# Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants

arXiv: https://arxiv.org/abs/2507.12269 · HTML: https://mlsanity.com/paper/2507.12269/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 85 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [TorchXRayVision: A library of chest X-ray datasets and models](https://mlsanity.com/paper/2111.00595/) (2021)
- [On the limits of cross-domain generalization in automated X-ray prediction](https://mlsanity.com/paper/2002.02497/) (2020)
- [CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation](https://mlsanity.com/paper/2101.06871/) (2021)
- [OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.18550/) (2024)
- [Guiding The Last Layer in Federated Learning with Pre-Trained Models](https://mlsanity.com/paper/2306.03937/) (2023)
- [Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing](https://mlsanity.com/paper/2408.09101/) (2024)
- [T-FAKE: Synthesizing Thermal Images for Facial Landmarking](https://mlsanity.com/paper/2408.15127/) (2024)
- [CycDA: Unsupervised Cycle Domain Adaptation from Image to Video](https://mlsanity.com/paper/2203.16244/) (2022)
- [X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization](https://mlsanity.com/paper/2403.19811/) (2024)
- [In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval](https://mlsanity.com/paper/2309.08928/) (2023)
- [Faster Federated Learning with Decaying Number of Local SGD Steps](https://mlsanity.com/paper/2305.09628/) (2023)

## Abstract (arXiv)

Bronchopulmonary dysplasia (BPD) is a chronic lung disease affecting 35% of extremely low birth weight infants. Defined by oxygen dependence at 36 weeks postmenstrual age, it causes lifelong respiratory complications. However, preventive interventions carry severe risks, including neurodevelopmental impairment, ventilator-induced lung injury, and systemic complications. Therefore, early BPD prognosis and prediction of BPD outcome is crucial to avoid unnecessary toxicity in low risk infants. Admission radiographs of extremely preterm infants are routinely acquired within 24h of life and could serve as a non-invasive prognostic tool. In this work, we developed and investigated a deep learning approach using chest X-rays from 163 extremely low-birth-weight infants (≤32 weeks gestation, 401-999g) obtained within 24 hours of birth. We fine-tuned a ResNet-50 pretrained specifically on adult chest radiographs, employing progressive layer freezing with discriminative learning rates to prevent overfitting and evaluated a CutMix augmentation and linear probing. For moderate/severe BPD outcome prediction, our best performing model with progressive freezing, linear probing and CutMix achieved an AUROC of 0.78 ± 0.10, balanced accuracy of 0.69 ± 0.10, and an F1-score of 0.67 ± 0.11. In-domain pre-training significantly outperformed ImageNet initialization (p = 0.031) which confirms domain-specific pretraining to be important for BPD outcome prediction. Routine IRDS grades showed limited prognostic value (AUROC 0.57 ± 0.11), confirming the need of learned markers. Our approach demonstrates that domain-specific pretraining enables accurate BPD prediction from routine day-1 radiographs. Through progressive freezing and linear probing, the method remains computationally feasible for site-level implementation and future federated learning deployments.