AI-based automated evaluation of image quality and protocol tailoring in patients undergoing MRI for suspected prostate cancer.

PURPOSE: To develop and validate an artificial intelligence (AI) application in a clinical setting to decide whether dynamic contrast-enhanced (DCE) sequences are necessary in multiparametric prostate MRI. METHODS: This study was approved by the institutional review board and requirement for study-specific informed consent was waived. A mobile app was developed to integrate AI-based image quality analysis into clinical workflow. An expert radiologist provided reference decisions. Diagnostic performance parameters (sensitivity and specificity) were calculated and inter-reader agreement was evaluated. RESULTS: Fully automated evaluation was possible in 87% of cases, with the application reaching a sensitivity of 80% and a specificity of 100% in selecting patients for multiparametric MRI. In 2% of patients, the application falsely decided on omitting DCE. With a technician reaching a sensitivity of 29% and specificity of 98%, and resident radiologists reaching sensitivity of 29% and specificity of 93%, the use of the application allowed a significant increase in sensitivity. CONCLUSION: The presented AI application accurately decides on a patient-specific MRI protocol based on image quality analysis, potentially allowing omission of DCE in the diagnostic workup of patients with suspected prostate cancer. This could streamline workflow and optimize time utilization of healthcare professionals.

Metabolic and inflammatory parameters in relation to baseline characterization and treatment outcome in patients with prolactinoma: insights from a retrospective cohort study at a single tertiary center.

Background: Prolactinomas (PRLs) are prevalent pituitary adenomas associated with metabolic changes and increased cardiovascular morbidity. This study examined clinical, endocrine, metabolic, and inflammatory profiles in PRL patients, aiming to identify potential prognostic markers. Methods: The study comprised data from 59 PRL patients gathered in a registry at the University Hospital of Zurich. Diagnostic criteria included MRI findings and elevated serum prolactin levels. We assessed baseline and follow-up clinical demographics, metabolic markers, serum inflammation-based scores, and endocrine parameters. Treatment outcomes were evaluated based on prolactin normalization, tumor shrinkage, and cabergoline dosage. Results: The PRL cohort exhibited a higher prevalence of overweight/obesity, prediabetes/diabetes mellitus, and dyslipidemia compared to the general population. Significant correlations were found between PRL characteristics and BMI, HbA1c, and fT4 levels. Follow-up data indicated decreases in tumor size, tumor volume, prolactin levels, and LDL-cholesterol, alongside increases in fT4 and sex hormones levels. No significant associations were observed between baseline parameters and tumor shrinkage at follow-up. A positive association was noted between PRL size/volume and the time to achieve prolactin normalization, and a negative association with baseline fT4 levels. Conclusion: This study underscores the metabolic significance of PRL, with notable correlations between PRL parameters and metabolic indices. However, inflammatory markers were not significantly correlated with patient stratification or outcome prediction. These findings highlight the necessity for standardized follow-up protocols and further research into the metabolic pathogenesis in PRL patients.

Whole Spine Segmentation Using Object Detection and Semantic Segmentation.

OBJECTIVE: Virtual and augmented reality have enjoyed increased attention in spine surgery. Preoperative planning, pedicle screw placement, and surgical training are among the most studied use cases. Identifying osseous structures is a key aspect of navigating a 3-dimensional virtual reconstruction. To automate the otherwise time-consuming process of labeling vertebrae on each slice individually, we propose a fully automated pipeline that automates segmentation on computed tomography (CT) and which can form the basis for further virtual or augmented reality application and radiomic analysis. METHODS: Based on a large public dataset of annotated vertebral CT scans, we first trained a YOLOv8m (You-Only-Look-Once algorithm, Version 8 and size medium) to detect each vertebra individually. On the then cropped images, a 2D-U-Net was developed and externally validated on 2 different public datasets. RESULTS: Two hundred fourteen CT scans (cervical, thoracic, or lumbar spine) were used for model training, and 40 scans were used for external validation. Vertebra recognition achieved a mAP50 (mean average precision with Jaccard threshold of 0.5) of over 0.84, and the segmentation algorithm attained a mean Dice score of 0.75 ± 0.14 at internal, 0.77 ± 0.12 and 0.82 ± 0.14 at external validation, respectively. CONCLUSION: We propose a 2-stage approach consisting of single vertebra labeling by an object detection algorithm followed by semantic segmentation. In our externally validated pilot study, we demonstrate robust performance for our object detection network in identifying individual vertebrae, as well as for our segmentation model in precisely delineating the bony structures.

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.

Safety of microneurosurgical interventions for superficial and deep-seated brain metastases: single-center cohort study of 637 consecutive cases.

