151. Open-source, machine and deep learning-based automated algorithm for gestational age estimation through smartphone lens imaging
- Author
-
Dibyendu Mukherjee, Leyuan Fang, Stephanie J Jaffe, Arjun D. Desai, Jennifer B. Griffin, Sina Farsiu, Andrew Ho-Fai Yeung, and Chunlei Peng
- Subjects
Artificial neural network ,business.industry ,Computer science ,Image quality ,Machine vision ,Deep learning ,Gestational age ,Image processing ,01 natural sciences ,Article ,Atomic and Molecular Physics, and Optics ,010309 optics ,Support vector machine ,03 medical and health sciences ,0302 clinical medicine ,Software ,0103 physical sciences ,030221 ophthalmology & optometry ,Computer vision ,Artificial intelligence ,business ,Biotechnology - Abstract
Gestational age estimation at time of birth is critical for determining the degree of prematurity of the infant and for administering appropriate postnatal treatment. We present a fully automated algorithm for estimating gestational age of premature infants through smartphone lens imaging of the anterior lens capsule vasculature (ALCV). Our algorithm uses a fully convolutional network and blind image quality analyzers to segment usable anterior capsule regions. Then, it extracts ALCV features using a residual neural network architecture and trains on these features using a support vector machine-based classifier. The classification algorithm is validated using leave-one-out cross-validation on videos captured from 124 neonates. The algorithm is expected to be an influential tool for remote and point-of-care gestational age estimation of premature neonates in low-income countries. To this end, we have made the software open source.
- Published
- 2018