Predicting Subtype of Growth Hormone Pituitary Adenoma based on Magnetic Resonance Imaging Characteristics.

PURPOSE: This study aimed to investigate the value of magnetic resonance (MR) characteristics in differentiating the subtypes of growth hormone pituitary adenomas. MATERIALS AND METHODS: The clinical and MR imaging data of 70 patients with growth hormone pituitary adenoma confirmed by surgery and pathology were retrospectively analyzed. The tumors were divided into dense granular (DG; 36 cases) and sparse granular subtypes (SG; 34 cases). The tumors' MR features were analyzed, including the mean and maximum diameters, T2 signal intensity, T2 relative signal intensity (rSI), homogeneity, enhancement degree, and invasiveness (Knosp grade). Mann-Whitney U test and χ2 test were used to analyze MR characteristics between the 2 groups. The independent predictors and predictive probabilities of tumor subtypes were obtained via a logistic regression model, and the efficacy was compared by receiver operating characteristic curve. RESULTS: The mean and maximum diameters of growth hormone adenoma in DG and SG were 1.77 versus 2.45 and 1.95 versus 3.00 cm (median, P < 0.05), respectively. There was a significant difference between the 2 groups in T2 signal intensity and rSI (P values were 0.02 and 0.001, respectively). Most DG adenomas (86.1%) appeared as hypointense on T2 images, and 38.2% of SG adenomas were hyperintense. There was no significant difference in tumor homogeneity (P = 0.622). A significant difference was found in the Knosp grade between the 2 subtypes (P = 0.004). In addition, the enhancement degree of SG adenomas was significantly higher than that of DG adenomas (P = 0.001). Logistic regression analysis showed that high T2 rSI value and marked contrast enhancement were independent predictors of the 2 subtypes, and the odds ratios were 4.811 and 4.649, respectively. The multivariate logistic model obtained relatively high predicting efficacy, and the area under the curve, sensitivity, and specificity were 0.765, 0.882, and 0.500, respectively. CONCLUSIONS: There are significant differences in tumor size, T2 signal intensity, T2 rSI, enhancement degree, and invasiveness between DG and SG adenomas. The logistic model based on the marked contrast enhancement and high T2 rSI value has an important value in predicting the subtype of growth hormone adenoma.

In-depth proteomic profiling captures subtype-specific features of craniopharyngiomas.

Craniopharyngiomas are rare epithelial tumors derived from pituitary gland embryonic tissue. This epithelial tumor can be categorized as an adamantinomatous craniopharyngioma (ACP) or papillary craniopharyngioma (PCP) subtype with histopathological and genetic differences. Genomic and transcriptomic profiles of craniopharyngiomas have been investigated; however, the proteomic profile has yet to be elucidated and added to these profiles. Recent improvements in high-throughput quantitative proteomic approaches have introduced new opportunities for a better understanding of these diseases and the efficient discovery of biomarkers. We aimed to confirm subtype-associated proteomic changes between ACP and PCP specimens. We performed a system-level proteomic study using an integrated approach that combines mass spectrometry-based quantitative proteomic, statistical, and bioinformatics analyses. The bioinformatics analysis showed that differentially expressed proteins between ACP and PCP were significantly involved in mitochondrial organization, fatty acid metabolic processes, exocytosis, the inflammatory response, the cell cycle, RNA splicing, cell migration, and neuron development. Furthermore, using network analysis, we identified hub proteins that were positively correlated with ACP and PCP phenotypes. Our findings improve our understanding of the pathogenesis of craniopharyngiomas and provide novel insights that may ultimately translate to the development of craniopharyngioma subtype-specific therapeutics.

Association of different pathologic subtypes of growth hormone producing pituitary adenoma and remission in acromegaly patients: a retrospective cohort study.

