Predictive value of cyst/tumor volume ratio of pituitary adenoma for tumor cell proliferation.

BACKGROUND: MRI has been widely used to predict the preoperative proliferative potential of pituitary adenoma (PA). However, the relationship between the cyst/tumor volume ratio (C/T ratio) and the proliferative potential of PA has not been reported. Herein, we determined the predictive value of the C/T ratio of PA for tumor cell proliferation. METHODS: The clinical data of 72 patients with PA and cystic change on MRI were retrospectively analyzed. PA volume, cyst volume, and C/T ratio were calculated. The corresponding intraoperative specimens were collected. Immunohistochemistry and hematoxylin-eosin staining were performed to evaluate the Ki67 index and nuclear atypia. Patients were categorized according to the Ki67 index (< 3% and ≥ 3%) and nuclear atypia (absence and presence). Univariate and multivariate analyses were used to identify the significant predictors of the Ki67 index and nuclear atypia. The receiver operating characteristic curve assessed the prediction ability of the significant predictors. RESULTS: Larger tumor volumes, smaller cyst volumes, and lower C/T ratios were found in patients with higher Ki67 indexes and those with nuclear atypia (P < 0.05). C/T ratio was an independent predictor of the Ki67 index (odds ratio = 0.010, 95% confidence interval = 0.000-0.462) and nuclear atypia (odds ratio = 0.010, 95% confidence interval = 0.000-0.250). The predictive value of the C/T ratio did not differ significantly from that of tumor volume (P > 0.05) but was better than that of cyst volume (P < 0.05). The area under the curve of the C/T ratio for predicting the Ki67 index and nuclear atypia was larger than that for predicting cyst volume and tumor volume. CONCLUSIONS: C/T ratios can be used to predict PA tumor proliferation preoperatively. Our findings may facilitate the selection of surgery timing and the efficacy evaluation of surgery.

Real-world experience with 11C-methionine positron emission tomography in the management of acromegaly.

BACKGROUND: L-[methyl-11C]-methionine-positron emission tomography (Met-PET) is a potentially important imaging adjunct in the diagnostic workup of pituitary adenomas, including somatotroph tumors. Met-PET can identify residual or occult disease and make definitive therapies accessible to a subgroup of patients who would otherwise require lifelong medical therapy. However, existing data on its use are still limited to small case series. Here, we report the largest single-center experience (n = 61) in acromegaly. METHODS: A total of 189 cases of acromegaly were referred to our national Met-PET service in the last 12 years. For this analysis, we have reviewed outcomes in those 61 patients managed exclusively by our multidisciplinary team (single center, single surgeon). Referral indications were as follows: indeterminate magnetic resonance imaging (MRI; n = 38, 62.3%), occult residual (n = 14, 23.0%), (radio-)surgical planning (n = 6, 9.8%), and occult de novo tumor (n = 3, 4.9%). RESULTS: A total of 33/61 patients (54.1%) underwent PET-guided surgery. Twenty-four of 33 patients (72.7%) achieved complete biochemical remission following (re-)surgery. Insulin-like growth factor 1 levels were reduced to <2 × upper limit of normal (ULN) in 6 of the remaining 9 cases, 3 of whom achieved levels of <1.1 × ULN compared with mean preoperative levels of 2.4 × ULN (SD 0.8) for n = 9. Only 3 patients developed single new hormonal deficits (gonadotropic/thyrotropic insufficiency). There were no neurovascular complications after surgery. CONCLUSION: In patients with persistent/recurrent acromegaly or occult tumors, Met-PET can facilitate further targeted intervention (surgery/radiosurgery). This led to complete remission in most cases (24/33) or significant improvement with comparatively low risk of complications. L-[methyl-11C]-methionine-positron emission tomography should therefore be considered in all patients who are potential candidates for further surgical intervention but present no clear target on MRI.

A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart.

