Advances in Genomic Data and Biomarkers: Revolutionizing NSCLC Diagnosis and Treatment

Cancers, Год журнала: 2023, Номер 15(13), С. 3474 - 3474

Опубликована: Июль 3, 2023

Non-small cell lung cancer (NSCLC) is a significant public health concern with high mortality rates. Recent advancements in genomic data, bioinformatics tools, and the utilization of biomarkers have improved possibilities for early diagnosis, effective treatment, follow-up NSCLC. Biomarkers play crucial role precision medicine by providing measurable indicators disease characteristics, enabling tailored treatment strategies. The integration big data artificial intelligence (AI) further enhances potential personalized through advanced biomarker analysis. However, challenges remain impact new on efficacy due to limited evidence. Data analysis, interpretation, adoption approaches clinical practice pose additional emphasize technologies such as analysis (AI), which enhance Despite these obstacles, into has shown promising results NSCLC, improving patient outcomes targeted therapies. Continued research discovery, utilization, evidence generation are necessary overcome medicine. Addressing obstacles will contribute continued improvement non-small cancer.

Язык: Английский

---

Optimization System Based on Convolutional Neural Network and Internet of Medical Things for Early Diagnosis of Lung Cancer

Bioengineering, Год журнала: 2023, Номер 10(3), С. 320 - 320

Опубликована: Март 2, 2023

Recently, deep learning and the Internet of Things (IoT) have been widely used in healthcare monitoring system for decision making. Disease prediction is one emerging applications current practices. In method described this paper, lung cancer implemented using IoT, which a challenging task computer-aided diagnosis (CAD). Because dangerous medical disease that must be identified at higher detection rate, disease-related information obtained from IoT devices transmitted to server. The data are then processed classified into two categories, benign malignant, multi-layer CNN (ML-CNN) model. addition, particle swarm optimization improve ability (loss accuracy). This step uses (CT scan sensor information) based on Medical (IoMT). For purpose, image IoMT sensors gathered, classification actions taken. performance proposed technique compared with well-known existing methods, such as Support Vector Machine (SVM), probabilistic neural network (PNN), conventional CNN, terms accuracy, precision, sensitivity, specificity, F-score, computation time. datasets were tested evaluate performance: Lung Image Database Consortium (LIDC) Linear Imaging Self-Scanning Sensor (LISS) datasets. Compared alternative trial outcomes showed suggested has potential help radiologist make an accurate efficient early diagnosis. ML-CNN was analyzed Python, where accuracy (2.5-10.5%) high when number instances, precision (2.3-9.5%) sensitivity (2.4-12.5%) several F-score (2-30%) cases, error rate (0.7-11.5%) low time (170 ms 400 ms) how many cases computed work, including previous known methods. architecture shows outperforms works.

Язык: Английский

---

Deep Learning for Lung Cancer Diagnosis, Prognosis and Prediction Using Histological and Cytological Images: A Systematic Review

Cancers, Год журнала: 2023, Номер 15(15), С. 3981 - 3981

Опубликована: Авг. 5, 2023

Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. accurate diagnosis based on distinct histological patterns combined molecular data for personalized treatment. Precise lung classification from single H&E slide can be challenging pathologist, requiring most time additional histochemical and special immunohistochemical stains final pathology report. According to WHO, small biopsy cytology specimens are available materials about 70% patients advanced-stage unresectable disease. Thus, limited diagnostic material necessitates its optimal management processing completion predictive testing according published guidelines. During new era Digital Pathology, Deep Learning offers potential interpretation assist pathologists’ routine practice. Herein, we systematically review current Artificial Intelligence-based approaches using cytological images cancer. Most literature centered distinction between adenocarcinoma, squamous cell carcinoma, reflecting realistic pathologist’s routine. Furthermore, several studies developed algorithms adenocarcinoma predominant architectural pattern determination, prognosis prediction, mutational status characterization, PD-L1 expression estimation.

Язык: Английский

---

Advancing Oncology Diagnostics: AI-Enabled Early Detection of Lung Cancer Through Hybrid Histological Image Analysis

IEEE Access, Год журнала: 2024, Номер 12, С. 64396 - 64415

Опубликована: Янв. 1, 2024

Against the backdrop of pervasive global challenge cancer, with particular emphasis on lung cancer (LC), this study centers its investigation critical realm early detection leveraging artificial intelligence (AI) within domain histological image analysis. Through fusion DenseNet201 color histogram techniques, a novel hybrid feature set emerges, engineered to elevate classification accuracy. The comprehensive evaluation encompasses eight diverse machine learning (ML) algorithms, spanning from K-Nearest Neighbors (KNN) Support Vector Machines (SVM), including notable contenders such as LightGBM (LGBM), CatBoost, XGBoost, decision trees (DT), random forests (RF), and multinomial naive Bayes (MultinomialNB). This rigorous examination illuminates distinguished model, achieving remarkable accuracy rate 99.683% LC25000 dataset. extension methodology breast detection, utilizing BreakHis dataset, yields commendable 94.808%. These findings underscore transformative potential AI in intricate landscape histopathological analysis, positioning it pivotal force advancing diagnostic capabilities. A meticulous comparative analysis not only underscores merits but also elucidates limitations existing applications medical imaging, thereby charting roadmap for future refinements clinical deployments. Consequently, continued research settings is advocated, ultimate aim fortifying diagnosis subsequently enhancing patient outcomes through judicious therapeutic interventions.

