Development and prospective validation of an artificial intelligence-based smartphone app for rapid intraoperative pituitary adenoma identification.

BACKGROUND: Intraoperative pathology consultation plays a crucial role in tumor surgery. The ability to accurately and rapidly distinguish tumor from normal tissue can greatly impact intraoperative surgical oncology management. However, this is dependent on the availability of a specialized pathologist for a reliable diagnosis. We developed and prospectively validated an artificial intelligence-based smartphone app capable of differentiating between pituitary adenoma and normal pituitary gland using stimulated Raman histology, almost instantly. METHODS: The study consisted of three parts. After data collection (part 1) and development of a deep learning-based smartphone app (part 2), we conducted a prospective study that included 40 consecutive patients with 194 samples to evaluate the app in real-time in a surgical setting (part 3). The smartphone app's sensitivity, specificity, positive predictive value, and negative predictive value were evaluated by comparing the diagnosis rendered by the app to the ground-truth diagnosis set by a neuropathologist. RESULTS: The app exhibits a sensitivity of 96.1% (95% CI: 89.9-99.0%), specificity of 92.7% (95% CI: 74-99.3%), positive predictive value of 98% (95% CI: 92.2-99.8%), and negative predictive value of 86.4% (95% CI: 66.2-96.8%). An external validation of the smartphone app on 40 different adenoma tumors and a total of 191 scanned SRH specimens from a public database shows a sensitivity of 93.7% (95% CI: 89.3-96.7%). CONCLUSIONS: The app can be readily expanded and repurposed to work on different types of tumors and optical images. Rapid recognition of normal versus tumor tissue during surgery may contribute to improved intraoperative surgical management and oncologic outcomes. In addition to the accelerated pathological assessments during surgery, this platform can be of great benefit in community hospitals and developing countries, where immediate access to a specialized pathologist during surgery is limited.

In tumor surgery, precise identification of abnormal tissue during surgical removal of the tumor is paramount. Traditional methods rely on the availability of specialized pathologists for a reliable diagnosis, which could be a limitation in many hospitals. Our study introduces a user-friendly smartphone app that quickly and precisely diagnoses pituitary tumors, powered by artificial intelligence (AI), which is the simulation of human intelligence in machines for tasks like learning, reasoning, problem-solving, and decision-making. Through data collection, app development, and validation, our findings demonstrate that the app can rapidly and accurately identify tumors in real-time. External validation further confirmed its effectiveness in detecting tumor tissue collected from a different source. This AI-driven app could contribute to elevating surgical precision, particularly in settings lacking immediate access to specialized pathologists.

Patient-Reported Outcomes in Endoscopic Endonasal Skull Base Surgery.

The functional outcome, quality of life, and patient feedback related to a chosen treatment approach in skull base surgery have become a subject of interest and focused research in recent years. The current advances in endoscopic optical imaging technology and surgical precision have radically lowered the perioperative morbidity associated with skull base surgery. This has pushed toward a higher focus on patient-reported outcomes (PROs). It is now critical to ensure that the offered treatment plan and approach align with the patient's preferences and expectations, in addition to the surgeon's best clinical judgment and experience. PROs represent a view that reflects the patient's own thoughts and perspective on their condition and the management options, without input or interpretations from the surgeon. Having PRO data enables patients the opportunity to learn from the experiences and perspectives of other patients. This input empowers the patient to become an active participant in the decision-making process at different stages of their care. An in-depth PRO evaluation requires specific validated tools and scoring systems, namely the patient-reported outcomes measures (PROM) tools. In this review, we discuss the currently available skull-base-related PROs, the assessment tools used to capture them, and the future trends of this important topic that is in its infancy.

Stimulated Raman Histology for Rapid Intra-Operative Diagnosis of Sinonasal and Skull Base Tumors.

