Radiation necrosis represents a potentially devastating complication after radiation therapy in brain tumors. The establishment of the diagnosis and especially the differentiation from progression and pseudoprogression with its therapeutic implications requires interdisciplinary consent and monitoring. Herein, we want to provide an overview of the diagnostic modalities, therapeutic possibilities and an outlook on future developments to tackle this challenging topic. The aim of this report is to provide an overview of the current morphological, functional, metabolic and evolving imaging tools described in the literature in order to (I) identify the best criteria to distinguish radionecrosis from tumor recurrence after the radio-oncological treatment of malignant gliomas and cerebral metastases, (II) analyze the therapeutic possibilities and (III) give an outlook on future developments to tackle this challenging topic. Additionally, we provide the experience of a tertiary tumor center with this important issue in neuro-oncology and provide an institutional pathway dealing with this problem.

Preoperative grade prediction is important in diagnostics of glioma. Even more important can be follow-up after chemotherapy and radiotherapy of high grade gliomas. In this review we provide an overview of MR-spectroscopy (MRS), technical aspects, and different clinical scenarios in the diagnostics and follow-up of gliomas in pediatric and adult populations. Furthermore, we provide a recap of the current research utility and possible future strategies regarding proton- and phosphorous-MRS in glioma research.

Background/Objectives: Large language models (LLMs), such as ChatGPT, have emerged as potential clinical support tools to enhance precision in personalized patient care, but their reliability in radiological image interpretation remains uncertain. The primary aim of our study was to evaluate the diagnostic accuracy of ChatGPT-4o in interpreting chest X-rays (CXRs) and abdominal X-rays (AXRs) by comparing its performance to expert radiology findings, whilst secondary aims were diagnostic confidence and patient safety. Methods: A total of 500 X-rays, including 257 CXR (51.4%) and 243 AXR (48.5%), were analyzed. Diagnoses made by ChatGPT-4o were compared to expert interpretations. Confidence scores (1–4) were assigned and responses were evaluated for patient safety. Results: ChatGPT-4o correctly identified 345 of 500 (69%) pathologies (95% CI: 64.81–72.9). For AXRs 175 of 243 (72.02%) pathologies were correctly diagnosed (95% CI: 66.06–77.28), while for CXRs 170 of 257 (66.15%) were accurate (95% CI: 60.16–71.66). The highest detection rates among CXRs were observed for pulmonary edema, tumor, pneumonia, pleural effusion, cardiomegaly, and emphysema, and lower rates were observed for pneumothorax, rib fractures, and enlarged mediastinum. AXR performance was highest for intestinal obstruction and foreign bodies, and weaker for pneumoperitoneum, renal calculi, and diverticulitis. Confidence scores were higher for AXRs (mean 3.45 ± 1.1) than CXRs (mean 2.48 ± 1.45). All responses (100%) were considered to be safe for the patient. Interobserver agreement was high (kappa = 0.920), and reliability (second prompt) was moderate (kappa = 0.750). Conclusions: ChatGPT-4o demonstrated moderate accuracy for the interpretation of X-rays, being higher for AXRs compared to CXRs. Improvements are required for its use as efficient clinical support tool.

Segmentation of specific brain tissue from MRI volumes is of great significance for brain disease diagnosis, progression assessment, and monitoring of neurological conditions. Manual segmentation is time-consuming, laborious, and subjective, which significantly amplifies the need for automated processes. Over the last decades, the active development in the field of deep learning, especially convolutional neural networks (CNNs), and the associated performance improvements have increased the demand for the application of CNN-based methods to provide consistent measurements and quantitative analyses. In this paper, we present an efficient deep learning approach for the segmentation of brain tissue. More specifically, we address the problem of segmentation of the posterior limb of the internal capsule (PLIC) in preterm neonates. To this end, we propose a CNN-based pipeline comprised of slice-selection modules and a multi-view segmentation model, which exploits the 3D information contained in the MRI volumes to improve segmentation performance. One special feature of the proposed method is its ability to identify one desired slice out of the whole image volume, which is relevant for pediatricians in terms of prognosis. To increase computational efficiency, we apply a strategy that automatically reduces the information contained in the MRI volumes to its relevant parts. Finally, we conduct an expert rating alongside standard evaluation metrics, such as dice score, to evaluate the performance of the proposed framework. We demonstrate the benefit of the multi-view technique by comparing it with its single-view counterparts, which reveals that the proposed method strikes a good balance between exploiting the available image information and reducing the required computing power compared to 3D segmentation networks. Standard evaluation metrics as, well as expert-based assessment, confirm the good performance of the proposed framework, with the latter being more relevant in terms of clinical applicability. We demonstrate that the proposed deep learning pipeline can compete with the experts in terms of accuracy. To prove the generalisability of the proposed method, we additionally assess our deep learning pipeline to data from the Developing Human Connectome Project (dHCP).

