Treffer: DEEP LEARNING BASED STACKED PROBABILISTIC ATTENTION NEURAL NETWORK FOR THE PREDICTION OF BIO MARKERS IN NON-HODGKIN LYMPHOMA.

The biomolecular characterization of Non-Hodgkin lymphoma (NHL) impacts the prognosis, therapy planning, and prediction of therapeutic response. The development of cancerous characteristics in lymphoma formation may often be attributed to certain genetic defects and the resulting disruption of oncogenic regulatory processes. The use of advanced technology has made it feasible to identify genetic variations and their corresponding biomarkers. However, the current challenges in histopathology include the identification techniques and the presence of different cell types inside a tumour. Computational techniques are now being used more often to diagnose genetic abnormalities without invasive procedures. This is done by analysing quantitative imaging data. Therefore, we are now deploying a deep learning-based stacking probabilistic attention neural network in this project. In this study, the histopathological images are obtained from the Kaggle source. Next, the image may undergo preprocessing using the soft switch Weiner filter (SSWF). The area of interest was segmented using the hierarchical seed polarity transform (HSPT). The biomarker linked with Non-Hodgkin lymphoma is categorised using the stacked probabilistic attention neural network (SPANN) based on the segmented output. The whole experiment was conducted using a histopathologic cancer dataset from Kaggle under python environment. The proposed strategy outperformed the current state-of-the-art alternatives by obtaining high range of accuracy(95%), precision(95%), recall(95%) and F score (92%). [ABSTRACT FROM AUTHOR]

Copyright of Scalable Computing: Practice & Experience is the property of Scalable Computing: Practice & Experience and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)