André Wirries

Purpose: The aim of our study is to compare anterior and posterior corrections of thoracic (Lenke I) and lumbar (Lenke V) curves when modern posterior pedicle screw systems with vertebral derotation techniques are used. Curves that could not be corrected with both systems were excluded. Methods: A thoracic group (N = 56) of Lenke I AIS patients (18 anterior and 38 posterior) and a lumbar group (N = 42) of Lenke V patients (14 anterior and 28 posterior) with similar curves < 65° were identified. Results: Thoracic group The mean postoperative correction (POC) was 68 ± 13.4% in the anterior and 72 ± 10.5% in the posterior group. The postoperative change in thoracic kyphosis was +4° and +5° respectively. The median length of fusion was eight segments in the posterior and seven segments in the anterior groups. In 89% the LIV was EV or shorter in the anterior, and in 71% of the posterior corrections. Lumbar group The mean POC was 75 ± 18.3% (anterior) and 72 ± 8.5% (posterior). The postoperative gain in lumbar lordosis was 0.8° (anterior) and 4° (posterior). The median length of fusion was five segments in both groups and there was no difference in relation of the LIV to the EV. Conclusion: With modern implants and derotation techniques, the posterior approach can achieve similar coronal correction, apical derotation and thoracic kyphosis with similar length of fusion and better lumbar lordosis restoration.

Introduction: The decision to instrument to L5 or ilium, in NMS, is usually based on radiologic factors, including pelvic obliquity (PO) > 15°, apex of curvature < L3, and Cobb angle > 60°. Since scoliosis in these patients is caused by a neurologic disease, we based our decision to stop at L5 on the presence of spasticity or flaccidity. Patients & Methods: The senior author did 109 primary fusions in NMS. Of those with DMD or SMA only 16% were instrumented to the ilium. The main factor for our decision was the correction potential of the truncal shift and PO in the supine traction radiographs and the absence of severe spasticity. Results: The 57 patients with DMD/SMA had a mean preoperative curvature of 68°, PO of 17°, and truncal shift of 20°. 74% should have been instrumented to the pelvis, but only 16% were. Those instrumented shorter as the rule, were corrected from 74° to 26° and had a postoperative PO of 8°. There was no significant difference in postoperative correction and PO compared to those instrumented to L5 on standard protocol. Subsequent extension to the pelvis was needed in 1 CP patient. There were no significant changes after 2 years. Of the 20 patients instrumented to the pelvis 11 had cerebral palsy and a preop curvature of 89°, a PO of 21° and a truncal shift of 25°. Discussion: The decision on instrumentation length should take flexibility and disease into consideration. If the trunk is centred over the pelvis, deterioration will not occur in absence of spasticity.

Purpose: We compared two techniques for thoracic apical derotation; one using conventional reduction screws (Single-Innie–SI) and one requiring special derotation screws that can be converted to monoaxial screws to enhance dorotation (Dual-Innie–DI) for coronal and sagittal correction and. Methods: A total of 200 patients with thoracic AIS have been included. In the SI-Group (n = 127) the convex rod was applied first. Vertebral derotation was done by translation to the concave rod with the convex rod being in place and center of rotation (COR). In the DI-Group (n = 73) correction started with translation on the concave side as well but now followed by derotation around the concave rod using the DI-mechanism. Results: The mean rotation according to Raimondi and coronal correction was not sig. affected (72 (± 12) % in the SI-Group versus 68 (± 15) % in the DI-Group), even when flexibility was respected (Cincinnati Correction Index CCI was 2.9 (± 4.9) versus 3.5 (± 4.4). (p < 0.01). The gain of kyphosis was sig greater (2.7°) in the SI-group, but not clinical relevant. Conclusion: The use of DI screws for apical derotation did not provide an advantage for coronal correction or derotation in thoracic curves. Presumably after translation is performed in the DI-group, there was too much tension and friction in the construct impeding further derotation. Simultaneous translation and derotation in the SI-group, with the convex rod being the COR, yielded similar correction with better kyphosis and was faster and more economic.

The treatment options for neuropathic pain caused by lumbar disc herniation have been debated controversially in the literature. Whether surgical or conservative therapy makes more sense in individual cases can hardly be answered. We have investigated whether a machine learning-based prediction of outcome, regarding neuropathic pain development, after lumbar disc herniation treatment is possible. The extensive datasets of 123 consecutive patients were used to predict the development of neuropathic pain, measured by a visual analogue scale (VAS) for leg pain and the Oswestry Disability Index (ODI), at 6 weeks, 6 months and 1 year after treatment of lumbar disc herniation in a machine learning approach. Using a decision tree regressor algorithm, a prediction quality within the limits of the minimum clinically important difference for the VAS and ODI value could be achieved. An analysis of the influencing factors of the algorithm reveals the important role of psychological factors as well as body weight and age with pre-existing conditions for an accurate prediction of neuropathic pain. The machine learning algorithm developed here can enable an assessment of the course of treatment after lumbar disc herniation. The early, comparative individual prediction of a therapy outcome is important to avoid unnecessary surgical therapies as well as insufficient conservative therapies and prevent the chronification of neuropathic pain.

