Novel Lobe-based Transformer model (LobTe) to predict emphysema progression in Alpha-1 Antitrypsin Deficiency

• Published in: Computers in biology and medicine Vol. 185; p. 109500
• Main Authors: Curiale, Ariel Hernán, San José Estépar, Raúl
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.02.2025; Elsevier Limited
• Subjects: A1-antitrypsin; Aged; alpha 1-Antitrypsin Deficiency - complications; alpha 1-Antitrypsin Deficiency - diagnostic imaging; Alpha-1 Antitrypsin Deficiency; Attention mechanisms; Computed tomography; COPD; Correlation coefficients; Deep learning; Disease Progression; Emphysema; Emphysema progression; Error analysis; Female; Genetic disorders; Heterogeneity; Humans; Internal Medicine; Lung - diagnostic imaging; Lungs; Male; Middle Aged; Other; Prognostic markers; Protein deficiency; Pulmonary Emphysema - diagnostic imaging; Root-mean-square errors; Smoking; Tomography, X-Ray Computed; Transformers; Prognostic markers; Deep learning; CT; Attention mechanisms; Alpha-1 Antitrypsin Deficiency; Emphysema progression; Transformers; COPD
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109500

Emphysema, marked by irreversible lung tissue destruction, poses challenges in progression prediction due to its heterogeneity. Early detection is particularly critical for patients with Alpha-1 Antitrypsin Deficiency (AATD), a genetic disorder reducing ATT protein levels. Heterozygous carriers (PiMS and PiMZ) have variable AAT levels thus complicating their prognosis. This study introduces a novel prognostic model, the Lobe-based Transformer encoder (LobTe), designed to predict the annual change in lung density (ΔALD [g/L-yr]) using CT scans. Utilizing a global self-attention mechanism, LobTe specifically analyzes lobar tissue destruction to forecast disease progression. In parallel, we developed and compared a second model utilizing an LSTM architecture that implements a local subject-specific attention mechanism. Our methodology was validated on a cohort of 2,019 participants from the COPDGene study. The LobTe model demonstrated a small root mean squared error (RMSE=1.73 g/L-yr) and a notable correlation coefficient (ρ=0.61), explaining over 35% of the variability in ΔALD (R2= 0.36). Notably, it achieved a higher correlation coefficient of 0.68 for PiMZ heterozygous carriers, indicating its effectiveness in detecting early emphysema progression among smokers with mild to moderate AAT deficiency. The presented models could serve as a tool for monitoring disease progression and informing treatment strategies in carriers and subjects with AATD. Our code is available at github.com/acil-bwh/LobTe. •Lobe-based Transformer encoder (LobTe) to predict the annual ΔALD [g/L] on CT scans.•For comparative purposes, a second prognostic model (LSTM) was proposed.•Evaluation of COPDGene subjects (n=2,019) shows our model detects AATD risk for emphysema early.