Detection Of Liver Cancer Research Articles

Multi-Class Liver Cancer Diseases Classification Using CT Images

Abstract Liver cancer is the fourth common cancer in the world and the third leading reason of cancer mortality. The conventional methods for detecting liver cancer are blood tests, biopsy and image tests. In this paper, we propose an automated computer-aided diagnosis technique for the classification of multi-class liver cancer i.e. primary, hepatocellular carcinoma, and secondary, metastases using computed tomography (CT) images. The proposed algorithm is a two-step process: enhancement of CT images using contrast limited adaptive histogram equalization algorithm and extraction of features for the detection and the classification of the different classes of the tumor. The overall achieved accuracy, sensitivity and specificity with the proposed method for the classification of multi-class tumors are 97%, 94.3% and 100% with experiment 1 and 84% all of them with experiment 2, respectively. By automatic feature selection scheme accuracy is deviated maximum by 10.5% from the overall and the ratio features accuracy decreases linearly by 5.5% with 20 to 5 selected features. The proposed methodology can help to assist radiologists in liver cancer diagnosis.

Cytochrome P450-2D6: A novel biomarker in liver cancer health disparity.

Liver cancer morbidity and mortality rates differ among ethnic groups. In the United States, the burden of liver cancer in Asian Americans (AS) is higher compared to Caucasian Americans (CA). Research on liver cancer health disparities has mainly focused on environmental and socioeconomic factors yet has ignored the genotypic differences among various racial/ethnic groups. This lack of molecular level understanding has hindered the development of personalized medical approaches for liver cancer treatment. To understand the genetic heterogeneity of liver cancer between AS and CA, we performed a systematic analysis of RNA-seq data of AS and CA patients from The Cancer Genome Atlas (TCGA). We used four differential gene expression analysis packages; DESeq2, limma, edgeR, and Superdelta2, to identify the differentially expressed genes. Our analysis identified cytochrome P450-2D6 enzyme (CYP2D6) as the gene with the greatest differential expression with higher levels in AS compared to CA. To scrutinize the underlying mechanism of CYP2D6, Ingenuity Pathway Analysis (IPA) and Cytoscape were conducted and found hepatocyte nuclear factor-4α (HNF4A) and interleukin-6 (IL6) in direct association with CYP2D6. IL6 is downregulated in AS compared to CA, while HNF4A is not significantly different. Herein, we report that CYP2D6 may serve as a putative biomarker in liver cancer health disparities. Its negative association with IL6 proclaims an intricate relationship between CYP2D6 and inflammation in the ethnic differences seen in AS and CA liver cancer patients. The goal of the present study was to understand how genetic factors may contribute to the interethnic variability of liver cancer prevalence and outcomes in AS and CA patients. Identifying ethnic-specific genes may help ameliorate detection, diagnosis, surveillance, and treatments of liver cancer, as well as reduce disease-related incidence and mortality rates in the vulnerable population.

Immune aspects of hepatocellular carcinoma: From immune markers for early detection to immunotherapy.

Hepatocellular carcinoma (HCC) is one of the most prevalent cancers and one of the main causes of cancer-related deaths worldwide. Most HCCs develop in an inflammatory microenvironment, and mounting evidence emphasizes the importance of immune aspects in hepatocarcinogenesis. In normal physiology, both innate and adaptive immune responses are responsible for eliminating malignantly transformed cells, thus preventing the development of liver cancer. However, in the setting of impaired natural killer cells and exhaustion of T cells, HCC can develop. The immunogenic features of HCC have relevant clinical implications. There is a large number of immune markers currently being studied for the early detection of liver cancer, which would be critical in order to improve surveillance programs. Moreover, novel immunotherapies have recently been proven to be effective, and the combination of atezolizumab and bevacizumab is currently the most effective treatment for advanced HCC. It is expected that in the near future different subgroups of patients will benefit from specific immunotherapy. The better we understand the immune aspects of HCC, the greater the benefit to patients through surveillance aiming for early detection of liver cancer, which allows for curative treatments, and, in cases of advanced disease, through the selection of the best possible therapy for each individual.

