arXiv 2507.122692025-10-10cs.CVcs.AIcs.LG

站点级微调与渐进式层冻结：面向极早产儿第1天胸部X光片支气管肺发育不良稳健预测

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

Saarland University（萨尔兰大学）；University Hospital of Saarland（萨尔兰大学医院）；Clinical Centre Karlsruhe（卡尔斯鲁厄临床中心）；Helmholtz Institute for Pharmaceutical Research Saarland（亥姆霍兹萨尔兰药物研究所）；University Hospital of Augsburg（奥格斯堡大学医院）

Sybelle Goedicke-Fritz, Michelle Bous, Annika Engel, Matthias Flotho, Pascal Hirsch, Hannah Wittig, Dino Milanovic, Dominik Mohr, Mathias Kaspar, Sogand Nemat, … 展开作者

Sybelle Goedicke-Fritz, Michelle Bous, Annika Engel, Matthias Flotho, Pascal Hirsch, Hannah Wittig, Dino Milanovic, Dominik Mohr, Mathias Kaspar, Sogand Nemat, Dorothea Kerner, Arno Bücker, Andreas Keller, Sascha Meyer, Michael Zemlin, Philipp Flotho

备注：: S.G.-F., M.B., and A.E. contributed equally to this work and share first authorship. M.Z. and P.F. contributed equally to this work and share senior authorship

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究提出基于域内预训练ResNet-50、渐进式层冻结和线性探针的深度学习方法，利用极早产儿第1天胸部X光片预测中重度支气管肺发育不良，AUROC达0.78，验证了特定领域预训练的关键作用。

摘要：

支气管肺发育不良（BPD）是一种慢性肺部疾病，影响35%的极低出生体重婴儿。该病以校正胎龄36周时的氧依赖为定义，导致终身呼吸系统并发症。然而，预防性干预措施存在严重风险，包括神经发育损害、呼吸机相关性肺损伤和全身性并发症。因此，早期BPD预后及结局预测对于避免低风险婴儿接受不必要的毒性治疗至关重要。极早产儿入院X光片通常在出生后24小时内常规获取，可作为非侵入性预后工具。在本研究中，我们开发并探究了一种深度学习方法，使用来自163名极低出生体重婴儿（胎龄≤32周，体重401-999克）出生后24小时内获取的胸部X光片。我们对一个专门在成人胸部X光片上预训练的ResNet-50模型进行微调，采用渐进式层冻结与判别性学习率以防止过拟合，并评估了CutMix增强和线性探针。对于中/重度BPD结局预测，我们采用渐进式冻结、线性探针和CutMix的最佳模型实现了AUROC为0.78±0.10，平衡准确率为0.69±0.10，F1分数为0.67±0.11。域内预训练显著优于ImageNet初始化（p=0.031），证实了特定领域预训练对BPD结局预测的重要性。常规IRDS分级显示有限的预后价值（AUROC 0.57±0.11），确认了学习型标记的必要性。我们的方法表明，特定领域预训练能够从常规第1天X光片中实现准确的BPD预测。通过渐进式冻结和线性探针，该方法在计算上仍适用于站点级实施和未来的联邦学习部署。

英文摘要：

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 ($\leq$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 $\pm$ 0.10, balanced accuracy of 0.69 $\pm$ 0.10, and an F1-score of 0.67 $\pm$ 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 $\pm$ 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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。