Search

Standard treatment of patients with glioblastoma includes surgical resection of the tumor. The extent of resection (EOR) achieved during surgery significantly impacts prognosis and is used to stratify patients in clinical trials. In this study, we developed a U-Net-based deep-learning model to segment contrast-enhancing tumor on post-operative MRI exams taken within 72 h of resection surgery and used these segmentations to classify the EOR as either maximal or submaximal. The model was trained on 122 multiparametric MRI scans from our institution and achieved a mean Dice score of 0.52 ± 0.03 on an external dataset (n = 248), a performance ­on par with the interrater agreement between expert annotators as reported in literature. We obtained an EOR classification precision/recall of 0.72/0.78 on the internal test dataset (n = 462) and 0.90/0.87 on the external dataset. Furthermore, Kaplan-Meier curves were used to compare the overall survival between patients with maximal and submaximal resection in the internal test dataset, as determined by either clinicians or the model. There was no significant difference between the survival predictions using the model's and clinical EOR classification. We find that the proposed segmentation model is capable of reliably classifying the EOR of glioblastoma tumors on early post-operative MRI scans. Moreover, we show that stratification of patients based on the model's predictions offers at least the same prognostic value as when done by clinicians.

Abstract Extent of resection after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification of residual tumor from post-operative MR images is essential. The current standard method for estimating it is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of extent of resection. In this study, two state-of-the-art neural network architectures for pre-operative segmentation were trained for the task. The models were extensively validated on a multicenter dataset with nearly 1000 patients, from 12 hospitals in Europe and the United States. The best performance achieved was a 61% Dice score, and the best classification performance was about 80% balanced accuracy, with a demonstrated ability to generalize across hospitals. In addition, the segmentation performance of the best models was on par with human expert raters. The predicted segmentations can be used to accurately classify the patients into those with residual tumor, and those with gross total resection.

Background: Gliomas have a heterogeneous nature, and identifying the most aggressive parts of the tumor and defining tumor borders are important for histomolecular diagnosis, surgical resection, and radiation therapy planning. This study evaluated [18F]-FACBC PET for glioma tissue classification. Methods: Pre-surgical [18F]-FACBC PET/MR images were used during surgery and image-localized biopsy sampling in patients with high- and low-grade glioma. TBR was compared to histomolecular results to determine optimal threshold values, sensitivity, specificity, and AUC values for the classification of tumor tissue. Additionally, PET volumes were determined in patients with glioblastoma based on the optimal threshold. [18F]-FACBC PET volumes and diagnostic accuracy were compared to ce-T1 MRI. In total, 48 biopsies from 17 patients were analyzed. Results: [18F]-FACBC had low uptake in non-glioblastoma tumors, but overall higher sensitivity and specificity for the classification of tumor tissue (0.63 and 0.57) than ce-T1 MRI (0.24 and 0.43). Additionally, [18F]-FACBC TBR was an excellent classifier for IDH1-wildtype tumor tissue (AUC: 0.83, 95% CI: 0.71–0.96). In glioblastoma patients, PET tumor volumes were on average eight times larger than ce-T1 MRI volumes and included 87.5% of tumor-positive biopsies compared to 31.5% for ce-T1 MRI. Conclusion: The addition of [18F]-FACBC PET to conventional MRI could improve tumor classification and volume delineation.

Abstract For patients suffering from central nervous system tumors, prognosis estimation, treatment decisions, and postoperative assessments are made from the analysis of a set of magnetic resonance (MR) scans. Currently, the lack of open tools for standardized and automatic tumor segmentation and generation of clinical reports, incorporating relevant tumor characteristics, leads to potential risks from inherent decisions’ subjectivity. To tackle this problem, the proposed Raidionics open-source software has been developed, offering both a user-friendly graphical user interface and stable processing backend. The software includes preoperative segmentation models for each of the most common tumor types (i.e., glioblastomas, lower grade gliomas, meningiomas, and metastases), together with one early postoperative glioblastoma segmentation model. Preoperative segmentation performances were quite homogeneous across the four different brain tumor types, with an average Dice around 85% and patient-wise recall and precision around 95%. Postoperatively, performances were lower with an average Dice of 41%. Overall, the generation of a standardized clinical report, including the tumor segmentation and features computation, requires about ten minutes on a regular laptop. The proposed Raidionics software is the first open solution enabling an easy use of state-of-the-art segmentation models for all major tumor types, including preoperative and postsurgical standardized reports.