In this study, we implemented a combination of data augmentation and artificial intelligence (AI) model-Convolutional Neural Network (CNN)-to help physicians classify colonic polyps into traditional adenoma (TA), sessile serrated adenoma (SSA), and hyperplastic polyp (HP). We collected ordinary endoscopy images under both white and NBI lights. Under white light, we collected 257 images of HP, 423 images of SSA, and 60 images of TA. Under NBI light, were collected 238 images of HP, 284 images of SSA, and 71 images of TA. We implemented the CNN-based artificial intelligence model, Inception V4, to build a classification model for the types of colon polyps. Our final AI classification model with data augmentation process is constructed only with white light images. Our classification prediction accuracy of colon polyp type is 94%, and the discriminability of the model (area under the curve) was 98%. Thus, we can conclude that our model can help physicians distinguish between TA, SSA, and HPs and correctly identify precancerous lesions such as TA and SSA.

Don't chase the adenoma: A probabilistic approach to imaging before parathyroidectomy.

BACKGROUND: Preoperative imaging before parathyroidectomy can localize adenomas and reduce unnecessary bilateral neck explorations. We hypothesized that (1) the utility of preoperative imaging varies substantially depending on the preoperative probability of having adenoma(s) and (2) that a selective imaging approach based on this probability could avoid unnecessary patient costs and radiation. METHODS: We analyzed 3,577 patients who underwent parathyroidectomy for primary hyperparathyroidism from 2001 to 2022. The predicted probability of patients having single or double adenoma versus hyperplasia was estimated using logistic regression. We then estimated the relationship between the predicted probability of single/double adenoma and the likelihood that sestamibi or 4-dimensional computed tomography was helpful for operative planning. Current Medicare costs and published data on radiation dosing were used to calculate costs and radiation exposure from non-helpful imaging. RESULTS: The mean age was 62 ± 13 years; 78% were women. Adenomas were associated with higher mean calcium (11.2 ± 0.74 mg/dL) and parathyroid hormone levels (140.6 ± 94 pg/mL) than hyperplasia (9.8 ± 0.52 mg/dL and 81.4 ± 66 pg/mL). The probability that imaging helped with operative planning increased from 12% to 65%, as the predicted probability of adenoma increased from 30% to 90%. For every 10,000 patients, a selective approach to imaging that considered the preoperative probability of having adenomas could save patients up to $3.4 million and >239,000 millisieverts of radiation. CONCLUSION: Rather than imaging all patients with primary hyperparathyroidism, a selective strategy that considers the probability of having adenomas could reduce costs and avoid excess radiation exposure.

Clinical application of combination [11C]C-methionine and [13N]N-ammonia PET/CT in recurrent functional pituitary adenomas with negative MRI or [18F]F-FDG PET/CT.

BACKGROUND: We assessed the value of positron emission tomography/computed tomography (PET/CT) with [13N]N-ammonia ([13N]N-NH3) and [11C]C-methionine ([11C]C-MET) for the evaluation and management of recurrent secreting pituitary adenoma, which could not be detected by magnetic resonance imaging (MRI) or fluorine-18 fluorodeoxyglucose ([18F]F-FDG) PET. METHODS: Nine consecutive patients with biochemical and clinical evidence of active recurrent tumor not detected by MRI and [18F]F-FDG PET were enrolled in this study. All of the patients underwent [13N]N-NH3 and [11C]C-MET PET/CT, after which the pattern of tracer uptake was studied, the tumor position was located, and a clinical decision was made. RESULTS: In general, [11C]C-MET had a higher uptake in pituitary adenomas (PAs) than that in pituitary tissues, while [13N]N-NH3 had a higher uptake in pituitary tissue than in pituitary adenomas. Increased [11C]C-MET uptake was observed in all nine PAs and three pituitary tissues, while all pituitary tissues and only one pituitary adenoma showed increased [13N]N-NH3 uptake. Four patients had concordant imaging and surgical findings indicative of biochemical remission without hypopituitarism after treatment. Radiotherapy was adopted in two patients, medication in another two, and follow-up observation in one case. CONCLUSION: Combined [11C]C-MET and [13N]N-NH3 PET/CT is effective in the differentiation of PAs from pituitary tissue in recurrent functional PAs with negative MRI or [18F]F-FDG PET. These results provide a valuable reference for further disease management.

The role of preoperative MRI in endoscopic transnasal transsphenoidal hypophysectomy of pituitary adenoma.