950P Ultra-sensitive and cost-effective method for early stage hepatocellular carcinoma and intrahepatic cholangiocarcinoma detection using plasma cfDNA fragmentomic profiles

Early detection of primary liver cancer (PLC), including hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC), is essential for patients’ survival. Previous studies mainly focused on HCC detection using DNA methylation or combined epigenetic and genetic profiles. This prospective study aims to develop an accurate and cost-effective method for PLC early detection and differentiating ICC from HCC using plasma cell-free DNA (cfDNA) fragmentomic profiles.

An automated slice sorting technique for multi-slice computed tomography liver cancer images using convolutional network

An early detection and diagnosis of liver cancer can help the radiation therapist in choosing the target area and the amount of radiation dose to be delivered to the patients. The radiologists usually spend a lot of time in selecting the most relevant slices from thousands of scans, which are usually obtained from multi-slice CT scanners. The purpose of this paper multi-organ classification of 3D CT images of liver cancer suspected patients by convolution network. A dataset consisting of 63503 CT images of liver cancer patients taken from The Cancer Imaging Archive (TCIA) has been used to validate the proposed method. The method is a CNN for classification of CT liver cancer images. The classification results in terms of accuracy, precision, sensitivity, specificity, true positive rate, false negative rate, and F1 score have been computed. The results manifest a high validation accuracy of 99.1%, when convolution network is trained with the data augmented volume slices as compared to accuracy of 98.7% with that obtained original volume slices. The overall test accuracy for data augmented volume slice dataset is 93.1% superior to other volume slices. The main contribution of this work is that it will help the radiation therapist to focus on a small subset of CT image data. This is achieved by segregating the whole set of 63503 CT images into three categories based on the likelihood of the spread of cancer to other organs in liver cancer suspected patients. Consequently, only 19453 CT images had liver visible in them, making rest of 44050 CT images less relevant for liver cancer detection. The proposed method will help in the rapid diagnosis and treatment of liver cancer patients.

Non-Coding RNA-Based Biosensors for Early Detection of Liver Cancer.

Primary liver cancer is an aggressive, lethal malignancy that ranks as the fourth leading cause of cancer-related death worldwide. Its 5-year mortality rate is estimated to be more than 95%. This significant low survival rate is due to poor diagnosis, which can be referred to as the lack of sufficient and early-stage detection methods. Many liver cancer-associated non-coding RNAs (ncRNAs) have been extensively examined to serve as promising biomarkers for precise diagnostics, prognostics, and the evaluation of the therapeutic progress. For the simple, rapid, and selective ncRNA detection, various nanomaterial-enhanced biosensors have been developed based on electrochemical, optical, and electromechanical detection methods. This review presents ncRNAs as the potential biomarkers for the early-stage diagnosis of liver cancer. Moreover, a comprehensive overview of recent developments in nanobiosensors for liver cancer-related ncRNA detection is provided.

A novel computer-aided diagnostic system for accurate detection and grading of liver tumors