Over the past decades, histopathological cancer diagnostics has become more complex, and the increasing number of biopsies is a challenge for most pathology laboratories. Thus, development of automatic methods for evaluation of histopathological cancer sections would be of value. In this study, we used 624 whole slide images (WSIs) of breast cancer from a Norwegian cohort. We propose a cascaded convolutional neural network design, called H2G-Net, for segmentation of breast cancer region from gigapixel histopathological images. The design involves a detection stage using a patch-wise method, and a refinement stage using a convolutional autoencoder. To validate the design, we conducted an ablation study to assess the impact of selected components in the pipeline on tumor segmentation. Guiding segmentation, using hierarchical sampling and deep heatmap refinement, proved to be beneficial when segmenting the histopathological images. We found a significant improvement when using a refinement network for post-processing the generated tumor segmentation heatmaps. The overall best design achieved a Dice similarity coefficient of 0.933±0.069 on an independent test set of 90 WSIs. The design outperformed single-resolution approaches, such as cluster-guided, patch-wise high-resolution classification using MobileNetV2 (0.872±0.092) and a low-resolution U-Net (0.874±0.128). In addition, the design performed consistently on WSIs across all histological grades and segmentation on a representative × 400 WSI took ~ 58 s, using only the central processing unit. The findings demonstrate the potential of utilizing a refinement network to improve patch-wise predictions. The solution is efficient and does not require overlapping patch inference or ensembling. Furthermore, we showed that deep neural networks can be trained using a random sampling scheme that balances on multiple different labels simultaneously, without the need of storing patches on disk. Future work should involve more efficient patch generation and sampling, as well as improved clustering.

For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on a set of preoperative MR scans. Currently, the lack of standardized and automatic methods for tumor detection and generation of clinical reports, incorporating a wide range of tumor characteristics, represents a major hurdle. In this study, we investigate the most occurring brain tumor types: glioblastomas, lower grade gliomas, meningiomas, and metastases, through four cohorts of up to 4,000 patients. Tumor segmentation models were trained using the AGU-Net architecture with different preprocessing steps and protocols. Segmentation performances were assessed in-depth using a wide-range of voxel and patient-wise metrics covering volume, distance, and probabilistic aspects. Finally, two software solutions have been developed, enabling an easy use of the trained models and standardized generation of clinical reports: Raidionics and Raidionics-Slicer. Segmentation performances were quite homogeneous across the four different brain tumor types, with an average true positive Dice ranging between 80 and 90%, patient-wise recall between 88 and 98%, and patient-wise precision around 95%. In conjunction to Dice, the identified most relevant other metrics were the relative absolute volume difference, the variation of information, and the Hausdorff, Mahalanobis, and object average symmetric surface distances. With our Raidionics software, running on a desktop computer with CPU support, tumor segmentation can be performed in 16–54 s depending on the dimensions of the MRI volume. For the generation of a standardized clinical report, including the tumor segmentation and features computation, 5–15 min are necessary. All trained models have been made open-access together with the source code for both software solutions and validation metrics computation. In the future, a method to convert results from a set of metrics into a final single score would be highly desirable for easier ranking across trained models. In addition, an automatic classification of the brain tumor type would be necessary to replace manual user input. Finally, the inclusion of post-operative segmentation in both software solutions will be key for generating complete post-operative standardized clinical reports.

