Oral squamous cell carcinoma detection using EfficientNet on histopathological images

Frontiers in Medicine, Journal Year: 2024, Volume and Issue: 10

Published: Jan. 29, 2024

Introduction Oral Squamous Cell Carcinoma (OSCC) poses a significant challenge in oncology due to the absence of precise diagnostic tools, leading delays identifying condition. Current methods for OSCC have limitations accuracy and efficiency, highlighting need more reliable approaches. This study aims explore discriminative potential histopathological images oral epithelium OSCC. By utilizing database containing 1224 from 230 patients, captured at varying magnifications publicly available, customized deep learning model based on EfficientNetB3 was developed. The model’s objective differentiate between normal tissues by employing advanced techniques such as data augmentation, regularization, optimization. Methods research utilized imaging Cancer analysis, incorporating patients. These images, taken various magnifications, formed basis training specialized built upon architecture. underwent distinguish tissues, sophisticated methodologies including regularization techniques, optimization strategies. Results achieved success, showcasing remarkable 99% when tested dataset. high underscores efficacy effectively discerning tissues. Furthermore, exhibited impressive precision, recall, F1-score metrics, reinforcing its robust tool Discussion demonstrates promising models address challenges associated with ability achieve rate test dataset signifies considerable leap forward earlier accurate detection Leveraging machine learning, augmentation optimization, has shown results improving patient outcomes through timely identification

Language: Английский

---

Artificial intelligence for oral squamous cell carcinoma detection based on oral photographs: A comprehensive literature review

Cancer Medicine, Journal Year: 2024, Volume and Issue: 13(1)

Published: Jan. 1, 2024

Abstract Introduction Oral squamous cell carcinoma (OSCC) presents a significant global health challenge. The integration of artificial intelligence (AI) and computer vision holds promise for the early detection OSCC through analysis digitized oral photographs. This literature review explores landscape AI‐driven automatic detection, assessing both performance limitations current state art. Materials Methods An electronic search using several data base was conducted, systematic performed in accordance with PRISMA guidelines (CRD42023441416). Results Several studies have demonstrated remarkable results this task, consistently achieving sensitivity rates exceeding 85% accuracy surpassing 90%, often encompassing around 1000 images. scrutinizes these studies, shedding light on their methodologies, including use recent machine learning pattern recognition approaches coupled different supervision strategies. However, comparing from papers is challenging due to variations datasets used. Discussion Considering findings, underscores urgent need more robust reliable field detection. Furthermore, it highlights potential advanced techniques such as multi‐task learning, attention mechanisms, ensemble crucial tools enhancing Conclusion These insights collectively emphasize transformative impact diagnosis, significantly improve patient outcomes healthcare practices.

Language: Английский

---

Artificial intelligence and the diagnosis of oral cavity cancer and oral potentially malignant disorders from clinical photographs: a narrative review

Frontiers in Oral Health, Journal Year: 2025, Volume and Issue: 6

Published: March 10, 2025

Oral cavity cancer is associated with high morbidity and mortality, particularly advanced stage diagnosis. cancer, typically squamous cell carcinoma (OSCC), often preceded by oral potentially malignant disorders (OPMDs), which comprise eleven variable risks for transformation. While OPMDs are clinical diagnoses, conventional exam followed biopsy histopathological analysis the gold standard diagnosis of OSCC. There vast heterogeneity in presentation OPMDs, possible visual similarities to early-stage OSCC or even various benign mucosal abnormalities. The diagnostic challenge OSCC/OPMDs compounded non-specialist primary care setting. has been significant research interest technology assist OSCC/OPMDs. Artificial intelligence (AI), enables machine performance human tasks, already shown promise several domains medical diagnostics. Computer vision, field AI dedicated data, over past decade applied photographs Various methodological concerns limitations may be encountered literature on OSCC/OPMD image analysis. This narrative review delineates current landscape photograph navigates limitations, issues, workflow implications this field, providing context future considerations.

Language: Английский

---

Role of Artificial Intelligence in the Diagnosis of Oral Squamous Cell Carcinoma: A Systematic Review

Cureus, Journal Year: 2025, Volume and Issue: unknown

Published: April 6, 2025

Oral squamous cell carcinoma (OSCC) is a serious worldwide health issue. Early OSCC identification by the analysis of digital oral photos possible with combination artificial intelligence (AI) and computer vision. The purpose this systematic review was to evaluate current evidence on role AI in diagnosis OSCC, focusing diagnostic performance, methodologies employed, potential limitations applications context. We followed Preferred Reporting Items for Systematic Reviews Meta-Analyses (PRISMA) guidelines search relevant studies across PubMed, Scopus, Web Science, Cumulative Index Nursing Allied Health Literature (CINAHL). In these databases, we found 286 studies, which were first screened duplicates then assessed inclusion exclusion criteria. Only 11 most included study. These also risk bias using Quality Assessment Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Numerous have shown impressive results job, frequently covering about 1000 regularly reaching sensitivity rates above 85% accuracy 90%. examines research detail, providing insight into their methods, include application contemporary machine learning pattern recognition techniques conjunction various supervision techniques. However, because datasets are utilized different articles, it can be difficult compare results. light results, study emphasizes how urgently area detection needs more solid trustworthy datasets. Additionally, sophisticated methods like ensemble learning, multi-task attention mechanisms used as essential instruments improve photos. Together, observations highlight AI-driven early greatly enhance patient outcomes medical procedures.

