Automatic metastatic brain tumor segmentation for stereotactic radiosurgery applications

Where Does Auto-Segmentation for Brain Metastases Radiosurgery Stand Today?

Detection and segmentation of brain metastases (BMs) play a pivotal role in diagnosis, treatment planning, and follow-up evaluations for effective BM management. Given the rising prevalence of BM cases and its predominantly multiple onsets, automated segmentation is becoming necessary in stereotactic radiosurgery. It not only alleviates the clinician's manual workload and improves clinical workflow efficiency but also ensures treatment safety, ultimately improving patient care. Recent strides in machine learning, particularly in deep learning (DL), have revolutionized medical image segmentation, achieving state-of-the-art results. This review aims to analyze auto-segmentation strategies, characterize the utilized data, and assess the performance of cutting-edge BM segmentation methodologies. Additionally, we delve into the challenges confronting BM segmentation and share insights gleaned from our algorithmic and clinical implementation experiences.

A Review of Artificial Intelligence Application for Radiotherapy

Background and Purpose

Artificial intelligence (AI) is a technique which tries to think like humans and mimic human behaviors. It has been considered as an alternative in a lot of human-dependent steps in radiotherapy (RT), since the human participation is a principal uncertainty source in RT. The aim of this work is to provide a systematic summary of the current literature on AI application for RT, and to clarify its role for RT practice in terms of clinical views.

Materials and Methods

A systematic literature search of PubMed and Google Scholar was performed to identify original articles involving the AI applications in RT from the inception to 2022. Studies were included if they reported original data and explored the clinical applications of AI in RT.

Results

The selected studies were categorized into three aspects of RT: organ and lesion segmentation, treatment planning and quality assurance. For each aspect, this review discussed how these AI tools could be involved in the RT protocol.

Conclusions

Our study revealed that AI was a potential alternative for the human-dependent steps in the complex process of RT.

Development of RLK-Unet: a clinically favorable deep learning algorithm for brain metastasis detection and treatment response assessment

Purpose/objectives

Previous deep learning (DL) algorithms for brain metastasis (BM) detection and segmentation have not been commonly used in clinics because they produce false-positive findings, require multiple sequences, and do not reflect physiological properties such as necrosis. The aim of this study was to develop a more clinically favorable DL algorithm (RLK-Unet) using a single sequence reflecting necrosis and apply it to automated treatment response assessment.

Methods and materials

A total of 128 patients with 1339 BMs, who underwent BM magnetic resonance imaging using the contrast-enhanced 3D T1 weighted (T1WI) turbo spin-echo black blood sequence, were included in the development of the DL algorithm. Fifty-eight patients with 629 BMs were assessed for treatment response. The detection sensitivity, precision, Dice similarity coefficient (DSC), and agreement of treatment response assessments between neuroradiologists and RLK-Unet were assessed.

Results

RLK-Unet demonstrated a sensitivity of 86.9% and a precision of 79.6% for BMs and had a DSC of 0.663. Segmentation performance was better in the subgroup with larger BMs (DSC, 0.843). The agreement in the response assessment for BMs between the radiologists and RLK-Unet was excellent (intraclass correlation, 0.84).

Conclusion

RLK-Unet yielded accurate detection and segmentation of BM and could assist clinicians in treatment response assessment.

Tumor volume features predict survival outcomes for patients diagnosed with diffuse intrinsic pontine glioma

Background

Diffuse intrinsic pontine glioma (DIPG) is a fatal childhood central nervous system tumor. Diagnosis and monitoring of tumor response to therapy is based on magnetic resonance imaging (MRI). MRI-based analyses of tumor volume and appearance may aid in the prediction of patient overall survival (OS).

Methods

Contrast-enhanced T1- and FLAIR/T2-weighted MR images were retrospectively collected from children with classical DIPG diagnosed by imaging (n = 43 patients). MRI features were evaluated at diagnosis (n = 43 patients) and post-radiation (n = 40 patients) to determine OS outcome predictors. Features included 3D tumor volume (Twv), contrast-enhancing tumor core volume (Tc), Tc relative to Twv (TC/Twv), and Twv relative to whole brain volume. Support vector machine (SVM) learning was used to identify feature combinations that predicted OS outcome (defined as OS shorter or longer than 12 months from diagnosis).

Results

Features associated with poor OS outcome included the presence of contrast-enhancing tumor at diagnosis, >15% Tc/Twv post-radiation therapy (RT), and >20% ∆Tc/Twv post-RT. Consistently, SVM learning identified Tc/Twv at diagnosis (prediction accuracy of 74%) and ∆Tc/Twv at <2 months post-RT (accuracy = 75%) as primary features of poor survival.

Conclusions

This study demonstrates that tumor imaging features at diagnosis and within 4 months of RT can predict differential OS outcomes in DIPG. These findings provide a framework for incorporating tumor volume-based predictive analyses into the clinical setting, with the potential for treatment customization based on tumor risk characteristics and future applications of machine-learning-based analysis.

Stratified assessment of an FDA-cleared deep learning algorithm for automated detection and contouring of metastatic brain tumors in stereotactic radiosurgery

PURPOSE

Artificial intelligence-based tools can be leveraged to improve detection and segmentation of brain metastases for stereotactic radiosurgery (SRS). VBrain by Vysioneer Inc. is a deep learning algorithm with recent FDA clearance to assist in brain tumor contouring. We aimed to assess the performance of this tool by various demographic and clinical characteristics among patients with brain metastases treated with SRS.