Язык: Английский

---

Exploring Local Explanation of Practical Industrial AI Applications: A Systematic Literature Review

Applied Sciences, Год журнала: 2023, Номер 13(9), С. 5809 - 5809

Опубликована: Май 8, 2023

In recent years, numerous explainable artificial intelligence (XAI) use cases have been developed, to solve real problems in industrial applications while maintaining the explainability level of used (AI) models judge their quality and potentially hold accountable if they become corrupted. Therefore, understanding state-of-the-art methods, pointing out issues, deriving future directions are important drive XAI research efficiently. This paper presents a systematic literature review local explanation techniques practical various sectors. We first establish need for response opaque AI survey different methods applications. The number studies is then examined with several factors, including industry sectors, models, data types, XAI-based usage purpose. also look at advantages disadvantages how well work settings. difficulties using covered, computing complexity trade-off between precision interpretability. Our findings demonstrate that can boost models’ transparency interpretability give insightful information about them. efficiency these procedures must be improved, ethical concerns application resolved. contributes increasing knowledge strategies offers guidance academics professionals who want

Язык: Английский

---

Demystifying the Black Box: A Survey on Explainable Artificial Intelligence (XAI) in Bioinformatics

Computational and Structural Biotechnology Journal, Год журнала: 2025, Номер 27, С. 346 - 359

Опубликована: Янв. 1, 2025

The widespread adoption of Artificial Intelligence (AI) and machine learning (ML) tools across various domains has showcased their remarkable capabilities performance. Black-box AI models raise concerns about decision transparency user confidence. Therefore, explainable (XAI) explainability techniques have rapidly emerged in recent years. This paper aims to review existing works on bioinformatics, with a particular focus omics imaging. We seek analyze the growing demand for XAI identify current approaches, highlight limitations. Our survey emphasizes specific needs both bioinformatics applications users when developing methods we particularly imaging data. analysis reveals significant driven by need confidence decision-making processes. At end survey, provided practical guidelines system developers.

Язык: Английский

---

A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer

Cancers, Год журнала: 2025, Номер 17(5), С. 882 - 882

Опубликована: Март 4, 2025

According to data from the World Health Organization (WHO), lung cancer is becoming a global epidemic. It particularly high in list of leading causes death not only developed countries, but also worldwide; furthermore, it holds place terms cancer-related mortality. Nevertheless, many breakthroughs have been made last two decades regarding its management, with one most prominent being implementation artificial intelligence (AI) various aspects disease management. We included 473 papers this thorough review, which published during 5-10 years, order describe these breakthroughs. In screening programs, AI capable detecting suspicious nodules different imaging modalities-such as chest X-rays, computed tomography (CT), and positron emission (PET) scans-but discriminating between benign malignant well, success rates comparable or even better than those experienced radiologists. Furthermore, seems be able recognize biomarkers that appear patients who may develop cancer, years before event. Moreover, can assist pathologists cytologists recognizing type tumor, well specific histologic genetic markers play key role treating disease. Finally, treatment field, guide development personalized options for patients, possibly improving their prognosis.

Язык: Английский

---

Interpretable synthetic signals for explainable one-class time-series classification

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 131, С. 107716 - 107716

Опубликована: Янв. 3, 2024

Язык: Английский

---

A lightweight xAI approach to cervical cancer classification

Medical & Biological Engineering & Computing, Год журнала: 2024, Номер 62(8), С. 2281 - 2304

Опубликована: Март 20, 2024

Cervical cancer is caused in the vast majority of cases by human papilloma virus (HPV) through sexual contact and requires a specific molecular-based analysis to be detected. As an HPV vaccine available, incidence cervical up ten times higher areas without adequate healthcare resources. In recent years, liquid cytology has been used overcome these shortcomings perform mass screening. addition, classifiers based on convolutional neural networks can developed help pathologists diagnose disease. However, systems always require final verification pathologist make diagnosis. For this reason, explainable AI techniques are required highlight most significant data professional, as it determine confidence results image for classification (allowing professional point out he/she thinks important cross-check them against those detected system order create incremental learning systems). work, 4-phase optimization process obtain custom deep-learning classifier distinguishing between 4 severity classes with liquid-cytology images. The obtains accuracy over 97% 100% 2 execution under 1 s (including report generation). Compared previous works, proposed better lower computational cost.

Язык: Английский

---

A Robust Ensemble of Convolutional Neural Networks for the Detection of Monkeypox Disease from Skin Images

Sensors, Год журнала: 2023, Номер 23(16), С. 7134 - 7134

Опубликована: Авг. 12, 2023

Monkeypox is a smallpox-like disease that was declared global health emergency in July 2022. Because of this resemblance, it not easy to distinguish monkeypox rash from other similar diseases; however, due the novelty disease, there are no widely used databases for purpose with which develop image-based classification algorithms. Therefore, three significant contributions proposed work: first, development publicly available dataset images; second, system based on convolutional neural networks order automatically marks those produced by and, finally, use explainable AI tools ensemble networks. For point 1, free images cases and diseases have been searched government processed until we left only section skin patients each case. 2, various pre-trained models were as classifiers second instance, combinations these form ensembles. And, 3, first documented time an technique (like GradCAM) applied results Among all tests, accuracy reaches 93% case single networks, up 98% using (ResNet50, EfficientNetB0, MobileNetV2). Comparing previous work, substantial improvement observed.

Язык: Английский

---