Liver cancer is a major cause of morbidity and mortality in the world. The primary goals of this manuscript are the identification of novel imaging markers (morphological, functional, and anatomical/textural), and development of a computer-aided diagnostic (CAD) system to accurately detect and grade liver tumors non-invasively. A total of 95 patients with liver tumors (M = 65, F = 30, age range = 34–82 years) were enrolled in the study after consents were obtained. 38 patients had benign tumors (LR1 = 19 and LR2 = 19), 19 patients had intermediate tumors (LR3), and 38 patients had hepatocellular carcinoma (HCC) malignant tumors (LR4 = 19 and LR5 = 19). A multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) was collected to extract the imaging markers. A comprehensive CAD system was developed, which includes the following main steps: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of textural markers using a novel rotation invariant gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) models, and iii) calculation of the functional markers by estimating the wash-in/wash-out slopes, which enable quantification of the enhancement characteristics across different CE-MR phases. These markers were subsequently processed using a two-stages random forest-based classifier to classify the liver tumor as benign, intermediate, or malignant and determine the corresponding grade (LR1, LR2, LR3, LR4, or LR5). The overall CAD system using all the identified imaging markers achieved a sensitivity of 91.8%±0.9%, specificity of 91.2%±1.9%, and F_{1} score of 0.91±0.01, using the leave-one-subject-out (LOSO) cross-validation approach. Importantly, the CAD system achieved overall accuracies of 88%pm 5%, 85%±2%, 78%±3%, 83%±4%, and 79%±3% in grading liver tumors into LR1, LR2, LR3, LR4, and LR5, respectively. In addition to LOSO, the developed CAD system was tested using randomly stratified 10-fold and 5-fold cross-validation approaches. Alternative classification algorithms, including support vector machine, naive Bayes classifier, k-nearest neighbors, and linear discriminant analysis all produced inferior results compared to the proposed two stage random forest classification model. These experiments demonstrate the feasibility of the proposed CAD system as a novel tool to objectively assess liver tumors based on the new comprehensive imaging markers. The identified imaging markers and CAD system can be used as a non-invasive diagnostic tool for early and accurate detection and grading of liver cancer.

The expression of microRNA-331-3p and microRNA-23b3 in Egyptian patients with early-stage hepatocellular carcinoma in hepatitis C-related liver cirrhosis

BackgroundHepatocellular carcinoma and hepatitis C are strongly associated. The current work aimed to study the expression levels of microRNA-331-3p and microRNA-23b-3p as propable biomarkers for detecting liver cancer (HCC) at its early stages in patients with HCV-related liver cirrhosis. The current prospective study included two hundred participants, divided into three groups: group I, 100 patients with HCV-related liver cirrhosis; group II, 50 HCC patients at early stages; and group III, 50 apparentlyhealthy controls. All patients had routine laboratory workup and ultrasound hepatic assessment. Values of microRNA-331-3p and microRNA-23b-3p were measured by real-time quantitative PCR.ResultsLevels of miR-331-3p were significantly higher in HCC patients than in cirrhotic patients and controls (p < 0.001), while levels of miR-23b-3p were significantly lower in HCC patients compared to cirrhotics and controls (p < 0.001). ROC curve revealed that miR-23b-3p had 80% sensitivity and 74% specificity, miR-331-3p had 66% sensitivity and 61% specificity, and AFP had 64% sensitivity and 61% specificity of 61% in discrimination between HCC patients from controls.ConclusionSerum miR-23b-3p is a more effective predictor than miR-331-3p and AFP for the development of hepatocellular carcinoma in hepatitis C (HCV)-related cirrhotic patients.

Research progress of serum biomarkers for early screening of hepatocellular carcinoma

The latest research data shows that the cause of death of liver cancer patients ranks third among malignant tumors. The global situation of early detection, early diagnosis and early treatment of liver cancer is severe. Therefore, how to achieve early diagnosis of liver cancer has important clinical significance. At present, alpha-fetoprotein, alpha-fetoprotein-L3 and des-gamma-carboxythrombin are commonly used in the clinical detection of hepatocellular carcinoma; however, their sensitivity cannot meet the diagnostic needs of patients with early liver cancer. With the development of molecular biology techniques such as serum oligosaccharide chains detection, B10, a member of the aldehyde ketone reductase family, microRNAs, circulating tumor cells, DNA methylation, and other novel serum biomarkers, a new option for the early screening and diagnosis of hepatocellular carcinoma patients will be offered.