BACKGROUND: Regarding the inconclusive results of previous investigations, this study aimed to determine the association between pathology, as a possible predictor, with remission outcomes, to know the role of pathology in the personalized decision making in acromegaly patients. METHODS: A retrospective cohort study was performed on the consecutive surgeries for growth hormone (GH) producing pituitary adenomas from February 2015 to January 2021. Seventy-one patients were assessed for granulation patterns and prolactin co-expression as dual staining adenomas. The role of pathology and some other predictors on surgical remission was evaluated using logistic regression models. RESULTS: Among 71 included patients, 34 (47.9%) patients had densely granulated (DG), 14 (19.7%) had sparsely granulated (SG), 23 (32.4%) had dual staining pituitary adenomas. The remission rate was about 62.5% in the patients with SG and DG adenomas named single staining and 52.2% in dual staining groups. Postoperative remission was 1.53-folds higher in the single staining adenomas than dual staining-one (non-significant). The remission rate was doubled in DG group compared to two other groups (non-significant). By adjusting different predictors, cavernous sinus invasion and one-day postoperative GH levels decreased remission rate by 91% (95% CI: 0.01-0.67; p = 0.015) and 64% (95% CI: 0.19-0.69; p < 0.001), respectively. Responses to the medications were not significantly different among three groups. CONCLUSION: Various pathological subtypes of pituitary adenomas do not appear to have a predictive role in estimating remission outcomes. Cavernous sinus invasion followed by one-day postoperative GH is the strongest parameter to predict biochemical remission.

Molecular, functional, and histopathological classification of the pituitary neuroendocrine neoplasms.

In 2017, WHO published an updated classification of the pituitary adenomas according to the lineages defined by the transcription factors, PIT1, SF1 and TPIT. Nomenclature of the pituitary tumors follows the mature cell types such as somatotroph (GH), lactotroph (LH), thyrotroph, corticotroph, and gonadotroph (FSH, LH). Null cell adenomas are defined by the absence of expression of any hormones and transcription factors. Not infrequently, the pituitary adenomas are invasive to the adjacent structures and are designated as aggressive adenomas. Knosp grading is often used to define the aggressiveness of the tumor. Sparsely granulated somatotroph adenomas and Crooke cell corticotroph adenomas are representative aggressive adenomas. Recently, genomics regarding various adenomas have been clarified, such as GNAS for somatotrophs and USP8 for corticotrophs. Familial pituitary adenomas are another aspect which has been clarified such as MEN1, Carney's complex, familial isolated pituitary adenoma and McCune-Albright syndrome. The pituitary adenomas often produce GH or PRL, hormones of PIT1 transcription factor. It has been agreed that the pituitary adenomas share the characteristics of neuroendocrine neoplasms. The terminology of pituitary neuroendocrine tumor has been discussed. This review article covers various aspects of pituitary adenomas.

Recommendations on the pathological report of pituitary tumors. A consensus of experts of the Spanish Society of Endocrinology and Nutrition and the Spanish Society of Pathology.

Pituitary neuroendocrine tumors (PitNETs) constitute, together with other tumors of the sellar region, 15-25% of intracranial neoplasms. In 2017, the World Health Organization proposed a new classification of PitNETs. The main innovation with respect to the 2004 classification was the recommendation to include in the immunohistochemical evaluation of PitNETs the determination of the transcription factors of the 3 pituitary cell lineages: Pit-1, Tpit and SF-1. Additionally, other clinicopathological classifications with a predictive capacity of tumor behavior during follow-up were proposed. Given these changes, it is appropriate to adapt the knowledge generated during the last 15 years to the daily practice of the treatment and monitoring of PitNETs at the Centers of Excellence in Pituitary Pathology. This document includes the positioning of the Spanish Society of Endocrinology and Nutrition (SEEN) and the Spanish Society of Pathology (SEAP) on the classification and denomination of the PitNETs and the information that the pathologist should provide to the clinician to facilitate the treatment and monitoring of these tumors.

Pituitary neuroendocrine tumors: a model for neuroendocrine tumor classification.

The classification of adenohypophysial neoplasms as "pituitary neuroendocrine tumors" (PitNETs) was proposed in 2017 to reflect their characteristics as epithelial neuroendocrine neoplasms with a spectrum of clinical behaviors ranging from small indolent lesions to large, locally invasive, unresectable tumors. Tumor growth and hormone hypersecretion cause significant morbidity and mortality in a subset of patients. The proposal was endorsed by a WHO working group that sought to provide a unified approach to neuroendocrine neoplasia in all body sites. We review the features that are characteristic of neuroendocrine cells, the epidemiology and prognosis of these tumors, as well as further refinements in terms used for other pituitary tumors to ensure consistency with the WHO framework. The intense study of PitNETs has provided information about the importance of cellular differentiation in tumor prognosis as a model for neuroendocrine tumors in different locations.