In recent years, applications using artificial intelligence have been gaining importance in the diagnosis and treatment of spinal diseases. In our review, we describe the basic features of artificial intelligence which are currently applied in the field of spine diagnosis and treatment, and we provide an orientation of the recent technical developments and their applications. Furthermore, we point out the possible limitations and challenges in dealing with such technological advances. Despite the momentary limitations in practical application, artificial intelligence is gaining ground in the field of spine treatment. As an applying physician, it is therefore necessary to engage with it in order to benefit from those advances in the interest of the patient and to prevent these applications being misused by non-medical partners.

Background: Processing whole-slide images (WSI) to train neural networks can be intricate and labor intensive. We developed an open-source library dealing with recurrent tasks in the processing of WSI and helping with the training and evaluation of neuronal networks for classification tasks. Methods: Two histopathology use-cases were selected and only hematoxylin and eosin (H&E) stained slides were used. The first use case was a two-class classification problem. We trained a convolutional neuronal network (CNN) to distinguish between dysembryoplastic neuroepithelial tumor (DNET) and ganglioglioma (GG), two neuropathological low-grade epilepsy-associated tumor entities. Within the second use case, we included four clinicopathological disease conditions in a multilabel approach. Here we trained a CNN to predict the hormone expression profile of pituitary adenomas. In the same approach, we also predicted clinically silent corticotroph adenoma. Results: Our DNET-GG classifier achieved an AUC of 1.00 for the ROC curve. For the second use case, the best performing CNN achieved an area under the curve (AUC) of 0.97 for the receiver operating characteristic (ROC) for corticotroph adenoma, 0.86 for silent corticotroph adenoma, and 0.98 for gonadotroph adenoma. All scores were calculated with the help of our library on predictions on a case basis. Conclusions: Our comprehensive and fastai-compatible library is helpful to standardize the workflow and minimize the burden of training a CNN. Indeed, our trained CNNs extracted neuropathologically relevant information from the WSI. This approach will supplement the clinicopathological diagnosis of brain tumors, which is currently based on cost-intensive microscopic examination and variable panels of immunohistochemical stainings.

Background: Processing whole-slide images (WSI) to train neural networks can be intricate and laborious. We developed an open-source library covering recurrent tasks in processing of WSI and in evaluating the performance of the trained networks for classification tasks. Methods: Two histopathology use-cases were selected. First we aimed to train a CNN to distinguish H&E-stained slides obtained from neuropathologically classified low-grade epilepsy-associated dysembryoplastic neuroepithelial tumor (DNET) and ganglioglioma (GG). The second project we trained a convolutional neural network (CNN) to predict the hormone expression of pituitary adenoms only from hematoxylin and eosin (H&E) stained slides. In the same approach, we addressed the issue to also predict clinically silent corticotroph adenoma. We included four clinico-pathological disease conditions in a multilabel approach. Results: Our best performing CNN achieved an area under the curve (AUC) of 0.97 for the receiver operating characteristic (ROC) for corticotroph adenoma, 0.86 for silent corticotroph adenoma and 0.98 for gonadotroph adenoma. Our DNET-GG classifier achieved an AUC of 1.00 for the ROC curve. All scores were calculated with the help of our library on predictions on a case basis. Conclusions: Our comprehensive library is most helpful to standardize the work-flow and minimize the work-burden in training CNN. It is also compatible with fastai. Indeed, our new CNNs reliably extracted neuropathologically relevant information from the H&E staining only. This approach will supplement the clinico-pathological diagnosis of brain tumors, which is currently based on cost-intense microscopic examination and variable panels of immunohistochemical stainings.

Patients with back pain are common and present a challenge in everyday medical practice due to the multitude of possible causes and the individual effects of treatments. Predicting causes and therapy efficien cy with the help of artificial intelligence could improve and simplify the treatment. In an exemplary collective of 1000 conservatively treated back pain patients, it was investigated whether the prediction of therapy efficiency and the underlying diagnosis is possible by combining different artificial intelligence approaches. For this purpose, supervised and unsupervised artificial intelligence methods were analyzed and a methodology for combining the predictions was developed. Supervised AI is suitable for predicting therapy efficiency at the borderline of minimal clinical difference. Non-supervised AI can show patterns in the dataset. We can show that the identification of the underlying diagnostic groups only becomes possible through a combination of different AI approaches and the baseline data. The presented methodology for the combined application of artificial intelligence algorithms shows a transferable path to establish correlations in heterogeneous data sets when individual AI approaches only provide weak results.