Search

Las profundas relaciones que unen el mundo de la Quinta Meditación Cartesiana de Husserl al problema de la empatía han sido objeto de muy ricos análisis, dentro del estudio de las formas interpretativas de la intersubjetividad. Este ensayo entreteje el tema empático al mundo de la llamada nostalgia diaspórica en la perspectiva de una valorización teórica del tema de la síntesis pasiva. Los vínculos relacionados con las formas sintéticas generadas por la relación figura-fondo de hecho parecen constituir un terreno ideal para repensar en términos antropológicos el tema de la reciprocidad entre las diferencias, que Husserl utiliza casi obsesivamente en los párrafos más explícitamente metodológicos de ese texto, en un nudo que aspira a resolver el enigma de la forma empática.

Background Indications and outcomes in lumbar spinal fusion for degenerative disease are notoriously heterogenous. Selected subsets of patients show remarkable benefit. However, their objective identification is often difficult. Decision-making may be improved with reliable prediction of long-term outcomes for each individual patient, improving patient selection and avoiding ineffective procedures. Methods Clinical prediction models for long-term functional impairment [Oswestry Disability Index (ODI) or Core Outcome Measures Index (COMI)], back pain, and leg pain after lumbar fusion for degenerative disease were developed. Achievement of the minimum clinically important difference at 12 months postoperatively was defined as a reduction from baseline of at least 15 points for ODI, 2.2 points for COMI, or 2 points for pain severity. Results Models were developed and integrated into a web-app (https://neurosurgery.shinyapps.io/fuseml/) based on a multinational cohort [N = 817; 42.7% male; mean (SD) age: 61.19 (12.36) years]. At external validation [N = 298; 35.6% male; mean (SD) age: 59.73 (12.64) years], areas under the curves for functional impairment [0.67, 95% confidence interval (CI): 0.59–0.74], back pain (0.72, 95%CI: 0.64–0.79), and leg pain (0.64, 95%CI: 0.54–0.73) demonstrated moderate ability to identify patients who are likely to benefit from surgery. Models demonstrated fair calibration of the predicted probabilities. Conclusions Outcomes after lumbar spinal fusion for degenerative disease remain difficult to predict. Although assistive clinical prediction models can help in quantifying potential benefits of surgery and the externally validated FUSE-ML tool may aid in individualized risk–benefit estimation, truly impacting clinical practice in the era of “personalized medicine” necessitates more robust tools in this patient population.

La obra de Piana se caracteriza por el amplio interés en la música. La experiencia perceptiva del material sonoro representa para el filósofo italiano un misterio que debe indagarse en to-dos sus diferentes aspectos. Los sonidos, los materiales de la música, vehiculan expresividad gracias a su propia materialidad fenomenológica y difícilmente podríamos apenas abrir el tema de la expresividad musical, si la materia prima pudiera entenderse como algo expresivamente neutro. Esta declaración apunta a una serie de problemas que deben resolverse en relación con las distinciones elementales que se aplican en este plano, y en el plano de la terminología que les corresponde. El objetivo de este artículo es introducir a los análisis de Piana sobre el soni-do y la experiencia de la escucha.

La obra de Piana se caracteriza por el amplio interés en la música. La experiencia perceptiva del material sonoro representa para el filósofo italiano un misterio que debe indagarse en to-dos sus diferentes aspectos. Los sonidos, los materiales de la música, vehiculan expresividad gracias a su propia materialidad fenomenológica y difícilmente podríamos apenas abrir el tema de la expresividad musical, si la materia prima pudiera entenderse como algo expresivamente neutro. Esta declaración apunta a una serie de problemas que deben resolverse en relación con las distinciones elementales que se aplican en este plano, y en el plano de la terminología que les corresponde. El objetivo de este artículo es introducir a los análisis de Piana sobre el soni-do y la experiencia de la escucha.

