A hybrid cancer prediction based on multi-omics data and reinforcement learning state action reward state action (SARSA)

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 154, P. 106617 - 106617

Published: Feb. 3, 2023

Language: Английский

---

Multiround Transfer Learning and Modified Generative Adversarial Network for Lung Cancer Detection

International Journal of Intelligent Systems, Journal Year: 2023, Volume and Issue: 2023, P. 1 - 14

Published: March 3, 2023

Lung cancer has been the leading cause of death for many decades. With advent artificial intelligence, various machine learning models have proposed lung detection (LCD). Typically, challenges in building an accurate LCD model are small-scale datasets, poor generalizability to detect unseen data, and selection useful source domains prioritization multiple transfer learning. In this paper, a multiround modified generative adversarial network (MTL-MGAN) algorithm is LCD. The MTL transfers knowledge between prioritized target domain get rid exhaust search datasets among maximizing transferability with process, avoiding negative via customization loss functions aspects domain, instance, feature. regard MGAN, it not only generates additional training data but also creates intermediate bridge gap domains. 10 benchmark chosen performance evaluation analysis MTL-MGAN. significantly improved accuracy compared related works. To examine contributions individual components MTL-MGAN, ablation studies conducted confirm effectiveness algorithm, MTL, avoidance functions, MGAN. research implications feasibility enhance optimal solution provide generic approach using

Language: Английский

---

Deep Learning for Medical Image Cryptography: A Comprehensive Review

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(14), P. 8295 - 8295

Published: July 18, 2023

Electronic health records (EHRs) security is a critical challenge in the implementation and administration of Internet Medical Things (IoMT) systems within healthcare sector’s heterogeneous environment. As digital transformation continues to advance, ensuring privacy, integrity, availability EHRs become increasingly complex. Various imaging modalities, including PET, MRI, ultrasonography, CT, X-ray imaging, play vital roles medical diagnosis, allowing professionals visualize assess internal structures, functions, abnormalities human body. These diagnostic images are typically stored, shared, processed for various purposes, segmentation, feature selection, image denoising. Cryptography techniques offer promising solution protecting sensitive data during storage transmission. Deep learning has potential revolutionize cryptography securing images. This paper explores application deep cryptography, aiming enhance privacy data. It investigates use models encryption, resolution enhancement, detection classification, encrypted compression, key generation, end-to-end encryption. Finally, we provide insights into current research challenges directions future field applications cryptography.

Language: Английский

---

A Comparative Study of Machine Learning Techniques for Early Prediction of Prostate Cancer

Published: Nov. 1, 2023

Prostate cancer is one of the leading causes cancer-related deaths among men. Early detection important in improving survival rate patients. In this study, we aimed to develop a machine learning model for and diagnosis using clinical radiological data. We used dataset 200 patients with healthy controls extracted set features from their then trained evaluated several machines models, including logistic regression, decision tree, random forest, support vector machine, neural network 10-fold cross-validation. Our results show that forest achieved highest accuracy 0.92, sensitivity 0.95 specificity 0.89. The tree similar 0.91, while models lower accuracies 0.86, 0.87, 0.88, respectively. findings suggest can be effective detecting diagnosing data, may most suitable task.

Language: Английский

---

Artificial intelligence in pathologic diagnosis, prognosis and prediction of prostate cancer

American Journal of Clinical and Experimental Urology, Journal Year: 2024, Volume and Issue: 12(4), P. 200 - 215

Published: Jan. 1, 2024

Histopathology, which is the gold-standard for prostate cancer diagnosis, faces significant challenges. With ranking among most common cancers in United States and worldwide, pathologists experience an increased number biopsies. At same time, precise pathological assessment classification are necessary risk stratification treatment decisions care, adding to challenge pathologists. Recent advancement digital pathology makes artificial intelligence learning tools adopted histopathology feasible. In this review, we introduce concept of AI its various techniques field histopathology. We summarize clinical applications cancer, including grading, prognosis evaluation, options. also discuss how can be integrated into routine workflow. these rapid advancements, it evident that go beyond initial goal being diagnosis grading. Instead, provide additional information improve long-term patient outcomes by assessing detailed histopathologic features at pixel level using AI. Our review not only provides a comprehensive summary existing research but offers insights future advancements.

Language: Английский

---

A Convolutional Neural Network-Based Feature Extraction and Weighted Twin Support Vector Machine Algorithm for Context-Aware Human Activity Recognition

Electronics, Journal Year: 2023, Volume and Issue: 12(8), P. 1915 - 1915

Published: April 18, 2023

Human activity recognition (HAR) is crucial to infer the activities of human beings, and provide support in various aspects such as monitoring, alerting, security. Distinct may possess similar movements that need be further distinguished using contextual information. In this paper, we extract features for context-aware HAR a convolutional neural network (CNN). Instead traditional CNN, combined 3D-CNN, 2D-CNN, 1D-CNN was designed enhance effectiveness feature extraction. Regarding classification model, weighted twin vector machine (WTSVM) used, which had advantages reducing computational cost high-dimensional environment compared machine. A performance evaluation showed proposed algorithm achieves an average training accuracy 98.3% 5-fold cross-validation. Ablation studies analyzed contributions individual components 1D-CNN, samples SVM, strategy solving two hyperplanes. The corresponding improvements these five were 6.27%, 4.13%, 2.40%, 2.29%, 3.26%, respectively.