Incidence and Possible Predictors of Sodium Disturbance After Craniopharyngioma Resection Based on QST Classification.

OBJECTIVE: Serum sodium abnormalities are one of the most common manifestations after radical craniopharyngioma (CP) excision. The aim of this study was to report the incidence and possible predictors of serum sodium disturbance and explore features of sodium destabilization manifestation among QST classification results after CP resection. METHODS: A retrospective analysis was performed of clinical, biochemical, radiologic, and operative data for 134 successive patients who underwent primary CP removal between September 2016 and March 2018. Univariate and multivariate analyses were conducted to determine predictors. RESULTS: Sixty patients (44.8%) experienced hyponatremia and 67 patients (50%) hypernatremia; the median time of onset was 6 days and the first day after surgery, respectively. The incidence, onset, severity, and type of sodium disturbance among different types of CP differed significantly based on statistical tests (P < 0.05). Sodium disturbance was more common and severe in patients with type T tumors (P < 0.05). Age, tumor type, and preoperative diabetes insipidus were independent prognostic factors for obvious disorders of serum sodium. CONCLUSIONS: Hyponatremia/hypernatremia is common after primary CP resection. The site of tumor origin has a direct effect on the growth pattern of CP, which may serve as a useful index for anticipating sodium perturbation after surgery. The level of sodium in children and patients with type T tumors, preoperative diabetes insipidus should be monitored closely throughout hospitalization.

How to Classify and Define Pituitary Tumors: Recent Advances and Current Controversies.

Pituitary tumors are very complex and heterogeneous and have a very wide range of proliferative and aggressive behaviors, and how to define and classify these tumors remains controversial. This review summarizes the epidemiology and progress in the classification and definition of pituitary tumors, as well as controversial issues. Based on the results of radiologic and autopsy studies, the prevalence of pituitary tumors has recently increased significantly. However, the majority of pituitary tumors are incidentally discovered and asymptomatic, and such tumors are called pituitary incidentalomas. Most of these incidentalomas do not induce symptoms, remain stable in size, and do not need treatment. The recent revised classification strategies mainly depend on immunohistochemistry (IHC) to detect pituitary hormones and pituitary transcription factors; therefore, the accuracy of diagnosing pituitary tumors has improved. Although new classification strategies and definitions for pituitary tumors have been presented, there are still some controversies. The term pituitary neuroendocrine tumor (PitNET) was proposed by the International Pituitary Pathology Club, and this terminology can encompass the unpredictable malignant behavior seen in the subset of aggressive pituitary adenomas (PAs). However, some endocrinologists who oppose this change in terminology have argued that the use of tumor in the terminology is misleading, as it gives PAs a harmful connotation when the majority are not aggressive. Such terminology may add new ambiguity to the origin of PAs and unnecessary anxiety and frustration for the majority of patients with benign PAs. The classification of aggressive PAs mainly relies on subjective judgment of clinical behavior and lacks objective biomarkers and unified diagnostic criteria. However, the term "refractory" could more accurately represent the characteristics of these tumors, including their clinical behaviors, radiological features, and pathologic characteristics. Moreover, the diagnostic criteria for refractory PAs are stricter, more objective, and more accurate than those for aggressive PAs. Early identification of patients with these tumors through recognition and increased awareness of the definition of refractory PAs will encourage the early use of aggressive therapeutic strategies.

Transcription factor immunohistochemistry in the diagnosis of pituitary tumours.

