Where Position Matters-Deep-Learning-Driven Normalization and Coregistration of Computed Tomography in the Postoperative Analysis of Deep Brain Stimulation

INTRODUCTION

Recent developments in the postoperative evaluation of deep brain stimulation surgery on the group level warrant the detection of achieved electrode positions based on postoperative imaging. Computed tomography (CT) is a frequently used imaging modality, but because of its idiosyncrasies (high spatial accuracy at low soft tissue resolution), it has not been sufficient for the parallel determination of electrode position and details of the surrounding brain anatomy (nuclei). The common solution is rigid fusion of CT images and magnetic resonance (MR) images, which have much better soft tissue contrast and allow accurate normalization into template spaces. Here, we explored a deep-learning approach to directly relate positions (usually the lead position) in postoperative CT images to the native anatomy of the midbrain and group space.

MATERIALS AND METHODS

Deep learning is used to create derived tissue contrasts (white matter, gray matter, cerebrospinal fluid, brainstem nuclei) based on the CT image; that is, a convolution neural network (CNN) takes solely the raw CT image as input and outputs several tissue probability maps. The ground truth is based on coregistrations with MR contrasts. The tissue probability maps are then used to either rigidly coregister or normalize the CT image in a deformable way to group space. The CNN was trained in 220 patients and tested in a set of 80 patients.

RESULTS

Rigorous validation of such an approach is difficult because of the lack of ground truth. We examined the agreements between the classical and proposed approaches and considered the spread of implantation locations across a group of identically implanted subjects, which serves as an indicator of the accuracy of the lead localization procedure. The proposed procedure agrees well with current magnetic resonance imaging-based techniques, and the spread is comparable or even lower.

CONCLUSIONS

Postoperative CT imaging alone is sufficient for accurate localization of the midbrain nuclei and normalization to the group space. In the context of group analysis, it seems sufficient to have a single postoperative CT image of good quality for inclusion. The proposed approach will allow researchers and clinicians to include cases that were not previously suitable for analysis.

Measurement of Lead Localization Accuracy Based on Magnetic Resonance Imaging

Post-implantation localization of deep brain stimulation (DBS) lead based on a magnetic resonance (MR) image is widely used. Existing localization methods use artifact center method or template registration method, which may lead to a considerable deviation of > 2 mm, and result in severe side effects or even surgical failure. Accurate measurement of lead position can instantly inform surgeons of the imprecise implantation. This study aimed to identify the influencing factors in DBS lead post-implantation localization approach, analyze their influence, and describe a localization approach that uses the individual template method to reduce the deviation. We verified that reconstructing direction should be parallel or perpendicular to lead direction, instead of the magnetic field. Besides, we used simplified relationship between magnetic field angle and deviation error to correct the localization results. The mean localization error can be reduced after correction and favors the feasibility of direct localization of DBS lead using MR images. We also discussed influence of in vivo noise on localization frequency and the possibility of using only MR images to localize the contacts.

The effect of pre-incubation of Allium cepa L. roots in the ATH-rich extract on Pb uptake and localization

The positive influence of anthocyanin (ATH) on toxic metal-treated plant material is well documented; however, it is still not explained if it is caused by changes in element absorption and distribution. Therefore, detailed analysis of the effect of the ATH-rich extract from red cabbage leaves on Pb uptake and localization at morphological, anatomical and ultrastructural level was the goal of this study. Two-day-old adventitious roots of Allium cepa L. (cv. Polanowska) were treated for 2 h with the aqueous solution of Pb(NO3)2 at the concentration of 100 μM with or without preliminary incubation in the anthocyanin-rich extract from Brassica oleracea L. var. capitata rubra leaves (250 μM, 3 h). The red cabbage extract did not change the total Pb uptake but it enhanced the translocation of accumulated metal from roots to shoots. Within the pretreated roots, more Pb was deposited in their basal part and definitely smaller amount of the metal was bound in the apoplast of the outer layers of cortex cells. The ultrastructural analysis (transmission electron microscopy and X-ray microanalysis) revealed that the ATH-rich extract lowered the number of Pb deposits in intracellular spaces, cell wall and cytoplasm of root meristematic cells as well as in such organelles important to cell metabolism as mitochondria, plastids and nucleus. The Pb deposits were preferably localised in those vacuoles where ATH also occurred. This sequestration of Pb in vacuoles is probably responsible for reduction of metal cytotoxicity and consequently could lead to better plant growth.

Lead accumulation and its translocation barriers in roots of Allium cepa L.-autoradiographic and ultrastructural studies

Lead migrating through the tissues of Allium cepa L. was found, by electron microscopy, autoradiography and other methods, to encounter at least three barriers to penetration. The layers of protoderm and hypodermic meristematic cells in the root meristematic zone and the layer of endodermis in the mature root zone were barriers to apoplastic transport. The central zone was a barrier to apoplastic and symplastic transport. It comprises the quiescent centre in the root meristem and the central part of the root cap. The cells of the deepest ground meristematic tissue layers seemed to act as a barrier, which keeps lead away from the procambium. Lead accumulated in roots but it was not uniformly distributed between their various tissues. The largest amount of lead accumulated both in ground meristematic and cortex tissues.