Language: Английский

---

Efficient Bioinspired Feature Selection and Machine Learning Based Framework Using Omics Data and Biological Knowledge Data Bases in Cancer Clinical Endpoint Prediction

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 2674 - 2699

Published: Jan. 1, 2023

Cancer Research has advanced during the past few years. Using high throughput technology and advances in artificial intelligence, it is now possible to improve cancer diagnosis targeted therapy, by integrating investigation analysis of clinical omics profiles. The dimensionality class imbalance majority available data sets represent a serious challenge development computational methods tools for biomarker discovery. Taking into account multi-omics further complicates undertaking. In this paper, we describe five-step integrative architecture dealing with three aforementioned problems incorporating proteomics data, protein-protein interaction networks, signaling pathways order identify protein biomarkers direct association cancerous patients' overall survival (OS) progression free interval (PFI). core parts are cluster based grey wolf optimization algorithm (CB-GWO) feature selection deep stacked canonical correlation autoencoder (DSCC-AE) endpoint prediction. A thorough experimental study was carried out evaluate performance proposed selection, as well learning model terms Mathew coefficient (MCC) Area under curve (AUC) on breast, lung, colon, rectum cancers. results were compared other literature. very promising show effectiveness framework its ability outperform algorithms models AUC (0.91) MCC (0.64). addition, hub marker genes potential occurence alterations colorectal cancer, breast lung have been identified.

Language: Английский

---

Amplifying Human Capabilities in Prostate Cancer Diagnosis: An Empirical Study of Current Practices and AI Potentials in Radiology

Published: May 11, 2024

This paper examines the potential of Human-Centered AI (HCAI) solutions to support radiologists in diagnosing prostate cancer. Prostate cancer is one most prevalent and increasing cancers among men. The scarcity raises concerns about their ability address growing demand for diagnosis, leading a significant surge workload radiologists. Drawing on an HCAI approach, we sought understand current practices concerning radiologists' work detecting cancer, as well challenges they face. findings from our empirical studies point toward that has expedite informed decision-making enhance accuracy, efficiency, consistency. particularly beneficial collaborative diagnosis processes. We discuss these results introduce design recommendations concepts domain with aim amplifying professional capabilities

Language: Английский

---

Image Denoising Techniques Using Unsupervised Machine Learning and Deep Learning Algorithms: A Review

Indonesian Journal of Computer Science, Journal Year: 2024, Volume and Issue: 13(1)

Published: Feb. 16, 2024

The continuous evolution of imaging technologies has accentuated the demand for robust and efficient image denoising techniques. Unsupervised machine learning algorithms have emerged as promising tools addressing this challenge. This review scrutinizes efficacy, versatility, limitations various unsupervised approaches in area denoising. paper commences with a clarification foundational concepts pivotal role plays enhancing its efficacy. Traditional methods, encompassing filters transforms, are briefly outlined, highlighting their insufficiencies handling complicated noise patterns prevalent modern systems. Subsequently, delves into an exploration techniques tailored includes in-depth analysis methodologies such clustering deep learning. Each technique is surveyed architectural variation, adaptability, performance diverse datasets. Additionally, encompasses evaluation metrics used quantifying performance, discussing relevance applicability across varying types characteristics. Furthermore, it delineates challenges faced by domain charts prospective avenues future research, emphasizing fusion methods other paradigms heightened merges empirical insights, critical analysis, perspectives, serving roadmap researchers practitioners navigating landscape through methodologies.

Language: Английский

---

HViT4Lung: Hybrid Vision Transformers Augmented by Transfer Learning to Enhance Lung Cancer Diagnosis

Published: June 7, 2023

Lung cancer is the leading cause of mortality among other forms worldwide. Early and accurate recognition lung nodules crucial for better life quality patients. Although chest Computed Tomography (CT) scan principal imaging procedure to evaluate recognize cancer, radiologists evaluation based on CT images subjective afflicted from a low accuracy compared post-surgery pathological tests. Computer Aided Diagnosis (CAD) has been proven be beneficial in this context by increasing minimizing expert involvement. Nevertheless, due various factors including size location inconsistency nodules, errorless detection cancerous cases still challenge CAD systems. Motivated fact, paper presents novel effective method, called HViT4Lung (Hybrid Vision Transformers detection), enhance diagnosis. The proposed deep learning-based hybrid framework combines Convolution Neural Networks, augmented transfer learning that extracts features detect predict their malignancy. pipeline implemented with blocks tested sample dataset. results model are very promising approaches field, achieving 99.20% training accuracy, 99.09% validation testing classification scans 1190 into three different classes normal, benign, malignant.

Language: Английский

---