Brain tumors, such as low grade gliomas (LGG), are molecularly classified which require the surgical collection of tissue samples. The pre-surgical or non-operative identification of LGG molecular type could improve patient counseling and treatment decisions. However, radiographic approaches to LGG molecular classification are currently lacking, as clinicians are unable to reliably predict LGG molecular type using magnetic resonance imaging (MRI) studies. Machine learning approaches may improve the prediction of LGG molecular classification through MRI, however, the development of these techniques requires large annotated data sets. Merging clinical data from different hospitals to increase case numbers is needed, but the use of different scanners and settings can affect the results and simply combining them into a large dataset often have a significant negative impact on performance. This calls for efficient domain adaption methods. Despite some previous studies on domain adaptations, mapping MR images from different datasets to a common domain without affecting subtitle molecular-biomarker information has not been reported yet. In this paper, we propose an effective domain adaptation method based on Cycle Generative Adversarial Network (CycleGAN). The dataset is further enlarged by augmenting more MRIs using another GAN approach. Further, to tackle the issue of brain tumor segmentation that requires time and anatomical expertise to put exact boundary around the tumor, we have used a tight bounding box as a strategy. Finally, an efficient deep feature learning method, multi-stream convolutional autoencoder (CAE) and feature fusion, is proposed for the prediction of molecular subtypes (1p/19q-codeletion and IDH mutation). The experiments were conducted on a total of 161 patients consisting of FLAIR and T1 weighted with contrast enhanced (T1ce) MRIs from two different institutions in the USA and France. The proposed scheme is shown to achieve the test accuracy of $74.81\%$ on 1p/19q codeletion and $81.19\%$ on IDH mutation, with marked improvement over the results obtained without domain mapping. This approach is also shown to have comparable performance to several state-of-the-art methods.

Background: In modern neurosurgery, there are often several treatment alternatives, with different risks and benefits. Shared decision-making (SDM) has gained interest during the last decade, although SDM in the neurosurgical field is not widely studied. Therefore, the aim of this scoping review was to present the current landscape of SDM in neurosurgery. Methods: A literature review was carried out in PubMed and Scopus. We used a search strategy based on keywords used in existing literature on SDM in neurosurgery. Full-text, peer-reviewed articles published from 2000 up to the search date February 16, 2021, with patients 18 years and older were included if articles evaluated SDM in neurosurgery from the patient’s perspective. Results: We identified 22 articles whereof 7 covered vestibular schwannomas, 7 covered spinal surgery, and 4 covered gliomas. The other topics were brain metastases, benign brain lesions, Parkinson’s disease and evaluation of neurosurgical care. Different methods were used, with majority using forms, questionnaires, or interviews. Effects of SDM interventions were studied in 6 articles; the remaining articles explored factors influencing patients’ decisions or discussed SDM aids. Conclusion: SDM is a tool to involve patients in the decision-making process and considers patients’ preferences and what the patients find important. This scoping review illustrates the relative lack of SDM in the neurosurgical literature. Even though results indicate potential benefit of SDM, the extent of influence on treatment, outcome, and patient’s satisfaction is still unknown. Finally, the use of decision aids may be a meaningful contribution to the SDM process.

Background: Glioma is the most common intra-axial tumor, and its location relative to critical areas of the brain is important for treatment decision-making. Studies often report tumor location based on anatomical taxonomy alone since the estimation of eloquent regions requires considerable knowledge of functional neuroanatomy and is, to some degree, a subjective measure. An unbiased and reproducible method to determine tumor location and eloquence is desirable, both for clinical use and for research purposes.Objective: To report on a voxel-based method for assessing anatomical distribution and proximity to eloquent regions in diffuse lower-grade gliomas (World Health Organization grades 2 and 3).Methods: A multi-institutional population-based dataset of adult patients (≥18 years) histologically diagnosed with lower-grade glioma was analyzed. Tumor segmentations were registered to a standardized space where two anatomical atlases were used to perform a voxel-based comparison of the proximity of segmentations to brain regions of traditional clinical interest.Results: Exploring the differences between patients with oligodendrogliomas, isocitrate dehydrogenase (IDH) mutated astrocytomas, and patients with IDH wild-type astrocytomas, we found that the latter were older, more often had lower Karnofsky performance status, and that these tumors were more often found in the proximity of eloquent regions. Eloquent regions are found slightly more frequently in the proximity of IDH-mutated astrocytomas compared to oligodendrogliomas. The regions included in our voxel-based definition of eloquence showed a high degree of association with performing biopsy compared to resection.Conclusion: We present a simple, robust, unbiased, and clinically relevant method for assessing tumor location and eloquence in lower-grade gliomas.

