Search Results (6)

Background: Pituitary neuroendocrine tumours (PitNETs) are clinically and biologically heterogeneous neoplasms that remain challenging to diagnose, prognosticate, and treat. Although recent WHO classifications using transcription-factor-based markers have refined pathological categorisation, histopathology alone still fails to predict tumour behaviour or support individualised therapy. Objective: This systematic review aimed to evaluate how machine learning (ML) and knowledge extraction approaches can complement pathology by integrating multi-dimensional omics datasets to generate predictive and clinically meaningful insights in PitNETs. Methods: The review followed the PRISMA 2020 statement for systematic reviews. Searches were conducted in PubMed, Google Scholar, arXiv, and SciSpace up to June 2025 to identify omics studies applying ML or computational data integration in PitNETs. Eligible studies included original research using genomic, transcriptomic, epigenomic, proteomic, or liquid biopsy data. Data extraction covered study design, ML methodology, data accessibility, and clinical annotation. Study quality and validation strategies were also assessed. Results: A total of 726 records were identified. After the reviewing process, 98 studies met inclusion criteria. PitNET research employed unsupervised clustering or regularised regression methods reflecting their suitability for high-dimensional omics datasets and the limited sample sizes. In contrast, deep learning approaches were rarely implemented, primarily due to the scarcity of large, clinically annotated cohorts required to train such models effectively. To support future research and model development, we compiled a comprehensive catalogue of all publicly available PitNET omics resources, facilitating reuse, methodological benchmarking, and integrative analyses. Conclusions: Although omics research in PitNETs is increasing, the lack of standardised, clinically annotated datasets remains a major obstacle to the development and deployment of robust predictive models. Coordinated efforts in data sharing and clinical harmonisation are required to unlock its full potential. Full article

BACKGROUND: Maximal safe resection is the objective of most neuro-oncological operations. Intraoperative magnetic resonance imaging (iMRI) may guide the surgeon to improve the extent of safe resection. There is limited evidence comparing the impact of iMRI on the rates of further resection between tumour types. AIM: To investigate the impact of iMRI on the rate of further resection following visualisation of residual tumour. METHODS: A retrospective cohort study identified all intracranial tumour operations performed in the 1.5 T iMRI machine of a single centre (2007–2023). Patients were identified using SurgiNet and were grouped according to their histopathological diagnosis in accordance with the WHO 2021 classification. The primary outcome was the rate of reoperation due to iMRI visualisation of residual tumours. RESULTS: A total of 574 cases were identified, including 152 low-grade gliomas (LGG), 108 high-grade gliomas (HGG), 194 pituitary neuroendocrine tumours (PitNETs), 15 metastases, and 6 meningiomas. Further resection following iMRI visualisation occurred in 45% of LGG cases, 47% of HGG cases, 29% of PitNET cases, and no meningioma or metastasis cases. Chi-square analysis showed that the rate of further resection after iMRI use across 2018–2023 was significantly higher than that across 2007–2012 (46% versus 33%, p = 0.036). CONCLUSION: Intraoperative MRI for guiding further resection was most useful in cases of LGG and HGG, possibly reflecting the difficulty of differentiating these tumour types from normal brain tissue. In addition, there was increased reliance on iMRI over time, which may represent our surgeons becoming accustomed to its use. Full article

Therapeutic options for pituitary neuroendocrine tumours (PitNETs) refractory to temozolomide are scarce. Immune checkpoint inhibitors (ICIs), particularly inhibitors of the programmed cell death-1 (PD-1) pathway and its ligand (PD-L1), have been experimentally used in aggressive or metastatic PitNETs. We aimed to study the therapeutic usefulness of anti-PD-1 drugs in patients with aggressive or metastatic PitNETs. Published cases and case series involving patients with PitNETs treated with PD-1/PD-L1 inhibitors were reviewed. Demographic data, clinical–pathological features, previous therapies, drug dosage and posology, and the best radiological and biochemical responses, as well as survival data, were evaluated. We identified 29 cases of aggressive (n = 13) or metastatic (n = 16) PitNETs treated with PD-1/PD-L1 inhibitors. The hypersecretion of adrenocorticotropic hormone (ACTH) was documented in eighteen cases (62.1%), seven were prolactinomas (24.1%), and four were non-functioning PitNETs. All patients underwent various therapies prior to using ICIs. Overall, a positive radiological response (i.e., partial/complete radiological response and stable disease) was observed in eighteen of twenty-nine cases (62.1%), of which ten and four were ACTH- and prolactin-secreting PitNETs, respectively. Hormonal levels reduced or stabilised after using ICIs in 11 of the 17 functioning PitNET cases with available data (64.7%). The median survival of patients treated with ICIs was 13 months, with a maximum of 42 months in two ACTH-secreting tumours. Among 29 patients with PitNETs treated with PD-1/PD-L1 inhibitors, the positive radiological and biochemical response rates were 62.1% and 64.7%, respectively. Altogether, these data suggest a promising role of ICIs in patients with aggressive or metastatic PitNETs refractory to other treatment modalities. Full article

