Deep Learning for Contrast Enhanced Mammography - a Systematic Review DOI Open Access
Vera Sorin, Miri Sklair‐Levy, Benjamin S. Glicksberg

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: May 13, 2024

Abstract Background/Aim: Contrast-enhanced mammography (CEM) is a relatively novel imaging technique that enables both anatomical and functional breast imaging, with improved diagnostic performance compared to standard 2D mammography. The aim of this study systematically review the literature on deep learning (DL) applications for CEM, exploring how these models can further enhance CEM potential. Methods This systematic was reported according PRISMA guidelines. We searched studies published up April 2024. MEDLINE, Scopus Google Scholar were used as search databases. Two reviewers independently implemented strategy. Results Sixteen relevant between 2018 2024 identified. All but one convolutional neural network models. evaluated DL algorithms classification lesions at while six also assessed lesion detection or segmentation. In three segmentation performed manually, two manual automatic segmentation, ten automatically segmented lesions. Conclusion While still an early research stage, improve precision. However, there small number evaluating different algorithms, most are retrospective. Further prospective testing assess actual clinical setting warranted. Graphic

Language: Английский

Deep Learning in Breast Cancer Imaging: State of the Art and Recent Advancements in Early 2024 DOI Creative Commons
Alessandro Carriero, Léon Groenhoff,

Elizaveta Vologina

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(8), P. 848 - 848

Published: April 19, 2024

The rapid advancement of artificial intelligence (AI) has significantly impacted various aspects healthcare, particularly in the medical imaging field. This review focuses on recent developments application deep learning (DL) techniques to breast cancer imaging. DL models, a subset AI algorithms inspired by human brain architecture, have demonstrated remarkable success analyzing complex images, enhancing diagnostic precision, and streamlining workflows. models been applied diagnosis via mammography, ultrasonography, magnetic resonance Furthermore, DL-based radiomic approaches may play role risk assessment, prognosis prediction, therapeutic response monitoring. Nevertheless, several challenges limited widespread adoption clinical practice, emphasizing importance rigorous validation, interpretability, technical considerations when implementing solutions. By examining fundamental concepts synthesizing latest advancements trends, this narrative aims provide valuable up-to-date insights for radiologists seeking harness power care.

Language: Английский

Citations

31
Improving the diagnostic performance of contrast-enhanced mammography through lesion conspicuity and enhancement quantification DOI Creative Commons

Iris Allajbeu,

Muzna Nanaa, Roido Manavaki

et al.

European Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: April 3, 2025

Language: Английский

Citations

1
Gold Nanobiosensors: Pioneering Breakthroughs in Precision Breast Cancer Detection DOI Creative Commons
Soheil Sadr, Ashkan Hajjafari, Abbas Rahdar

et al.

European Journal of Medicinal Chemistry Reports, Journal Year: 2024, Volume and Issue: unknown, P. 100238 - 100238

Published: Oct. 1, 2024

Language: Английский

Citations

5
Artificial Intelligence and medical specialties: support or substitution? DOI Open Access
Stefan‐Lucian Popa, Abdulrahman Ismaiel, Vlad Dumitru Brata

et al.

Medicine and Pharmacy Reports, Journal Year: 2024, Volume and Issue: 97(4), P. 409 - 418

Published: June 11, 2024

The rapid advancement of artificial intelligence (AI) in healthcare has spurred extensive debate regarding its potential to replace human expertise across various medical specialties. This narrative review critically examines the integration AI within diverse specialties discern role as a substitute or supporter. analysis encompasses AI's impact on diagnostic precision, treatment planning, and patient care. Although systems have demonstrated remarkable proficiency tasks reliant data pattern recognition, they fall short areas necessitating nuanced decision-making, empathetic communication, application diagnosis planning. evolution applications is propelled by swift advancements both hardware software technologies, fostering dynamic synergy that continues redefine boundaries precision efficiency delivery. While demonstrates capabilities automating tasks, it underscored complex domains necessitates balanced approach preserves indispensable contributions activity.

Language: Английский

Citations

4
A Scientometric Analysis of Four Decades of Scientific Production in Breast Imaging: A Study of Keywords, Trends, and Research Support DOI
Sepideh Ghalambaz

Deleted Journal, Journal Year: 2025, Volume and Issue: 18(1), P. 4 - 30

Published: March 1, 2025

Language: Английский

Citations

0
Benchmarking Deep Learning Algorithms for Breast Cancer Detection: A Comprehensive Review and Evaluation Across Public Imaging Datasets DOI Creative Commons
Dariush Moslemi, Seyed Mohammad Hassan Hosseini,

Elham Jafarian

et al.

InfoScience Trends, Journal Year: 2025, Volume and Issue: 2(4), P. 11 - 24

Published: April 14, 2025

Language: Английский

Citations

0
Radiomics for Predicting Prognostic Factors in Breast Cancer: Insights from Contrast-Enhanced Mammography (CEM) DOI Open Access
Claudia Lucia Piccolo,

Marina Sarli,

Matteo Pileri

et al.

Journal of Clinical Medicine, Journal Year: 2024, Volume and Issue: 13(21), P. 6486 - 6486

Published: Oct. 29, 2024

Objectives: To evaluate the correlation between radiomic features extracted from contrast-enhanced mammography (CEM) tumor lesions and peritumoral background with prognostic factors in breast cancer (BC). Methods: In this retrospective, single-center study, 134 women histologically confirmed underwent CEM examination. Radiomic were manually segmented lesion contours automatically delineated using PyRadiomics. The categorized into seven classes: First-order Features, Shape Features (2D), Gray Level Co-occurrence Matrix (GLCM), Run Length (GLRLM), Size Zone (GLSZM), Neighboring Tone Difference (NGTDM). Histological examination assessed type, grade, receptor structure (ER, PgR, HER2), Ki67 index, lymph node involvement. Pearson multivariate regression applied to associations factors. Results: Significant correlations found such as ER, (p < 0.05). GLCM-based texture showed strong HER2 0.01). regions, especially shape GLSZM metrics, significantly correlated Conclusions: analysis of both regions offers significant insights BC prognosis. These findings support integration radiomics personalized diagnostic therapeutic strategies, potentially improving clinical decision making management.

Language: Английский

Citations

1
Deep Learning for Contrast Enhanced Mammography - A Systematic Review DOI
Vera Sorin, Miri Sklair‐Levy, Benjamin S. Glicksberg

et al.

Academic Radiology, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 1, 2024

Language: Английский

Citations

1
Deep Learning for Contrast Enhanced Mammography - a Systematic Review DOI Open Access
Vera Sorin, Miri Sklair‐Levy, Benjamin S. Glicksberg

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: May 13, 2024

Abstract Background/Aim: Contrast-enhanced mammography (CEM) is a relatively novel imaging technique that enables both anatomical and functional breast imaging, with improved diagnostic performance compared to standard 2D mammography. The aim of this study systematically review the literature on deep learning (DL) applications for CEM, exploring how these models can further enhance CEM potential. Methods This systematic was reported according PRISMA guidelines. We searched studies published up April 2024. MEDLINE, Scopus Google Scholar were used as search databases. Two reviewers independently implemented strategy. Results Sixteen relevant between 2018 2024 identified. All but one convolutional neural network models. evaluated DL algorithms classification lesions at while six also assessed lesion detection or segmentation. In three segmentation performed manually, two manual automatic segmentation, ten automatically segmented lesions. Conclusion While still an early research stage, improve precision. However, there small number evaluating different algorithms, most are retrospective. Further prospective testing assess actual clinical setting warranted. Graphic

Language: Английский

Citations

0