OBJECTIVE: Intra-operative stimulated Raman histology (SRH) is a novel technology that uses laser spectroscopy and color-matching algorithms to create images similar to the formalin-fixed paraffin-embedded (FFPE) section. We aim to assess the accuracy of SRH in a novel range of sinonasal and skull base tumors. METHODS: Select patients undergoing sinonasal and skull base surgery using the Invenio Imaging™ Nio™ Laser Imaging SRH system between June 2020 and September 2021 were assessed. The SRH images were reviewed for pathologic features similar to frozen section (FS) and FFPE. Time taken for results and diagnostic concordance was assessed. RESULTS: Sixty-seven SRH images from 7 tumor types in 12 patients were assessed. Pathologies included squamous cell carcinoma, rhabdomyosarcoma, inverted papilloma, adenoid cystic carcinoma, SMARCB1-deficient sinonasal carcinoma, mucosal melanoma, metastatic colonic adenocarcinoma, and meningioma. Tumor was identified in 100% of lesional specimens, with characteristic diagnostic features readily appreciable on SRH. Median time for diagnosis was significantly faster for SRH (4.3 min) versus FS (44.5 min; p = <.0001). Where SRH sample site matched precisely to FS (n = 32/67, 47.8%), the same diagnosis was confirmed in 93.8%. Sensitivity, specificity, precision, and overall accuracy of SRH were 93.3%, 94.1%, 93.8%, and 93.3%, respectively. Near-perfect concordance was seen between SRH and FS (Cohen's kappa [κ] = 0.89). CONCLUSION: Stimulated Raman histology can rapidly produce images similar to FFPE H&E in sinonasal and skull base tumors. This technology has the potential to act as an adjunct or alternative to standard FS. LEVEL OF EVIDENCE: 4 Laryngoscope, 132:2142-2147, 2022.

Spinal meningiomas, from biology to management - A literature review.

Meningiomas arise from arachnoidal cap cells of the meninges, constituting the most common type of central nervous system tumors, and are considered benign tumors in most cases. Their incidence increases with age, and they mainly affect females, constituting 25-46% of primary spinal tumors. Spinal meningiomas could be detected incidentally or be unraveled by various neurological symptoms (e.g., back pain, sphincter dysfunction, sensorimotor deficits). The gold standard diagnostic modality for spinal meningiomas is Magnetic resonance imaging (MRI) which permits their classification into four categories based on their radiological appearance. According to the World Health Organization (WHO) classification, the majority of spinal meningiomas are grade 1. Nevertheless, they can be of higher grade (grades 2 and 3) with atypical or malignant histology and a more aggressive course. To date, surgery is the best treatment where the big majority of meningiomas can be cured. Advances in surgical techniques (ultrasonic dissection, microsurgery, intraoperative monitoring) increase the complete resection rate. Operated patients have a satisfactory prognosis, even in those with poor preoperative neurological status. Adjuvant therapy has a growing role in treating spinal meningiomas, mainly in the case of subtotal resection and tumor recurrence. The current paper reviews the fundamental epidemiological and clinical aspects of spinal meningiomas, their histological and genetic characteristics, and their management, including the various surgical novelties and techniques.

Atypical Presentation of Parietal Convexity Dural-Based Cavernous Hemangioma: A Case Report and Review of Literature.

BACKGROUND: Dural presentation of a cavernous hemangioma is a rare occurrence. Classically an intraparenchymal lesion with varying symptomatology including mostly headaches, seizures, and neurologic deficits depending on its location, a few cases have been reported along the convexity of the brain, even less eroding the calvaria, with none occasioning abnormal movements as the initial presentation. CASE DESCRIPTION: This is a case of a 67-year-old male who presented to the clinic for atypical progressive choreiform movements of the right side of his body and a soft subgaleal mass. Radiographic imaging showed a parietal tumor with intradural and extradural invasion mimicking a meningioma, which does not provide, given its location, a clear explanation of the symptoms. A craniotomy was performed on 29 January, 2018, during which the tumor was resected along with the invaded dura mater and calvaria. CONCLUSIONS: A pathology report was positive for cavernous hemangioma, an unexpected diagnosis based on the tumor's characteristics. After surgery, the patient recovered completely without residual symptoms, suggesting a compressive mass effect causing the atypical movement disorders.

Extent of resection and Carmustine wafer implantation safely improve survival in patients with a newly diagnosed glioblastoma: a single center experience of the current practice.

