Myeloma Cell Detection in Bone Marrow Aspiration Using Microscopic Images

Multiple myeloma is a haematological cancer that occurs in plasma cells. The increase in the myeloma cells induces the reduction in all the blood cells. This paper presents the computer-aided methodology for multiple myeloma detection and diagnosis. Convolutional neural network is employed in order to detect multiple myeloma while using microscopic images of blood. Pre- trained and fine- tuned AlexNet is used for diagnosis of myeloma. Microscopic images are classified into normal and blast using AlexNet as feature extractor and SVM for classification. Proposed methodology is compared with state-of-the art in literature and the presented technique outperforms the previous methodologies.