.jpg)
15.Role of Machine Learning and Computed Tomography in Thoracic Radiology
Nosheen Noor1, Abdul Baseer2 and Muhammad Hammad Khan3
ABSTRACT
Objective: The objective of the study is to find the role of machine learning and computed tomography in thoracic radiology.
Study Design: Cross sectional study
Place and Duration of Study: This study was conducted at the Thoracic Surgery Department and the Radiology Department at MTI-LRH in Peshawar, Pakistan from March 2022 to April 2023.
Materials and Methods: A total of 145 patients were included in the study. These patients were selected based on their medical conditions and the machine learning ability of thoracic radiological data. Patient data, including thoracic radiographic images and relevant clinical information, were collected from the hospital's electronic medical records system.
Results: Data was collected from 145 patients of both genders. There were 85 males and 60 female patients. The machine learning models exhibited a high sensitivity and specificity in detecting pulmonary nodules on chest X-rays and CT scans. The algorithms demonstrated an accuracy rate of over 90% in identifying nodules of varying sizes, including subtle and ground-glass opacities that are often challenging to detect even for experienced radiologists. The machine learning-powered algorithms demonstrated proficiency in distinguishing between benign and malignant lung lesions.
Conclusion: It is concluded that machine learning and deep learning have shown promise in thoracic radiology, augmenting radiologists' capabilities and leading to more accurate diagnoses. Continued research and responsible implementation are essential to unlock the full potential of machine learning in transforming thoracic imaging and patient care.
Key Words: Machine learning, patients, model, computed tomography, thoracic, surgery, lung