Variable Kernel Feature Fusion and Transfer Learning for Pap Smear Image-Based Cervical Cancer Classification DOI Open Access

S. Priya,

V. Mary Amala Bai

International Journal of Electronics and Communication Engineering, Journal Year: 2024, Volume and Issue: 11(11), P. 228 - 243

Published: Nov. 30, 2024

Cervical cancer, a malignant tumour that forms in the cervix, significantly contributes to cancer-related mortality among women globally, making early diagnosis crucial for effective treatment. Pap smear images, which are microscopic images of cervical cells, commonly used detection abnormal cells may lead cancer. This study introduces novel classification approach, Variable Kernel Feature Fusion-CNN (VKFF-CNN), improves performance by fusing multi-scale features using convolutional layers with 3x3, 4x4, and 5x5 kernels. architecture captures diverse set features, enhancing ability model accurately classify cells. With an average accuracy 98.03%, precision 97.83%, recall 97.11%, F1 score 98.23%, VKFF-CNN exhibited outstanding outcomes on Herlev Smear dataset. These results demonstrate outperforms traditional machine learning models. The model's confusion matrix indicated fewer misclassifications, underscoring its robustness effectiveness. Including batch normalization softmax activation function further enhanced stability accurate classification. Overall, presents promising advancement automated cancer screening, providing highly reliable detection.

Language: Английский

The importance of clinical experience in AI-assisted corneal diagnosis: verification using intentional AI misleading DOI Creative Commons

Hiroki Maehara,

Yuta Ueno,

Takefumi Yamaguchi

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 9, 2025

Abstract We developed an AI system capable of automatically classifying anterior eye images as either normal or indicative corneal diseases. This study aims to investigate the influence AI’s misleading guidance on ophthalmologists’ responses. cross-sectional included 30 cases each infectious and immunological keratitis. Responses regarding presence infection were collected from 7 specialists 16 non-corneal-specialist ophthalmologists, first based alone then after presenting classification results. The diagnoses deliberately altered present a correct in 70% incorrect 30%. overall accuracy ophthalmologists did not significantly change assistance was introduced [75.2 ± 8.1%, 75.9 7.2%, respectively ( P = 0.59)]. In where presented diagnoses, before showing no significant [60.3 35.2% 53.2 30.9%, 0.11)]. contrast, for non-corneal dropped 54.5 27.8% 31.6 29.3% < 0.001), especially options. Less experienced misled due guidance, but not. Even with introduction diagnostic support systems, importance ophthalmologist’s experience remains crucial.

Language: Английский

Citations

2
Evaluation of Convolutional Neural Networks (CNNs) in Identifying Retinal Conditions Through Classification of Optical Coherence Tomography (OCT) Images DOI Open Access

Rohin R. Teegavarapu,

Harshal A. Sanghvi,

Triya Belani

et al.

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

Published: Jan. 7, 2025

Introduction Diabetic retinopathy (DR) is a leading cause of blindness globally, emphasizing the urgent need for efficient diagnostic tools. Machine learning, particularly convolutional neural networks (CNNs), has shown promise in automating diagnosis retinal conditions with high accuracy. This study evaluates two CNN models, VGG16 and InceptionV3, classifying optical coherence tomography (OCT) images into four categories: normal, choroidal neovascularization, diabetic macular edema (DME), drusen. Methods Using 83,000 OCT across categories, CNNs were trained tested via Python-based libraries, including TensorFlow Keras. Metrics such as accuracy, sensitivity, specificity analyzed confusion matrices performance graphs. Comparisons dataset sizes evaluated impact on model accuracy tools deployed JupyterLab. Results InceptionV3 achieved between 85% 95%, peaking at 94% outperforming (92%). Larger datasets improved sensitivity by 7% all highest normal drusen classifications. like positively correlated size. Conclusions The confirms CNNs' potential diagnostics, achieving classification Limitations included reliance grayscale computational intensity, which hindered finer distinctions. Future work should integrate data augmentation, patient-specific variables, lightweight architectures to optimize clinical use, reducing costs improving outcomes.