For newly diagnosed glioblastomas treated with resection in association with the standard combined chemoradiotherapy, the impact of Carmustine wafer implantation remains debated regarding postoperative infections, quality of life, and feasibility of adjuvant oncological treatments. To assess together safety, tolerance and efficacy of Carmustine wafer implantation and of extent of resection for glioblastoma patients in real-life experience. Observational retrospective monocentric study including 340 consecutive adult patients with a newly diagnosed supratentorial glioblastoma who underwent surgical resection with (n = 123) or without (n = 217) Carmustine wafer implantation as first-line oncological treatment. Carmustine wafer implantation and extent of resection did not significantly increase postoperative complications, including postoperative infections (p = 0.269, and p = 0.446, respectively). Carmustine wafer implantation and extent of resection did not significantly increase adverse events during adjuvant oncological therapies (p = 0.968, and p = 0.571, respectively). Carmustine wafer implantation did not significantly alter the early postoperative Karnofsky performance status (p = 0.402) or the Karnofsky performance status after oncological treatment (p = 0.636) but a subtotal or total surgical resection significantly improved those scores (p < 0.001, and p < 0.001, respectively). Carmustine wafer implantation, subtotal and total resection, and standard combined chemoradiotherapy were independently associated with longer event-free survival (adjusted Hazard Ratio (aHR), 0.74 [95% CI 0.55-0.99], p = 0.043; aHR, 0.70 [95% CI 0.54-0.91], p = 0.009; aHR, 0.40 [95% CI 0.29-0.55], p < 0.001, respectively) and with longer overall survival (aHR, 0.69 [95% CI 0.49-0.96], p = 0.029; aHR, 0.52 [95% CI 0.38-0.70], p < 0.001; aHR, 0.58 [95% CI 0.42-0.81], p = 0.002, respectively). Carmustine wafer implantation in combination with maximal resection, followed by standard combined chemoradiotherapy is safe, efficient, and well-tolerated in newly diagnosed supratentorial glioblastomas in adults.

Lumbar microdiscectomy: a clinicoradiological analysis of outcome.

BACKGROUND: The long-term outcome after lumbar microdiscectomy (LMD) may be affected by low back pain (LBP) and segmental instability, the determinants of which remain unclear. We sought to analyze the interaction between clinical, functional, and radiological variables and their impact on patient outcome. METHODS: All patients who underwent LMD in 2004-2005 were invited to participate in this retrospective cohort study. Patients were re-evaluated clinically and radiologically after a three to five year follow-up. RESULTS: Forty-one of 97 eligible patients were enrolled. Twelve patients (29.3%) reported moderate-to-severe sciatica, 12 (29.3%) had moderate LBP, and 13 (31.7%) exhibited clinical evidence of segmental instability. Thirty-eight patients (92.7%) had minimal disability and 3 (7.3%) had moderate disability. Twenty-three patients (56.1%) were fully satisfied, while 18 (43.9%) had only partial satisfaction, having expected a better outcome. Thirty-three patients (80.5%) returned to full-time work. Median disc space collapse (DSC) was 20% (range 5-66%) and L4-L5 was particularly affected. Prevalence of Modic changes increased from 46.3% to 78% with type 2 predominance. Multivariate logistic regression analysis identified the following negative prognostic factors: female sex, young age, lack of regular exercise, and chronic preoperative LBP. There was no correlation between the course of Modic changes, DSC, and patient outcome. CONCLUSION: Although many patients may be symptomatic following LMD, significant disability and dissatisfaction are uncommon. Female sex, young age, lack of exercise, and chronic preoperative LBP may predict a worse outcome. Disc collapse is a universal finding, particularly at L4-L5. Neither DSC nor Modic changes seem to affect patient outcome.

What happens to Modic changes following lumbar discectomy? Analysis of a cohort of 41 patients with a 3- to 5-year follow-up period.

OBJECT: The natural history of Modic changes (MCs) in the lumbar spine is often marked by conversion from one type to another, but their course following lumbar discectomy remains unknown. The authors sought to study the impact of surgery on the natural history of these lesions. METHODS: Forty-one patients treated with lumbar microdiscectomy between 2004 and 2005 were enrolled in this study and underwent clinical evaluation and repeat MR imaging after a median follow-up of 41 months (range 32-59 months). Preoperative and follow-up MR images were reviewed and the type, location, and extent of MCs at the operated level were recorded and compared. RESULTS: The study population consisted of 27 men and 14 women with a mean age of 54 years (range 24-78 years). During the follow-up period, the prevalence of MCs increased from 46.3% to 78%, and 26 patients (63.4%) had Type 2 lesions at the operated level. Of the 22 patients without MCs, 4 (18.2%) converted to Type 1 and 9 (40.9%) to Type 2. Of the 5 Type 1 lesions, 3 (60%) converted to Type 2, and 2 (40%) remained Type 1 but increased in size. In contrast, none of the 14 Type 2 changes converted to another type, although 10 (71.4%) increased in extent. There were no reverse conversions to Type 0. CONCLUSIONS: Following lumbar discectomy, most patients develop Type 2 changes at the operated level, possibly as a result of accelerated degeneration in the operated disc. Neither the preoperative presence of MCs nor their postoperative course appears to affect the clinical outcome.