OBJECTIVE: The clinical utility and prognostic value of WHO 2017 lineage-based classification of pituitary tumours have not been assessed. This study aimed to (1) determine the clinical utility of transcription factor analysis for classification of pituitary tumours and (2) determine the prognostic value of improved lineage-based classification of pituitary tumours. METHODS: This was a retrospective evaluation of patients who underwent surgical resection of pituitary tumours at St Vincent's Public and Private Hospitals, Sydney, Australia between 1990 and 2016. Included patients were at least 18 years of age and had complete histopathological data, forming the 'histological cohort'. Patients with at least 12 months of post-surgical follow-up were included in the subgroup 'clinical cohort'. The diagnostic efficacy of transcription factor immunohistochemistry in conjunction with hormone immunohistochemistry was compared with hormone immunohistochemistry alone. The prognostic value of identifying 'higher-risk' histological subtypes was assessed. RESULTS: There were 171 patient tumour samples analyzed in the histological cohort. Of these, there were 95 patients forming the clinical cohort. Subtype diagnosis was changed in 20/171 (12%) of tumours. Within the clinical cohort, there were 21/95 (22%) patients identified with higher-risk histological subtype tumours. These were associated with tumour invasiveness (P = 0.050), early recurrence (12-24 months, P = 0.013), shorter median time to recurrence (49 (IQR: 22.5-73.0) vs 15 (IQR: 12.0-25.0) months, P = 0.005) and reduced recurrence-free survival (P = 0.031). CONCLUSIONS: Application of transcription factor analysis, in addition to hormone immunohistochemistry, allows for refined pituitary tumour classification and may facilitate an improved approach to prognostication.

Cytokeratin 8/18-negative somatotroph pituitary neuroendocrine tumours (PitNETs, adenomas) show variable morphological features and do not represent a clinicopathologically distinct entity.

AIMS: In somatotroph pituitary neuroendocrine tumours (adenomas), a pattern of cytokeratin (CK) 18 expression is used for tumour subclassification, with possible clinical implications. Rare somatotroph tumours do not express CK 18. We aimed to characterise this subset clinically and histologically. METHODS AND RESULTS: Clinical and pathological data for the study were derived from a previously published data set of a cohort of 110 patients with acromegaly. Data included serum levels of insulin-like growth factor 1 (IGF1), growth hormone (GH), prolactin and thyroid-stimulating hormone (TSH), tumour diameter, tumour invasion defined by Knosp grade and immunohistochemical data concerning the expression of Ki67, p53, E-cadherin, somatostatin receptor (SSTR)1, SSTR2A, SSTR3, SSTR5 and D2 dopamine receptor. Additional immunohistochemical analysis (AE1/3, CK 8/18, vimentin, neurofilament light chain, internexin-α) was performed. CK 18 was negative in 10 of 110 (9.1%) tumours. One of these tumours was immunoreactive with CK 8/18 antibody, while the remainder expressed only internexin-α intermediate filament in patterns similar to CK 18 (perinuclear fibrous bodies). CK-negative tumours showed no significant differences with respect to biochemical, radiological or pathological features. They showed significantly higher expression of SSTR2A compared to the sparsely granulated subtype and significantly lower expression of E-cadherin compared to the non-sparsely granulated subtypes of tumours. The tumours showed divergent morphology and hormonal expression: two corresponded to densely granulated tumours and three showed co-expression of prolactin and morphology of either mammosomatotroph or somatotroph-lactotroph tumours. Four tumours showed morphology and immunoprofile compatible with plurihormonal Pit1-positive tumours. CONCLUSIONS: CK-negative somatotroph tumours do not represent a distinct subtype of somatotroph tumours, and can be further subdivided according to their morphology and immunoprofile.

Clinical Implications of the New WHO Classification 2017 for Pituitary Tumors.

