A deep look into radiomics

La radiologia medica, Journal Year: 2021, Volume and Issue: 126(10), P. 1296 - 1311

Published: July 2, 2021

Abstract Radiomics is a process that allows the extraction and analysis of quantitative data from medical images. It an evolving field research with many potential applications in imaging. The purpose this review to offer deep look into radiomics, basis, deeply discussed technical point view, through main applications, challenges have be addressed translate clinical practice. A detailed description techniques used various steps radiomics workflow, which includes image acquisition, reconstruction, pre-processing, segmentation, features analysis, here proposed, as well overview promising results achieved focusing on limitations possible solutions for implementation. Only in-depth comprehensive current methods can suggest power fostering precision medicine thus care patients, especially cancer detection, diagnosis, prognosis treatment evaluation.

Language: Английский

---

Radiomics and artificial intelligence in lung cancer screening

Translational Lung Cancer Research, Journal Year: 2021, Volume and Issue: 10(2), P. 1186 - 1199

Published: Feb. 1, 2021

Abstract: Lung cancer is responsible for more fatalities than any other worldwide, with 1.76 million associated deaths reported in 2018. The key issue the fight against this disease detection and diagnosis of all pulmonary nodules at an early stage. Artificial intelligence (AI) algorithms play a vital role automated detection, segmentation, computer-aided malignant lesions. Among existing algorithms, radiomics deep-learning-based types appear to show most promise. Radiomics growing field related extraction set features from image, which allows classification medical images into predefined group. process comprises series consecutive steps including image acquisition pre-processing, segmentation desired region interest, calculation defined features, feature engineering, construction model. calculated are mainly shape as well first- higher-order texture features. To date, 100 have been defined, although number varies depending on application. greatest challenge building cross-validated model based selected known radiomic signature. Numerous signatures successfully developed; however, reproducibility clinical validity results obtained constitutes considerable modern radiomics. Deep learning another rapidly evolving technique recognized valuable tool analysis characterization, assessment Such approach involves design artificial neural network architecture while upholding goal high accuracy. This paper illuminates evolution current state methods lung imaging nodules, particular emphasis deep methods.

Language: Английский

---

Machine Learning and AI in Cancer Prognosis, Prediction, and Treatment Selection: A Critical Approach

Journal of Multidisciplinary Healthcare, Journal Year: 2023, Volume and Issue: Volume 16, P. 1779 - 1791

Published: June 1, 2023

Cancer is a leading cause of morbidity and mortality worldwide. While progress has been made in the diagnosis, prognosis, treatment cancer patients, individualized data-driven care remains challenge. Artificial intelligence (AI), which used to predict automate many cancers, emerged as promising option for improving healthcare accuracy patient outcomes. AI applications oncology include risk assessment, early prognosis estimation, selection based on deep knowledge. Machine learning (ML), subset that enables computers learn from training data, highly effective at predicting various types cancer, including breast, brain, lung, liver, prostate cancer. In fact, ML have demonstrated greater than clinicians. These technologies also potential improve quality life patients with illnesses, not just Therefore, it important current develop new programs benefit patients. This article examines use algorithms prediction, their applications, limitations, future prospects.

Language: Английский

---

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential

Frontiers in Oncology, Journal Year: 2022, Volume and Issue: 12

Published: Feb. 17, 2022

The high-throughput extraction of quantitative imaging features from medical images for the purpose radiomic analysis, i.e., radiomics in a broad sense, is rapidly developing and emerging research field that has been attracting increasing interest, particularly multimodality multi-omics studies. In this context, analysis multidimensional data plays an essential role assessing spatio-temporal characteristics different tissues organs their microenvironment. Herein, recent developments method, including manually defined features, acquisition preprocessing, lesion segmentation, feature extraction, selection dimension reduction, statistical model construction, are reviewed. addition, deep learning-based techniques automatic segmentation being analyzed to address limitations such as rigorous workflow, manual/semi-automatic annotation, inadequate criteria, multicenter validation. Furthermore, summary current state-of-the-art applications technology disease diagnosis, treatment response, prognosis prediction perspective radiology images, histopathology three-dimensional dose distribution data, oncology, presented. potential value diagnostic therapeutic strategies also further analyzed, first time, advances challenges associated with dosiomics radiotherapy summarized, highlighting latest progress radiomics. Finally, robust framework presented recommendations future development discussed, but not limited factors affect stability (medical big multitype expert knowledge medical), data-driven processes (reproducibility interpretability studies, alternatives various institutions, prospective researches clinical trials), thoughts on directions (the capability achieve open platform analysis).

Language: Английский

---

Deep Learning for Medical Image-Based Cancer Diagnosis

Cancers, Journal Year: 2023, Volume and Issue: 15(14), P. 3608 - 3608

Published: July 13, 2023

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one the research hotspots in field artificial intelligence and computer vision. Due rapid development methods, requires very high accuracy timeliness as well inherent particularity complexity imaging. A comprehensive review relevant studies necessary help readers better understand current status ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission (PET), histopathological are reviewed this paper. basic architecture classical pretrained models comprehensively reviewed. In particular, advanced neural networks emerging recent years, transfer learning, ensemble (EL), graph network, vision transformer (ViT), introduced. overfitting prevention methods summarized: batch normalization, dropout, weight initialization, data augmentation. image-based analysis sorted out. (3) Results: Deep has achieved great success diagnosis, showing good results image classification, reconstruction, detection, segmentation, registration, synthesis. However, lack high-quality labeled datasets limits role faces challenges rare multi-modal fusion, model explainability, generalization. (4) Conclusions: There a need for more public standard databases cancer. pre-training potential be improved, special attention should paid multimodal fusion supervised paradigm. Technologies such ViT, few-shot will bring surprises images.