BACKGROUND: The trans-sphenoidal approach, commonly used for removing pituitary adenomas, has become a widely accepted and successful method. In recent years, the endoscopic trans-sphenoidal technique has emerged as a minimally invasive surgical approach for pituitary adenoma removal. The majority of pituitary adenomas exhibit a soft consistency and can be successfully extracted with aspiration and curettage using the trans-sphenoidal approach. However, a subset of around 5-15% of these adenomas possess a solid and fibrous texture. The occurrence of firm and fibrous adenomas is relatively common; unfortunately, there are no reliable predictors to identify them preoperatively. OBJECTIVES: The ability to forecast the reliability of magnetic resonance imaging (MRI) holds promise for improving prior preparation and impacts the extent of resection. DESIGN: A cross-sectional analysis of the investigation of magnetic resonance imaging (MRI) in relation to cancer histology was performed on 68 patients who had endoscopic trans-nasal excision for nonfunctional adenomas. MATERIALS AND METHODS: The determination of an intensity ratio was performed by employing quantitative estimates of MRI signal intensity obtained from both the adenoma and pons. During the surgical procedure, a series of sequential-graded procedures were used for the removal of tumours with varying consistencies. Softer tumours were addressed using the Suction technique (R1), while tumours of intermediate consistency were treated using curettes (R2). In order to evaluate the fibrotic content of firmer tumours, the utilization of Cavitron Ultrasound Surgical Aspirator (CUSA), and/or other micro-instruments (R3) was employed, with the histologic collagen fraction being quantified. In order to investigate and analyse the data, a statistical analysis was conducted. A predictive relationship between resection category and both intensity ratio, and collagen percentage was noted. The primary objective of this study was to determine the appropriate cutoff criteria for clinical utilization, as well as to investigate the association between intensity ratios and collagen percentage. RESULTS: Tumors with ratios ≤ 1.6 on the T2-weighted image and collagen content > 5.3% required more meticulous and sharp dissection for resection. CONCLUSIONS: The utilization of MRI analysis may offer some assistance, but not conclusive, in the prediction of tumour consistency.

Endonasal endoscopic surgery for pituitary adenomas.

Pituitary adenomas are slow-growing, benign intracranial tumors that can be characterized as functional (hormone-producing) or non-functional (non-hormone producing). Symptoms therefore arise from either endocrinologic abnormalities or mass effect on surrounding structures resulting in symptoms such as visual impairment and headache. In the last two decades, technical innovations have shifted surgical resection of such adenomas to endoscopic endonasal approaches. In this review, we describe the evolving approach to pituitary adenomas in the modern endoscopic era, including preoperative multidisciplinary review, relevant surgical anatomy, and a description of the technical nuances of standard and expanded approaches to the anterior skull base.

Development and validation of a prediction model for consistency of pituitary adenoma: the PiTCon score.

PURPOSE: Pituitary adenomas (PAs) usually have a soft consistency, facilitating gross total resection. However, 5-13% of PAs with fibrous consistency are challenging to remove entirely and are accompanied by greater morbimortality. This study aims to identify the clinical and radiological characteristics that correlate with PA fibrous consistency preoperatively. A simple scoring system has been proposed to predict incidence of fibrous PAs. MATERIALS AND METHODS: Consecutive interventions (226) were analyzed, all performed through an endoscopic endonasal transsphenoidal approach. Univariable and multivariable logistic regression analysis was performed. Hosmer-Lemeshow test and receiver operating characteristic (ROC) curves were assessed to evaluate the model. A point scoring system (PiTCon) was derived based on the multivariable regression model. Our study aimed to identify the clinical and radiological characteristics that correlate with fibrous tumor consistency preoperatively. RESULTS: The best diagnostic accuracy for predicting PA consistency consisted of five predictive factors: age, compressive symptoms, panhypopituitarism, craniocaudal extension of the PA in mm, and prior surgery. The multivariable model achieved good discrimination with an area under the curve (AUC) of the ROC curve being 0.82 and the 95% CI 0.76 to 0.88. Internal validation yielded an optimism-adjusted C-statistic of 0.80 (95% CI 0.74 to 0.86). A point scoring system (PiTCon score) was designed using the best predictive model. CONCLUSIONS: PA consistency can be estimated preoperatively regarding clinical and radiological characteristics. We propose a point-based scoring system (PiTCon score) that can better guide neurosurgeons in clinical decision-making and surgical risk assessment and help establish and describe patient prognosis.