Purpose We aimed to summarize the available data on the objective rhinologic outcome after endoscopic transnasal-transsphenoidal (ETT) surgery. Methods Retrospective study on a consecutive cohort of treatment-naïve patients undergoing ETT pituitary gland surgery. Additionally, a systematic review and meta-analysis with focus on the rhinologic outcome, including postoperative smell function was performed. Results The institutional series incorporated 168 patients. A concomitant endoscopic septoplasty was performed in 29/168 patients (17.3%). A nasoseptal flap was used for reconstruction of large skull-base defects or high-flow CSF leaks in 4/168 (2.4%) patients. Early postoperative rhinologic complications (p = 1.0). The systematic review included 19 studies on 1533 patients with a median postoperative epistaxis rate of 1.4% (IQR 1.0–2.2), a postoperative acute rhinosinusitis rate of 2.3% (IQR 2.1–3.0), a postoperative synechiae rate of 7.5% (IQR 1.8–19.1) and a postoperative septal perforation rate of 2.2% (IQR 0.5–5.4). Seven studies including a total of 206 patients reported adequate outcome measures for smell function before and after ETT surgery. Only 2/7 studies reported an impairment of smell function postoperatively, especially in patients with nasoseptal flap harvesting. Conclusion Early and late postoperative rhinologic complication rates after ETT surgery for pituitary lesions seem to be low. A thorough evaluation of smell function, in particular in patients at risk for nasoseptal flap harvesting, may be an important factor in optimal postoperative care.

Considering ileocolic resection as a surgical standard for the treatment of ileocecal valve Crohn's disease, we propose a limited resection of the terminal ileum and ileocecal valve with ileocecal anastomosis.Three patiens between 20 and 37 years of age, diagnosed with Crohn's disease unresponsive to medical therapy, who have stenoses or fissures confined to the terminal ileum and ileocecal valve, seen during instrumental investigations.The proposed procedure allowed us to perform a minimal resection and reconstruction of a new ileocecal valve. Once the symptoms have resolved, at endoscopic follow ups, at 6 and 12 months after surgery, there were no changes in the mucosa of the ileocecal neo-anastomosis.Since Crohn's disease is a systemic disease with a chronic relapsing course complicated by a high rate of post-surgical relapses, it is essential to limit the extension of resections to the macroscopically involved tissues and reduce the anastomotic surfaces. The proposed surgical procedure allows to preserve the caecum and the colon with an optimal postoperative course.We believe that, with specific clinical and endoscopic conditions, the treatment we illustrated can be proposed to other patients as an alternative to the standard VL ileocolic resection.Crohn's Disease, Ileocaecal Valve, Ileocaecal Anastomosis.La malattia di Crohn (MC) è, insieme alla Rettocolite ulcerosa, una malattia infiammatoria cronica dell’intestino (MICI) ad eziopatogenesi multifattoriale. Si distinguono tre profili di malattia associati o meno alla localizzazione a livello perianale non stricturing/non penetrating, stricturing, penetrating. Il quadro clinico e l’evoluzione della patologia sono strettamente correlati al fenotipo. Il trattamento medico, nella maggioranza dei casi, rappresenta il primo step nella gestione del paziente; esso si compone di un ampio ventaglio di scelta tra farmaci anti-infiammatori, cortisonici, immunomodulatori e terapia biologica; la scelta del tipo di farmaco da impiegare viene fatta in funzione del quadro clinico ed anatomopatologico. Il ricorso all’intervento chirurgico è invece indispensabile in presenza di complicanze responsabili di fenomeni occlusivi, perforativi o ascessuali e in caso di fallimento della terapia medica. Tuttavia, in casi selezionati e documentati in letteratura, la terapia chirurgica rappresenta una scelta migliore come primo approccio terapeutico al paziente. Giungono alla nostra attenzione tre pazienti tra i 20 e i 40 anni con diagnosi di Malattia di Crohn non responsiva a trattamento farmacologico. Alle indagini strumentali si individuano stenosi o fissurazioni in corrispondenza dell’ileo terminale e della valvola ileocecale. Le anse a monte delle stenosi appaiono dilatate; alla colonscopia, la mucosa del cieco risulta indenne da malattia o solo lievemente infiammata. L’intervento chirurgico standard per questo tipo di patologia consiste in una resezione ileocolica eseguita in laparoscopia. Dopo una attenta valutazione multispecialistica, accompagnata anche da una revisione della letteratura, si decide di sottoporre i pazienti ad una procedura mininvasiva videolaparoscopica consistente nella resezione dell’ileo terminale stenotico/fistolizzato, asportazione della valvola ileocecale e successivo confezionamento di anastomosi volta a ricreare la valvola rimossa. La tipologia di intervento proposto ci ha consentito di ricreare la valvola effettuando un’anastomosi ileo-cecale e al tempo stesso di risparmiare quanto più intestino possibile considerando l’andamento cronico recidivante proprio della MC. Nel periodo post-operatorio non sono state riscontrate complicanze ed ai controlli endoscopici, a 6 e a 12 mesi dall’intervento, non sono presenti alterazioni della mucosa in corrispondenza dell’anastomosi ileocecale. Riteniamo che, in specifiche condizioni cliniche ed endoscopiche, il trattamento da noi illustrato possa essere proposto ad altri pazienti in alternativa alla resezione ileocolica standard eseguita in VL.