Liver Cancer Patient Classification on a Multiple-Stage using Hybrid Classification Methods

This paper proposes a model to detect liver cancer patients and estimate the abnormality level of livers using a classification method based on an Indian liver patient dataset. The dataset is prepared by 3 processes: preliminary study, data cleansing, and handling imbalanced class to build the model based on multiple-stages using hybrid classification methods. The 1st stage is liver cancer patient detection. The 2nd stage is abnormality level of liver estimation, as divided using the DeRitis Ratio. The abnormality level of livers is divided into 3 levels: low, medium, and high, called ALL framework. Machine learning method is used to build multiple classification stages, which consist of Multilayer Perceptron, Logistic Regression, and Random Forest. The experimental results demonstrate that the 1st model (stage I) can detect liver cancer patient with 78.88 % accuracy. The 2nd model (stage II) achieves accuracy of 99.83 % for abnormality level of liver estimation. In addition, we compare our proposed model with another dataset. Our proposed model also outperforms detection with 76.73 and 98.26 % accuracy in stage I and stage II, respectively. Our proposed model is a benefit for physicians to support diagnosis and treatment, especially in the case of physicians desiring an intelligent decision support system.

A biosensing method for the direct serological detection of liver diseases by integrating a SERS-based sensor and a CNN classifier

Direct serological detection, due to its clinical facility and testing economy, affords prominent clinical values to the early detection of cancer. Surface-enhanced Raman spectroscopy (SERS)-based sensors have shown great promise in realizing this form of detection. Detecting liver cancer early with such a form, especially in terms of monitoring the pathogenic progression from hepatic inflammations to cancer, is the most effective clinical path to reducing the mortality rate. However, the methodology investigation for this purpose remains a formidable challenge. We fabricated a SERS-based sensor, consisting of Au-Ag nanocomplex-decorated ZnO nanopillars on paper. The sensor has an analytic enhancement factor of 1.02 × 107, which is enough to sense the biomolecular information of liver diseases through direct serum SERS analysis. A convolutional neural network (CNN) classifier for recognizing serum SERS spectra was constructed by deep learning. Integrating this sensor with the CNN, we established an intelligent biosensing method and realized direct serological detection of liver diseases within 1 min. As a proof-of-concept, the method achieved a prediction accuracy of 97.78% on an independent test dataset randomly sampled from 30 normal controls, 30 hepatocellular carcinoma (HCC) cases, and 30 hepatitis B (HB) patients. The results suggest this method can be developed for detecting liver diseases clinically and is worthy of exploration as a means of liver cancer surveillance. The presented sensor holds potential for clinical translation to the direct serological detection of diseases.

A SURVEY ON CLASSIFICATION OF LIVER TUMOUR FROM ABDOMINAL COMPUTED TOMOGRAPHY USING MACHINE LEARNING TECHNIQUES

Pattern recognition is a significant area of research in medicine because many applications like diagnostic system benefit from it. The aim of this research is to analyze developments of liver cancer detection using machine learning techniques for liver disease. The study highlights how liver cancer diagnosis is assisted using machine learning with supervised, unsupervised and deep learning techniques. Several state of art techniques are compared based on performance measures such as accuracy, sensitivity, specificity. Finally, challenges are also highlighted for possible future work. KEYWORDS: Machine Learning, Liver, Liver disease, Computer Aided Diagnosis system, Liver Cancer, Computed Tomography

Analysis of liver cancer screening results and influencing factors of urban residents in Zhejiang Province from 2013 to 2018