A computer-aided polyp detection system in screening and surveillance colonoscopy: an international, multicentre, randomised, tandem trial.

BACKGROUND: Studies on the effect of computer-aided detection (CAD) in a daily clinical screening and surveillance colonoscopy population practice are scarce. The aim of this study was to evaluate a novel CAD system in a screening and surveillance colonoscopy population. METHODS: This multicentre, randomised, controlled trial was done in ten hospitals in Europe, the USA, and Israel by 31 endoscopists. Patients referred for non-immunochemical faecal occult blood test (iFOBT) screening or surveillance colonoscopy were included. Patients were randomomly assigned to CAD-assisted colonoscopy or conventional colonoscopy; a subset was further randomly assigned to undergo tandem colonoscopy: CAD followed by conventional colonoscopy or conventional colonoscopy followed by CAD. Primary objectives included adenoma per colonoscopy (APC) and adenoma per extraction (APE). Secondary objectives included adenoma miss rate (AMR) in the tandem colonoscopies. The study was registered at ClinicalTrials.gov, NCT04640792. FINDINGS: A total of 916 patients were included in the modified intention-to-treat analysis: 449 in the CAD group and 467 in the conventional colonoscopy group. APC was higher with CAD compared with conventional colonoscopy (0·70 vs 0·51, p=0·015; 314 adenomas per 449 colonoscopies vs 238 adenomas per 467 colonoscopies; poisson effect ratio 1·372 [95% CI 1·068-1·769]), while showing non-inferiority of APE compared with conventional colonoscopy (0·59 vs 0·66; p<0·001 for non-inferiority; 314 of 536 extractions vs 238 of 360 extractions). AMR in the 127 (61 with CAD first, 66 with conventional colonoscopy first) patients completing tandem colonoscopy was 19% (11 of 59 detected during the second pass) in the CAD first group and 36% (16 of 45 detected during the second pass) in the conventional colonoscopy first group (p=0·024). INTERPRETATION: CAD increased adenoma detection in non-iFOBT screening and surveillance colonoscopies and reduced adenoma miss rates compared with conventional colonoscopy, without an increase in the resection of non-adenomatous lesions. FUNDING: Magentiq Eye.

Rarely Used Endoscopic Transnasal Transdiaphragmatic Technique in Patients with Suprasellar Extension: A Tertiary Center's Experience with Eleven Patient Cases.

OBJECTIVE: As surgical techniques become less invasive, the use of endoscopy in brain surgery supports this trend. Numerous endoscopic surgical approaches have been defined, especially for skull base diseases. The current study summarizes our experience of using the rarely reported endoscopic transnasal transdiaphragmatic approach through the existing hole in the diaphragma sella to access lesions extending into the suprasellar region. METHODS: Our surgical team performed 4876 endoscopic endonasal surgeries between August 1997 and December 2022 at the Department of Neurosurgery, Pituitary Research Center, Faculty of Medicine, Kocaeli University. The study retrospectively analyzed data from 11 patients who had undergone endoscopic transnasal transdiaphragmatic surgery since January 2020. Preoperative and postoperative magnetic resonance imaging, pituitary function examination, and clinical observation were carried out. RESULTS: The mean age of the patients was 31.1 ± 10.7 years and the female/male ratio was 6:5. Pathologic subtypes observed included breast cancer metastasis (n = 1), adrenocorticotropic hormone-secreting adenoma (n = 4), growth hormone-secreting adenoma (n = 3), craniopharyngioma (n = 2), and Rathke cleft cyst (n = 1). The mean postoperative hospital stay was 4.7 ± 1.1 days and none of the patients showed cerebrospinal fluid leakage during this period. CONCLUSIONS: The endoscopic transnasal transdiaphragmatic approach may be considered an alternative to the conventional extended endoscopic transnasal approach in patients with lesions extending into the suprasellar region. The main strength of this method is that it facilitates suprasellar region access through a small dural incision and bone defect in the base of the skull. As a result, it also reduces the risk of postoperative cerebrospinal fluid leakage and associated complications.

