Decision Support System for Lung Cancer Using PET/CT and Microscopic Images

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Lung cancer is a leading global cancer, necessitating accurate diagnostic methods.
• Current diagnostic workflows involve multiple expert consultations and time-intensive image analysis.
• Positron Emission Tomography/Computed Tomography (PET/CT) and pathological examinations are crucial for lung cancer diagnosis.

Purpose of the Study:

• To develop an automated decision support system for lung cancer diagnosis.
• To enhance the efficiency and accuracy of image diagnosis in lung cancer.
• To integrate PET/CT and microscopic image analysis for improved treatment decisions.

Main Methods:

• Development of a decision support system leveraging deep learning algorithms.
• Application of radiomic techniques for feature extraction from medical images.
• Integration of data from PET/CT scans and microscopic pathological images.

Main Results:

• The proposed system aims to reduce the time and effort required for image diagnosis.
• The system is designed to assist experts in distinguishing lung lesions and guiding treatment.
• Demonstration of a novel approach combining deep learning and radiomics for lung cancer diagnostics.

Conclusions:

• The developed system offers a promising approach to streamline lung cancer diagnosis.
• This AI-driven tool can support clinical decision-making for lung cancer patients.
• Further integration of advanced imaging and AI techniques can improve patient outcomes.