PURPOSE: Microneurosurgical techniques have greatly improved over the past years due to the introduction of new technology and surgical concepts. To reevaluate the role of micro-neurosurgery in brain metastases (BM) resection in the era of new systemic and local treatment options, its safety profile needs to be reassessed. The aim of this study was to analyze the rate of adverse events (AEs) according to a systematic, comprehensive and reliably reproducible grading system after microneurosurgical BM resection in a large and modern microneurosurgical series with special emphasis on anatomical location. METHODS: Prospectively collected cases of BM resection between 2013 and 2022 were retrospectively analyzed. Number of AEs, defined as any deviations from the expected postoperative course according to Clavien-Dindo-Grade (CDG) were evaluated. Patient, surgical, and lesion characteristics, including exact anatomic tumor locations, were analyzed using uni- and multivariate logistic regression and survival analysis to identify predictive factors for AEs. RESULTS: We identified 664 eligible patients with lung cancer being the most common primary tumor (44%), followed by melanoma (25%) and breast cancer (11%). 29 patients (4%) underwent biopsy only whereas BM were resected in 637 (96%) of cases. The overall rate of AEs was 8% at discharge. However, severe AEs (≥ CDG 3a; requiring surgical intervention under local/general anesthesia or ICU treatment) occurred in only 1.9% (n = 12) of cases with a perioperative mortality of 0.6% (n = 4). Infratentorial tumor location (OR 5.46, 95% 2.31-13.8, p = .001), reoperation (OR 2.31, 95% 1.07-4.81, p = .033) and central region tumor location (OR 3.03, 95% 1.03-8.60) showed to be significant predictors in a multivariate analysis for major AEs (CDG ≥ 2 or new neurological deficits). Neither deep supratentorial nor central region tumors were associated with more major AEs compared to convexity lesions. CONCLUSIONS: Modern microneurosurgical resection can be considered an excellent option in the management of BM in terms of safety, as the overall rate of major AEs are very rare even in eloquent and deep-seated lesions.

Intracardiac Thrombi in Morbus Adamantiades-Behçet in Two Swedish Patients.

Morbus Adamantiades-Behçet (MAB) is an inflammatory disease typically manifesting with oral and genital aphthosis, erythema nodosum, and vasculopathy, and in only around 2%, cardiac involvement. Its prevalence is usually higher along the historic Silk Road, but rarer in Scandinavia where 0.64-4.9 in 100,000 people are affected. We herein present two Swedish patients with cardiac manifestations of Morbus Adamantiades-Behçet. Along with the intracardial thrombi, which both patients presented with, one patient also had cerebrovascular insults leading to visual field deficits as well as involvement of peripheral nerves. Being of Scandinavian origin and showing uncommon symptoms as their initial manifestations of MAB, the 62- and 35-year-old patients presenting herein constitute rare cases.

DeepEOR: automated perioperative volumetric assessment of variable grade gliomas using deep learning.

PURPOSE: Volumetric assessments, such as extent of resection (EOR) or residual tumor volume, are essential criterions in glioma resection surgery. Our goal is to develop and validate segmentation machine learning models for pre- and postoperative magnetic resonance imaging scans, allowing us to assess the percentagewise tumor reduction after intracranial surgery for gliomas. METHODS: For the development of the preoperative segmentation model (U-Net), MRI scans of 1053 patients from the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2021 as well as from patients who underwent surgery at the University Hospital in Zurich were used. Subsequently, the model was evaluated on a holdout set containing 285 images from the same sources. The postoperative model was developed using 72 scans and validated on 45 scans obtained from the BraTS 2015 and Zurich dataset. Performance is evaluated using Dice Similarity score, Jaccard coefficient and Hausdorff 95%. RESULTS: We were able to achieve an overall mean Dice Similarity Score of 0.59 and 0.29 on the pre- and postoperative holdout sets, respectively. Our algorithm managed to determine correct EOR in 44.1%. CONCLUSION: Although our models are not suitable for clinical use at this point, the possible applications are vast, going from automated lesion detection to disease progression evaluation. Precise determination of EOR is a challenging task, but we managed to show that deep learning can provide fast and objective estimates.

Improving workflow in prostate MRI: AI-based decision-making on biparametric or multiparametric MRI.

OBJECTIVES: To develop and validate an artificial intelligence algorithm to decide on the necessity of dynamic contrast-enhanced sequences (DCE) in prostate MRI. METHODS: This study was approved by the institutional review board and requirement for study-specific informed consent was waived. A convolutional neural network (CNN) was developed on 300 prostate MRI examinations. Consensus of two expert readers on the necessity of DCE acted as reference standard. The CNN was validated in a separate cohort of 100 prostate MRI examinations from the same vendor and 31 examinations from a different vendor. Sensitivity/specificity were calculated using ROC curve analysis and results were compared to decisions made by a radiology technician. RESULTS: The CNN reached a sensitivity of 94.4% and specificity of 68.8% (AUC: 0.88) for the necessity of DCE, correctly assigning 44%/34% of patients to a biparametric/multiparametric protocol. In 2% of all patients, the CNN incorrectly decided on omitting DCE. With a technician reaching a sensitivity of 63.9% and specificity of 89.1%, the use of the CNN would allow for an increase in sensitivity of 30.5%. The CNN achieved an AUC of 0.73 in a set of examinations from a different vendor. CONCLUSIONS: The CNN would have correctly assigned 78% of patients to a biparametric or multiparametric protocol, with only 2% of all patients requiring re-examination to add DCE sequences. Integrating this CNN in clinical routine could render the requirement for on-table monitoring obsolete by performing contrast-enhanced MRI only when needed.