Background Despite improvements in closure techniques by using a vital nasoseptal flap, the use of sealing materials, and improved neurosurgical techniques, cerebrospinal fluid (CSF) leak after transsphenoidal surgery still is a clinically relevant problem. Liqoseal® (Polyganics bv, Groningen, The Netherlands) is a CE-approved bioresorbable sealant patch for use as an adjunct to standard methods of cranial dural closure to prevent CSF leakage. This study aims to evaluate the application of Liqoseal in transsphenoidal surgery ex vivo and in vivo. Methods 1. We created an ex vivo setup simulating the sphenoidal anatomy, using a fluid pump and porcine dura positioned on a conus with the anatomical dimensions of the sella to evaluate whether the burst pressure of Liqoseal applied to a bulging surface was above physiological intracranial pressure. Burst pressure was measured with a probe connected to dedicated computer software. Because of the challenging transsphenoidal environment, we tested in 4 groups with varying compression weight and time for the application of Liqoseal. 2. We subsequently describe the application of Liqoseal® in 3 patients during transsphenoidal procedures with intraoperative CSF leakage to prevent postoperative CSF leakage. Results 1. Ex vivo: The overall mean burst pressure in the transsphenoidal setup was 231 (± 103) mmHg. There was no significant difference in mean burst pressure between groups based on application weight and time (p = 0.227). 2. In Vivo: None of the patients had a postoperative CSF leak. No nose passage problems were observed. One patient had a postoperative meningitis and ventriculitis, most likely related to preoperative extensive CSF leakage. Postoperative imaging did not show any local infection, swelling, or other device-related adverse effects. Conclusions We assess the use of Liqoseal® to seal a dural defect during an endoscopic transsphenoidal procedure as to be likely safe and potentially effective.

Minimally invasive surgery (MIS) is a widespread approach in general surgery. Computer guiding software, such as the augmented reality (AR), the virtual reality (VR) and mixed reality (MR), has been proposed to help surgeons during MIS. This study aims to report these technologies' current knowledge and diffusion during surgical training in Italy. A web-based survey was developed under the aegis of the Italian Society of Endoscopic Surgery (SICE). Two hundred and seventeen medical doctors' answers were analyzed. Participants were surgeons (138, 63.6%) and residents in surgery (79, 36.4%). The mean knowledge of the role of the VR, AR and MR in surgery was 4.9 ± 2.4 (range 1-10). Most of the participants (122, 56.2%) did not have experience with any proposed technologies. However, although the lack of experience in this field, the answers about the functioning of the technologies were correct in most cases. Most of the participants answered that VR, AR and MR should be used more frequently for the teaching and training and during the clinical activity (170, 80.3%) and that such technologies would make a significant contribution, especially in training (183, 84.3%) and didactic (156, 71.9%). Finally, the main limitations to the diffusion of these technologies were the insufficient knowledge (182, 83.9%) and costs (175, 80.6%). Based on the present study, in Italy, the knowledge and dissemination of these technologies are still limited. Further studies are required to establish the usefulness of AR, VR and MR in surgical training.