Clinical and Surgical Outcomes of Endoscopic Endonasal Approach for Giant Pituitary Adenomas: Analysis of Predictive Factors.

BACKGROUND: Giant pituitary adenomas (GPAs) are defined as tumors with ≥40 mm in any maximum diameter, and these tend to invade multiple intracranial compartments. Hence, treatment remains a surgical challenge. OBJECTIVE: To describe the clinical and surgical outcomes of the endoscopic endonasal approach (EEA) for GPA in a pituitary referral center in Latin America and to analyze associated predictive factors. METHODS: 37 patients with histologically-confirmed GPA treated solely through the EEA between a 2-year period were included. Preoperative and postoperative clinical and neuroimaging findings; surgical morbidity and mortality; and binary logistic regression analysis to assess predictive factors were analyzed. RESULTS: Preoperative visual impairment prevalence was 97.3%. Mean tumor volume was 32 cc and gross total resection rate was 40.5%. Favorable visual acuity and visual fields outcome rate was 75% and 82.9%, respectively. In the multivariate analysis, bilateral cavernous sinus invasion (P = 0.018) and postoperative cerebrospinal fluid (CSF) leak (P = 0.036) were associated with an unfavorable visual acuity outcome, while radiation therapy (P = 0.035) was for visual fields. Similarly, intraoperative CSF leak was a predictive factor for postoperative CSF leak (10.8%) (P = 0.042) and vascular injury (13.5%) (P = 0.048). CONCLUSIONS: In this first Mexican clinical series, we demonstrated that the EEA is a safe and effective technique for GPA, although early diagnosis and prompt intervention may promote further visual function preservation without significant endocrine morbidity.

Follicular adenoma with a papillary architecture originating from an ectopic thyroid gland: a case report.

BACKGROUND: Follicular adenomas with papillary architecture are rare tumors of thyroid origin and are composed of completely encapsulated follicular cells with a papillary architecture lacking the nuclear characteristics of papillary carcinoma. Herein, we present a case of follicular adenoma with papillary architecture originating from an ectopic thyroid gland, diagnosed from a mass in the submandibular region. CASE PRESENTATION: A 70-year-old woman was referred to our hospital with the chief complaint of a painless left submandibular mass that had been present for one year. The patient underwent left submandibular dissection for therapy and diagnosis. Microscopically, papillary lesions with fibrovascular cores were observed in the interior, and the epithelial cells were cylindrical in shape with eosinophilic cytoplasm, round or oval nuclei, with no pathological features, leading to a diagnosis of papillary carcinoma or follicular carcinoma. The mass was diagnosed as a follicular thyroid adenoma with papillary architecture. This is the first report of a follicular adenoma with a papillary architecture originating from an ectopic thyroid gland. CONCLUSION: This experience suggests that follicular adenoma should be included in the differential diagnosis of ectopic thyroid tumors.

Multi-center application of a convolutional neural network for preoperative detection of cavernous sinus invasion in pituitary adenomas.

OBJECTIVE: Cavernous sinus invasion (CSI) plays a pivotal role in determining management in pituitary adenomas. The study aimed to develop a Convolutional Neural Network (CNN) model to diagnose CSI in multiple centers. METHODS: A total of 729 cases were retrospectively obtained in five medical centers with (n = 543) or without CSI (n = 186) from January 2011 to December 2021. The CNN model was trained using T1-enhanced MRI from two pituitary centers of excellence (n = 647). The other three municipal centers (n = 82) as the external testing set were imported to evaluate the model performance. The area-under-the-receiver-operating-characteristic-curve values (AUC-ROC) analyses were employed to evaluate predicted performance. Gradient-weighted class activation mapping (Grad-CAM) was used to determine models' regions of interest. RESULTS: The CNN model achieved high diagnostic accuracy (0.89) in identifying CSI in the external testing set, with an AUC-ROC value of 0.92 (95% CI, 0.88-0.97), better than CSI clinical predictor of diameter (AUC-ROC: 0.75), length (AUC-ROC: 0.80), and the three kinds of dichotomizations of the Knosp grading system (AUC-ROC: 0.70-0.82). In cases with Knosp grade 3A (n = 24, CSI rate, 0.35), the accuracy the model accounted for 0.78, with sensitivity and specificity values of 0.72 and 0.78, respectively. According to the Grad-CAM results, the views of the model were confirmed around the sellar region with CSI. CONCLUSIONS: The deep learning model is capable of accurately identifying CSI and satisfactorily able to localize CSI in multicenters.

