الفهرس 
TITLEOnly 14 pages are availabe for public view
 |  | from | 86 |  |  |
| | | from | 86 | | |
Abstract
Almost any malignancy may produce mesenteric lymphadenopathy. Lymphoma is the most prevalent malignancy related to mesenteric lymphadenopathy, and it can cause lymphadenopathy practically anywhere in the body. It can cause lymphadenopathy in the chest, retroperitoneum, or superficial lymph node chains, but it can also cause mesenteric lymphadenopathy. The most common screening tool for detecting abdominal lymph node enlargement is abdominal sonography. Size, localisation, and invasion pattern must all be known for correct classification. The size of the lymph nodes alone cannot establish whether the lesion is benign or malignant. The objective of the present study was to use the python software package for the precise identification of lymph node lesions compared to that of the healthy controls.
The study included 150 sonographic images of pathologically proven Abdominal Lymphadenopathy patients and Healthy Controls from worldwide databases. Images were preprocessed before being split into training and testing datasets for the SVM classification algorithm. SVM with optimized kernel and C parameter was the machine learning algorithm used in this investigation. For these data, the optimal training parameter combination of the Support Vector Machine model was C = 200 and linear kernel.
The training, validation, and testing accuracies were 1.00, 0.99, and 0.99, respectively, with a mean squared error of 0.16 and a score of 0.02 seconds. The output vector of sonographic images consists of two classes: Abdominal Lymphadenopathy and Healthy Control. Precision, Recall, F1-Score, and Specificity results. The precision and specificity were as high as 100 and 99% for Healthy Controls and Abdominal Lymphadenopathy, respectively. Thus, the Support Vector Machine algorithm is a powerful tool for assisting radiologist in classifying and diagnosing sonographic images for Abdominal Lymphadenopathy with great precision.