According to the WHO classification 2017 of Pituitary Tumors adenomas are classified not only by structure and immunostaining for pituitary hormones but also by expression of the pituitary transcription factors Pit-1, T-pit and SF-1. By these factors, three cell lineages can be identified: Pit-1 for the GH-, Prolactin- and TSH-cell lineage, T-pit for the ACTH-cell lineage, and SF-1 for the gonadotrophic cell lineage. By this principle, all GH and/or Prolactin producing and all TSH producing adenomas must be positive for Pit-1, all corticotrophic adenomas for T-pit, and all gonadotrophic for SF-1. In adenomas without expression of pituitary hormones immunostainings for the transcription factors have to be examined. If these are also negative the criteria for an endocrine inactive null cell adenoma are fulfilled. If one transcription factor is positive the corresponding cell lineage indicates a potential hormonal activity of the adenoma. So Pit-1 expressing hormone-negative adenomas can account for acromegaly, hyperprolactinemia, or TSH hyperfunction. T-pit positive hormone negative adenomas can induce Cushing's disease, and SF-1 positive hormone negative tumors indicate gonadotrophic adenomas. Instead of the deleted atypical adenoma of the WHO classification of 2004 now (WHO classification 2017) criteria exist for the identification of aggressive adenomas with a conceivably worse prognosis. Some adenoma subtypes are described as aggressive "per se" without necessity of increased morphological signs of proliferation. All other adenoma subtypes must also be designated as aggressive if they show signs of increased proliferation (mitoses, Ki-67 index>3-5%, clinically rapid tumor growth) and invasion. By these criteria about one third of pituitary adenoma belong to the group of aggressive adenomas with potentially worse prognosis. The very rare pituitary carcinoma (0.1 % of pituitary tumors) is defined only by metastases. Many of them develop after several recurrences of Prolactin or ACTH secreting adenomas. The correlation of clinical findings and histological classification of pituitary adenomas is very important since every discrepancy has to be discussed between clinicians and pathologists. Based on data of the German Registry of Pituitary Tumors a table for examinations of correlations is shown in this review.

Pituitary tumour types in dogs and cats.

Pituitary tumours are common in dogs and are being increasingly recognized in cats. Pituitary tumours are usually classified as adenomas and should only be classified as carcinomas when there is evidence of metastatic spread of the tumour, which is rare. Despite the benign nature of most pituitary tumours, they can still compress or invade neighbouring tissues. Pituitary tumours can be functional (hormonally active) or non-functional (hormonally silent). The aim of this review was to provide an overview of the different pituitary tumour types in dogs and cats that have been reported in the literature. In dogs, the most common pituitary tumour type is the corticotroph adenoma, which can cause pituitary-dependent hypercortisolism. In cats, the most common pituitary tumour is the somatotroph adenoma, which can cause hypersomatotropism, and the second-most common is the corticotroph adenoma. A lactotroph adenoma has been described in one dog, while gonadotroph, thyrotroph and null cell adenomas have not been described in dogs or cats. Hormonally silent adenomas are likely underdiagnosed because they do not result in an endocrine syndrome. Tools used to classify pituitary tumours in humans, particularly immunohistochemistry for lineage-specific transcription factors, are likely to be useful to classify canine and feline pituitary tumours of unknown origin. Future studies are required to better understand the full range of pituitary adenoma pathology in dogs and cats and to determine whether certain adenoma subtypes behave more aggressively than others. Currently, the mechanisms that underlie pituitary tumorigenesis in dogs and cats are still largely unknown. A better understanding of the molecular background of these tumours could help to identify improved pituitary-targeted therapeutics.

Pituicytoma: Case report of a rare suprasellar tumor.

Pituicytoma is a distinct sellar or supracellar tumor which originates from specialized glial cells of neurohypophyses and infundibulum known as pituicytes. Because of its sellar location patients present with headache, visual disturbance, and endocrine abnormalities. Pituicytoma is difficult to diagnose on neuroimaging as radiological features overlap with other more common tumors of this region. Thus, diagnosis is established by histopathology and immunohistochemistry of resected tumor only. Pituicytomas are composed of bipolar spindle cells arranged as fascicles and are immunoreactive for TTF-1, S100p, and vimentin. These tumors are extremely rare and only around 70 published cases are known in literature. We report a case of suprasellar SOL in a 58-year-old male who presented with headache and gradual visual deterioration in both eyes. He was diagnosed as a case of pituicytoma based on light microscopy findings and immunohistochemical expression of TTF-1, vimentin, S100p, and bcl-2.

The Role of T-box Transcription Factor in a Pituitary Adenoma Diagnostic Algorithm.

