State-of-the-art video deblurring methods cannot handle blurry videos recorded in dynamic scenes since they are built under a strong assumption that the captured scenes are static. Contrary to the existing methods, we propose a new video deblurring algorithm that can deal with general blurs inherent in dynamic scenes. To handle general and locally varying blurs caused by various sources, such as moving objects, camera shake, depth variation, and defocus, we estimate pixel-wise varying non-uniform blur kernels. We infer bidirectional optical flows to handle motion blurs, and also estimate Gaussian blur maps to remove optical blur from defocus. Therefore, we propose a single energy model that jointly estimates optical flows, defocus blur maps and latent frames. We also provide a framework and efficient solvers to minimize the proposed energy model. By optimizing the energy model, we achieve significant improvements in removing general blurs, estimating optical flows, and extending depth-of-field in blurry frames. Moreover, in this work, to evaluate the performance of non-uniform deblurring methods objectively, we have constructed a new realistic dataset with ground truths. In addition, extensive experimental results on publicly available challenging videos demonstrate that the proposed method produces qualitatively superior performance than the state-of-the-art methods which often fail in either deblurring or optical flow estimation.

The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnostic tympanic membranes images were appropriately labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), or cholesteatoma and were used for training. We developed the “ResNet18 + Shuffle” network and validated the model performance. Seventy-one representative cases were selected to test the final accuracy of the network and resident physicians. We asked 10 resident physicians to make diagnoses from tympanic membrane images with and without the help of the machine learning network, and the change of the diagnostic performance of resident physicians with the aid of the answers from the machine learning network was assessed. The devised network showed a highest accuracy of 97.18%. A five-fold validation showed that the network successfully diagnosed ear diseases with an accuracy greater than 93%. All resident physicians were able to diagnose middle ear diseases more accurately with the help of the machine learning network. The increase in diagnostic accuracy was up to 18% (1.4% to 18.4%). The machine learning network successfully classified middle ear diseases and was assistive to clinicians in the interpretation of tympanic membrane images.

Acute thoracic aortic dissection is a life-threatening disease, in which blood leaking from the damaged inner layer of the aorta causes dissection between the intimal and adventitial layers. The diagnosis of this disease is challenging. Chest x-rays are usually performed for initial screening or diagnosis, but the diagnostic accuracy of this method is not high. Recently, deep learning has been successfully applied in multiple medical image analysis tasks. In this paper, we attempt to increase the accuracy of diagnosis of acute thoracic aortic dissection based on chest x-rays by applying deep learning techniques. In aggregate, 3,331 images, comprising 716 positive images and 2615 negative images, were collected from 3,331 patients. Residual neural network 18 was used to detect acute thoracic aortic dissection. The diagnostic accuracy of the ResNet18 was observed to be 90.20% with a precision of 75.00%, recall of 94.44%, and F1-score of 83.61%. Further research is required to improve diagnostic accuracy based on aorta segmentation.

Early prediction of surgical necrotizing enterocolitis (sNEC) in preterm infants is important. However, owing to the complexity of the disease, identifying infants with NEC at a high risk for surgical intervention is difficult. We developed a machine learning (ML) algorithm to predict sNEC using perinatal factors obtained from the national cohort registry of very low birth weight (VLBW) infants. Data were collected from the medical records of 16,385 VLBW infants registered in the Korean Neonatal Network (KNN). Infants who underwent surgical intervention were identified with sNEC, and infants who received medical treatment, with medical NEC (mNEC). We used 38 variables, including maternal, prenatal, and postnatal factors that were obtained within 1 week of birth, for training. A total of 1085 patients had NEC (654 with sNEC and 431 with mNEC). VLBW infants showed a higher incidence of sNEC at a lower gestational age (GA) (p < 0.001). Our proposed ensemble model showed an area under the receiver operating characteristic curve of 0.721 for sNEC prediction.    Conclusion: Proposed ensemble model may help predict which infants with NEC are likely to develop sNEC. Through early prediction and prompt intervention, prognosis of sNEC may be improved. What is Known:• Machine learning (ML)-based techniques have been employed in NEC research for prediction, diagnosis, and prognosis, with promising outcomes.• While most studies have utilized abdominal radiographs and clinical manifestations of NEC as data sources, and have demonstrated their usefulness, they may prove weak in terms of early prediction. What is New:• We analyzed the perinatal factors of VLBW infants acquired within 7 days of birth and used ML-based analysis to identify which infants with NEC are vulnerable to clinical deterioration and at high risk for surgical intervention using nationwide cohort data.