OBJECTIVE Enhanced Recovery After Surgery (ERAS) has led to a paradigm shift in perioperative care through multimodal interventions. Still, ERAS remains a relatively new concept in neurosurgery, and there is no summary of evidence on ERAS applications in cranial neurosurgery. METHODS The authors systematically reviewed the literature using the PubMed/MEDLINE, Embase, Scopus, and Cochrane Library databases for ERAS protocols and elements. Studies had to assess at least one pre-, peri-, or postoperative ERAS element and evaluate at least one of the following outcomes: 1) length of hospital stay, 2) length of ICU stay, 3) postoperative pain, 4) direct and indirect healthcare cost, 5) complication rate, 6) readmission rate, or 7) patient satisfaction. RESULTS A final 27 articles were included in the qualitative analysis, with mixed quality of evidence ranging from high in 3 cases to very low in 1 case. Seventeen studies reported a complete ERAS protocol. Preoperative ERAS elements include patient selection through multidisciplinary team discussion, patient counseling and education to adjust expectations of the postoperative period, and mental state assessment; antimicrobial, steroidal, and antiepileptic prophylaxes; nutritional assessment, as well as preoperative oral carbohydrate loading; and postoperative nausea and vomiting (PONV) prophylaxis. Anesthesiology interventions included local anesthesia for pin sites, regional field block or scalp block, avoidance or minimization of the duration of invasive monitoring, and limitation of intraoperative mannitol. Other intraoperative elements include absorbable skin sutures and avoidance of wound drains. Postoperatively, the authors identified early extubation, observation in a step-down unit instead of routine ICU admission, early mobilization, early fluid de-escalation, early intake of solid food and liquids, early removal of invasive monitoring, professional nutritional assessment, PONV management, nonopioid rescue analgesia, and early postoperative imaging. Other postoperative interventions included discharge criteria standardization and home visits or progress monitoring by a nurse. CONCLUSIONS A wide range of evidence-based interventions are available to improve recovery after elective craniotomy, although there are few published ERAS protocols. Patient-centered optimization of neurosurgical care spanning the pre-, intra-, and postoperative periods is feasible and has already provided positive results in terms of improved outcomes such as postoperative pain, patient satisfaction, reduced length of stay, and cost reduction with an excellent safety profile. Although fast-track recovery protocols and ERAS studies are gaining momentum for elective craniotomy, prospective trials are needed to provide stronger evidence.

Recent therapeutic advances in metastatic melanoma have led to improved overall survival (OS) rates, with consequently an increased incidence of brain metastases (BM). The role of BM resection in the era of targeted and immunotherapy should be reassessed. In the current study we analysed the role of residual intracranial tumour load in a cohort of melanoma BM patients.Retrospective single-centre analysis of a prospective registry of resected melanoma BM from 2013 to 2021. Correlations of residual tumour volume and outcome were determined with respect to patient, tumour and treatment regimens characteristics.121 individual patients (66% male, mean age 59.9 years) were identified and included in the study. Pre- and postoperative systemic treatments included BRAF/MEK inhibitors, as well as combination or monotherapy of immune-checkpoint inhibitors (ICIs). Median OS of the entire cohort was 20 months. Cox proportional-hazard analysis revealed postoperative anti-CTLA4+anti-PD-1 therapy (HR 0.07, p = .01) and postoperative residual intracranial tumour burden (HR 1.4, p = .027) as significant predictors for OS. Further analysis revealed that ICI-naïve patients with residual tumour volume ≤3.5 cmsup3/supand postoperative ICI showed significantly prolonged OS compared to patients with residual volumegt;3.5 cmsup3/sup(p lt; .0001). Subgroup analysis of ICI-naïve patients showed steroid intake postoperatively to be negatively associated with OS, however residual tumour volume ≤3.5 cmsup3/supremained independently correlated with superior OS (HR 0.14, p lt; .001).Besides known predictive factors like postoperative ICI, a maximal intracranial tumour burden reduction seems to be beneficial, especially in ICI-naïve patients. This highlights the importance of local CNS control and the need to further investigating the role of initial surgical tumour load reduction in randomised clinical trials.

BACKGROUND The literature on white matter anatomy underlying the human orbitofrontal cortex (OFC) is scarce in spite of its relevance for glioma surgery. OBJECTIVE To describe the anatomy of the OFC and of the underlying white matter fiber anatomy, with a particular focus on the surgical structures relevant for a safe and efficient orbitofrontal glioma resection. Based on anatomical and radiological data, the secondary objective was to describe the growth pattern of OFC gliomas. METHODS The study was performed on 10 brain specimens prepared according to Klingler's protocol and dissected using the fiber microdissection technique modified according to U.T., under the microscope at high magnification. RESULTS A detailed stratigraphy of the OFC was performed, from the cortex up to the frontal horn of the lateral ventricle. The interposed neural structures are described together with relevant neighboring topographic areas and nuclei. Combining anatomical and radiological data, it appears that the anatomical boundaries delimiting and guiding the macroscopical growth of OFC gliomas are as follows: the corpus callosum superiorly, the external capsule laterally, the basal forebrain and lentiform nucleus posteriorly, and the gyrus rectus medially. Thus, OFC gliomas seem to grow ventriculopetally, avoiding the laterally located neocortex. CONCLUSION The findings in our study supplement available anatomical knowledge of the OFC, providing reliable landmarks for a precise topographical diagnosis of OFC lesions and for perioperative orientation. The relationships between deep anatomic structures and glioma formations described in this study are relevant for surgery in this highly interconnected area.

