Comparative Analysis of Yolo Models in Mammogram Lesion Detection: Insights from a Retrospective Study in Thailand DOI

Anongnat Intasam,

Nicholas Piyawattanametha,

Yuttachon Promworn

et al.

Published: Jan. 1, 2023

Early detection of breast cancer through mammogram screening is vital for effective treatment and care. Radiologists often face challenges in distinguishing specific lesion types from complex images. Accurate classification these lesions essential administering the correct treatment. Manual analysis can be both tedious prone to mistakes, highlighting need automated solutions like YOLO model. In our research, we classified into six distinct categories: Masses Benign (MB), Calcifications (CB), Associated Features (AFB), Malignant (MM), (CM), (AFM). Our approach consisted two phases. Initially, created a Web-based image annotation labeling tool specifically designed Thai radiologists facilitate We then evaluated various model variations on their ability detect using annotated YOLOv8 emerged as superior model, incorporating advanced features quicker more precise detection. Using mammograms 2,969 female patients Thailand, findings showcased exceptional performance YOLOv8, particularly with an size 1280, demonstrating high Recall, Precision, F1-Score, [email protected], [email protected]:0.95 values, outpacing other iterations.

Language: Английский

BreastHybridNet: A Hybrid Deep Learning Framework for Breast Cancer Diagnosis Using Mammogram Images DOI Open Access

Bandla Raghuramaiah,

Suresh Chittineni

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 25, 2025

As a common malignancy in females, breast cancer represents one of the most serious threats to female's life, which is also closely associated with Sustainable Development Goal 3 (SDG 3) United Nations for keeping healthy lives and promoting well-being all people. Breast accounts highest number mortality early diagnosis key reducing disease-specific general. Current methods struggle accurately localize important regions, model sequential dependencies, or combine different features despite considerable improvements artificial intelligence deep learning domains. They prevent diagnostic frameworks from being reliable scalable, especially low-resourced healthcare settings. This study proposes novel hybrid framework, BreastHybridNet, using mammogram images tackle these mutual challenges. The proposed framework combines pre-trained CNN backbone feature extraction, spatial attention mechanism automatically highlight image area, contains signature patterns carrying information, BiLSTM layer obtain dependencies features, fusion strategy process complementarily. Experimental results show that accuracy 98.30%, outperforms state-of-the-art LMHistNet, BreastMultiNet, DOTNet 2.0 extent quantitatively. BreastHybridNet works towards feasibility interpretability scalability on existing systems while contributing worldwide efforts alleviate cancer-related cost-efficient lenses. highlights need AI-enabled solutions contribute accessing technologies screening.

Language: Английский

Citations

7
Detection and Diagnosis of Small Target Breast Masses Based on Convolutional Neural Networks DOI
Ling Tan, Ying Liang,

Jingming Xia

et al.

Tsinghua Science & Technology, Journal Year: 2024, Volume and Issue: 29(5), P. 1524 - 1539

Published: May 2, 2024

Language: Английский

Citations

6
Hybrid segmentation and 3D Imaging: Comprehensive framework for breast cancer patient segmentation and classification based on digital breast tomosynthesis DOI
Wail M. Idress,

Khalid A. Abouda,

Rawal Javed

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 100, P. 106992 - 106992

Published: Oct. 9, 2024

Language: Английский

Citations

5
A Hybrid Deep Learning Approach for Breast Cancer Classification Based on Histology Images DOI
Sameh Zarif,

Hatem Abdul-Kader,

Ibrahim Sayed Elaraby

et al.

Lecture notes on data engineering and communications technologies, Journal Year: 2025, Volume and Issue: unknown, P. 265 - 274

Published: Jan. 1, 2025

Language: Английский

Citations

0
Bridging research gaps in breast cancer detection: An ensemble approach informed by bibliometric analysis DOI
Hanaa ZainEldin, Amna Bamaqa,

Mohammed Farsi

et al.

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 109, P. 108041 - 108041

Published: May 22, 2025

Language: Английский

Citations

0
Multi-scale control and action recognition based human-robot collaboration framework facing new generation intelligent manufacturing DOI
Zipeng Wang, Jihong Yan,

Guanzhong Yan

et al.

Robotics and Computer-Integrated Manufacturing, Journal Year: 2024, Volume and Issue: 91, P. 102847 - 102847

Published: Aug. 6, 2024

Language: Английский

Citations

2
The digital eye for mammography: deep transfer learning and model ensemble based open-source toolkit for mass detection and classification DOI
Ramazan Terzi, Ahmet Kılıç,

Gökhan Karaahmetoğlu

et al.

Signal Image and Video Processing, Journal Year: 2024, Volume and Issue: 19(1)

Published: Dec. 31, 2024

Language: Английский

Citations

1
A Deep Learning Classifier Using Sliding Patches For Detection of Mammographical Findings DOI
Diego Mellado, Marvin Querales, Julio Sotelo

et al.

Published: Nov. 15, 2023

Mammography is known as one of the best forms to screen possible breast cancer in women, and recently deep learning models have been developed assist radiologist diagnosis. However, their lack interpretability has become a significant drawback extended use clinical practice. This paper introduces novel approach for detecting localising pathological findings mammography exams through EfficientNet-based model. The model trained using cropped segments labelled from Vindr Dataset. Achieving an average F1-score 72.7 %, reaching on mass suspicious calcifications F1-Score 79.9 % 84.5 respectively. Using this classifier we propose method visualise local information regions interest where could be present complete image. Plus, describe limitations regarding area coverage these patches model's capability generalization certainty its predictions, explaining functionality.

Language: Английский

Citations

1
Wild Life Detection Providing Security to Villages – YOLO v8 DOI

Shayan Hore,

K. Deepa Thilak,

Silpi Kartheek Achari

et al.

Published: Dec. 21, 2023

In response to the increasing challenge of wild animal intrusions in rural areas, this study presents an innovative solution for community protection. The proposed system utilizes cameras and sound recognition technology detect presence potentially dangerous wildlife concurrently emit a loud deter animals alert villagers. ensures safety economic security by mitigating attacks crop damage. With user-friendly interface real-time alerting capabilities, represents significant step towards harmonious human-wildlife coexistence supports achievement Sustainable Development Goals.

Language: Английский

Citations

1
Real-time Front-end Detection Technology of UAV for Transmission Line Defects Based on YOLOv5 DOI
Ziyi Feng, Hengrui Ma, Jiahao Wang

et al.

Published: Dec. 6, 2024

Language: Английский

Citations

0