Diffusion-weighted imaging does not seem to be a predictor of consistency in pituitary adenomas.

PURPOSE: To prospectively evaluate the usefulness of T1-weighted imaging (T1WI) and diffusion-weighted imaging (DWI) sequences in predicting the consistency of macroadenomas. In addition, to determine their values ​​as prognostic factors of surgical outcomes. METHODS: Patients with pituitary macroadenoma and surgical indication were included. All patients underwent pre-surgical magnetic resonance imaging (MRI) that included the sequences T1WI before and after contrast administration and DWI with the apparent diffusion coefficient (ADC) map. Post-surgical MRI was performed at least 3 months after surgery. The consistency of the macroadenomas was evaluated at surgery, and they were grouped into soft and intermediate/hard adenomas. Mean ADC values, signal on T1WI and the ratio of tumor ADC values ​​to pons (ADCR) were compared with tumor consistency and grade of surgical resection. RESULTS: A total of 80 patients were included. A softened consistency was found at surgery in 53 patients and hardened in 27 patients. The median ADC in the soft consistency group was 0.532 × 10-3 mm2/sec (0.306 - 1.096 × 10-3 mm2/sec), and in the intermediate/hard consistency group was 0.509 × 10-3 mm2/sec (0.308 - 0.818 × 10-3 mm2/sec). There was no significant difference between the median values ​​of ADC, ADCR and signal on T1W between the soft and hard tumor groups, or between patients with and without tumor residue. CONCLUSION: Our results did not show usefulness of the DWI and T1WI for assessing the consistency of pituitary macroadenomas, nor as a predictor of the degree of surgical resection.

Endoloop pre-ligation assisted resection of a giant Brunner's gland adenoma of the duodenal bulb.

Brunner's gland adenoma (BGA), also known as Brunneroma or polypoid hamartoma, is a rare benign duodenal tumor that proliferates from Brunner's glands of the duodenum. They are usually asymptomatic and discovered by chance during endoscopy. Some giant lesions can sometimes present with chronic abdominal pain, nausea, vomiting, and anemia, including gastrointestinal bleeding and obstructive symptoms, and need to be resected by surgery or endoscopy. Here we report a giant BGA that was easily and safely removed by Endoloop pre-ligation assisted resection.

Preoperatively Predicting Ki67 Expression in Pituitary Adenomas Using Deep Segmentation Network and Radiomics Analysis Based on Multiparameter MRI.

RATIONALE AND OBJECTIVES: Ki67 proliferation index is associated with more aggressive tumor behavior and recurrence of pituitary adenomas (PAs). Recently, radiomics and deep learning have been introduced into the study of pituitary tumors. The present study aimed to investigate the feasibility of predicting the Ki67 proliferation index of PAs using the deep segmentation network and radiomics analysis based on multiparameter MRI. MATERIALS AND METHODS: First, the cfVB-Net autosegmentation model was trained; subsequently, its performance was evaluated in terms of the dice similarity coefficient (DSC). In the present study, 1214 patients were classified into the high Ki67 expression group (HG) and the low Ki67 expression group (LG). Analyses of three classification models based on radiomics features were performed to distinguish HG from LG. Clinical factors, imaging features, and Radscores were collectively used to create a nomogram in order to effectively predict Ki67 expression. RESULTS: The cfVB-Net segmentation model demonstrated good performance (DSC: 0.723-0.930). Overall, 18, 15, and 11 optimal features in contrast-enhanced (CE) T1WI, T1WI, and T2WI were obtained for differentiating between HG and LG, respectively. Notably, the best results were presented in the bagging decision tree when CE T1WI and T1WI were combined (area under the receiver operating characteristic curve: training set, 0.927; validation set, 0.831; and independent testing set, 0.825). In the nomogram, age, Hardy' grade, and Radscores were identified as risk predictors of high Ki67 expression. CONCLUSION: The deep segmentation network and radiomics analysis based on multiparameter MRI exhibited good performance and clinical application value in predicting the expression of Ki67 in PAs.