Deep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for working with WSIs, but few support deployment of CNN models. These applications use third-party solutions for inference, making them less user-friendly and unsuitable for high-performance image analysis. To make deployment of CNNs user-friendly and feasible on low-end machines, we have developed a new platform, FastPathology, using the FAST framework and C++. It minimizes memory usage for reading and processing WSIs, deployment of CNN models, and real-time interactive visualization of results. Runtime experiments were conducted on four different use cases, using different architectures, inference engines, hardware configurations and operating systems. Memory usage for reading, visualizing, zooming and panning a WSI were measured, using FastPathology and three existing platforms. FastPathology performed similarly in terms of memory to the other C++-based application, while using considerably less than the two Java-based platforms. The choice of neural network model, inference engine, hardware and processors influenced runtime considerably. Thus, FastPathology includes all steps needed for efficient visualization and processing of WSIs in a single application, including inference of CNNs with real-time display of the results. Source code, binary releases, video demonstrations and test data can be found online on GitHub at https://github.com/SINTEFMedtek/FAST-Pathology/.

Application of deep learning on histopathological whole slide images (WSIs) holds promise of improving diagnostic efficiency and reproducibility but is largely dependent on the ability to write computer code or purchase commercial solutions. We present a code-free pipeline utilizing free-to-use, open-source software (QuPath, DeepMIB, and FastPathology) for creating and deploying deep learning-based segmentation models for computational pathology. We demonstrate the pipeline on a use case of separating epithelium from stroma in colonic mucosa. A dataset of 251 annotated WSIs, comprising 140 hematoxylin-eosin (HE)-stained and 111 CD3 immunostained colon biopsy WSIs, were developed through active learning using the pipeline. On a hold-out test set of 36 HE and 21 CD3-stained WSIs a mean intersection over union score of 95.5 and 95.3% was achieved on epithelium segmentation. We demonstrate pathologist-level segmentation accuracy and clinical acceptable runtime performance and show that pathologists without programming experience can create near state-of-the-art segmentation solutions for histopathological WSIs using only free-to-use software. The study further demonstrates the strength of open-source solutions in its ability to create generalizable, open pipelines, of which trained models and predictions can seamlessly be exported in open formats and thereby used in external solutions. All scripts, trained models, a video tutorial, and the full dataset of 251 WSIs with ~31 k epithelium annotations are made openly available at https://github.com/andreped/NoCodeSeg to accelerate research in the field.

BackgroundGlioma is the most common intra-axial tumor, and its location relative to critical areas of the brain is important for treatment decision-making. Studies often report tumor location based on anatomical taxonomy alone since the estimation of eloquent regions requires considerable knowledge of functional neuroanatomy and is, to some degree, a subjective measure. An unbiased and reproducible method to determine tumor location and eloquence is desirable, both for clinical use and for research purposes.ObjectiveTo report on a voxel-based method for assessing anatomical distribution and proximity to eloquent regions in diffuse lower-grade gliomas (World Health Organization grades 2 and 3).MethodsA multi-institutional population-based dataset of adult patients (≥18 years) histologically diagnosed with lower-grade glioma was analyzed. Tumor segmentations were registered to a standardized space where two anatomical atlases were used to perform a voxel-based comparison of the proximity of segmentations to brain regions of traditional clinical interest.ResultsExploring the differences between patients with oligodendrogliomas, isocitrate dehydrogenase (IDH) mutated astrocytomas, and patients with IDH wild-type astrocytomas, we found that the latter were older, more often had lower Karnofsky performance status, and that these tumors were more often found in the proximity of eloquent regions. Eloquent regions are found slightly more frequently in the proximity of IDH-mutated astrocytomas compared to oligodendrogliomas. The regions included in our voxel-based definition of eloquence showed a high degree of association with performing biopsy compared to resection.ConclusionWe present a simple, robust, unbiased, and clinically relevant method for assessing tumor location and eloquence in lower-grade gliomas.

