Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{181047,
        author = {Vinod A M and Pranav S and P M Aneesh Srivats and Sagar M S and Praharsha H V},
        title = {V NET for Blood Smear Analysis: A Deep Learning Approach to Leukemia Cell Segmentation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3260-3268},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181047},
        abstract = {This work focuses on detecting leukaemia-affected cells in microscopic blood smear images using deep learning. Leukemia is a blood- related cancer that can be identified by examining blood cells. Traditional manual checking by pathologists takes a lot of time and effort. To help this, we are using a segmentation-based approach where our goal is to separate and highlight the affected white blood cells (WBCs) from the rest of the image using a neural network architecture called V-Net. The dataset used for this work is the publicly available ALL_IDB1 dataset, which includes both the images and the coordinates of affected regions. The segmented regions are used to create true masks, and these are later used to train the V-Net model. The model tries to learn from these masks to predict affected regions in new images. The output of our model is compared with true masks to improve accuracy. So far, the segmentation phase is under progress, and classification will be the next part of this work.},
        keywords = {—Leukemia Detection, Blood Smear Analysis, V-Net Architecture, 2D Medical Image Segmentation, Deep Learning, Dice Loss, PyTorch Implementation, ALL_IDB1 Dataset},
        month = {June},
        }