ONCOSCOPIC PREDICTION: BLOOD CANCER PREDICTION USING CNN ALGORITHM IN DEEP LEARNING
- Version
- Download 10
- File Size 518.83 KB
- File Count 1
- Create Date 12 June 2025
- Last Updated 12 June 2025
ONCOSCOPIC PREDICTION: BLOOD CANCER PREDICTION USING CNN ALGORITHM IN DEEP LEARNING
Authors:
M.VASUKI1, DR.T. AMALRAJ VICTORIE2, SURUTHEKA.S3
1 Professor, Department of MCA, Sri Manakula Vinayagar Engineering College, Puducherry-605107, India.
2 Associate Professor, Department of MCA, Sri Manakula Vinayagar Engineering College, Puducherry-605107, India.
3PG Student, Department of MCA, Sri Manakula Vinayagar Engineering College, Puducherry-605107 India.
dheshna@gmail.com1, amalrajvictorie@gmail.com2, suruthekascindia@gmail.com3
ABSTRACT
Blood cancer poses a significant threat to human life, emphasizing the need for timely and accurate diagnosis to ensure effective treatment. Conventional diagnostic methods often depend on manual inspection of blood smear images under a microscope, which can be labor-intensive, subjective, and susceptible to human error. To address these limitations, this study introduces an automated detection system utilizing a Convolutional Neural Network (CNN) trained on labeled blood smear images. The CNN architecture incorporates multiple convolutional, pooling, and dense layers to extract deep features and classify the images into cancerous and non-cancerous categories. Preprocessing techniques such as normalization and data augmentation were applied to enhance the model’s accuracy and generalizability. The model’s effectiveness was assessed using evaluation metrics including accuracy, precision, recall, and F1-score, all of which indicated strong performance. To ensure usability in clinical settings, the trained model was integrated with a Tkinter-based graphical user interface (GUI), allowing users to upload blood smear images and receive diagnostic results. This system highlights the practical potential of deep learning in supporting healthcare professionals with early, efficient, and consistent blood cancer detection.
Download