With the recent developments in machine learning and modern graphics processing units (GPUs), there is a marked shift in the way intra-operative ultrasound (iUS) images can be processed and presented during surgery. Real-time processing of images to highlight important anatomical structures combined with in-situ display, has the potential to greatly facilitate the acquisition and interpretation of iUS images when guiding an operation. In order to take full advantage of the recent advances in machine learning, large amounts of high-quality annotated training data are necessary to develop and validate the algorithms. To ensure efficient collection of a sufficient number of patient images and external validity of the models, training data should be collected at several centers by different neurosurgeons, and stored in a standard format directly compatible with the most commonly used machine learning toolkits and libraries. In this paper, we argue that such effort to collect and organize large-scale multi-center datasets should be based on common open source software and databases. We first describe the development of existing open-source ultrasound based neuronavigation systems and how these systems have contributed to enhanced neurosurgical guidance over the last 15 years. We review the impact of the large number of projects worldwide that have benefited from the publicly available datasets “Brain Images of Tumors for Evaluation” (BITE) and “Retrospective evaluation of Cerebral Tumors” (RESECT) that include MR and US data from brain tumor cases. We also describe the need for continuous data collection and how this effort can be organized through the use of a well-adapted and user-friendly open-source software platform that integrates both continually improved guidance and automated data collection functionalities.

For patients with presumed glioblastoma, essential tumor characteristics are determined from preoperative MR images to optimize the treatment strategy. This procedure is time-consuming and subjective, if performed by crude eyeballing or manually. The standardized GSI-RADS aims to provide neurosurgeons with automatic tumor segmentations to extract tumor features rapidly and objectively. In this study, we improved automatic tumor segmentation and compared the agreement with manual raters, describe the technical details of the different components of GSI-RADS, and determined their speed. Two recent neural network architectures were considered for the segmentation task: nnU-Net and AGU-Net. Two preprocessing schemes were introduced to investigate the tradeoff between performance and processing speed. A summarized description of the tumor feature extraction and standardized reporting process is included. The trained architectures for automatic segmentation and the code for computing the standardized report are distributed as open-source and as open-access software. Validation studies were performed on a dataset of 1594 gadolinium-enhanced T1-weighted MRI volumes from 13 hospitals and 293 T1-weighted MRI volumes from the BraTS challenge. The glioblastoma tumor core segmentation reached a Dice score slightly below 90%, a patientwise F1-score close to 99%, and a 95th percentile Hausdorff distance slightly below 4.0 mm on average with either architecture and the heavy preprocessing scheme. A patient MRI volume can be segmented in less than one minute, and a standardized report can be generated in up to five minutes. The proposed GSI-RADS software showed robust performance on a large collection of MRI volumes from various hospitals and generated results within a reasonable runtime.

Treatment decisions for patients with presumed glioblastoma are based on tumor characteristics available from a preoperative MR scan. Tumor characteristics, including volume, location, and resectability, are often estimated or manually delineated. This process is time consuming and subjective. Hence, comparison across cohorts, trials, or registries are subject to assessment bias. In this study, we propose a standardized Glioblastoma Surgery Imaging Reporting and Data System (GSI-RADS) based on an automated method of tumor segmentation that provides standard reports on tumor features that are potentially relevant for glioblastoma surgery. As clinical validation, we determine the agreement in extracted tumor features between the automated method and the current standard of manual segmentations from routine clinical MR scans before treatment. In an observational consecutive cohort of 1596 adult patients with a first time surgery of a glioblastoma from 13 institutions, we segmented gadolinium-enhanced tumor parts both by a human rater and by an automated algorithm. Tumor features were extracted from segmentations of both methods and compared to assess differences, concordance, and equivalence. The laterality, contralateral infiltration, and the laterality indices were in excellent agreement. The native and normalized tumor volumes had excellent agreement, consistency, and equivalence. Multifocality, but not the number of foci, had good agreement and equivalence. The location profiles of cortical and subcortical structures were in excellent agreement. The expected residual tumor volumes and resectability indices had excellent agreement, consistency, and equivalence. Tumor probability maps were in good agreement. In conclusion, automated segmentations are in excellent agreement with manual segmentations and practically equivalent regarding tumor features that are potentially relevant for neurosurgical purposes. Standard GSI-RADS reports can be generated by open access software.

