AI Evaluation of Imaging Factors in the Evolution of Stage-Treated Metastases Using Gamma Knife.

BACKGROUND: The study investigated whether three deep-learning models, namely, the CNN_model (trained from scratch), the TL_model (transfer learning), and the FT_model (fine-tuning), could predict the early response of brain metastases (BM) to radiosurgery using a minimal pre-processing of the MRI images. The dataset consisted of 19 BM patients who underwent stereotactic-radiosurgery (SRS) within 3 months. The images used included axial fluid-attenuated inversion recovery (FLAIR) sequences and high-resolution contrast-enhanced T1-weighted (CE T1w) sequences from the tumor center. The patients were classified as responders (complete or partial response) or non-responders (stable or progressive disease). METHODS: A total of 2320 images from the regression class and 874 from the progression class were randomly assigned to training, testing, and validation groups. The DL models were trained using the training-group images and labels, and the validation dataset was used to select the best model for classifying the evaluation images as showing regression or progression. RESULTS: Among the 19 patients, 15 were classified as "responders" and 4 as "non-responders". The CNN_model achieved good performance for both classes, showing high precision, recall, and F1-scores. The overall accuracy was 0.98, with an AUC of 0.989. The TL_model performed well in identifying the "progression" class, but could benefit from improved precision, while the "regression" class exhibited high precision, but lower recall. The overall accuracy of the TL_model was 0.92, and the AUC was 0.936. The FT_model showed high recall for "progression", but low precision, and for the "regression" class, it exhibited a high precision, but lower recall. The overall accuracy for the FT_model was 0.83, with an AUC of 0.885. CONCLUSIONS: Among the three models analyzed, the CNN_model, trained from scratch, provided the most accurate predictions of SRS responses for unlearned BM images. This suggests that CNN models could potentially predict SRS prognoses from small datasets. However, further analysis is needed, especially in cases where class imbalances exist.

Dental Appliances for the Treatment of Obstructive Sleep Apnea in Children: A Systematic Review and Meta-Analysis.

Background and objectives: Obstructive sleep apnea (OSA) in children is a debilitating disease, difficult to treat. Dental appliances have been proposed as a valid therapy for improving functional outcomes with good compliance rates. Herein, we aimed to perform a meta-analysis comparing clinical outcomes between OSA children treated with dental appliances versus controls. Materials Methods: The study was registered with PROSPERO. A systematic search was performed for all comparative studies examining outcomes in pediatric patients who underwent treatment of OSA with oral appliances versus controls. Data was extracted and analyzed using a random effects model via Rev Man 5.3. Results: Six studies including 180 patients were analyzed split into two groups: patients treated with dental appliances (n = 123) and the controls (n = 119). Therapy with dental appliances was shown to significantly improve the apnea-hypopnea index (p = 0.009) and enlarge the superior posterior airway space (p = 0.02). Maxilla-to-mandible measurements were not significantly different between the two groups, nor was the mean SO2 (p = 0.80). Conclusions: This is the most updated meta-analysis assessing the role of dental appliances for OSA in children; it shows that such devices can improve functional outcomes by decreasing the apnea-hypopnea index.

One Step Forward-The Current Role of Artificial Intelligence in Glioblastoma Imaging.

Artificial intelligence (AI) is rapidly integrating into diagnostic methods across many branches of medicine. Significant progress has been made in tumor assessment using AI algorithms, and research is underway on how image manipulation can provide information with diagnostic, prognostic and treatment impacts. Glioblastoma (GB) remains the most common primary malignant brain tumor, with a median survival of 15 months. This paper presents literature data on GB imaging and the contribution of AI to the characterization and tracking of GB, as well as recurrence. Furthermore, from an imaging point of view, the differential diagnosis of these tumors can be problematic. How can an AI algorithm help with differential diagnosis? The integration of clinical, radiomics and molecular markers via AI holds great potential as a tool for enhancing patient outcomes by distinguishing brain tumors from mimicking lesions, classifying and grading tumors, and evaluating them before and after treatment. Additionally, AI can aid in differentiating between tumor recurrence and post-treatment alterations, which can be challenging with conventional imaging methods. Overall, the integration of AI into GB imaging has the potential to significantly improve patient outcomes by enabling more accurate diagnosis, precise treatment planning and better monitoring of treatment response.

The Roles of Imaging Biomarkers in the Management of Chronic Neuropathic Pain.

Chronic neuropathic pain (CNP) affects around 10% of the general population and has a significant social, emotional, and economic impact. Current diagnosis techniques rely mainly on patient-reported outcomes and symptoms, which leads to significant diagnostic heterogeneity and subsequent challenges in management and assessment of outcomes. As such, it is necessary to review the approach to a pathology that occurs so frequently, with such burdensome and complex implications. Recent research has shown that imaging methods can detect subtle neuroplastic changes in the central and peripheral nervous system, which can be correlated with neuropathic symptoms and may serve as potential markers. The aim of this paper is to review available imaging methods used for diagnosing and assessing therapeutic efficacy in CNP for both the preclinical and clinical setting. Of course, further research is required to standardize and improve detection accuracy, but available data indicate that imaging is a valuable tool that can impact the management of CNP.