Objective: To analyze the results of liver cancer screening for urban residents in Zhejiang Province from 2013 to 2018 and explore the influencing factors of the detection rate. Methods: From September 2013 to August 2019, six urban communities in Hangzhou (Jianggan District and Gongshu District), Ningbo (Haishu District, Yinzhou District and Jiangbei District), and Quzhou (Kecheng District) were selected as study sites. All permanent residents aged 40-74 (with local household registration and living in the local area for more than 3 years) were selected as the research subjects by using cluster sampling method. Patients with confirmed cancers and other serious medical and surgical diseases were excluded. A total of 166 293 research subjects were included. Basic demographic characteristics and risk factors of subjects were obtained through questionnaire surveys. The cancer risk assessment system was used to evaluate the liver cancer risk of subjects. Clinical screening participation and screening results for subjects at high risk of liver cancer were obtained from participating hospitals. The high-risk rate of liver cancer, clinical screening rate, detection rate of positive lesions, and detection rate of suspected liver cancer were analyzed. Poisson regression was used to analyze the influencing factors of detection rate. Results: The age of 166 293 subjects was (56.01±8.40) years, of which 41.36% (68 777) were males. A total of 23 765 high-risk subjects for liver cancer were screened (the high-risk rate was 14.29%). Among them, a total of 12 375 subjects participated in clinical screening for liver cancer, with a screening rate of 52.07% (12 375/23 765). A total of 297 cases of positive lesions were detected and the detection rate was 2.40% (297/12 375). A total of 8 cases of suspected liver cancer were detected, with a detection rate of 0.06% (8/12 375). The results of multivariate Poisson regression model analysis showed that compared with men, people who never smoked, never ate pickled food, had low oil content, and had no history of hepatobiliary disease, female, people who were smoking or had smoked, sometimes ate pickled food, ate higher oil content, and had a history of hepatobiliary disease had a higher detection rate of positive lesions. The incidence rate ratio (IRR) (95%CI) values were 1.98 (1.45-2.70), 2.23 (1.61-3.09)/2.08 (1.31-3.28), 1.82 (1.22-2.70), 1.44 (1.08-1.91), and 1.45 (1.05-2.00), respectively. Compared with those aged from 40 to 49 years old and without HBsAg test, the IRR (95%CI) of suspected liver cancer in people aged 70 to 74 years old and HBsAg positive were 16.30 (1.32-200.74) and 6.43 (1.24-33.22), respectively. Conclusion: The urban cancer early diagnosis and early treatment project in Zhejiang Province has good compliance in clinical screening of liver cancer. Abdominal ultrasound examination and serum alpha-fetoprotein detection are helpful to detect liver cancer and its precancerous lesions in the high-risk population of liver cancer.

Abstract PO-022: Automated liver tissue segmentation in point of care ultrasound b-mode images using U-Net

Abstract Introduction/Purpose: We have recently developed and demonstrated that tissue acoustic properties can facilitate early detection of liver cancer during period abdominal ultrasound surveillance exams in high risk patients. Automated segmentation of the liver is a necessary step in increasing the accuracy, sensitivity, and specificity of Machine Learning Models which detect cancer using the lower quality data generated from Point-of-Care Ultrasound (PoCUS). We have developed deep learning algorithms which can successfully segment the data generated by these PoCUS systems. Methods: A total of 1000 patients from 4 collaboration sites were recruited, though for this study only 25 of which were manually segmented were used.. For this HIPPA compliant study, all data was obtained through IRBs approved at the local data acquisition site; all patients were consented before data acquisition. The patient's mean age and BMI were 43(11 STD) and 23 (5 STD). All patients were scanned using the same acquisition protocol, capturing the same 5 scan visualization windows of the liver using a PoCUS system, with capabilities to capture raw signal data. We use a deep learning algorithm to automatically segment out the liver. The initial version of the U-net Deep learning architecture was trained on a subset of our data containing B-mode images from 20 patients (500 frames) and tested on a dataset with 5 patients (125 frames). The Regions of interest that served as training and testing labels for the algorithm were outlined on an image-by-image basis by expert sonographers. U-Net is a fully convolutional neural network that consists of a block of contraction layers followed by a block of expansion layers. The architecture contains feature channels to relay context information to higher resolution layers. U-Net has been used at multiple medical segmentations tasks in which it performs particularly well even with small datasets. Results: The architecture successfully segmented the images both in the train and test datasets with a great degree of accuracy and generalization. Test accuracies surpassed 86% with a sensitivity of 80% and specificity of 95% and results can be further improved by applying thresholds to the algorithm’s output. Conclusion: This automated segmentation algorithm is a clear next step in the improvement of any automated disease detection method in the liver. Once in place it will greatly aid in the early screening of all liver diseases and improve the outcomes for at risk patients. Citation Format: Raul Blazquez Garcia, Adi Lightstone, Miriam Naim Ibrahim, Ahmed El Kaffas. Automated liver tissue segmentation in point of care ultrasound b-mode images using U-Net [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-022.