Language: Английский

Citations

0
Antioxidants in Age-Related Macular Degeneration: Lights and Shadows DOI Creative Commons
Uday Pratap Singh Parmar, Pier Luigi Surico,

Takamasa Mori

et al.

Antioxidants, Journal Year: 2025, Volume and Issue: 14(2), P. 152 - 152

Published: Jan. 27, 2025

Age-related macular degeneration (AMD) is a leading cause of vision impairment worldwide, primarily driven by oxidative stress and inflammation. This review examines the role antioxidants in mitigating damage, emphasizing both their therapeutic potential limitations AMD management. Key findings underscore efficacy specific antioxidants, including vitamins C E, lutein, zeaxanthin, Coenzyme Q10, slowing progression. Landmark studies such as AREDS AREDS2 have shaped current antioxidant formulations, although challenges persist, patient variability long-term safety concerns. Emerging therapies, mitochondrial-targeted novel compounds like saffron resveratrol, offer promising avenues for treatment. Complementary lifestyle interventions, antioxidant-rich diets physical activity, further support holistic management approaches. highlights critical therapy, advocating personalized strategies to optimize outcomes.

Language: Английский

Citations

0
Detection of retinal diseases from OCT images using a VGG16 and transfer learning DOI Creative Commons

W. J. Jaimes,

Wilson J. Arenas,

Humberto J. Navarro

et al.

Deleted Journal, Journal Year: 2025, Volume and Issue: 7(3)

Published: Feb. 20, 2025

Language: Английский

Citations

0
A Systematic Review of Advances in AI-Assisted Analysis of Fundus Fluorescein Angiography (FFA) Images: From Detection to Report Generation DOI Creative Commons
Yu Tao, An Shao,

Hongkang Wu

et al.

Ophthalmology and Therapy, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 21, 2025

Fundus fluorescein angiography (FFA) serves as the current gold standard for visualizing retinal vasculature and detecting various fundus diseases, but its interpretation is labor-intensive requires much expertise from ophthalmologists. The medical application of artificial intelligence (AI), especially deep learning machine learning, has revolutionized field automatic FFA image analysis, leading to rapid advancements in AI-assisted lesion detection, diagnosis, report generation. This review examined studies PubMed, Web Science, Google Scholar databases January 2019 August 2024, with a total 23 articles incorporated. By integrating research findings, this highlights crucial breakthroughs analysis explores their potential implications ophthalmic clinical practice. These advances have shown promising results improving diagnostic accuracy workflow efficiency. However, further needed enhance model transparency ensure robust performance across diverse populations. Challenges such data privacy technical infrastructure remain broader applications.

Language: Английский

Citations

0
Enhancing Ophthalmic Diagnosis and Treatment with Artificial Intelligence DOI Creative Commons
David B. Olawade,

Kusal Weerasinghe,

Mathugamage Don Dasun Eranga Mathugamage

et al.

Medicina, Journal Year: 2025, Volume and Issue: 61(3), P. 433 - 433

Published: Feb. 28, 2025

The integration of artificial intelligence (AI) in ophthalmology is transforming the field, offering new opportunities to enhance diagnostic accuracy, personalize treatment plans, and improve service delivery. This review provides a comprehensive overview current applications future potential AI ophthalmology. algorithms, particularly those utilizing machine learning (ML) deep (DL), have demonstrated remarkable success diagnosing conditions such as diabetic retinopathy (DR), age-related macular degeneration, glaucoma with precision comparable to, or exceeding, human experts. Furthermore, being utilized develop personalized plans by analyzing large datasets predict individual responses therapies, thus optimizing patient outcomes reducing healthcare costs. In surgical applications, AI-driven tools are enhancing procedures like cataract surgery, contributing better recovery times reduced complications. Additionally, AI-powered teleophthalmology services expanding access eye care underserved remote areas, addressing global disparities availability. Despite these advancements, challenges remain, concerning data privacy, security, algorithmic bias. Ensuring robust governance ethical practices crucial for continued conclusion, research should focus on developing sophisticated models capable handling multimodal data, including genetic information histories, provide deeper insights into disease mechanisms responses. Also, collaborative efforts among governments, non-governmental organizations (NGOs), technology companies essential deploy solutions effectively, especially low-resource settings.

