Integrating Support Vector Machines and Deep Learning Features for Oral Cancer Histopathology Analysis DOI Creative Commons
Tuan D. Pham

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

Published: Dec. 17, 2024

Abstract This study introduces an approach to classifying histopathological images for detecting dys- plasia in oral cancer through the fusion of support vector machine (SVM) classifiers trained on deep learning features extracted from InceptionResNet-v2 and vision transformer (ViT) models. The classification dysplasia, a critical indicator progression, is of- ten complicated by class imbalance, with higher prevalence dysplastic lesions compared non-dysplastic cases. research addresses this challenge leveraging comple- mentary strengths two model, paired SVM classifier, excels identifying presence capturing fine-grained morphological indicative condition. In contrast, ViT-based demonstrates superior performance absence effectively global contextual information images. A strategy was employed combine these selection: majority (presence dysplasia) predicted using InceptionResNet-v2-SVM, while minority (absence us- ing ViT-SVM. significantly outperformed individual models other state-of-the-art methods, achieving balanced accuracy, sensitivity, precision, area under curve. its ability handle imbalance maintaining high diagnostic accuracy. results highlight potential integrating feature extraction improve complex medical imaging tasks. underscores value combining strategies address challenges workflows.

Language: Английский

Recurrent and Metastatic Head and Neck Cancer: Mechanisms of Treatment Failure, Treatment Paradigms, and New Horizons DOI Open Access

William T. Barham,

Marshall Patrick Stagg,

Rula Mualla

et al.

Cancers, Journal Year: 2025, Volume and Issue: 17(1), P. 144 - 144

Published: Jan. 5, 2025

Background: Head and neck cancer is a deadly disease with over 500,000 cases annually worldwide. Metastatic head accounts for large proportion of the mortality associated this disease. Many advances have been made in our understanding mechanisms metastasis. The application immunotherapy to locally recurrent or metastatic has not only improved oncologic outcomes but also provided valuable insights into immune evasion ultimately treatment failure. Objectives: This review paper will current biological failure Published ongoing clinical trials management be summarized. Methods: A narrative was conducted address paradigms carcinoma. Conclusions: Our rapidly evolving. Immunotherapy represents new tool fight against squamous cell Integrating patient tumor specific data via artificial intelligence deep learning allow precision oncology approach, thereby achieving better prognostication patients

Language: Английский

Citations

1
Radiotherapy dosage: A neural network approach for uninvolved liver dose in stereotactic body radiation therapy for liver cancer DOI
Arunkumar Krishnan

World Journal of Gastrointestinal Oncology, Journal Year: 2025, Volume and Issue: 17(2)

Published: Jan. 18, 2025

A recent study by Zhang et al developed a neural network-based predictive model for estimating doses to the uninvolved liver during stereotactic body radiation therapy (SBRT) in cancer. The reported significant advancement personalized radiotherapy improving accuracy and reducing treatment-related toxicity. demonstrated strong performance with R-values above 0.8, indicating its potential improve treatment consistency. However, concerns arise from small sample size exclusion criteria, which may limit generalizability. Future studies should incorporate larger, more diverse patient cohorts, explore confounding factors such as tumor characteristics delivery technique variability, address long-term effects of SBRT.

Language: Английский

Citations

1
Artificial Intelligence Models Accuracy for Odontogenic Keratocyst Detection From Panoramic View Radiographs: A Systematic Review and Meta‐Analysis DOI Creative Commons
Reyhaneh Shoorgashti,

Mohadeseh Alimohammadi,

Sana Baghizadeh

et al.

Health Science Reports, Journal Year: 2025, Volume and Issue: 8(4)

Published: March 31, 2025

ABSTRACT Background and Aims Odontogenic keratocyst (OKC) is a radiolucent jaw lesion often mistaken for similar conditions like ameloblastomas on panoramic radiographs. Accurate diagnosis vital effective management, but manual image interpretation can be inconsistent. While deep learning algorithms in AI have shown promise improving diagnostic accuracy OKCs, their performance across studies still unclear. This systematic review meta‐analysis aimed to evaluate the of models detecting OKC from Methods A search was performed 5 databases. Studies were included if they examined PICO question whether (I) could improve (O) radiographs (P) compared reference standards (C). Key metrics including sensitivity, specificity, accuracy, area under curve (AUC) extracted pooled using random‐effects models. Meta‐regression subgroup analyses conducted identify sources heterogeneity. Publication bias evaluated through funnel plots Egger's test. Results Eight meta‐analysis. The sensitivity all 83.66% (95% CI:73.75%–93.57%) specificity 82.89% CI:70.31%–95.47%). YOLO‐based demonstrated superior with 96.4% 96.0%, other architectures. analysis indicated that model architecture significant predictor performance, accounting portion observed However, also revealed publication high variability (Egger's test, p = 0.042). Conclusion models, particularly architectures, OKCs shows strong capabilities simple cases, it should complement, not replace, human expertise, especially complex situations.