Use of BERT (Bidirectional Encoder Representations from Transformers)-Based Deep Learning Method for Extracting Evidences in Chinese Radiology Reports: Development of a Computer-Aided Liver Cancer Diagnosis Framework.

BackgroundLiver cancer is a substantial disease burden in China. As one of the primary diagnostic tools for detecting liver cancer, dynamic contrast-enhanced computed tomography provides detailed evidences for diagnosis that are recorded in free-text radiology reports.ObjectiveThe aim of our study was to apply a deep learning model and rule-based natural language processing (NLP) method to identify evidences for liver cancer diagnosis automatically.MethodsWe proposed a pretrained, fine-tuned BERT (Bidirectional Encoder Representations from Transformers)-based BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Field) model to recognize the phrases of APHE (hyperintense enhancement in the arterial phase) and PDPH (hypointense in the portal and delayed phases). To identify more essential diagnostic evidences, we used the traditional rule-based NLP methods for the extraction of radiological features. APHE, PDPH, and other extracted radiological features were used to design a computer-aided liver cancer diagnosis framework by random forest.ResultsThe BERT-BiLSTM-CRF predicted the phrases of APHE and PDPH with an F1 score of 98.40% and 90.67%, respectively. The prediction model using combined features had a higher performance (F1 score, 88.55%) than those using APHE and PDPH (84.88%) or other extracted radiological features (83.52%). APHE and PDPH were the top 2 essential features for liver cancer diagnosis.ConclusionsThis work was a comprehensive NLP study, wherein we identified evidences for the diagnosis of liver cancer from Chinese radiology reports, considering both clinical knowledge and radiology findings. The BERT-based deep learning method for the extraction of diagnostic evidence achieved state-of-the-art performance. The high performance proves the feasibility of the BERT-BiLSTM-CRF model in information extraction from Chinese radiology reports. The findings of our study suggest that the deep learning–based method for automatically identifying evidences for diagnosis can be extended to other types of Chinese clinical texts.

A novel serum protein purification technique combined with surface-enhanced Raman spectroscopy for liver cancer detection

In this study, silver nanoparticles-based surface-enhanced Raman spectroscopy combined with a serum protein purification method was employed to screen liver tumors. The cellulose acetate membrane was used to separate proteins from human serum, and then the purified serum proteins were mixed with silver nanoparticles for surface-enhanced Raman spectroscopy detection. High-quality spectra were recorded from serum protein samples belonging to 45 healthy volunteers and 42 liver cancer patients, and the diagnostic sensitivity and specificity of liver cancer were 90.5% and 95.6%, respectively, indicating that this method has great application potential for the detection and screening of liver cancer.

Novel method for liver cancer detection using super pixel and ANN algorithm

Nowadays most of the people are affected by liver cancer that can be the leading cause of cancer death. To analyze the liver cancer detection using super pixel segmentation and artificial neural network (ANN) Algorithm and it reduces the time complexity. An automatic 3D segmentation method for high energy sound waves in ultrasound liver images, which is based on a fusion of accurate time-consuming method and statistical texture prior. Three orthogonal linear filter banks are used to extract texture features from each image in the region around the point of the database. The atlas database includes registered liver images from previous patients and their segmented liver surfaces. To train the problem of patient–specific frequency content in the image features from the atlas database are using ANN algorithm and then to segment the super pixel segmentation the liver image from a new patient. The dataset of liver cancer detection are benign and malign.

