NeoJaundice-AI: 基于智能手机的新生儿黄疸检测，采用双输入深度学习与合成增强
NeoJaundice-AI: Smartphone-Based Neonatal Jaundice Detection Using Dual-Input Deep Learning and Synthetic Augmentation
AI总结：
提出NeoJaundice-AI系统，通过双分支EfficientNet-B0处理皮肤和巩膜图像，融合手工YCbCr颜色特征，实现四类严重度分类和胆红素回归，采用合成黄疸生成和肤色归一化，在印度新生儿数据集上达到91.8%准确率。
摘要：
新生儿黄疸（高胆红素血症）是全球最常见的新生儿疾病之一，仅印度每年就有约1500万例。早期检测至关重要，但标准诊断需要血液检测，这在实验室设施有限的农村诊所往往不可行。本文提出NeoJaundice-AI，一种基于智能手机的筛查系统，通过拍摄婴儿皮肤和巩膜（眼白）的照片，在三秒内估计黄疸严重程度并预测血清胆红素水平，无需互联网连接。该系统基于双分支EfficientNet-B0架构，独立处理皮肤和巩膜图像。深度特征与手工制作的YCbCr颜色统计融合，共同执行四类严重度分类和连续胆红素回归。一个关键贡献是合成黄疸生成方法，通过控制正常新生儿皮肤图像的YCbCr通道修改来模拟胆红素引起的黄染。该方法解决了数据稀缺问题，特别是针对严重黄疸病例和较深的印度肤色（Fitzpatrick IV至VI型）。此外，肤色归一化模块提高了跨不同新生儿肤色的预测一致性。实验结果表明，总体分类准确率为91.8%，临床灵敏度为93.5%，胆红素平均绝对误差为1.4 mg/dL。经过INT8量化和ONNX转换后，模型大小减小至8.3 MB，同时在标准Android设备上保持低于三秒的推理时间。据我们所知，这是首个针对印度的新生儿黄疸AI系统，在多模态图像融合、肤色适应、合成数据增强和完全离线移动部署方面集成了单一框架。
英文摘要：
Neonatal jaundice (hyperbilirubinemia) is one of the most common conditions affecting newborns worldwide, with India alone recording roughly 15 million cases per year. Early detection is critical, yet standard diagnosis requires blood tests that are often impractical in rural clinics where laboratory facilities are limited. This paper presents NeoJaundice-AI, a smartphone-based screening system that uses photographs of a baby's skin and sclera (eye white) to estimate jaundice severity and predict serum bilirubin levels in under three seconds without requiring internet connectivity. The proposed system is built on a dual-branch EfficientNet-B0 architecture that independently processes skin and sclera images. Deep features are fused with handcrafted YCbCr color statistics to jointly perform four-class severity classification and continuous bilirubin regression. A key contribution is a synthetic jaundice generation method that simulates bilirubin-induced yellowing through controlled YCbCr channel modifications on normal neonatal skin images. This approach addresses data scarcity, particularly for severe jaundice cases and darker Indian skin tones (Fitzpatrick Types IV to VI). In addition, a skin-tone normalization module improves prediction consistency across diverse neonatal complexions. Experimental results demonstrate an overall classification accuracy of 91.8 percent, a clinical sensitivity of 93.5 percent, and a bilirubin mean absolute error of 1.4 mg/dL. After INT8 quantization and ONNX conversion, the model size is reduced to 8.3 MB while maintaining inference times below three seconds on standard Android devices. To the best of our knowledge, this is the first India-focused neonatal jaundice AI system that combines multimodal image fusion, skin-tone adaptation, synthetic data augmentation, and fully offline mobile deployment within a single framework.
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。