PURPOSE:The aim of this paper is to show how a specialized planning and guidance application called Fraxinus, can be built on top of the CustusX platform (www.custusx.org), which is an open source image-guided intervention software platform. Fraxinus has been customized to meet the clinical needs in navigated bronchoscopy. METHODS:The application requirements for Fraxinus were defined in close collaboration between research scientists, software developers and clinicians (pulmonologists), and built on top of CustusX. Its superbuild system downloads specific versions of the required libraries and builds them for the application in question, including the selected plugins. New functionality is easily added through the plugin framework. The build process enables the creation of specialized applications, adding additional documentation and custom configurations. The toolkit's libraries offer building blocks for image-guided applications. An iterative development process was applied, where the clinicians would test and provide feedback during the entire process. RESULTS:Fraxinus has been developed and is released as an open source planning and guidance application built on top of CustusX. It is highly specialized for bronchoscopy. The proposed workflow is adapted to the different steps in this procedure. The user interface of CustusX has been modified to enhance information, quality assurance and user friendliness with the intention to increase the overall yield for the patient. As the workflow of the procedure is relatively constant, some actions are predicted and automatically performed by the application, according to the requirements from the clinicians. CONCLUSIONS:The CustusX platform facilitates development of new and specialized applications. The toolkit supports the process and makes important extension and injection points available for customization.

Background: Tumor location is important for surgical decision making. Particular attention is paid to regions that contain sensorimotor and language functions, but it is unknown if these are the most important regions from the patients' perspective. Objective: To develop an atlas for depicting and assessing the potential importance of tumor location for perioperative health-related quality of life (HRQoL) in patients with newly diagnosed high-grade glioma. Methods: Patient-reported HRQoL data and semi-automatically segmented preoperative 3D MRI-images were combined in 170 patients. The images were registered to a standardized space where the individual tumors were given the values and color intensity of the corresponding HRQoL. Descriptive brain maps of HRQoL, defined quantitative analyses, and voxel-based lesion symptom mapping comparing patients with tumors in different locations were made. Results: There was no statistical difference in overall perioperative HRQoL between patients with tumors located in left or right hemisphere, between patients with tumors in different lobes, or between patients with tumors located in non-eloquent, near eloquent, or eloquent areas. Patients with tumors involving the internal capsule, and patients with preoperative motor symptoms and postoperative motor deficits, reported significantly worse overall HRQoL-scores. Conclusions: The impact of anatomical tumor location on overall perioperative HRQoL seems less than frequently believed, and the distinction between critical and less critical brain regions seems more unclear according to the patients than perhaps when judged by physicians. However, worse HRQoL was found in patients with tumors in motor-related regions, indicating that these areas are crucial also from the patients' perspective. Keywords: Brain neoplasms, Cerebral cortex, Eloquence, Magnetic resonance imaging, Patient-reported outcome measures, Surgery

To facilitate a more widespread use of volumetric tumor segmentation in clinical studies, there is an urgent need for reliable, user-friendly segmentation software. The aim of this study was therefore to compare three different software packages for semi-automatic brain tumor segmentation of glioblastoma; namely BrainVoyagerTM QX, ITK-Snap and 3D Slicer, and to make data available for future reference. Pre-operative, contrast enhanced T1-weighted 1.5 or 3 Tesla Magnetic Resonance Imaging (MRI) scans were obtained in 20 consecutive patients who underwent surgery for glioblastoma. MRI scans were segmented twice in each software package by two investigators. Intra-rater, inter-rater and between-software agreement was compared by using differences of means with 95% limits of agreement (LoA), Dice's similarity coefficients (DSC) and Hausdorff distance (HD). Time expenditure of segmentations was measured using a stopwatch. Eighteen tumors were included in the analyses. Inter-rater agreement was highest for BrainVoyager with difference of means of 0.19 mL and 95% LoA from -2.42 mL to 2.81 mL. Between-software agreement and 95% LoA were very similar for the different software packages. Intra-rater, inter-rater and between-software DSC were ≥ 0.93 in all analyses. Time expenditure was approximately 41 min per segmentation in BrainVoyager, and 18 min per segmentation in both 3D Slicer and ITK-Snap. Our main findings were that there is a high agreement within and between the software packages in terms of small intra-rater, inter-rater and between-software differences of means and high Dice's similarity coefficients. Time expenditure was highest for BrainVoyager, but all software packages were relatively time-consuming, which may limit usability in an everyday clinical setting.