CONTEXT.­: We previously examined pituitary adenomas with immunohistochemical (IHC) stains for steroidogenic factor 1, Pit-1, anterior pituitary hormones, cytokeratin CAM 5.2, and the α-subunit of human chorionic gonadotropin and found that a screening panel comprising stains for steroidogenic factor 1, Pit-1, and adrenocorticotropic hormone successfully classified most cases and reduced the overall number of stains required. OBJECTIVES.­: To examine the potential role of IHC stain for T-box transcription factor (Tpit) in the classification of our series of pituitary adenomas and to update our screening panel as necessary. DESIGN.­: We collected 157 pituitary adenomas from 2 institutions and included these in tissue microarrays. Immunostains for Tpit were scored in a blinded fashion using the Allred system. Adenomas were assigned to a gold standard class based on IHC pattern followed by application of available clinical and serologic information. Test characteristics were calculated. Correlation analyses, cluster analyses, and classification tree analyses were used to see whether IHC staining patterns reliably reflected adenoma class. RESULTS.­: Of the cases collected, 147 (93.6%) had sufficient material for Tpit analysis. IHC stain for Tpit identified 8 null cell adenomas (all nonfunctioning clinically) as silent corticotrophs; Tpit stains showed better sensitivity, specificity, positive predictive value, and negative predictive value than IHC for adrenocorticotropic hormone and cytokeratin CAM 5.2. Correlation analyses continued to show the expected relationships among IHC stains. Cluster analyses showed grouping of adenomas into clinically consistent groups. Classification tree analysis underscored the central role of transcription factor IHC stains, including Tpit, in adenoma classification. CONCLUSIONS.­: Substitution of Tpit stain for the adrenocorticotropic hormone stain improves our prior algorithm by reducing the number of false-negatives and false-positives. As a result, fewer adenomas are classified as null cell adenoma, and more adenomas are classified as silent corticotroph adenoma.

Primary Tumors of the Posterior Pituitary Gland: A Systematic Review of the Literature in Light of the New 2017 World Health Organization Classification of Pituitary Tumors.

OBJECTIVE: The rare clinical entity of primary posterior pituitary tumors (PPTs) includes pituicytomas, granular cell tumors, spine cell oncocytomas, and sellar ependymomas. The recent World Health Organization classification of PPTs based on thyroid transcription factor 1 positivity has led to more investigations into the epidemiology, clinical presentation, nature history, histologic features, and operative characteristics of these tumors. The aim of this review is to summarize the characteristics of primary PPTs. METHODS: Our summary involved an in-depth review of the literature on PPTs. Our systematic review was carried out using the PubMed database and PRISMA guidelines. RESULTS: An initial search identified 282 publications. After strict application of the inclusion criteria, we found 16 articles for case series of patients with primary PPT (N > 5), which were included in our table for literature review. An additional 10 articles were review articles on PPTs published in the last 20 years and were used as resource for our systematic review. An extensive analysis was then performed to extract relevant clinical data with respect to the clinical radiologic histopathologic profile of primary PPTs and their treatment outcome. CONCLUSIONS: Primary PPTs are a rare group of pituicyte-derived low-grade nonneuroendocrine neoplasms that arise from the sellar region. The nondescript radiographic findings and subtle endocrine abnormalities also veil their accurate diagnostic prediction. As shown through the narrative as well as the literature review, there is still a lot to be understood about PPTs. A prospective multicenter registry of these rare tumors would benefit both the neurosurgical as well as the endocrinologic knowledge base.

Proposal of a clinically relevant working classification of pituitary neuroendocrine tumors based on pituitary transcription factors.

