AI for Healthcare: Applications of Semantic Segmentation in Lung Cancer Detection Using Python and Implications for Public Policy

The purpose of this paper is to study of how machine learning algorithms, artificial intelligence, semantic segmentation and fine recognition can be used to enhance computer vision in order to determine anomalies indicating cancer in lung cancer image datasets. Methodology: We run the semantic segmentation model Deeplab V3 ResNet 50 on the lung image dataset to identify different segments and examine how to they can be used to detect anomalies in the tissue. Findings: The current research study applied semantic segmentation and fine recognition to identify anomalies indicating cancer in a lung images dataset, and identify avenues and areas of further improvement in accuracy of the classification, predictions and preventive care. Implications: The research presents a further study of previous literature on how these 2 attributes can be used to identify cancerous growths and tumors in image datasets of organs for prediction, pain management, dosages for chemotherapy and preventive care. Originality: Since the pandemic, the need for improving the quality of healthcare has drastically increased and hence more accurate diagnosis are required.