The pharynx plays a most significant role in serving both the body’s air food passageway
systems. Pharyngeal neoplasm happens when tissues in the throat grow and spread abnormally,
destroying healthy cells. So, pharyngeal neoplasm detection plays a vital role in timely and
accurate diagnostic methods for improved patient result outcomes. In this project, we propose
a machine learning-based classification system for the automated detection of pharyngeal
neoplasm using medical imaging data. A convolution neural network (CNN) architecture was
designed and trained on the labelled dataset for classification. The CNN model demonstrates
remarkable efficiency in the difference between normal pharynx anatomy and multiple
neoplasm symptom performance evaluation metrics, including accuracy, sensitivity,
specificity, and area under the receiver operating characteristics (ROC) curve, which was
utilized to access the model’s diagnostic capability. So, our motto is to provide promising
accuracy in pharyngeal neoplasm detection. The pharynx serves as a crucial intersection for
both the respiratory and digestive systems, making its health paramount. Pharyngeal
neoplasms, characterized by abnormal tissue growth, pose a significant threat, necessitating
timely and accurate detection for optimal patient outcomes. In this study, we propose a novel
approach utilizing machine learning for automated pharyngeal neoplasm detection through
medical imaging analysis. A convolutional neural network (CNN) architecture was
meticulously designed and trained on a meticulously curated dataset, annotated by expert
clinicians. The CNN model exhibits exceptional performance in discerning between normal
pharyngeal anatomy and various neoplasm presentations. Performance metrics including
accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC)
curve were employed to evaluate the model's diagnostic prowess. Our results underscore the
promising accuracy and efficacy of the CNN-based classification system in pharyngeal
neoplasm detection. By harnessing the power of machine learning, we aim to revolutionize
diagnostic methods, enabling early intervention and improved patient outcomes in the realm of
pharyngeal pathology.