Cited by SVM in Classification of stage 0~II and III~IV with Breast Cancer : A Retrospective Cohort Study on a bicentric cohort

How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications DOI

Luís Coelho

Bioengineering, Journal Year: 2023, Volume and Issue: 10(12), P. 1435 - 1435

Published: Dec. 18, 2023

The integration of artificial intelligence (AI) into medical imaging has guided in an era transformation healthcare. This literature review explores the latest innovations and applications AI field, highlighting its profound impact on diagnosis patient care. innovation segment cutting-edge developments AI, such as deep learning algorithms, convolutional neural networks, generative adversarial which have significantly improved accuracy efficiency image analysis. These enabled rapid accurate detection abnormalities, from identifying tumors during radiological examinations to detecting early signs eye disease retinal images. article also highlights various imaging, including radiology, pathology, cardiology, more. AI-based diagnostic tools not only speed up interpretation complex images but improve disease, ultimately delivering better outcomes for patients. Additionally, processing facilitates personalized treatment plans, thereby optimizing healthcare delivery. paradigm shift that brought role revolutionizing By combining techniques their practical applications, it is clear will continue shaping future positive ways.

Language: Английский

Citations

163

Quantum computational infusion in extreme learning machines for early multi-cancer detection DOI

Anas Bilal, Muhammad Shafiq, Waeal J. Obidallah

et al.

Journal Of Big Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Feb. 6, 2025

Language: Английский

Citations

Diagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program DOI

Mustafa Ege Şeker, Yılmaz Onat Köylüoğlu, Ayşe Özaydın

et al.

European Radiology, Journal Year: 2024, Volume and Issue: 34(9), P. 6145 - 6157

Published: Feb. 22, 2024

Abstract Objectives We aimed to evaluate the early-detection capabilities of AI in a screening program over its duration, with specific focus on detection interval cancers, early cancers assistance from prior visits, and impact workload for various reading scenarios. Materials methods The study included 22,621 mammograms 8825 women within 10-year biennial two-reader program. statistical analysis focused 5136 4282 due data retrieval issues, among whom 105 were diagnosed breast cancer. software assigned scores 1 100. Histopathology results determined ground truth, Youden’s index was used establish threshold. Tumor characteristics analyzed ANOVA chi-squared test, different workflow scenarios evaluated using bootstrapping. Results achieved an AUC 89.6% (86.1–93.2%, 95% CI). optimal threshold 30.44, yielding 72.38% sensitivity 92.86% specificity. Initially, identified 57 screening-detected (83.82%), 15 (51.72%), 4 missed (50%). as second reader could have led earlier diagnosis 24 patients (average 29.92 ± 19.67 months earlier). No significant differences found cancer-characteristics groups. A hybrid triage scenario showed potential 69.5% reduction 30.5% increase accuracy. Conclusion This system exhibits high specificity mammograms, effectively identifying 23% mammograms. Adopting mechanism has reduce by nearly 70%. Clinical relevance statement proposes more efficient method programs, both terms Key Points • Incorporating tool improves (72.38%) (92.86%), enhancing rates cancers. AI-assisted triaging is effective differentiating low high-risk cases, reduces radiologist workload, potentially enables broader coverage. facilitate compared human reading.

Language: Английский

Citations

IMPORTANT-Net: Integrated MRI multi-parametric increment fusion generator with attention network for synthesizing absent data DOI

Tianyu Zhang, Tao Tan, Luyi Han

et al.

Information Fusion, Journal Year: 2024, Volume and Issue: 108, P. 102381 - 102381

Published: March 26, 2024

Magnetic resonance imaging (MRI) is highly sensitive for lesion detection. Sequences obtained with different settings can capture specific characteristics of lesions. Such multi-parametric MRI information has been shown to aid radiologist performance in classification, as well improving the artificial intelligence models various tasks. However, obtaining makes examination costly from both financial and time perspectives, there may also be safety concerns special populations, thus making acquisition full spectrum sequences less durable. In this study, a sophisticated Integrated Multi-Parametric increment fusiOn generatoR wiTh AtteNTion Network (IMPORTANT-Net) developed generate absent sequences/parameters. First, parameter reconstruction module used encode restore existing parameters obtain corresponding latent representation at any scale level. Then fusion attention enables interaction encoded through set algorithmic strategies, applies weights mechanism after refined information. Finally, scheme embedded V-shape generation combine hierarchical representations specified parameter. Results showed that our IMPORTANT-Net capable synthesizing MRI, outperforms comparable state-of-the-art networks more importantly benefit downstream The codes are available https://github.com/Netherlands-Cancer-Institute/MRI_IMPORTANT_NET

Language: Английский

Citations

Predicting axillary response to neoadjuvant chemotherapy using peritumoral and intratumoral ultrasound radiomics in breast cancer molecular subtypes DOI

Jiejie Yao,

Xiaohong Jia,

Wei Zhou

et al.

iScience, Journal Year: 2024, Volume and Issue: 27(9), P. 110716 - 110716

Published: Aug. 13, 2024

To explore machine learning (ML)-based breast tumor peritumoral (P) and intratumoral ultrasound radiomics signatures (IURS) for predicting axillary response to neoadjuvant chemotherapy (NAC) in patients with cancer (BC) node-positive. A total of 435 were divided into hormone receptor (HR)+/human epidermal growth factor (HER)2-, HER2+, triple-negative (TN) subtypes. ML classifiers including random forest (RF), support vector (SVM), linear discriminant analysis (LDA) applied construct PURS, IURS, the combined P-IURS models. SVM TN subtype obtained most favorable performance an AUC 0.917 (95%CI: 0.859, 0.960) PURS models, RF HER2+ yielded highest efficacy IURS models [AUC = 0.935 0.843, 0.976)]. The RF-based model improved a maximum 0.952 0.868, 0.994). ML-based US can be promising biomarker predict response.

Language: Английский

Citations

Optimizing BI-RADS 4 Lesion Assessment Using Lightweight Convolutional Neural Network with CBAM in Contrast Enhanced Mammography DOI

Oladosu Oyebisi Oladimeji, Hamail Ayaz, Ian McLoughlin

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 96 - 106

Published: Jan. 1, 2025

Language: Английский

Citations

One for All: UNET Training on Single-Sequence Masks for Multi-sequence Breast MRI Segmentation DOI

Jarek M. van Dijk,

Luyi Han,

Luuk Balkenende

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 32 - 41

Published: Jan. 1, 2025

Language: Английский

Citations

Graph Neural Networks for Modelling Breast Biomechanical Compression DOI

Hadeel Awwad,

Eloy García, Robert Martí

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 169 - 180

Published: Jan. 1, 2025

Language: Английский

Citations

Multimodal Breast MRI Language-Image Pretraining (MLIP): An Exploration of a Breast MRI Foundation Model DOI

Nika Rasoolzadeh, Tianyu Zhang, Yuan Gao

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 42 - 53

Published: Jan. 1, 2025

Language: Английский

Citations

MRI Breast Tissue Segmentation Using nnU-Net for Biomechanical Modeling DOI

Melika Pooyan,

Hadeel Awwad,

Eloy García

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 191 - 201

Published: Jan. 1, 2025

Language: Английский

Citations