Redha Ali1,2, Hailong Li1,2,3,4, Jonathan R Dillman1,2,3,5, Mekibib Altaye4,6, Hui Wang1,2,7, Nehal A Parikh4,8,9, Lili He10,11,12,13,14. 1. Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 2. Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., MLC 5033, Cincinnati, OH, 45229, USA. 3. Center for Artificial Intelligence in Imaging Research, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 4. Center for Prevention of Neurodevelopmental Disorders, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 5. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 6. Biostatistics & Epidemiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 7. MR Clinical Science, Philips, Cincinnati, OH, USA. 8. The Perinatal Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 9. Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 10. Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. Lili.He@cchmc.org. 11. Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., MLC 5033, Cincinnati, OH, 45229, USA. Lili.He@cchmc.org. 12. Center for Artificial Intelligence in Imaging Research, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. Lili.He@cchmc.org. 13. Center for Prevention of Neurodevelopmental Disorders, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. Lili.He@cchmc.org. 14. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA. Lili.He@cchmc.org.
Abstract
BACKGROUND: Deep learning has been employed using brain functional connectome data for evaluating the risk of cognitive deficits in very preterm infants. Although promising, training these deep learning models typically requires a large amount of labeled data, and labeled medical data are often very difficult and expensive to obtain. OBJECTIVE: This study aimed to develop a self-training deep neural network (DNN) model for early prediction of cognitive deficits at 2 years of corrected age in very preterm infants (gestational age ≤32 weeks) using both labeled and unlabeled brain functional connectome data. MATERIALS AND METHODS: We collected brain functional connectome data from 343 very preterm infants at a mean (standard deviation) postmenstrual age of 42.7 (2.5) weeks, among whom 103 children had a cognitive assessment at 2 years (i.e. labeled data), and the remaining 240 children had not received 2-year assessments at the time this study was conducted (i.e. unlabeled data). To develop a self-training DNN model, we built an initial student model using labeled brain functional connectome data. Then, we applied the trained model as a teacher model to generate pseudo-labels for unlabeled brain functional connectome data. Next, we combined labeled and pseudo-labeled data to train a new student model. We iterated this procedure to obtain the best student model for the early prediction task in very preterm infants. RESULTS: In our cross-validation experiments, the proposed self-training DNN model achieved an accuracy of 71.0%, a specificity of 71.5%, a sensitivity of 70.4% and an area under the curve of 0.75, significantly outperforming transfer learning models through pre-training approaches. CONCLUSION: We report the first self-training prognostic study in very preterm infants, efficiently utilizing a small amount of labeled data with a larger share of unlabeled data to aid the model training. The proposed technique is expected to facilitate deep learning with insufficient training data.
BACKGROUND: Deep learning has been employed using brain functional connectome data for evaluating the risk of cognitive deficits in very preterm infants. Although promising, training these deep learning models typically requires a large amount of labeled data, and labeled medical data are often very difficult and expensive to obtain. OBJECTIVE: This study aimed to develop a self-training deep neural network (DNN) model for early prediction of cognitive deficits at 2 years of corrected age in very preterm infants (gestational age ≤32 weeks) using both labeled and unlabeled brain functional connectome data. MATERIALS AND METHODS: We collected brain functional connectome data from 343 very preterm infants at a mean (standard deviation) postmenstrual age of 42.7 (2.5) weeks, among whom 103 children had a cognitive assessment at 2 years (i.e. labeled data), and the remaining 240 children had not received 2-year assessments at the time this study was conducted (i.e. unlabeled data). To develop a self-training DNN model, we built an initial student model using labeled brain functional connectome data. Then, we applied the trained model as a teacher model to generate pseudo-labels for unlabeled brain functional connectome data. Next, we combined labeled and pseudo-labeled data to train a new student model. We iterated this procedure to obtain the best student model for the early prediction task in very preterm infants. RESULTS: In our cross-validation experiments, the proposed self-training DNN model achieved an accuracy of 71.0%, a specificity of 71.5%, a sensitivity of 70.4% and an area under the curve of 0.75, significantly outperforming transfer learning models through pre-training approaches. CONCLUSION: We report the first self-training prognostic study in very preterm infants, efficiently utilizing a small amount of labeled data with a larger share of unlabeled data to aid the model training. The proposed technique is expected to facilitate deep learning with insufficient training data.
Authors: Betty R Vohr; Bonnie E Stephens; Rosemary D Higgins; Carla M Bann; Susan R Hintz; Abhik Das; Jamie E Newman; Myriam Peralta-Carcelen; Kimberly Yolton; Anna M Dusick; Patricia W Evans; Ricki F Goldstein; Richard A Ehrenkranz; Athina Pappas; Ira Adams-Chapman; Deanne E Wilson-Costello; Charles R Bauer; Anna Bodnar; Roy J Heyne; Yvonne E Vaucher; Robert G Dillard; Michael J Acarregui; Elisabeth C McGowan; Gary J Myers; Janell Fuller Journal: J Pediatr Date: 2012-03-14 Impact factor: 4.406
Authors: R Devon Hjelm; Vince D Calhoun; Ruslan Salakhutdinov; Elena A Allen; Tulay Adali; Sergey M Plis Journal: Neuroimage Date: 2014-03-28 Impact factor: 6.556
Authors: A Di Martino; C-G Yan; Q Li; E Denio; F X Castellanos; K Alaerts; J S Anderson; M Assaf; S Y Bookheimer; M Dapretto; B Deen; S Delmonte; I Dinstein; B Ertl-Wagner; D A Fair; L Gallagher; D P Kennedy; C L Keown; C Keysers; J E Lainhart; C Lord; B Luna; V Menon; N J Minshew; C S Monk; S Mueller; R-A Müller; M B Nebel; J T Nigg; K O'Hearn; K A Pelphrey; S J Peltier; J D Rudie; S Sunaert; M Thioux; J M Tyszka; L Q Uddin; J S Verhoeven; N Wenderoth; J L Wiggins; S H Mostofsky; M P Milham Journal: Mol Psychiatry Date: 2013-06-18 Impact factor: 15.992