Language: Английский

Citations

1
Machine learning in ocular oncology and oculoplasty: Transforming diagnosis and treatment DOI Open Access

Dipali Mane,

Khuspe Pankaj Ramdas

IP International Journal of Ocular Oncology and Oculoplasty, Journal Year: 2025, Volume and Issue: 10(4), P. 196 - 207

Published: Jan. 14, 2025

In the domains of ocular oncology and oculoplasty, machine learning (ML) has become a game-changing technology, providing previously unheard-of levels precision in diagnosis, treatment planning, outcome prediction. Using imaging modalities, genomic data, clinical characteristics, this chapter investigates integration algorithms detection tumours, including retinoblastoma uveal melanoma. Through predictive modelling real-time decision-making, it also emphasises how ML might improve surgical outcomes orbital reconstruction eyelid correction. Automated examination fundus photographs, histological slides, 3D been made possible by methods like deep natural language processing, which have improved individualised therapeutic approaches decreased diagnostic errors. Additionally, use augmented reality robotics surgery is significant development oculoplasty. Notwithstanding its potential, issues data heterogeneity, algorithm interpretability, ethical considerations are roadblocks that need to be addressed. This explores cutting-edge developments, real-world uses, potential future paths, offering researchers doctors thorough resource. Dipali Vikas Mane, Associate Professor, Shriram Shikshan Sanstha’s College Pharmacy, Paniv-413113

Language: Английский

Citations

0
Advances in paper and microfluidic based miniaturized systems for cancer biomarkers detection DOI

Ghita Yammouri,

Maliana El Amri,

Abdellatif Ait Lahcen

et al.

Microchemical Journal, Journal Year: 2025, Volume and Issue: unknown, P. 113257 - 113257

Published: March 1, 2025

Language: Английский

Citations

0
Oral Potentially Malignant Disorders DOI
Omar Kujan

Dental Clinics of North America, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
The Limitations of Artificial Intelligence in Head and Neck Oncology DOI Creative Commons
Karthik Rao, Verónica Fernández‐Álvarez, Orlando Guntinas‐Lichius

et al.

Advances in Therapy, Journal Year: 2025, Volume and Issue: unknown

Published: April 29, 2025

Language: Английский

Citations

0
Machine learning in risk assessment for microvascular head and neck surgery DOI
Gabriele Monarchi,

D. C. Buso,

Chiara Paolantonio

et al.

European Archives of Oto-Rhino-Laryngology, Journal Year: 2025, Volume and Issue: unknown

Published: March 26, 2025

Language: Английский

Citations

0
Integrating Support Vector Machines and Deep Learning Features for Oral Cancer Histopathology Analysis DOI Creative Commons
Tuan D. Pham

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

Published: Dec. 17, 2024

Abstract This study introduces an approach to classifying histopathological images for detecting dys- plasia in oral cancer through the fusion of support vector machine (SVM) classifiers trained on deep learning features extracted from InceptionResNet-v2 and vision transformer (ViT) models. The classification dysplasia, a critical indicator progression, is of- ten complicated by class imbalance, with higher prevalence dysplastic lesions compared non-dysplastic cases. research addresses this challenge leveraging comple- mentary strengths two model, paired SVM classifier, excels identifying presence capturing fine-grained morphological indicative condition. In contrast, ViT-based demonstrates superior performance absence effectively global contextual information images. A strategy was employed combine these selection: majority (presence dysplasia) predicted using InceptionResNet-v2-SVM, while minority (absence us- ing ViT-SVM. significantly outperformed individual models other state-of-the-art methods, achieving balanced accuracy, sensitivity, precision, area under curve. its ability handle imbalance maintaining high diagnostic accuracy. results highlight potential integrating feature extraction improve complex medical imaging tasks. underscores value combining strategies address challenges workflows.

Language: Английский

Citations

0