Automated Diagnosis and Detection of Blood Cancer Using Deep Learning-Based Approaches: A Recent Study and Challenges
Jaswinder Bir Singh, Vijay Luxmi · 2023
Blood cancer, also referred to as haematological malignancy, is a collection of cancers that affect the blood, bone marrow, and lymphatic systems. Early and accurate blood cancer detection is essential for effective treatment and enhanced patient outcomes. Deep learning algorithms have emerged as potent instruments for medical image analysis and disease detection in recent years. This paper intends to provide a comprehensive overview of the application of deep learning techniques to the detection of blood cancer. The paper begins by describing the various forms of blood cancer and the difficulties involved in their detection. The merits and weaknesses of various deep learning architectures and frameworks used in blood cancer research are described. The review then focuses on the datasets and imaging modalities that are commonly used for blood cancer detection. It discusses the pre-processing techniques used to improve image quality and reduce noise, as well as the data augmentation techniques used to increase the robustness of deep learning models in the proposed system architecture. The paper concludes with a discussion of prospective future directions and developments in the field. It highlights the significance of developing robust and interpretable deep learning models, incorporating multi-modal data for enhanced accuracy, and integrating clinical and genomic data to facilitate personalised treatment strategies.