McNair Scholars Research Journal
Abstract
Health professionals must diagnose correctly to avoid unnecessary costs in care and medicine. Different conditions, come with different treatments. Therefore, it is key to produce the right diagnoses promptly to help treat people appropriately and quickly. As lung cancer is the leading cancer type in the world, it is often diagnosed too late once symptoms appear which becomes difficult to treat at certain stages. In the race against time, recruiting the use of machine learning next to traditional methods of diagnosing will improve the confidence of professionals to predict specific conditions accurately and with speed. For our research, we will develop a convolutional neural network (CNN) model using the TinyVGG architecture to classify subtypes of lung cancer taken anonymously from patients. Pictures will be taken during the 10 days of incubating these cells. Over time, we will look at the results and determine if there are unique overgrowth patterns from different lung cancer cell lines. Alongside this, we will measure the accuracy of the CNN model and its ability to detect features that are not obvious to the human eye. This will aid in the understanding of this model by optimizing and adjusting its parameters to help classify these tumor growths correctly. A simultaneous goal is to determine if these unique overgrowth patterns are correlated with specific activation of certain oncogenes.
Recommended Citation
Khoun, Sandra Channeary
(2024)
"Using Machine Learning to Improve Confidence in Lung Cancer Diagnosis,"
McNair Scholars Research Journal: Vol. 28, Article 7.
DOI: https://doi.org/10.32855/2642-2492.1605
Available at:
https://mavmatrix.uta.edu/mcnairscholars/vol28/iss1/7