The disparity in access to machine learning tools for medical imaging across different regions significantly limits the potential for universal healthcare innovation, particularly in remote areas. Our research addresses this issue by implementing Neural Cellular Automata (NCA) training directly on smartphones for accessible X-ray lung segmentation. We confirm the practicality and feasibility of deploying and training these advanced models on five Android devices, improving medical diagnostics accessibility and bridging the tech divide to extend machine learning benefits in medical imaging to low- and middle-income countries (LMICs). We further enhance this approach with an unsupervised adaptation method using the novel Variance-Weighted Segmentation Loss (VWSL), which efficiently learns from unlabeled data by minimizing the variance from multiple NCA predictions. This strategy notably improves model adaptability and performance across diverse medical imaging contexts without the need for extensive computational resources or labeled datasets, effectively lowering the participation threshold. Our methodology, tested on three multisite X-ray datasets -- Padchest, ChestX-ray8, and MIMIC-III -- demonstrates improvements in segmentation Dice accuracy by 0.7 to 2.8%, compared to the classic Med-NCA. Additionally, in extreme cases where no digital copy is available and images must be captured by a phone from an X-ray lightbox or monitor, VWSL enhances Dice accuracy by 5-20%, demonstrating the method's robustness even with suboptimal image sources.

翻译：不同地区在获取医学影像机器学习工具方面的显著差异，严重限制了全球医疗保健创新的潜力，尤其是在偏远地区。我们的研究通过直接在智能手机上实现神经细胞自动机（NCA）训练，用于可及的X射线肺部图像分割，以解决这一问题。我们在五款安卓设备上验证了部署和训练这些先进模型的实用性和可行性，从而提升了医疗诊断的可及性，并弥合了技术鸿沟，将医学影像机器学习的益处扩展到中低收入国家（LMICs）。我们进一步采用了一种无监督适应方法，利用新颖的方差加权分割损失（VWSL）来增强这一方法，该方法通过最小化多个NCA预测的方差，有效地从未标记数据中学习。这一策略显著提升了模型在不同医学影像场景下的适应性和性能，而无需大量的计算资源或标记数据集，从而有效降低了参与门槛。我们的方法在三个多中心X射线数据集——Padchest、ChestX-ray8和MIMIC-III——上进行了测试，结果显示其分割Dice准确率相较于经典的Med-NCA提升了0.7%至2.8%。此外，在极端情况下，当没有数字副本可用，必须通过手机从X射线灯箱或显示器上拍摄图像时，VWSL将Dice准确率提升了5-20%，证明了该方法即使在图像来源不理想的情况下也具有鲁棒性。