Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment

npj Precision Oncology, Journal Year: 2024, Volume and Issue: 8(1)

Published: March 29, 2024

Abstract This review delves into the most recent advancements in applying artificial intelligence (AI) within neuro-oncology, specifically emphasizing work on gliomas, a class of brain tumors that represent significant global health issue. AI has brought transformative innovations to tumor management, utilizing imaging, histopathological, and genomic tools for efficient detection, categorization, outcome prediction, treatment planning. Assessing its influence across all facets malignant management- diagnosis, prognosis, therapy- models outperform human evaluations terms accuracy specificity. Their ability discern molecular aspects from imaging may reduce reliance invasive diagnostics accelerate time diagnoses. The covers techniques, classical machine learning deep learning, highlighting current applications challenges. Promising directions future research include multimodal data integration, generative AI, large medical language models, precise delineation characterization, addressing racial gender disparities. Adaptive personalized strategies are also emphasized optimizing clinical outcomes. Ethical, legal, social implications discussed, advocating transparency fairness integration neuro-oncology providing holistic understanding impact patient care.

Language: Английский

---

Deep learning based synthesis of MRI, CT and PET: Review and analysis

Medical Image Analysis, Journal Year: 2023, Volume and Issue: 92, P. 103046 - 103046

Published: Dec. 1, 2023

Medical image synthesis represents a critical area of research in clinical decision-making, aiming to overcome the challenges associated with acquiring multiple modalities for an accurate workflow. This approach proves beneficial estimating desired modality from given source among most common medical imaging contrasts, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission (PET). However, translating between two presents difficulties due complex non-linear domain mappings. Deep learning-based generative modelling has exhibited superior performance synthetic contrast applications compared conventional methods. survey comprehensively reviews deep translation 2018 2023 on pseudo-CT, MR, PET. We provide overview contrasts frequently employed learning networks synthesis. Additionally, we conduct detailed analysis each method, focusing their diverse model designs based input domains network architectures. also analyse novel architectures, ranging CNNs recent Transformer Diffusion models. includes comparing loss functions, available datasets anatomical regions, quality assessments other downstream tasks. Finally, discuss identify solutions within literature, suggesting possible future directions. hope that insights offered this paper will serve valuable roadmap researchers field

Language: Английский

---

A review of recent advances and strategies in transfer learning

International Journal of Systems Assurance Engineering and Management, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 21, 2025

Language: Английский

---

AI-Driven Advances in Low-Dose Imaging and Enhancement—A Review

Diagnostics, Journal Year: 2025, Volume and Issue: 15(6), P. 689 - 689

Published: March 11, 2025

The widespread use of medical imaging techniques such as X-rays and computed tomography (CT) has raised significant concerns regarding ionizing radiation exposure, particularly among vulnerable populations requiring frequent imaging. Achieving a balance between high-quality diagnostic minimizing exposure remains fundamental challenge in radiology. Artificial intelligence (AI) emerged transformative solution, enabling low-dose protocols that enhance image quality while significantly reducing doses. This review explores the role AI-assisted imaging, CT, X-ray, magnetic resonance (MRI), highlighting advancements deep learning models, convolutional neural networks (CNNs), other AI-based approaches. These technologies have demonstrated substantial improvements noise reduction, artifact removal, real-time optimization parameters, thereby enhancing accuracy mitigating risks. Additionally, AI contributed to improved radiology workflow efficiency cost reduction by need for repeat scans. also discusses emerging directions AI-driven including hybrid systems integrate post-processing with data acquisition, personalized tailored patient characteristics, expansion applications fluoroscopy positron emission (PET). However, challenges model generalizability, regulatory constraints, ethical considerations, computational requirements must be addressed facilitate broader clinical adoption. potential revolutionize safety, optimizing quality, improving healthcare efficiency, paving way more advanced sustainable future

Language: Английский

---

AdvancedMRTechniques for Preoperative Glioma Characterization: Part 2

Journal of Magnetic Resonance Imaging, Journal Year: 2023, Volume and Issue: 57(6), P. 1676 - 1695

Published: March 13, 2023

Preoperative clinical MRI protocols for gliomas, brain tumors with dismal outcomes due to their infiltrative properties, still rely on conventional structural MRI, which does not deliver information tumor genotype and is limited in the delineation of diffuse gliomas. The GliMR COST action wants raise awareness about state art advanced techniques gliomas possible translation. This review describes current methods, limits, applications preoperative assessment glioma, summarizing level validation different techniques. In this second part, we magnetic resonance spectroscopy (MRS), chemical exchange saturation transfer (CEST), susceptibility-weighted imaging (SWI), MRI-PET, MR elastography (MRE), MR-based radiomics applications. first part addresses dynamic susceptibility contrast (DSC) contrast-enhanced (DCE) arterial spin labeling (ASL), diffusion-weighted vessel imaging, fingerprinting (MRF). EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Language: Английский

