Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed previously. However, there is still no method that solves the entire brain extraction problem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings of existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet was recently proposed and has been widely used for volumetric segmentation in medical images due to its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which is based on a deep learning network, specifically, the convolutional neural network. We evaluated 3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with three existing methods (BSE, ROBEX, and Kleesiek’s method; BSE and ROBEX are two conventional methods, and Kleesiek’s method is based on deep learning). The 3D-UNet outperforms two typical methods and shows comparable results with the specific deep learning-based algorithm, exhibiting a mean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953.

Skull stripping in brain magnetic resonance volume has recently been attracting attention due to an increased demand to develop an efficient, accurate, and general algorithm for diverse datasets of the brain. Accurate skull stripping is a critical step for neuroimaging diagnostic systems because neither the inclusion of non-brain tissues nor removal of brain parts can be corrected in subsequent steps, which results in unfixed error through subsequent analysis. The objective of this review article is to give a comprehensive overview of skull stripping approaches, including recent deep learning-based approaches. In this paper, the current methods of skull stripping have been divided into two distinct groups—conventional or classical approaches, and convolutional neural networks or deep learning approaches. The potentials of several methods are emphasized because they can be applied to standard clinical imaging protocols. Finally, current trends and future developments are addressed giving special attention to recent deep learning algorithms.

PurposeTo evaluate the impact of temporary internal ureteral stents on the surgical outcomes of dismembered pyeloplasty in children.Materials and MethodsThe medical records of 70 children (76 renal units) who underwent dismembered pyeloplasty for ureteropelvic junction (UPJ) obstruction at at Asan Medical Center between January 2005 and December 2010 were retrospectively reviewed. We classified the renal units into the stented group (22 renal units) and the nonstented group (54 renal units). Fifty-four of 70 patients were male and their mean age was 2.2±3.8 years old. The mean follow-up period was 29.6±16.8 months.ResultsSixty-four children had unilateral UPJ obstruction. The mean stent duration was 31.9 days. As shown by evaluation of radiologic images, there were no significant differences between the stented group and the nonstented group during the follow-up period (p>0.05). The mean preoperative and postoperative anteroposterior pelvic diameters (APPDs) of the nonstented group were 31.3 mm and 15.1 mm, respectively (p<0.001). The preoperative and postoperative grades of hydronephrosis were 3.9 and 2.9, respectively (p=0.037). The mean preoperative and postoperative APPDs of the stented group were 36.4 mm and 15.6 mm, respectively (p<0.001). The preoperative and postoperative grades of hydronephrosis were 4 and 3.1, respectively (p<0.001). Repeat obstruction was shown in 4 subjects as a postoperative complication (5.7%). Two children from each group had recurrent UPJ obstruction, with percentages of 3.7% and 9%, respectively (p=0.575).ConclusionsIn a comparison of nonstented and stented groups during pediatric dismembered pyeloplasty for UPJ obstruction, no significant differences were found in the resolution of hydronephrosis or overall postoperative complications.

As failures in rotating machines can have serious implications, the timely detection and diagnosis of faults in these machines is imperative for their smooth and safe operation. Although deep learning offers the advantage of autonomously learning the fault characteristics from the data, the data scarcity from different health states often limits its applicability to only binary classification (healthy or faulty). This work proposes synthetic data augmentation through virtual sensors for the deep learning-based fault diagnosis of a rotating machine with 42 different classes. The original and augmented data were processed in a transfer learning framework and through a deep learning model from scratch. The two-dimensional visualization of the feature space from the original and augmented data showed that the latter’s data clusters are more distinct than the former’s. The proposed data augmentation showed a 6–15% improvement in training accuracy, a 44–49% improvement in validation accuracy, an 86–98% decline in training loss, and a 91–98% decline in validation loss. The improved generalization through data augmentation was verified by a 39–58% improvement in the test accuracy.

No abstract