Language: Английский

---

Radiomics and artificial intelligence for precision medicine in lung cancer treatment

Seminars in Cancer Biology, Journal Year: 2023, Volume and Issue: 93, P. 97 - 113

Published: May 19, 2023

Lung cancer is the leading cause of cancer-related deaths worldwide. It exhibits, at mesoscopic scale, phenotypic characteristics that are generally indiscernible to human eye but can be captured non-invasively on medical imaging as radiomic features, which form a high dimensional data space amenable machine learning. Radiomic features harnessed and used in an artificial intelligence paradigm risk stratify patients, predict for histological molecular findings, clinical outcome measures, thereby facilitating precision medicine improving patient care. Compared tissue sampling-driven approaches, radiomics-based methods superior being non-invasive, reproducible, cheaper, less susceptible intra-tumoral heterogeneity. This review focuses application radiomics, combined with intelligence, delivering lung treatment, discussion centered pioneering groundbreaking works, future research directions area.

Language: Английский

---

An Overview of Artificial Intelligence in Oncology

Future Science OA, Journal Year: 2022, Volume and Issue: 8(4)

Published: Feb. 10, 2022

Cancer is associated with significant morbimortality globally. Advances in screening, diagnosis, management and survivorship were substantial the last decades, however, challenges providing personalized data-oriented care remain. Artificial intelligence (AI), a branch of computer science used for predictions automation, has emerged as potential solution to improve healthcare journey promote precision healthcare. AI applications oncology include, but are not limited to, optimization cancer research, improvement clinical practice (eg., prediction association multiple parameters outcomes – prognosis response) better understanding tumor molecular biology. In this review, we examine current state oncology, including fundamentals, applications, limitations future perspectives.

Language: Английский

---

Medical Images Segmentation for Lung Cancer Diagnosis Based on Deep Learning Architectures

Diagnostics, Journal Year: 2023, Volume and Issue: 13(3), P. 546 - 546

Published: Feb. 2, 2023

Lung cancer presents one of the leading causes mortalities for people around world. image analysis and segmentation are primary steps used early diagnosis cancer. Handcrafted medical imaging a very time-consuming task radiation oncologists. To address this problem, we propose in work to develop full entire system lung CT scan imaging. The proposed is composed two main parts: first part developed on top UNETR network, second classification classify output part, either benign or malignant, self-supervised network. powerful tool diagnosing combatting using 3D-input data. Extensive experiments have been performed contribute better results. Training testing Decathlon dataset. Experimental results conducted new state-of-the-art performances: accuracy 97.83%, 98.77% as accuracy. use

Language: Английский

---

A Review of Deep Learning Techniques for Lung Cancer Screening and Diagnosis Based on CT Images

Diagnostics, Journal Year: 2023, Volume and Issue: 13(16), P. 2617 - 2617

Published: Aug. 8, 2023

One of the most common and deadly diseases in world is lung cancer. Only early identification cancer can increase a patient's probability survival. A frequently used modality for screening diagnosis computed tomography (CT) imaging, which provides detailed scan lung. In line with advancement computer-assisted systems, deep learning techniques have been extensively explored to help interpreting CT images identification. Hence, goal this review provide that were developed diagnosing This covers an overview (DL) techniques, suggested DL applications, novelties reviewed methods. focuses on two main methodologies cancer, are classification segmentation methodologies. The advantages shortcomings current models will also be discussed. resultant analysis demonstrates there significant potential methods precise effective using scans. At end review, list future works regarding improving application provided spearhead systems.

Language: Английский

---

Artificial Intelligence and Lung Cancer: Impact on Improving Patient Outcomes

Cancers, Journal Year: 2023, Volume and Issue: 15(21), P. 5236 - 5236

Published: Oct. 31, 2023

Lung cancer remains one of the leading causes cancer-related deaths worldwide, emphasizing need for improved diagnostic and treatment approaches. In recent years, emergence artificial intelligence (AI) has sparked considerable interest in its potential role lung cancer. This review aims to provide an overview current state AI applications screening, diagnosis, treatment. algorithms like machine learning, deep radiomics have shown remarkable capabilities detection characterization nodules, thereby aiding accurate screening diagnosis. These systems can analyze various imaging modalities, such as low-dose CT scans, PET-CT imaging, even chest radiographs, accurately identifying suspicious nodules facilitating timely intervention. models exhibited promise utilizing biomarkers tumor markers supplementary tools, effectively enhancing specificity accuracy early detection. distinguish between benign malignant assisting radiologists making more informed decisions. Additionally, hold integrate multiple modalities clinical data, providing a comprehensive assessment. By high-quality including patient demographics, history, genetic profiles, predict responses guide selection optimal therapies. Notably, these success predicting likelihood response recurrence following targeted therapies optimizing radiation therapy patients. Implementing tools practice aid diagnosis management potentially improve outcomes, mortality morbidity

Language: Английский

---