OBJECTIVE Decision-making for intracranial tumor surgery requires balancing the oncological benefit against the risk for resection-related impairment. Risk estimates are commonly based on subjective experience and generalized numbers from the literature, but even experienced surgeons overestimate functional outcome after surgery. Today, there is no reliable and objective way to preoperatively predict an individual patient’s risk of experiencing any functional impairment. METHODS The authors developed a prediction model for functional impairment at 3 to 6 months after microsurgical resection, defined as a decrease in Karnofsky Performance Status of ≥ 10 points. Two prospective registries in Switzerland and Italy were used for development. External validation was performed in 7 cohorts from Sweden, Norway, Germany, Austria, and the Netherlands. Age, sex, prior surgery, tumor histology and maximum diameter, expected major brain vessel or cranial nerve manipulation, resection in eloquent areas and the posterior fossa, and surgical approach were recorded. Discrimination and calibration metrics were evaluated. RESULTS In the development (2437 patients, 48.2% male; mean age ± SD: 55 ± 15 years) and external validation (2427 patients, 42.4% male; mean age ± SD: 58 ± 13 years) cohorts, functional impairment rates were 21.5% and 28.5%, respectively. In the development cohort, area under the curve (AUC) values of 0.72 (95% CI 0.69–0.74) were observed. In the pooled external validation cohort, the AUC was 0.72 (95% CI 0.69–0.74), confirming generalizability. Calibration plots indicated fair calibration in both cohorts. The tool has been incorporated into a web-based application available at https://neurosurgery.shinyapps.io/impairment/. CONCLUSIONS Functional impairment after intracranial tumor surgery remains extraordinarily difficult to predict, although machine learning can help quantify risk. This externally validated prediction tool can serve as the basis for case-by-case discussions and risk-to-benefit estimation of surgical treatment in the individual patient.

Background Residual tumor tissue after pituitary adenoma surgery, is linked with additional morbidity and mortality. Intraoperative magnetic resonance imaging (ioMRI) could improve resection. We aim to assess the improvement in gross total resection (GTR), extent of resection (EOR), and residual tumor volume (RV) achieved using ioMRI. Methods A systematic review was carried out on PubMed/MEDLINE to identify any studies reporting intra- and postoperative (1) GTR, (2) EOR, or (3) RV in patients who underwent resection of pituitary adenomas with ioMRI. Random effects meta-analysis of the rate of improvement after ioMRI for these three surgical outcomes was intended. Results Among 34 included studies (2130 patients), the proportion of patients with conversion to GTR (∆GTR) after ioMRI was 0.19 (95% CI 0.15–0.23). Mean ∆EOR was + 9.07% after ioMRI. Mean ∆RV was 0.784 cm3. For endoscopically treated patients, ∆GTR was 0.17 (95% CI 0.09–0.25), while microscopic ∆GTR was 0.19 (95% CI 0.15–0.23). Low-field ioMRI studies demonstrated a ∆GTR of 0.19 (95% CI 0.11–0.28), while high-field and ultra-high-field ioMRI demonstrated a ∆GTR of 0.19 (95% CI 0.15–0.24) and 0.20 (95% CI 0.13–0.28), respectively. Conclusions Our meta-analysis demonstrates that around one fifth of patients undergoing pituitary adenoma resection convert from non-GTR to GTR after the use of ioMRI. EOR and RV can also be improved to a certain extent using ioMRI. Endoscopic versus microscopic technique or field strength does not appear to alter the impact of ioMRI. Statistical heterogeneity was high, indicating that the improvement in surgical results due to ioMRI varies considerably by center.

