detection of colorectal cancer (CRC), supplementing existing techniques.

Methylation analysis of DCC gene in saliva samples is an efficient method for non-invasive detection of superficial hypopharyngeal cancer

BackgroundAdvances in upper gastrointestinal endoscopic technology have enabled early detection and treatment of hypopharyngeal cancer. However, in-depth pharyngeal observations require sedation and are invasive. It is important to establish a minimally invasive and simple evaluation method to identify high-risk patients.MethodsEighty-seven patients with superficial hypopharyngeal cancer and 51 healthy controls were recruited. We assessed the methylation status of DCC, PTGDR1, EDNRB, and ECAD, in tissue and saliva samples and verified the diagnostic accuracy by methylation analyses of their promoter regions using quantitative methylation-specific PCR.ResultsSignificant differences between cancer and their surrounding non-cancerous tissues were observed in the methylation values of DCC (p = 0.003), EDNRB (p = 0.001), and ECAD (p = 0.043). Using receiver operating characteristic analyses of the methylation values in saliva samples, DCC showed the highest area under the curve values for the detection of superficial hypopharyngeal cancer (0.917, 95% confidence interval = 0.864–0.970), compared with those for EDNRB (0.680) and ECAD (0.639). When the cutoff for the methylation values of DCC was set at ≥0.163, the sensitivity to detect hypopharyngeal cancer was 82.8% and the specificity was 90.2%.ConclusionsDCC methylation in saliva samples could be a non-invasive and efficient tool for early detection of hypopharyngeal cancer in high-risk patients.

Red blood cells function as reservoirs of tumor DNA.

Novel screening techniques for early detection of lung cancer are urgently needed. Profiling circulating tumor cell-free DNA (ctDNA) has emerged as a promising tool for biopsy-free tumor genotyping. However, both the scarcity and short half-life of ctDNA substantially limit the sensitivity and clinical utility of ctDNA detection methodologies. Our discovery that red blood cells (RBCs) sequester mitochondrial DNA opens a new avenue for detecting circulating nucleic acids, as RBCs represent an unrecognized reservoir of circulating nucleic acid. Here, we show that RBCs acquire tumor DNA following coculture with lung cancer cell lines harboring Kirsten rat sarcoma viral oncogene homolog (KRAS) and epidermal growth factor receptor (EGFR) mutations. RBC-bound tumor DNA is detectable in patients with early-stage non-small cell lung cancer (NSCLC) but not in healthy controls by qPCR. Our results collectively uncover a previously unrecognized yet easily accessible reservoir of tumor DNA, offering a promising foundation for future RBC-based tumor diagnostics.NEW & NOTEWORTHY We present a novel method for lung cancer detection by revealing RBCs as a reservoir for tumor DNA, overcoming the limitations of current circulating tumor ctDNA methodologies. By demonstrating that RBCs can capture tumor DNA, including critical mutations found in lung cancer, we provide a promising, biopsy-free avenue for early cancer diagnostics. This discovery opens up exciting possibilities for developing RBC-based diagnostic tools, significantly enhancing the sensitivity and clinical utility of noninvasive cancer detection.

Application of different methods for cervical cancer detection

Cervical cancer remains a widespread and challenging malignancy that affects women worldwide and poses significant clinical and public health issues. Since it is difficult to find early cervical lesions in the patient's own state, it is very important to apply appropriate and effective detection and screening for cervical cancer and precancerous lesions. This research investigates the development of cervical cancer and the various subtypes of HPV, which are the primary cause of cervical lesions. Combined with the investigation of the three most common clinical screening methods, including liquid-based thin-layer cell assay (TCT), human papillomavirus detection (HPV) and colposcopy detection operating methods and screening standards, data were used to comprehensively analyze the accuracy, sensitivity and specificity of single or combined screening of the three detection methods. This research examines various methods and technologies for cervical cancer screening, with the goal of determining their clinical effectiveness in detecting cervical lesions. Based on screening data, the results are positive and the methods are deemed suitable for early diagnosis of the condition. It is recommended that these screening tools be utilized in a clinical setting.

Abstract 1065: Two-step method for early detection of ovarian cancer with high specificity via platelet RNA

Abstract Owing to lack of disease-specific symptoms and screening methods, most of patients with ovarian cancer are diagnosed at an advanced stage. Recent technology based on platelet RNA aids in detection of tumors at the early stages. Also, for population screening of low-prevalence diseases like cancer, accurate detection with high specificity is essential to improve diagnostic methods. Thus, we proposed platelet RNA-based early ovarian cancer detection with great specificity. It is a two-step method for detecting ovarian tumors with more than 99% specificity using exon-exon junction features and sampling invariant normalization and finding their malignancy with more than 99% negative predictive value using exon-exon junction and hematology parameters. First, we downloaded public platelet transcriptome data of gynecological cancer including ovarian cancer (n=151), benign tumor (n=30), and healthy counterparts (n=218) from GEO (GSE158508, 89843, and 183635). Second, we prospectively enrolled patients with gynecological cancer (n=31), benign tumors (n=20), and healthy women (n=18) at Seoul National University Hospital (SNUH) and Boaz Medical Center and obtained platelet transcriptome data (FMH data). Feature selection and model development were conducted using public training set (n=243), public validation set (n=156), and FMH training/validation set (n=47). The batch-invariant normalization was performed, and 198 splice junctions were selected as features from training/validation set for the bootstrap aggregation of the SVM model diagnosing the existence of an ovarian tumor. The model performance was assessed from a separate test set only composed of FMH data (n=22). Our model that demonstrated 96.8% sensitivity, 100.0% specificity, with a predetermined cut-off value. Next, FMH training/validation set was used for model development of following malignancy test. 10 splice junctions and 19 hematology parameters were selected and SVM models were separately developed for splice junctions and hematology parameters using 5-fold cross validation. The predictions were combined using a logical OR operation to obtain the final prediction result. The result showed its diagnostic performance with 100% sensitivity or NPV, and 50.0% specificity in the test data set with a predetermined cut-off value. We proposed a two-step method to operationally improve the existing protocol for ovarian cancer screening. Our model initially excludes most healthy individuals who do not have ovarian tumors and excludes patients with benign ovarian tumors who do not necessitate medical testing. To conclude, our model allows physicians to identify a subset of ovarian tumor patients with a higher risk of malignancy even at early stages; it exhibits potential in enhancing early diagnosis of ovarian cancer, leading to increase of treatment effectiveness and ultimately augmenting the survival of patients with ovarian cancer. Citation Format: Eunyong Ahn, Se Ik Kim, Sungmin Park, Sarah Kim, Yeochan Kim, Eunchong Huang, Suyeon Lee, Dong Won Hwang, Heeyeon Kim, HyunA Jo, Untack Cho, Juwon Lee, TaeJin Ahn, Yong-Sang Song. Two-step method for early detection of ovarian cancer with high specificity via platelet RNA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 1065.