Post-operative tumour progression in patients with non-functioning pituitary neuroendocrine tumours is variable. The aim of this study was to use machine learning (ML) models to improve the prediction of post-operative outcomes in patients with NF PitNET. We studied data from 383 patients who underwent surgery with or without radiotherapy, with a follow-up period between 6 months and 15 years. ML models, including k-nearest neighbour (KNN), support vector machine (SVM), and decision tree, showed superior performance in predicting tumour progression when compared with parametric statistical modelling using logistic regression, with SVM achieving the highest performance. The strongest predictor of tumour progression was the extent of surgical resection, with patient age, tumour volume, and the use of radiotherapy also showing influence. No features showed an association with tumour recurrence following a complete resection. In conclusion, this study demonstrates the potential of ML models in predicting post-operative outcomes for patients with NF PitNET. Future work should look to include additional, more granular, multicentre data, including incorporating imaging and operative video data. Full article

Pituitary neuroendocrine tumours (PitNETs) are usually benign and slow-growing; however, in some cases, they may behave aggressively and become resistant to conventional treatments. Therapeutic options for aggressive or metastatic PitNETs are limited, and currently mainly consist of temozolomide, with little experience of other emerging approaches, including peptide receptor radionuclide therapy (PRRT). Somatostatin receptor expression in PitNETs explains the effectiveness of somatostatin analogues for treating PitNETs, particularly those hypersecreting pituitary hormones, such as growth hormone or adrenocorticotropic hormone. The expression of such receptors in pituitary tumour cells has provided the rationale for using PRRT to treat patients with aggressive or metastatic PitNETs. However, the PRRT efficacy in this setting remains unestablished, as knowledge on this today is based only on few case reports and small series of cases, which are reviewed here. A total of 30 PRRT-treated patients have been thus far reported: 23 aggressive PitNETs, 5 carcinomas, and 2 of malignancy status unspecified. Of the 27 published cases with information regarding the response to PRRT, 5 (18%) showed a partial response, 8 (30%) had stable disease, and 14 (52%) had progressive disease. No major adverse effects have been reported, and there is also no increased risk of clinically relevant hypopituitarism in patients with pituitary or non-pituitary neuroendocrine tumours following PRRT. PRRT may be regarded as a safe option for patients with aggressive or metastatic PitNETs if other treatment approaches are not feasible or have failed in controlling the disease progression, with tumour shrinkage occurring in up to a fifth of cases, while about a third of aggressive pituitary tumours may achieve stable disease. Here, the data on PRRT in the management of patients with aggressive pituitary tumours are reviewed, as well as the effects of PRRT on the pituitary function in other PRRT-treated cancer patients. Full article

miR-17-5p and E2F1 have been described as deregulated in cancer, but they have scarcely been studied in pituitary neuroendocrine tumours (PitNETs). This study evaluates the relationship of E2F1 and miR-17-5p with the invasiveness and proliferation of PitNETs. In this cross-sectional descriptive study, we evaluated the expression of E2F1, MYC, and miR-17-5p by quantitative real time PCR analysis in 60 PitNETs: 29 gonadotroph (GT), 15 functioning somatotroph (ST), and 16 corticotroph (CT) tumours, of which 8 were silent (sCT). The clinical data were collected from the Spanish Molecular Register of Pituitary Adenomas (REMAH) database. We defined invasiveness according to the Knosp classification and proliferation according to a molecular expression of Ki-67 ≥ 2.59. E2F1 was more expressed in invasive than in non-invasive tumours in the whole series (p = 0.004) and in STs (p = 0.01). In addition, it was overexpressed in the silent subtypes (GTs and sCTs; all macroadenomas) and normoexpressed in the functioning ones (fCTs and STs; some microadenomas). miR-17-5p was more expressed in proliferative than in non-proliferative tumours (p = 0.041) in the whole series but not by subtypes. Conclusions: Our study suggests that in PitNETs, E2F1 could be a good biomarker of invasiveness, and miR-17-5p of proliferation, helping the clinical management of these tumours. Full article