---

Contrast Limited Adaptive Histogram Equalization for Recognizing Road Marking at Night Based on Yolo Models

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 92926 - 92942

Published: Jan. 1, 2023

In recent years, artificial intelligence has led to rapid development and application across various industries, which prompted this. One of the significant developments is improvement transportation methods. Accidents involving vehicles frequently result in a high number fatalities as well economic damage. Road detection one applications that can be used by self-driving cars. Traffic accidents happen, but many nations construct smart cities apps for Since public road sign datasets have been research identification analysis, these are particularly training autonomous vehicles. This study records roads Taiwan through driving. It manually collects traffic signs create data set daytime environments nighttime environments. there currently no Taiwan, this necessary Taiwan. The YOLO model utilized work design mark detection. techniques Contrast Stretching (CS), Histogram Equalization (HE), Limited Adaptive (CLAHE) evaluated setting compared original image captured at night. experimental results show best during day V4 (no flip), test mAP 86.77%, Precision 82%, Recall 87%, F1-score 84%, IoU 63.92%. At night, CLAHE method works YOLOv5x model, with 86.40%. And YOLOv5 mobile devices or embedded devices, so recommends using CLAHE's night improve effect

Language: Английский

---

Sustainable Advanced Techniques for Enhancing the Image Process

Practice, progress, and proficiency in sustainability, Journal Year: 2024, Volume and Issue: unknown, P. 350 - 374

Published: Jan. 22, 2024

This chapter discusses modern techniques for image improvement, including pixel editing, clarity enhancement, and minimal-size object recognition. An outline of photo enhancement how deep learning could address its issues comes first. Both sophisticated like cut-out style transfer frequently used ones rotation scaling are covered in this chapter. Additionally included manipulating pixels, such as brightness adjustment, colour space conversion, denoising algorithms. Assisting super-resolution, deblurring, contrast amplification also In order to the with recognition, looks into single-shot detectors multi-scale networks. Through case studies applications medical imaging, autonomous driving, surveillance systems, value these is demonstrated. A discussion prospective future study areas affect computer vision processing brings a close.

Language: Английский

---

Image Processing Techniques for Improving Quality of 3D Profile in Digital Holographic Microscopy Using Deep Learning Algorithm

Sensors, Journal Year: 2024, Volume and Issue: 24(6), P. 1950 - 1950

Published: March 19, 2024

Digital Holographic Microscopy (DHM) is a 3D imaging technology widely applied in biology, microelectronics, and medical research. However, the noise generated during process can affect accuracy of diagnoses. To solve this problem, we proposed several frequency domain filtering algorithms. algorithms have limitation that they only be when distance between direct current (DC) spectrum sidebands are sufficiently far. address these limitations, among algorithms, HiVA algorithm deep learning algorithm, which effectively filter by distinguishing detailed information object, used to enable regardless DC sidebands. In paper, combination traditional image processing methods proposed, aiming reduce profile using Improved Denoising Diffusion Probabilistic Models (IDDPM) algorithm.

Language: Английский

---

New Frontiers in Breast Cancer Imaging: The Rise of AI

Bioengineering, Journal Year: 2024, Volume and Issue: 11(5), P. 451 - 451

Published: May 2, 2024

Artificial intelligence (AI) has been implemented in multiple fields of medicine to assist the diagnosis and treatment patients. AI implementation radiology, more specifically for breast imaging, advanced considerably. Breast cancer is one most important causes mortality among women, there increased attention towards creating efficacious methods detection utilizing improve radiologist accuracy efficiency meet increasing demand our can be applied imaging studies image quality, increase interpretation accuracy, time cost efficiency. mammography, ultrasound, MRI allows improved while decreasing intra- interobserver variability. The synergistic effect between a potential patient care underserved populations with intention providing quality equitable all. Additionally, allowed risk stratification. Further, application have implications as well by identifying upstage ductal carcinoma situ (DCIS) invasive better predicting individualized response neoadjuvant chemotherapy. advancement pre-operative 3-dimensional models viability reconstructive grafts.

Language: Английский

---

Deep learning for medical imaging super-resolution: A comprehensive review

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 129667 - 129667

Published: Feb. 1, 2025

Language: Английский

---