چاپ صفحه |  صفحه نخست سامانه |  نویسندگان |  اطلاعات تفضیلی |  دانلود مقاله | دانشگاه علوم پزشکی تبریز |
| نویسنده | نفر چندم مقاله |
|---|---|
| ناصر صمدزاده اقدم | اول |
| عنوان | متن |
|---|---|
| کلمات کلیدی | Keywords: Acute Lymphoblastic Leukemia, Artificial Intelligence, Machine Learning, Convolutional Neural Network |
| خلاصه مقاله | Abstract Introduction Acute lymphoblastic leukemia (ALL) is the most common form of pediatric cancer of white blood cells which is categorized into three types of L1, L2, and L3. It is usually detected through screening of blood and bone marrow smears by pathologists. Since manual detection might be time-consuming and boring, artificial intelligence (AI) based decision systems can result in convenient detection. The rigorous similarity between morphology of ALL types and other forms such as normal, reactive and atypical lymphocytes, makes the automatic recognition a challenging problem. Materials & Methods First, the image contrast is enhanced; then the cell nucleus is segmented by the fuzzy c-means clustering algorithm. Post processing such as binary morphological opening and closing are applied to the cluster corresponding to the nuclei to remove stain artifacts and fill the small holes. Finally, the nuclei images are input to convolutional neural networks for classification. Here, we used the two networks developed by visual geometric group i.e. VGG-16 and VGG-19. Results Accuracy is used for quantitative evaluation that shows the closeness of the model output to the true label of the data. Classification accuracy equal to approximately 91% and 93% for VGG-16 and VGG-19, respectively. Conclusion While most of the previous studies have done a 3-class or 4-claas (cancerous plus normal) classification regarding ALL subtypes, in this study we have done a 6-class classification that is very challenging. The results show that the proposed algorithm has acceptable performance for the diagnosis of ALL and its subtypes as well as other lymphocyte types. Therefore, it can be an assistant diagnostic tool for pathologists. |
| نام فایل | تاریخ درج فایل | اندازه فایل | دانلود |
|---|---|---|---|
| Govahi hamayesh.pdf | 1402/03/22 | 136654 | دانلود |
| Abstract book-final.pdf | 1402/03/24 | 2229812 | دانلود |
