The Role of Artificial Intelligence in Early Cancer Diagnosis

Cancers, Journal Year: 2022, Volume and Issue: 14(6), P. 1524 - 1524

Published: March 16, 2022

Improving the proportion of patients diagnosed with early-stage cancer is a key priority World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are challenges. addition, there concerns about limited diagnostic workforces, particularly light COVID-19 pandemic, placing strain on pathology radiology services. this review, we discuss how artificial intelligence algorithms could assist clinicians (1) asymptomatic at cancer, (2) investigating triaging symptomatic patients, (3) more effectively diagnosing recurrence. We provide an overview main approaches, including historical models such as logistic regression, well deep learning neural networks, highlight their early diagnosis applications. Many data types suitable for computational analysis, electronic healthcare records, images, slides peripheral blood, examples these can be utilised diagnose cancer. also potential clinical implications algorithms, currently used practice. Finally, limitations pitfalls, ethical concerns, resource demands, security reporting standards.

Language: Английский

---

Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework

Methods, Journal Year: 2020, Volume and Issue: 188, P. 20 - 29

Published: June 3, 2020

The advancement of artificial intelligence concurrent with the development medical imaging techniques provided a unique opportunity to turn from mostly qualitative, further quantitative and mineable data that can be explored for clinical decision support systems (cDSS). Radiomics, method high throughput extraction hand-crafted features images, deep learning -the driven modeling based on principles simplified brain neuron interactions, are most researched techniques. Many studies reported potential such in context cDSS. Such could highly appealing due reuse existing data, automation workflows, minimal invasiveness, three-dimensional volumetric characterization, promise accuracy reproducibility results cost-effectiveness. Nevertheless, there several challenges face, need addressed before translation use. These include, but not limited to, explainability models, features, their sensitivity variations image acquisition reconstruction parameters. In this narrative review, we report status analysis using radiomics learning, field is facing, propose framework robust analysis, discuss future prospects.

Language: Английский

---

Artificial intelligence and machine learning in cancer imaging

Communications Medicine, Journal Year: 2022, Volume and Issue: 2(1)

Published: Oct. 27, 2022

An increasing array of tools is being developed using artificial intelligence (AI) and machine learning (ML) for cancer imaging. The development an optimal tool requires multidisciplinary engagement to ensure that the appropriate use case met, as well undertake robust testing prior its adoption into healthcare systems. This review highlights key developments in field. We discuss challenges opportunities AI ML imaging; considerations algorithms can be widely used disseminated; ecosystem needed promote growth

Language: Английский

---

Deep learning in head & neck cancer outcome prediction

Scientific Reports, Journal Year: 2019, Volume and Issue: 9(1)

Published: Feb. 26, 2019

Abstract Traditional radiomics involves the extraction of quantitative texture features from medical images in an attempt to determine correlations with clinical endpoints. We hypothesize that convolutional neural networks (CNNs) could enhance performance traditional radiomics, by detecting image patterns may not be covered a radiomic framework. test this hypothesis training CNN predict treatment outcomes patients head and neck squamous cell carcinoma, based solely on their pre-treatment computed tomography image. The (194 patients) validation sets (106 patients), which are mutually independent include 4 institutions, come Cancer Imaging Archive. When compared framework applied same patient cohort, our method results AUC 0.88 predicting distant metastasis. combining model previous model, improves 0.92. Our yields models shown explicitly recognize features, directly visualized perform accurate outcome prediction.

Language: Английский

---

Responsible Radiomics Research for Faster Clinical Translation

Journal of Nuclear Medicine, Journal Year: 2017, Volume and Issue: 59(2), P. 189 - 193

Published: Nov. 24, 2017

It is now recognized that intratumoral heterogeneity associated with more aggressive tumor phenotypes leading to poor patient outcomes ([1][1]). Medical imaging plays a central role in related investigations, because radiologic images are routinely acquired during cancer management. Imaging

Language: Английский

---