BLOOD CELL TYPE DETECTION USING DEEP LEARNING
Dr. D.V.Krishna Reddy1, Associate Professor, Department of IT,
KKR & KSR INSTITUTE OF TECHNOLOGY AND SCIENCES,Vinjanampadu
Guntur Dt., Andhra Pradesh-522217.
Challa Jhansi Lakshmi Bhavani2, Dasari Hema Latha3, Harshitha Telanakula4, Alavalapati Pujitha5
2,3,4,5 UG Students, Department of IT,
KKR & KSR INSTITUTE OF TECHNOLOGY AND SCIENCES,Vinjanampadu
Guntur Dt., Andhra Pradesh-522217.
1 krishnareddydp@gmail.com, 2 jhansichalla45@gmail.com,
3 hemadasari2003@gmail.com,
4 hharshi347@gmail.com, 5 pujithaalavalapati27@gmail.com
Abstract
Accurate and timely analysis of blood cells plays an important role in the diagnosis and treatment of many diseases. The manual blood testing method is labor-intensive, time-consuming, and prone to human error. In this context, the use of deep learning technology seems to be a great promise in terms of automating the process and increasing the efficiency of the treatment. This work presents a blood cell detection system based on deep learning algorithms. The YOLOv8 model is used to analyze microscopic images of blood samples and accurately identify identical cells. Periods must be trained to obtain higher predictions. The model is trained on many different data sets to ensure good performance across different blood types and conditions. Even with limited data, transfer learning can be used to optimize training models, thus improving the transfer process to different clinical settings. Rapid identification of blood cells allows doctors to make faster, more informed decisions and improve patient outcomes. Early detection of blood-related diseases leads to intervention and timely treatment, ultimately improving the quality of all medical services. Additionally, the automation of this application reduces the workload of laboratory workers, allowing them to focus on more complex tasks and be more efficient throughout the laboratory. The technology has the potential to be integrated into existing treatments, resulting in a variety of treatments.
Keywords: YOLO, pytorch, tensorflow, nvidia, flask, image processing.
