AI-Driven Automated Lung Sizing from Chest Radiographs

• Published in: American journal of transplantation
• Main Authors: Ismail, Mostafa K, Araki, Tetsuro, Gefter, Warren B, Suzuki, Yoshikazu, Raevsky, Allie, Saleh, Aya, Yusuf, Sophia, Marquis, Abigail, Alcudia, Alyster, Duncan, Ian, Schaubel, Douglas E, Cantu, Edward, Rizi, Rahim
• Format: Journal Article
• Language: English
• Published: United States 23.08.2024
• Subjects: Artificial Intelligence; Lung Transplant; Donor Assessment
• ISSN: 1600-6143

Lung size measurements play an important role in transplantation, as optimal donor-recipient size matching is necessary to ensure the best possible outcome. While several strategies for size matching are currently used, all have limitations, and none has proven superior. In this pilot study, we leveraged deep learning and computer vision to develop an automated system for generating standardized lung size measurements using portable chest radiographs to improve accuracy, reduce variability, and streamline donor/recipient matching. We developed a two-step framework involving lung mask extraction from chest radiographs followed by feature points detection to generate six distinct lung height and width measurements, which we validated against measurements reported by two radiologists for 50 lung transplant recipients. Our system demonstrated <2.5% error (< 7 mm) with robust inter- and intra-rater agreement compared to expert radiologist review. This is especially promising given that the radiographs used in this study were purposely chosen to include images with technical challenges such as consolidations, effusions, and patient rotation. While validation in a larger cohort is necessary, this study highlights AI's potential to both provide reproducible lung size assessment in real patients and enable studies on the effect of lung size matching on transplant outcomes in large datasets.