A nuclear protein of testis (NUT) carcinoma, also known as NUT midline carcinoma, is a rare subtype of squamous carcinoma known for its aggressive growth behaviour. It can form anywhere in the body. Although, it usually occurs along midline structures (head, neck, lungs). The authors present the first report of intrasellar NUT carcinoma with cavernous sinus infiltration in a 47-year-old patient. MRI showed an inhomogeneous, gadolinium-enhancing lesion with intra- and suprasellar growth, invasion of the cavernous sinus without clear differentiation from normal pituitary tissue. Given the lymphoma diagnosis in the frozen section and invasion of the cavernous sinus, the patient underwent endoscopic, transnasal, and transsphenoidal subtotal resection only. Local tumour and spinal metastases showed a good response to radio-chemotherapy. Despite combined radio-chemotherapy, the patient died of pulmonary insufficiency due to rapid progression of pulmonary metastasis 6 months after the initial diagnosis.

Hyponatremia after pituitary surgery is a frequent finding with potential severe complications and the most common cause for readmission. Several studies have found parameters associated with postoperative hyponatremia, but no reliable specific predictor was described yet. This pilot study evaluates the feasibility of machine learning (ML) algorithms to predict postoperative hyponatremia after resection of pituitary lesions. Retrospective screening of a prospective registry of patients who underwent transsphenoidal surgery for pituitary lesions. Hyponatremia within 30 days after surgery was the primary outcome. Several pre- and intraoperative clinical, procedural and laboratory features were selected to train different ML algorithms. Trained models were compared using common performance metrics. Final model was internally validated on the testing dataset. From 207 patients included in the study, 44 (22%) showed a hyponatremia within 30 days postoperatively. Hyponatremic measurements peaked directly postoperatively (day 0–1) and around day 7. Bootstrapped performance metrics of different trained ML-models showed largest area under the receiver operating characteristic curve (AUROC) for the boosted generalized linear model (67.1%), followed by the Naive Bayes classifier (64.6%). The discriminative capability of the final model was assessed by predicting on unseen dataset. Large AUROC (84.3%; 67.0–96.4), sensitivity (81.8%) and specificity (77.5%) with an overall accuracy of 78.4% (66.7–88.2) was reached. Our trained ML-model was able to learn the complex risk factor interactions and showed a high discriminative capability on unseen patient data. In conclusion, ML-methods can predict postoperative hyponatremia and thus potentially reduce morbidity and improve patient safety.

Purpose Biochemical remission (BR), gross total resection (GTR), and intraoperative cerebrospinal fluid (CSF) leaks are important metrics in transsphenoidal surgery for acromegaly, and prediction of their likelihood using machine learning would be clinically advantageous. We aim to develop and externally validate clinical prediction models for outcomes after transsphenoidal surgery for acromegaly. Methods Using data from two registries, we develop and externally validate machine learning models for GTR, BR, and CSF leaks after endoscopic transsphenoidal surgery in acromegalic patients. For the model development a registry from Bologna, Italy was used. External validation was then performed using data from Zurich, Switzerland. Gender, age, prior surgery, as well as Hardy and Knosp classification were used as input features. Discrimination and calibration metrics were assessed. Results The derivation cohort consisted of 307 patients (43.3% male; mean [SD] age, 47.2 [12.7] years). GTR was achieved in 226 (73.6%) and BR in 245 (79.8%) patients. In the external validation cohort with 46 patients, 31 (75.6%) achieved GTR and 31 (77.5%) achieved BR. Area under the curve (AUC) at external validation was 0.75 (95% confidence interval: 0.59–0.88) for GTR, 0.63 (0.40–0.82) for BR, as well as 0.77 (0.62–0.91) for intraoperative CSF leaks. While prior surgery was the most important variable for prediction of GTR, age, and Hardy grading contributed most to the predictions of BR and CSF leaks, respectively. Conclusions Gross total resection, biochemical remission, and CSF leaks remain hard to predict, but machine learning offers potential in helping to tailor surgical therapy. We demonstrate the feasibility of developing and externally validating clinical prediction models for these outcomes after surgery for acromegaly and lay the groundwork for development of a multicenter model with more robust generalization.