3D Printed Models-A Useful Tool in Endovascular Treatment of Intracranial Aneurysms.

Many developments were made in the area of endovascular treatment of intracranial aneurysms, but this procedure also requires a good assessment of vascular anatomy prior to intervention. Seventy-six cases with brain aneurysms were selected and 1:1 scale 3D printed models were created. We asked three interventional neurosurgeons with different degrees of experience (ten years, four years, and a fourth-year resident) to review the cases using CTA (computed tomography angiogram) with MPR (multiplanar reconstructions) and VRT (volume rendering technique) and make a decision: coil embolization or stent-assisted coil embolization. After we provided them with the 3D printed models, they were asked to review their treatment plan. Statistical analysis was performed and the endovascular approach changed in 11.84% of cases for ten-year experienced neurosurgeons, 13.15% for four years experienced neurosurgeon, and 21.05% for residents. The interobserver agreement was very good between the ten years experienced interventionist and four years experienced interventionist when they analyzed the data set that included the 3D printed model. The agreement was higher between all physicians after they examined the printed model. 3D patient-specific printed models may be useful in choosing between two different endovascular techniques and also help the residents to better understand the vascular anatomy and the overall procedure.

A novel combination of double primary malignancies: penile carcinoma and glioblastoma. A series of two cases.

AIM: Penile squamous cell carcinoma (pSCC) and glioblastoma (GB) are rare malignant tumors that develop especially in the elderly. The aim of our paper is to present two patients diagnosed and treated for a cerebral GB developed after a prior pSCC and to discuss the possible mechanism of their association. PATIENTS, MATERIALS, AND METHODS: The medical records of 632 patients admitted for a GB in the Department of Neurosurgery, "Prof. Dr. Nicolae Oblu" Emergency Clinical Hospital, Iasi, Romania, between April 2010 and April 2018, were retrospectively searched for those having a prior histological proven cancer. The review found only two patients (0.31% of all cases with GB) and their demographics, clinical presentation, medical history, treatment and pathological diagnosis were reviewed and discussed. RESULTS: Both patients were 65-year-old on their admission in the Department of Neurosurgery. Their prior penile tumors were both located at the penis glans. In both cases, the histopathological exam revealed a penile keratinized squamous cell carcinoma stage T1aN0M0 at the moment of their first urological diagnosis. At the time of the neurosurgical evaluation, brain radiological investigations demonstrated right frontal cystic neoformation in the first case, and a right frontal-parietal solid, expansive lesion for the second patient. The patients underwent subtotal surgical excision of their brain masses. The histopathological exam revealed in both cases a World Health Organization (WHO) grade IV GB. CONCLUSIONS: This is the first clinical report of a new association between pSCC and subsequent development of GB in a series of two patients. Both our patients developed a prior pSCC without any lymph node and distant metastasis at their first diagnosis and this situation reinforces the idea that this type of cancer has a good prognosis and that the patient can develop a second cancer during his post-penectomy life, probably due to a genetic predisposition, post-therapeutic effects, life style factors (smoke effects), sporadic association, or due to the common embryological origin of the nervous and skin tissues.

Longer survival of a patient with glioblastoma resected with 5-aminolevulinic acid (5-ALA)-guided surgery and foreign body reaction to polyglycolic acid (PGA) suture.

In recent years, there is a growing evidence that using 5-aminolevulinic acid (5-ALA)-guided resection of a cerebral glioblastoma, associated with chemoradiotherapy determine a prolonged survival of these patients, even though this period do not exceed 15 months. 5-ALA is a natural biochemical precursor of heme that is metabolized to fluorescent porphyrins, particularly protoporphyrin IX (PPIX) and no foreign reaction were noted until now. However, foreign body reaction developing in neurosurgery is documented in a few number of cases to suture material, surgical hemostatic material, or surgical glove starch, but up to now we could not find any article about granulomatous inflammation to polyglycolic acid (PGA) suture after brain tumor resection. Here we present a case of a delayed foreign body granuloma to PGA suture diagnosed after 10 months following fluorescence-guided surgery with 5-ALA for resection of a cerebral glioblastoma that was difficult to diagnosis both clinically and on magnetic resonance imaging (MRI). Moreover, the survival time was longer. We correlate the appearance of foreign body granuloma with the patient's persistent pre- and postoperative lymphocytosis. We also suggest that the chronic inflammation inhibited the proliferation of any tumoral cells which could remain in the tumor bed because we did not noticed on serial MRI scans a rapidly tumor growth during the first 10 months after the initial surgery as we have expected to be for a glioblastoma.