Introduction: In this post hoc analysis we compared various response-assessment criteria in newly diagnosed glioblastoma (GB) patients treated with tumor lysate-charged autologous dendritic cells (Audencel) and determined the differences in prediction of progression-free survival (PFS) and overall survival (OS). Methods: 76 patients enrolled in a multicenter phase II trial receiving standard of care (SOC, n = 40) or SOC + Audencel vaccine (n = 36) were included. MRI scans were evaluated using MacDonald, RANO, Vol-RANO, mRANO, Vol-mRANO and iRANO criteria. Tumor volumes (T1 contrast-enhancing as well as T2/FLAIR volumes) were calculated by semiautomatic segmentation. The Kruskal-Wallis-test was used to detect differences in PFS among the assessment criteria; for correlation analysis the Spearman test was used. Results: There was a significant difference in median PFS between mRANO (8.6 months) and Vol-mRANO (8.6 months) compared to MacDonald (4.0 months), RANO (4.2 months) and Vol-RANO (5.4 months). For the vaccination arm, median PFS by iRANO was 6.2 months. There was no difference in PFS between SOC and SOC + Audencel. The best correlation between PFS/OS was detected for mRANO (r = 0.65) and Vol-mRANO (r = 0.69, each p < 0.001). A total of 16/76 patients developed a pure T2/FLAIR progressing disease, and 4/36 patients treated with Audencel developed pseudoprogression. Conclusion: When comparing different response-assessment criteria in GB patients treated with dendritic cell-based immunotherapy, the best correlation between PFS and OS was observed for mRANO and Vol-mRANO. Interestingly, iRANO was not superior for predicting OS in patients treated with Audencel.

The World Health Organisation’s (WHO) classification of brain tumors requires consideration of both histological appearance and molecular characteristics. Possible differences in brain energy metabolism could be important in designing future therapeutic strategies. Forty-three patients with primary, isocitrate dehydrogenase 1 (IDH1) wild type glioblastomas (GBMs) were included in this study. Pre-operative standard MRI was obtained with additional phosphorous magnetic resonance spectroscopy (31-P-MRS) imaging. Following microsurgical resection of the tumors, biopsy specimens underwent neuropathological diagnostics including standard molecular diagnosis. The spectroscopy results were correlated with epidermal growth factor (EGFR) and $O^6$-Methylguanine-DNA methyltransferase (MGMT) status. EGFR amplified tumors had significantly lower phosphocreatine (PCr) to adenosine triphosphate (ATP)-PCr/ATP and PCr to inorganic phosphate (Pi)-PCr/Pi ratios, and higher Pi/ATP and phosphomonoesters (PME) to phosphodiesters (PDE)-PME/PDE ratio than those without the amplification. Patients with MGMT-methylated tumors had significantly higher cerebral magnesium (Mg) values and PME/PDE ratio, while their PCr/ATP and PCr/Pi ratios were lower than in patients without the methylation. In survival analysis, not-EGFR-amplified, MGMT-methylated GBMs showed the longest survival. This group had lower PCr/Pi ratio when compared to MGMT-methylated, EGFR-amplified group. PCr/Pi ratio was lower also when compared to the MGMT-unmethylated, EGFR not-amplified group, while PCr/ATP ratio was lower than all other examined groups. Differences in energy metabolism in various molecular subtypes of wild-type-GBMs could be important information in future precision medicine approach.