Feature Set Segmentation Model to Detect Lung Tumor Size with Deep Learning Model

This electronic document is a “live” template and already defines the components of your paper [title, text, heads, etc.] in its style sheet. Accurate and timely detection of lung tumors are critical for early diagnosis and effective treatment planning. This paper presented a novel lung tumor detection, segmentation, and classification using the Median Probabilistic Feature Set Segmentation (MPFSS) method. The proposed framework leverages a combination of image processing, feature extraction, and deep learning techniques to address the complex challenges associated with lung tumor analysis in medical images. The MPFSS method demonstrates robust segmentation capabilities, accurately delineating tumor regions within lung images. Additionally, feature engineering is explored, highlighting the importance of selecting and engineering feature sets to enhance classification performance. Deep learning models are employed for classification, showcasing their effectiveness in achieving high accuracy and balanced precision and recall. Comparative analysis with traditional machine learning models further validates the superiority of the MPFSS approach. The proposed MPFSS model provides accurate lung tumor detection and classification, providing valuable insights for the field of medical image analysis and its potential impact on clinical diagnosis and treatment planning. The propsed model emerges as a strong performer, with balanced precision and recall, high F1-Scores, and an impressive ROC AUC.