Background: Recently, the Therapy-Disability-Neurology (TDN) was introduced as a multidimensional reporting system to detect adverse events in neurosurgery. The aim of this study was to compare the novel TDN score with the Landriel–Ibanez classification (LIC) grade in a large cohort of patients with diffuse lower-grade glioma (dLGG). Since the TDN score lacks validation against patient-reported outcomes, we described health-related quality of life (HRQoL) change in relation to TDN scores in a subset of patients.Methods: We screened adult patients with a surgically treated dLGG World Health Organization (WHO) grade 2 and 3 between 2010 and 2020. Up until 2017, it consists of a retrospective cohort (n = 158). From 2017 and onwards, HRQoL was registered using EuroQoL-5-dimension, three levels of response (EQ-5D 3L) questionnaire at baseline and 3 months follow-up, in a prospectively recruited cohort (n = 102). Both the LIC grade and TDN score were used to classify adverse events.Results: In total, 231 patients were included. In 110/231 (47.6%) of the surgical procedures, a postoperative complication was registered. When comparing the TDN score to LIC grades, only a minor shift towards complications of higher order could be observed. EQ-5D 3L was reported for 45 patients. Patients with complications related to surgery had pre- to postoperative changes in EQ-5D 3L index values (n = 27; mean 0.03, 95% CI −0.06 to 0.11) that were comparable to patients without complications (n = 18; mean −0.06, 95% CI −0.21 to 0.08). In contrast, patients with new-onset neurological deficit had a deterioration in HRQoL at follow-up, with a mean change in the EQ-5D 3L index value of 0.11 (n = 13, 95% CI 0.0 to 0.22) compared to −0.06 (n = 32, 95% CI −0.15 to 0.03) for all other patients.Conclusions: In patients with dLGG, TDN scores compared to the standard LIC tend to capture more adverse events of higher order. There was no clear relation between TDN severity and HRQoL. However, new-onset neurological deficit caused impairment in HRQoL. For the TDN score to better align with patient-reported outcomes, more emphasis on neurological deficit and function should be considered.

At the group level, health-related quality of life (HRQoL) in patients with IDH-mutant diffuse glioma grades 2 and 3 seems to remain stable over time. However, clinical experience indicates that there are patients with unfavorable outcomes on key HRQoL subdomains. The aim of this longitudinal population-based study, following patients over a period of 12 months from surgery, was to describe individual-level data on global health status and fatigue score and explore possible predictors of deterioration. All patients undergoing surgery for presumed glioma grades 2 or 3 at the Sahlgrenska University Hospital during 2017–2022, were screened for the study. Patients were invited to complete the European Organization of Research and Treatment of Cancer core questionnaires and brain module at baseline, 3 and 12 months postoperatively. Data is reported with respect to minimal clinical important difference (MCID). We included 51 patients with IDH-mutant diffuse glioma grades 2 or 3. There was no difference in group-level data of either global health status or fatigue score from baseline to the 12-month follow-up (P-value > .05). Unfavorable individual changes (beyond MCID) in global health status and fatigue score were observed in 12 and in 17 patients, respectively (23.5% and 33.3%). A lower proportion of proton radiotherapy was found in patients with unfavorable changes in fatigue (10/15, 66.7%) compared to all other patients undergoing radiotherapy (22/23, 95.7%, P-value .03). Deterioration beyond MCID was seen in approximately one-third of patients. Changes in global health status could not be predicted, but changes in fatigue may be influenced by tumor-targeted and symptomatic treatment.

Radiologically presumed diffuse lower-grade glioma (dLGG) are typically non or minimal enhancing tumors, with hyperintensity in T2w-images. The aim of this study was to test the clinical usefulness of deep learning (DL) in IDH mutation prediction in patients with radiologically presumed dLGG. Three hundred and fourteen patients were retrospectively recruited from 6 neurosurgical departments in Sweden, Norway, France, Austria, and the United States. Collected data included patients’ age, sex, tumor molecular characteristics (IDH, and 1p19q), and routine preoperative radiological images. A clinical model was built using multivariable logistic regression with the variables age and tumor location. DL models were built using MRI data only, and 4 DL architectures used in glioma research. In the final validation test, the clinical model and the best DL model were scored on an external validation cohort with 155 patients from the Erasmus Glioma Dataset. The mean age in the recruited and external cohorts was 45.0 (SD 14.3) and 44.3 years (SD 14.6). The cohorts were rather similar, except for sex distribution (53.5% vs 64.5% males, P-value = .03) and IDH status (30.9% vs 12.9% IDH wild-type, P-value <.01). Overall, the area under the curve for the prediction of IDH mutations in the external validation cohort was 0.86, 0.82, and 0.87 for the clinical model, the DL model, and the model combining both models’ probabilities. In their current state, when these complex models were applied to our clinical scenario, they did not seem to provide a net gain compared to our baseline clinical model.