Hybrid Open Access - OA-Veröffentlichung in einer Subskriptionszeitschrift/-medium
Refine
Year of publication
- 2020 (2) (remove)
Document Type
- Article (2) (remove)
Language
- English (2)
Has Fulltext
- no (2)
Is part of the Bibliography
- no (2)
Keywords
- ANTERIOR CINGULATE CORTEX (1)
- Adenocarcinom (1)
- Adenocarcinoma (1)
- Barrett's esophagus (1)
- CONNECTIVITY (1)
- Depression (1)
- Diagnose (1)
- FRONTAL-CORTEX (1)
- Generative adversarial networks (1)
- Machine learning (1)
Institute
- Regensburg Center of Health Sciences and Technology - RCHST (2) (remove)
Begutachtungsstatus
- peer-reviewed (2)
Resting motor threshold and magnetic field output of the figure-of-8 and the double-cone coil
(2020)
The use of the double-cone (DC) coil in transcranial magnetic stimulation (TMS) is promoted with the notion that the DC coil enables stimulation of deeper brain areas in contrast to conventional figure-of-8 (Fo8) coils. However, systematic comparisons of these two coil types with respect to the spatial distribution of the magnetic field output and also to the induced activity in superficial and deeper brain areas are limited. Resting motor thresholds of the left and right first dorsal interosseous (FDI) and tibialis anterior (TA) were determined with the DC and the Fo8 coil in 17 healthy subjects. Coils were orientated over the corresponding motor area in an angle of 45 degrees for the hand area with the handle pointing in posterior direction and in medio-lateral direction for the leg area. Physical measurements were done with an automatic gantry table using a Gaussmeter. Resting motor threshold was higher for the leg area in contrast to the hand area and for the Fo8 in contrast to the DC coil. Muscle by coil interaction was also significant providing higher differences between leg and hand area for the Fo8 (about 27%) in contrast to the DC coil (about 15%). Magnetic field strength was higher for the DC coil in contrast to the Fo8 coil. The DC coil produces a higher magnetic field with higher depth of penetration than the figure of eight coil.
Barrett's esophagus figured a swift rise in the number of cases in the past years. Although traditional diagnosis methods offered a vital role in early-stage treatment, they are generally time- and resource-consuming. In this context, computer-aided approaches for automatic diagnosis emerged in the literature since early detection is intrinsically related to remission probabilities. However, they still suffer from drawbacks because of the lack of available data for machine learning purposes, thus implying reduced recognition rates. This work introduces Generative Adversarial Networks to generate high-quality endoscopic images, thereby identifying Barrett's esophagus and adenocarcinoma more precisely. Further, Convolution Neural Networks are used for feature extraction and classification purposes. The proposed approach is validated over two datasets of endoscopic images, with the experiments conducted over the full and patch-split images. The application of Deep Convolutional Generative Adversarial Networks for the data augmentation step and LeNet-5 and AlexNet for the classification step allowed us to validate the proposed methodology over an extensive set of datasets (based on original and augmented sets), reaching results of 90% of accuracy for the patch-based approach and 85% for the image-based approach. Both results are based on augmented datasets and are statistically different from the ones obtained in the original datasets of the same kind. Moreover, the impact of data augmentation was evaluated in the context of image description and classification, and the results obtained using synthetic images outperformed the ones over the original datasets, as well as other recent approaches from the literature. Such results suggest promising insights related to the importance of proper data for the accurate classification concerning computer-assisted Barrett's esophagus and adenocarcinoma detection.