Beyond Accuracy: Quantifying Pulmonary Attribution in Anatomy-Guided Chest X-Ray Classification Under Domain Shift

Deep-learning models can achieve strong chest X-ray (CXR) classification performance without establishing whether their predictions predominantly rely on pulmonary image content. This study evaluates pulmonary attribution containment as an anatomy-related reliability property distinct from diagnostic performance. We propose DBCA-SegNet-MGAP, a multi-task anatomy-guided CNN-Transformer framework that combines complementary feature representations through bidirectional cross-backbone attention, predicts a soft lung mask, and incorporates this anatomical prior directly into classification through Mask-Guided Adaptive Global Average Pooling (MGAP). Pulmonary attribution containment is quantified using the Anatomical Local Energy Ratio (ALR) and high-intensity cumulative ALR ([email protected]). Experiments were repeated across three training seeds using the COVID-19 Radiography Database for four-class internal testing and a locked Shenzhen-to-Montgomery protocol for zero-shot external tuberculosis testing. On COVID-19, the proposed model achieved a weighted F1 of 0.9615 ± 0.0015 and macro ROC-AUC of 0.9906 ± 0.0007. In an architecture-matched dual-bridge comparison, replacing conventional GAP with MGAP increased ALR from 0.3878 ± 0.0098 to 0.7086 ± 0.0104 and [email protected] from 0.5265 ± 0.0101 to 0.9905 ± 0.0018, while weighted F1 remained essentially unchanged (0.9618 ± 0.0015 vs. 0.9615 ± 0.0015). Under locked external transfer to Montgomery, ROC-AUC remained 0.9080 ± 0.0043 and pulmonary ALR remained 0.6466 ± 0.0081, whereas weighted F1 decreased to 0.7528 ± 0.0080 and ECE increased to 0.1683 ± 0.0055. These findings show that diagnostic discrimination, calibration, and pulmonary attribution containment are distinct model properties and support their joint evaluation under internal testing and external domain shift.