Search

Abstract Objective Clinical and surgical decisions for glioblastoma patients depend on a tumor imaging-based evaluation. Artificial Intelligence (AI) can be applied to magnetic resonance imaging (MRI) assessment to support clinical practice, surgery planning and prognostic predictions. In a real-world context, the current obstacles for AI are low-quality imaging and postoperative reliability. The aim of this study is to train an automatic algorithm for glioblastoma segmentation on a clinical MRI dataset and to obtain reliable results both pre- and post-operatively. Methods The dataset used for this study comprises 237 (71 preoperative and 166 postoperative) MRIs from 71 patients affected by a histologically confirmed Grade IV Glioma. The implemented U-Net architecture was trained by transfer learning to perform the segmentation task on postoperative MRIs. The training was carried out first on BraTS2021 dataset for preoperative segmentation. Performance is evaluated using DICE score (DS) and Hausdorff 95% (H95). Results In preoperative scenario, overall DS is 91.09 (± 0.60) and H95 is 8.35 (± 1.12), considering tumor core, enhancing tumor and whole tumor (ET and edema). In postoperative context, overall DS is 72.31 (± 2.88) and H95 is 23.43 (± 7.24), considering resection cavity (RC), gross tumor volume (GTV) and whole tumor (WT). Remarkably, the RC segmentation obtained a mean DS of 63.52 (± 8.90) in postoperative MRIs. Conclusions The performances achieved by the algorithm are consistent with previous literature for both pre-operative and post-operative glioblastoma’s MRI evaluation. Through the proposed algorithm, it is possible to reduce the impact of low-quality images and missing sequences.

Abstract Background Peripheral nerve injuries (PNIs) include several conditions in which one or more peripheral nerves are damaged. Trauma is one of the most common causes of PNIs and young people are particularly affected. They have a significant impact on patients’ quality of life and on the healthcare system, while timing and type of surgical treatment are of the utmost importance to guarantee the most favorable functional recovery. To date, several different classifications of PNIs have been proposed, most of them focusing on just one or few aspects of these complex conditions, such as type of injury, anatomic situation, or prognostic factors. Current classifications do not enable us to have a complete view of this pathology, which includes diagnosis, treatment choice, and possible outcomes. This fragmentation sometimes leads to an ambiguous definition of PNIs and the impossibility of exchanging crucial information between different physicians and healthcare structures, which can create confusion in the choice of therapeutic strategies and timing of surgery. Materials The authors retrospectively analyzed a group of 24 patients treated in their center and applied a new classification for PNI injuries. They chose (a) five injury-related factors, namely nerve involved, lesion site, nerve type (whether motor, sensory or mixed), surrounding tissues (whether soft tissues were involved or not), and lesion type—whether partial/in continuity or complete. An alphanumeric code was applied to each of these classes, and (b) four prognostic codes, related to age, timing, techniques, and comorbidities. Results An alphanumeric code was produced, similar to that used in the AO classification of fractures. Conclusions The authors propose this novel classification for PNIs, with the main advantage to allow physicians to easily understand the characteristics of nerve lesions, severity, possibility of spontaneous recovery, onset of early complications, need for surgical treatment, and the best surgical approach. Level of evidence: according to the Oxford 2011 level of evidence, level 2.