Language: Английский

Citations

0
Influence of Non-Mydriasis on Optical Coherence Tomography Imaging Quality in Patients with Retinitis Pigmentosa DOI Creative Commons
Salvador Pastor‐Idoate,

Santiago Mejía-Freire,

Milagros Mateos-Olivares

et al.

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: March 5, 2025

This chapter examines the influence of non-mydriasis on quality optical coherence tomography (OCT) imaging in patients with retinitis pigmentosa (RP). The focus is analysis OCT quality, specifically addressing types artifacts that can potentially confound interpretation and angiography (OCTA) images. Common such as signal attenuation, motion artifacts, projection are identified discussed. also explores methods for removing these compensation techniques applicable clinical settings RP cases. Findings suggest does not significantly limit acquisition images mild to moderate stages RP. However, pupillary dilation may be necessary severe disease enhance image reduce despite potential increase glare photophobia patients. discussion includes practical strategies optimizing protocols without using mydriatic agents, improving patient comfort, efficiency procedures. Ultimately, this aims diagnostic accuracy care by mitigating challenges associated

Language: Английский

Citations

0
Seeing the unseen: The low treatment rate of eye emergencies in Africa DOI
Babatunde Ismail Bale, Marco Zeppieri, Obehi Suzan Idogen

et al.

World Journal of Methodology, Journal Year: 2025, Volume and Issue: 15(3)

Published: March 6, 2025

BACKGROUND Emergency medical care is essential in preventing morbidity and mortality, especially when interventions are time-sensitive require immediate access to supplies trained personnel. AIM To assess the treatment rates of eye emergencies Africa. Ocular particularly delicate due eye’s intricate structure necessity for its refractive components remain transparent. METHODS This review examines low Africa, drawing on 96 records extracted from PubMed database using predetermined search criteria. RESULTS The epidemiology ocular injuries, as detailed studies, reveals significant relationships between incidence prevalence injuries factors such age, gender, occupation. causes range accidents gender-based violence insect or animal attacks. Management approaches reported include both surgical non-surgical interventions, medication evisceration enucleation eye. Preventive measures emphasize health education use protective eyewear facial protection. However, inadequate healthcare infrastructure personnel, cultural geographical barriers, socioeconomic behavioral hinder effective prevention, service uptake, management emergencies. CONCLUSION authors recommend developing policies, enhancing community engagement, improving personnel training retention, increasing funding programs solutions address rate

Language: Английский

Citations

0
Editorial to the Special Issue “Retinopathies: A Challenge for Early Diagnosis, Innovative Treatments, and Reliable Follow-Up” DOI Creative Commons
Dario Rusciano, Stefania Marsili

Medicina, Journal Year: 2025, Volume and Issue: 61(4), P. 662 - 662

Published: April 3, 2025

The Special Issue “Retinopathies: A Challenge for Early Diagnosis, Innovative Treatments, and Reliable Follow-Up” brings together a diverse yet interconnected collection of research papers that collectively address the multifaceted challenges retinal diseases [...]

Language: Английский

Citations

0
Paradigm of Nanophotonics Integrated Smart Contact Lenses: A New Frontier in Wearable Healthcare DOI
Bakr Ahmed Taha,

S.A. Abdulateef,

Ali J. Addie

et al.

Materials Research Bulletin, Journal Year: 2025, Volume and Issue: unknown, P. 113511 - 113511

Published: April 1, 2025

Language: Английский

Citations

0