The Application of Image Processing in Liver Cancer Detection

Hepatic cancer is caused by the uncontrolled growth of liver cells, an HCC is the most common form of malignant liver cancer, accounting for 75 percent of cases. This tumor is difficult to diagnose, and it is often discovered at an advanced stage, posing a life-threatening danger. As a result, early diagnosis of liver cancer increases life expectancy. So, using a digital image processing method, we suggest an automated computer-aided diagnosis of liver tumors from MRI images. Magnetic Resonance Imaging (MRI) images are used to identify liver tumors in this case. The image goes through image preprocessing, image segmentation, and feature extraction, all of which are done within the layers of an Artificial Neural Network, making it an automated operation. To make the edge continuous, this operation combines two processes: edge and manual labeling. On the basis of statistical characteristics, tumors are often divided into four categories: cyst, adenoma, hemangioma, and malignant liver tumor. The aim of this proposed technique is to automatically highlight and categorize tumor regions in Magnetic Resonance Imaging images without the need for a medical practitioner.

Integrative analysis of long extracellular RNAs reveals a detection panel of noncoding RNAs for liver cancer.

Rationale: Long extracellular RNAs (exRNAs) in plasma can be profiled by new sequencing technologies, even with low abundance. However, cancer-related exRNAs and their variations remain understudied.Methods: We investigated different variations (i.e. differential expression, alternative splicing, alternative polyadenylation, and differential editing) in diverse long exRNA species (e.g. long noncoding RNAs and circular RNAs) using 79 plasma exosomal RNA-seq (exoRNA-seq) datasets of multiple cancer types. We then integrated 53 exoRNA-seq datasets and 65 self-profiled cell-free RNA-seq (cfRNA-seq) datasets to identify recurrent variations in liver cancer patients. We further combined TCGA tissue RNA-seq datasets and validated biomarker candidates by RT-qPCR in an individual cohort of more than 100 plasma samples. Finally, we used machine learning models to identify a signature of 3 noncoding RNAs for the detection of liver cancer.Results: We found that different types of RNA variations identified from exoRNA-seq data were enriched in pathways related to tumorigenesis and metastasis, immune, and metabolism, suggesting that cancer signals can be detected from long exRNAs. Subsequently, we identified more than 100 recurrent variations in plasma from liver cancer patients by integrating exoRNA-seq and cfRNA-seq datasets. From these datasets, 5 significantly up-regulated long exRNAs were confirmed by TCGA data and validated by RT-qPCR in an independent cohort. When using machine learning models to combine two of these validated circular and structured RNAs (SNORD3B-1, circ-0080695) with a miRNA (miR-122) as a panel to classify liver cancer patients from healthy donors, the average AUROC of the cross-validation was 89.4%. The selected 3-RNA panel successfully detected 79.2% AFP-negative samples and 77.1% early-stage liver cancer samples in the testing and validation sets.Conclusions: Our study revealed that different types of RNA variations related to cancer can be detected in plasma and identified a 3-RNA detection panel for liver cancer, especially for AFP-negative and early-stage patients.

A novel approach for hepatocellular carcinoma detection with region merging segmentation method

We present a noninvasive method for the detection and an advanced segmentation of Hepatocellular carcinoma (HCC) based on Computed Tomography (CT) images.This proposed method basically starts with the processing of the data set. 60 CT images are prepared for the segmentation process. Image data is divided into two groups; 50 CT images of the HCC, and 10 CT images of the normal liver. The ground truth images are created with the specialist abdominal radiologist. Images are in 256x256 µm size in JPEG format. For the segmentation part, the Statistical Region Merging method is used. The proposed method consists of three main parts, these are thresholding, segmentation, and estimation of ROC parameters. By using the database and the ground truth, according to the simulation results, the average of the sensitivity, specificity, and accuracy are obtained as 0.7476 %, 0.9723 %, and 0.9502 %, respectively. In conclusion, HCC is the most common primary malignant tumor in the liver. It is considered an important and life-threatening disease. Early detection of liver cancer has become very important for the patients. The Region Merging Segmentation Method is a very useful liver segmentation technique for detection of the HCC.