Automatic Urine Sediment Detection and Classification Based on YoloV8

Akhtar, Sania; Hanif, Muhammad; Malih, Hamidi

doi:10.1007/978-3-031-37129-5_22

Cited by 6 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motivation: Building on the experiences of recent models such as [19] and [23], our approach incorporates an error analysis-driven iteration process. By systematically analyz-…”

Section: ) Error Analysis-driven Iterationsmentioning

confidence: 99%

“…They conducted seven clinically relevant cell segmentation and classification studies. The Yolov7 algorithm successfully segmented urine cell images, achieving a mean classification accuracy of 0.822 for all classes Akhtar et al [23] recently utilized YoloV8 [32] to accurately detect and categorize urine particles, introducing a data-centric strategy to enhance dataset quality by addressing issues such as missing data, incorrect labeling, and class imbalance. Experimental results demonstrated that YOLOv8 outperforms existing techniques, achieving a mean average precision of 91% for eleven categories of urine sediments, with an average detection time of 0.6 ms. Li et al [33] employed a combination of Faster RCNN [34] to detect urine erythrocytes were the focus of Li et al's study, where their model, trained on a dataset comprising 3969 images, achieved an impressive recall rate of up to 99.8% for five types of urine erythrocytes.…”

Section: B Contributions/noveltiesmentioning

confidence: 99%

See 1 more Smart Citation

An Optimized Data and Model Centric Approach for Multi-Class Automated Urine Sediment Classification

Akhtar,

Hanif,

Rashid

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Automated urine sediment analyzers play a crucial role in diagnosing urinary tract infections, offering real-time data analysis and expediting patient diagnosis. This paper introduces a novel hybrid approach combining data-centric and model-centric techniques for automated urine sediment analysis. The proposed methodology addresses challenges such as morphological similarities among particle classes, uneven particle distribution, and intra/inter-class variations. A modified version of convolutional neural network (CNN), specifically the Visual Geometry Group (VGG-19) model, incorporating transfer learning, along with data augmentation is proposed for automated urine sediment classification with 98% accuracy and impressive inference time of 61ms per image. The proposed approach outperforms existing methods, especially in handling diverse sediment categories, demonstrating its potential for practical applications in medical diagnostics. We proposed the integration of a data-centric approach for improved labeling reliability and a model-centric approach for fine-tuning of the deep learning model, showcasing promising results in recognizing 12 distinct urine sediment classes. This study also emphasizes the importance of collaboration with medical professionals in refining the model's performance and handling challenges related to data acquisition and class imbalance. The proposed approach provides a significant advancement in automating and enhancing urine sediment analysis processes.

show abstract

“…Motivation: Building on the experiences of recent models such as [19] and [23], our approach incorporates an error analysis-driven iteration process. By systematically analyz-…”

Section: ) Error Analysis-driven Iterationsmentioning

confidence: 99%

Section: B Contributions/noveltiesmentioning

confidence: 99%

An Optimized Data and Model Centric Approach for Multi-Class Automated Urine Sediment Classification

Akhtar,

Hanif,

Rashid

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

Real-time detection of plastic part surface defects using deep learning- based object detection model

Çelik,

Arslankaya,

Yildiz

2024

Measurement

View full text Add to dashboard Cite

Assessing the Effectiveness of YOLO Architectures for Smoke and Wildfire Detection

Casas,

Ramos,

Bendek

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This paper presents a comprehensive evaluation of various YOLO architectures for smoke and wildfire detection, including YOLOv5, YOLOv6, YOLOv7, YOLOv8, and YOLO-NAS. The study aims to assess their effectiveness in early detection of wildfires using the Foggia dataset, comprising 8,974 images specifically designed for this purpose. Performance evaluation employs metrics such as Recall, Precision, F1-score, and mean Average Precision to provide a holistic assessment of the models' performance. The study follows a rigorous methodology involving fixed epochs, continuous performance tracking, and unbiased testing. Results show that YOLOv5, YOLOv7, and YOLOv8 exhibit a balanced performance across all metrics in both validation and testing. YOLOv6 performs slightly lower in recall during validation but achieves a good balance on testing. YOLO-NAS variants excel in recall, making them suitable for critical applications. However, precision performance is lower for YOLO-NAS models. Visual results demonstrate that the top-performing models accurately identify most instances in the test set. However, they struggle with distant scenes and poor lighting conditions, occasionally detecting false positives. In favorable conditions, the models perform well in identifying relevant instances. We conclude that no single model excels in all aspects of smoke and wildfire detection. The choice of model depends on specific application requirements, considering accuracy, recall, and inference time. This research contributes to the field of computer vision in smoke and wildfire detection, providing a foundation for improving detection systems and mitigating the impact of wildfires. Researchers can build upon these findings to propose modifications and enhance the effectiveness of wildfire detection systems.

show abstract

Automatic Urine Sediment Detection and Classification Based on YoloV8

Cited by 6 publications

References 13 publications

An Optimized Data and Model Centric Approach for Multi-Class Automated Urine Sediment Classification

An Optimized Data and Model Centric Approach for Multi-Class Automated Urine Sediment Classification

Real-time detection of plastic part surface defects using deep learning- based object detection model

Assessing the Effectiveness of YOLO Architectures for Smoke and Wildfire Detection

Contact Info

Product

Resources

About