The immunohistochemistry (IHC) characterization of pituitary transcription factors (PTFs) PIT1, TPIT, and SF1, which enable the identification of three different adenohypophyseal cell lines, has been incorporated into the latest classification system of the World Health Organization (WHO) for pituitary adenomas. This change overturns the concept of the adenoma as solely a hormone producer and classifies these tumors based on their cell lineage. The aim of the study was to provide a diagnostic algorithm, based on IHC expression of hypophyseal hormones with potential use in diagnostic practice, contributing to an improved classification of pituitary adenomas. Our sample included 146 pituitary adenomas previously classified based on hormonal subtypes by IHC (former 2004 WHO criteria) and re-evaluated after the IHC quantification of PIT1, TPIT, and SF1 expression, under WHO 2017 recommendations. We assessed the correlation between expression of PTFs and the classification as per hormonal IHC and correlated clinicopathological profiles based on PTFs. The IHC study of PTFs allowed reclassification of 82% of tumors that were negative for all pituitary hormones, with 21 positive cases for SF1 (reclassified as gonadotroph tumors), 1 positive case for TPIT (reclassified as a corticotroph tumor), and 4 positive cases for PIT1. Using SF1 enabled detection of a substantial portion of gonadotroph tumors, reducing the estimated prevalence of null cell tumors to less than 5%, and identification of plurihormonal pituitary neuroendocrine tumors with PIT1-SF1 coexpression and hormone-negative PIT1s, a group in which we did not observe differences in the clinical behavior compared with the rest of the tumors of the same cell lineage.Our results suggest that applying a diagnostic algorithm based on the study of PTFs could contribute to improving the classification of pituitary adenomas. By adding TPIT assessment, we propose a two-step algorithm, with hypophyseal hormones being used in a selective modality, depending on initial results.

Semi-supervised method for image texture classification of pituitary tumors via CycleGAN and optimized feature extraction.

BACKGROUND: Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. METHODS: We present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN (Cycle-Consistent Adversarial Networks) model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet (Densely Connected Convolutional Networks)-ResNet(Deep Residual Networks) based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN (Convolutional Recurrent Neural Network) model to classify pituitary tumors based on their predicted softness levels. RESULTS: Experiments show that our method is the best in terms of efficiency and accuracy (91.78%) compared to other methods. CONCLUSIONS: We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.

Structure, Function, and Morphology in the Classification of Pituitary Neuroendocrine Tumors: the Importance of Routine Analysis of Pituitary Transcription Factors.

The traditional approach to the diagnosis of primary adenohypophyseal cell proliferations uses hormone immunohistochemistry to classify pituitary neuroendocrine tumors (PitNETs). The routine application of immunolocalization of pituitary transcription factors (SF1, PIT1, TPIT, ERα, and recently GATA3) along with adenohypophyseal hormones has taught us critical lessons that are discussed in this communication. We point out that appropriate patient care requires accurate diagnosis and is critical in the era of precision medicine. A misdiagnosis can result in far greater health care costs than the cost of accurate tumor classification and may have other unintended consequences. We provide additional insights about confusing findings in genomic studies, emphasizing that high-quality pathology is essential for strong science and translational research.

World Health Ozganization 2017 Classification of Pituitary Tumors.

The 2017 (fourth edition) World Health Organization Classification of Endocrine Tumors has recommended major changes in classification of tumors of the pituitary gland and region. In addition to the accurate tumor subtyping, assessment of the tumor proliferative potential (mitotic and/or Ki-67 index) and other clinical parameters such as tumor invasion is strongly recommended in individual cases for consideration of clinically aggressive adenomas. It is expected that this new WHO classification will establish more uniform biologically and clinically groups of pituitary tumors and contribute to understanding of clinical outcomes for patients harboring pituitary tumors.

Newer Concepts in the Classification of Pituitary Adenomas.

The classification of tumors of the pituitary gland has seen several changes in recent years. The 4th edition of the World Health Organization Classification of Tumours of Endocrine Organs, published in 2017, saw the introduction of a classification based on cell lineage using immunohistochemistry for both pituitary specific hormones as well as pituitary specific transcription factors. The term "hormone-producing" was thus replaced by "-troph." The other major change was that the entity of "atypical adenoma," which was introduced in the 2004 classification, to identify tumors with a poor prognosis, was removed as it failed to identify aggressive tumors. Instead, assessment of markers of proliferation, clinical parameters, such as invasive status and histological subtypes were recommended to identify tumors with aggressive potential. The diagnostic criteria for pituitary carcinoma, however, remained unchanged and continued to be defined as a tumor of adenohypophyseal cells that metastasize craniospinally or systemically. Null cell adenomas were more clearly defined as tumors that did not show any cell-type differentiation, lacking immunoexpression of hormones as well as transcription factors. Since 2017, the classification has continued to evolve with the identification of aggressive histological variants. There is more recently a proposal to change the terminology from pituitary adenoma to pituitary neuroendocrine tumor (PitNET). This review summarizes the recent advances in the classification of pituitary adenomas.