Machine learning (ML) and artificial intelligence (AI) applications in the field of neuroimaging have been on the rise in recent years, and their clinical adoption is increasing worldwide. Deep learning (DL) is a field of ML that can be defined as a set of algorithms enabling a computer to be fed with raw data and progressively discover-through multiple layers of representation-more complex and abstract patterns in large data sets. The combination of ML and radiomics, namely the extraction of features from medical images, has proven valuable, too: Radiomic information can be used for enhanced image characterization and prognosis or outcome prediction. This chapter summarizes the basic concepts underlying ML application for neuroimaging and discusses technical aspects of the most promising algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), in order to provide the readership with the fundamental theoretical tools to better understand ML in neuroimaging. Applications are highlighted from a practical standpoint in the last section of the chapter, including: image reconstruction and restoration, image synthesis and super-resolution, registration, segmentation, classification, and outcome prediction.

Selecting a set of features to include in a clinical prediction model is not always a simple task. The goals of creating parsimonious models with low complexity while, at the same time, upholding predictive performance by explaining a large proportion of the variance within the dependent variable must be balanced. With this aim, one must consider the clinical setting and what data are readily available to clinicians at specific timepoints, as well as more obvious aspects such as the availability of computational power and size of the training dataset. This chapter elucidates the importance and pitfalls in feature selection, focusing on applications in clinical prediction modeling. We demonstrate simple methods such as correlation-, significance-, and variable importance-based filtering, as well as intrinsic feature selection methods such as Lasso and tree- or rule-based methods. Finally, we focus on two algorithmic wrapper methods for feature selection that are commonly used in machine learning: Recursive Feature Elimination (RFE), which can be applied regardless of data and model type, as well as Purposeful Variable Selection as described by Hosmer and Lemeshow, specifically for generalized linear models.

Radiomics defines a set of techniques for extraction and quantification of digital medical data in an automated and reproducible way. Its goal is to detect features potentially related to a clinical task, like classification, diagnosis, prognosis, and response to treatment, going beyond the intrinsic limits of operator-dependency and qualitative description of conventional radiological evaluation on a mesoscopic scale. In the field of neuro-oncology, researchers have tried to create prognostic models for a better tumor diagnosis, histological and biomolecular classification, prediction of response to treatment, and identification of disease relapse. Concerning glioma surgery, the most significant aid that radiomics can give to surgery is to improve tumor extension detection and identify areas that are more prone to recurrence to increase the extent of tumor resection, thereby ameliorating the patients' prognosis. This chapter aims to review the fundamentals of radiomics models' creation, the latest advance of radiomics in neuro-oncology, and possible radiomic features associated with the extent of resection in the brain gliomas.

Machine learning (ML) and artificial intelligence (AI) applications in the field of neuroimaging have been on the rise in recent years, and their clinical adoption is increasing worldwide. Deep learning (DL) is a field of ML that can be defined as a set of algorithms enabling a computer to be fed with raw data and progressively discover-through multiple layers of representation-more complex and abstract patterns in large data sets. The combination of ML and radiomics, namely the extraction of features from medical images, has proven valuable, too: Radiomic information can be used for enhanced image characterization and prognosis or outcome prediction. This chapter summarizes the basic concepts underlying ML application for neuroimaging and discusses technical aspects of the most promising algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), in order to provide the readership with the fundamental theoretical tools to better understand ML in neuroimaging. Applications are highlighted from a practical standpoint in the last section of the chapter, including: image reconstruction and restoration, image synthesis and super-resolution, registration, segmentation, classification, and outcome prediction.

Machine learning applications in neurosurgery are increasingly reported for diverse tasks such as faster and more accurate preoperative diagnosis, enhanced lesion characterization, as well as surgical outcome, complications and healthcare cost prediction. Even though the pertinent literature in pituitary surgery is less extensive with respect to other neurosurgical diseases, past research attempted to answer clinically relevant questions to better assist surgeons and clinicians. In the present chapter we review reported ML applications in pituitary surgery including differential diagnosis, preoperative lesion characterization (immunohistochemistry, cavernous sinus invasion, tumor consistency), surgical outcome and complication predictions (gross total resection, tumor recurrence, and endocrinological remission, cerebrospinal fluid leak, postoperative hyponatremia). Moreover, we briefly discuss from a practical standpoint the current barriers to clinical translation of machine learning research. On the topic of pituitary surgery, published reports can be considered mostly preliminary, requiring larger training populations and strong external validation. Thoughtful selection of clinically relevant outcomes of interest and transversal application of model development pipeline-together with accurate methodological planning and multicenter collaborations-have the potential to overcome current limitations and ultimately provide additional tools for more informed patient management.