Automated volumetric assessment of pituitary adenoma.

PURPOSE: Assessment of pituitary adenoma (PA) volume and extent of resection (EOR) through manual segmentation is time-consuming and likely suffers from poor interrater agreement, especially postoperatively. Automated tumor segmentation and volumetry by use of deep learning techniques may provide more objective and quick volumetry. METHODS: We developed an automated volumetry pipeline for pituitary adenoma. Preoperative and three-month postoperative T1-weighted, contrast-enhanced magnetic resonance imaging (MRI) with manual segmentations were used for model training. After adequate preprocessing, an ensemble of convolutional neural networks (CNNs) was trained and validated for preoperative and postoperative automated segmentation of tumor tissue. Generalization was evaluated on a separate holdout set. RESULTS: In total, 193 image sets were used for training and 20 were held out for validation. At validation using the holdout set, our models (preoperative / postoperative) demonstrated a median Dice score of 0.71 (0.27) / 0 (0), a mean Jaccard score of 0.53 ± 0.21/0.030 ± 0.085 and a mean 95th percentile Hausdorff distance of 3.89 ± 1.96./12.199 ± 6.684. Pearson's correlation coefficient for volume correlation was 0.85 / 0.22 and -0.14 for extent of resection. Gross total resection was detected with a sensitivity of 66.67% and specificity of 36.36%. CONCLUSIONS: Our volumetry pipeline demonstrated its ability to accurately segment pituitary adenomas. This is highly valuable for lesion detection and evaluation of progression of pituitary incidentalomas. Postoperatively, however, objective and precise detection of residual tumor remains less successful. Larger datasets, more diverse data, and more elaborate modeling could potentially improve performance.

Analysis of Diffusion-Weighted and T2-Weighted Imaging in the Prediction of Distinct Granulation Patterns of Somatotroph Adenomas.

OBJECTIVE: The heterogeneity of the somatotroph adenomas, especially for sparsely granulated (SG) and densely granulated (DG) subtypes, has attracted great attention in identifying their imaging biomarker. The purpose of the current study was to compare the diagnostic performance of diffusion-weighted and T2-weighted magnetic resonance imaging (MRI) sequences for preoperatively distinguishing the granulation patterns of somatotroph adenomas. METHODS: Thirty-two patients with a clinical diagnosis of somatotroph adenomas from October 2018 to March 2023 were included in this study. Coronal diffusion-weighted imaging (DWI) and T2-weighted MRI sequence data were collected from 3.0T MRI and compared between SG and DG groups. The immunohistochemistry was used to confirm the electron microscopy pathologic subtypes and Ki67 expression levels of somatotroph adenomas postoperatively. RESULTS: Patients in the SG group had significantly higher signal intensity (SI) ratio of DWI (rDWI) (P < 0.001), lower SI ratio of apparent diffusion coefficient (rADC) (P < 0.001), and higher SI ratio of T2-weighted imaging (P = 0.011). The combined diagnosis index of rDWI and rADC had the highest diagnostic efficiency in predicting SG adenomas (sensitivity, 93.3%; specificity, 88.2%; P < 0.001). The rDWI and rADC values had positive and negative correlations with the Ki67 index and tumor maximum diameter, respectively. Lower rADC×103 was an independent predictor for SG adenomas. CONCLUSIONS: Our results indicated that compared with previously used T2-weighted imaging, the DWI sequence, especially the combined diagnosis index of rDWI and rADC, could more efficiently distinguish the granulation patterns of somatotroph adenomas preoperatively.