Language: Английский

---

Diagnostic performance of artificial intelligence in detecting oral potentially malignant disorders and oral cancer using medical diagnostic imaging: a systematic review and meta-analysis

Frontiers in Oral Health, Journal Year: 2024, Volume and Issue: 5

Published: Nov. 6, 2024

Objective Oral cancer is a widespread global health problem characterised by high mortality rates, wherein early detection critical for better survival outcomes and quality of life. While visual examination the primary method detecting oral cancer, it may not be practical in remote areas. AI algorithms have shown some promise from medical images, but their effectiveness remains Naïve. This systematic review aims to provide an extensive assessment existing evidence about diagnostic accuracy AI-driven approaches potentially malignant disorders (OPMDs) using imaging. Methods Adhering PRISMA guidelines, scrutinised literature PubMed, Scopus, IEEE databases, with specific focus on evaluating performance architectures across diverse imaging modalities these conditions. Results The models, measured sensitivity specificity, was assessed hierarchical summary receiver operating characteristic (SROC) curve, heterogeneity quantified through I 2 statistic. To account inter-study variability, random effects model utilized. We screened 296 articles, included 55 studies qualitative synthesis, selected 18 meta-analysis. Studies efficacy AI-based methods reveal 0.87 specificity 0.81. odds ratio (DOR) 131.63 indicates likelihood accurate diagnosis OPMDs. SROC curve (AUC) 0.9758 exceptional such models. research showed that deep learning (DL) architectures, especially CNNs (convolutional neural networks), were best at finding OPMDs cancer. Histopathological images exhibited greatest detections. Conclusion These findings suggest potential function as reliable tools offering significant advantages, particularly resource-constrained settings. Systematic Review Registration https://www.crd.york.ac.uk/ , PROSPERO (CRD42023476706).

Language: Английский

---

Automatic oral cancer detection using deep learning techniques

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 106, P. 107731 - 107731

Published: Feb. 26, 2025

Language: Английский

---

Automated Detection of Oral Cancer Through Deep Learning: A Histopathological Approach

Studies in computational intelligence, Journal Year: 2025, Volume and Issue: unknown, P. 145 - 161

Published: Jan. 1, 2025

Language: Английский

---

An End-to-End Deep Learning Framework for Accurate Tumor Detection and Segmentation in Brain MRI Scans

Advances in medical diagnosis, treatment, and care (AMDTC) book series, Journal Year: 2025, Volume and Issue: unknown, P. 113 - 132

Published: Feb. 14, 2025

This chapter presents an automated biomedical image classification system, HBDL-FBTA (Hybrid Bio-inspired Deep Learning with Fusion Brain Tumor Analysis), focused on brain tumors—abnormal cell growths in the or surrounding tissues that require early, accurate detection for effective treatment. The employs pre-processing to enhance quality, Swin-UNet-based segmentation precise region delineation, and fusion-based feature extraction robust acquisition. It uses Humpback Whale Optimization Simulated Annealing (HSSA) parameter tuning a Gated Recurrent Unit (GRU) reliable classification. Simulations benchmark datasets, including BraTS2017, demonstrate superior performance, achieving accuracies of 94.51% ISIC 2017 95.38% 2020 datasets. Future work will focus evaluating computational complexity large-scale integrating multi-modal imaging data, developing interpretable deep learning models clinical adoption reliability.

Language: Английский

---

Intelligent deep learning supports biomedical image detection and classification of oral cancer

Technology and Health Care, Journal Year: 2024, Volume and Issue: 32, P. 465 - 475

Published: May 14, 2024

Oral cancer is a malignant tumor that usually occurs within the tissues of mouth. This type mainly includes tumors in lining mouth, tongue, lips, buccal mucosa and gums. on rise globally, especially some specific risk groups. The early stage oral asymptomatic, while late may present with ulcers, lumps, bleeding, etc.

Language: Английский

---

Oral cavity carcinoma detection using BAT algorithm-optimized machine learning models with transfer learning and random sampling

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 192, P. 110250 - 110250

Published: May 5, 2025

Language: Английский

---