MATERIALS AND METHODS

We randomly selected 100 patients with brain metastases who underwent initial SRS on the CyberKnife from 2017 to 2020 at a single institution. Cases with resection cavities were excluded from the analysis. Computed tomography (CT) and axial T1-weighted post-contrast magnetic resonance (MR) image data were extracted for each patient and uploaded to VBrain. A brain metastasis was considered "detected" when the VBrain- "predicted" contours overlapped with the corresponding physician contours ("ground-truth" contours). We evaluated performance of VBrain against ground-truth contours using the following metrics: lesion-wise Dice similarity coefficient (DSC), lesion-wise average Hausdorff distance (AVD), false positive count (FP), and lesion-wise sensitivity (%). Kruskal-Wallis tests were performed to assess the relationships between patient characteristics including sex, race, primary histology, age, and size and number of brain metastases, and performance metrics such as DSC, AVD, FP, and sensitivity.

RESULTS

We analyzed 100 patients with 435 intact brain metastases treated with SRS. Our cohort consisted of patients with a median number of 2 brain metastases (range: 1 to 52), median age of 69 (range: 19 to 91), and 50% male and 50% female patients. The primary site breakdown was 56% lung, 10% melanoma, 9% breast, 8% gynecological, 5% renal, 4% gastrointestinal, 2% sarcoma, and 6% other, while the race breakdown was 60% White, 18% Asian, 3% Black/African American, 2% Native Hawaiian or other Pacific Islander, and 17% other/unknown/not reported. The median tumor size was 0.112 c.c. (range: 0.010-26.475 c.c.). We found mean lesion-wise DSC to be 0.723, mean lesion-wise AVD to be 7.34% of lesion size (0.704 mm), mean FP count to be 0.72 tumors per case, and lesion-wise sensitivity to be 89.30% for all lesions. Moreover, mean sensitivity was found to be 99.07%, 97.59%, and 96.23% for lesions with diameter equal to and greater than 10 mm, 7.5 mm, and 5 mm, respectively. No other significant differences in performance metrics were observed across demographic or clinical characteristic groups.

CONCLUSION

In this study, a commercial deep learning algorithm showed promising results in segmenting brain metastases, with 96.23% sensitivity for metastases with diameters of 5 mm or higher. As the software is an assistive AI, future work of VBrain integration into the clinical workflow can provide further clinical and research insights.

DeSeg: auto detector-based segmentation for brain metastases

Delineation of brain metastases (BMs) is a paramount step in stereotactic radiosurgery treatment. Clinical practice has specific expectation on BM auto-delineation that the method is supposed to avoid missing of small lesions and yield accurate contours for large lesions. In this study, we propose a novel coarse-to-fine framework, named detector-based segmentation (DeSeg), to incorporate object-level detection into pixel-wise segmentation so as to meet the clinical demand. DeSeg consists of three components: a center-point-guided single-shot detector to localize the potential lesion regions, a multi-head U-Net segmentation model to refine contours, and a data cascade unit to connect both tasks smoothly. Performance on tiny lesions is measured by the object-based sensitivity and positive predictive value (PPV), while that on large lesions is quantified by dice similarity coefficient (DSC), average symmetric surface distance (ASSD) and 95% Hausdorff distance (HD95). Besides, computational complexity is also considered to study the potential of method in real-time processing. This study retrospectively collected 240 BM patients with Gadolinium injected contrast-enhanced T1-weighted magnetic resonance imaging (T1c-MRI), which were randomly split into training, validating and testing datasets (192, 24 and 24 scans, respectively). The lesions in the testing dataset were further divided into two groups based on the volume size (smallS: ≤1.5 cc,N= 88; largeL: > 1.5 cc,N= 15). On average, DeSeg yielded a sensitivity of 0.91 and a PPV of 0.77 on S group, and a DSC of 0.86, an ASSD 0f 0.76 mm and a HD95 of 2.31 mm onLgroup. The results indicated that DeSeg achieved leading sensitivity and PPV for tiny lesions as well as segmentation metrics for large ones. After our clinical validation, DeSeg showed competitive segmentation performance while kept faster processing speed comparing with existing 3D models.

Automated brain tumour identification using magnetic resonance imaging: a systematic review and meta-analysis

Background

Automated brain tumor identification facilitates diagnosis and treatment planning. We evaluate the performance of traditional machine learning (TML) and deep learning (DL) in brain tumor detection and segmentation, using MRI.

Methods

A systematic literature search from January 2000 to May 8, 2021 was conducted. Study quality was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Detection meta-analysis was performed using a unified hierarchical model. Segmentation studies were evaluated using a random effects model. Sensitivity analysis was performed for externally validated studies.

Results

Of 224 studies included in the systematic review, 46 segmentation and 38 detection studies were eligible for meta-analysis. In detection, DL achieved a lower false positive rate compared to TML; 0.018 (95% CI, 0.011 to 0.028) and 0.048 (0.032 to 0.072) (P < .001), respectively. In segmentation, DL had a higher dice similarity coefficient (DSC), particularly for tumor core (TC); 0.80 (0.77 to 0.83) and 0.63 (0.56 to 0.71) (P < .001), persisting on sensitivity analysis. Both manual and automated whole tumor (WT) segmentation had “good” (DSC ≥ 0.70) performance. Manual TC segmentation was superior to automated; 0.78 (0.69 to 0.86) and 0.64 (0.53 to 0.74) (P = .014), respectively. Only 30% of studies reported external validation.

Conclusions

The comparable performance of automated to manual WT segmentation supports its integration into clinical practice. However, manual outperformance for sub-compartmental segmentation highlights the need for further development of automated methods in this area. Compared to TML, DL provided superior performance for detection and sub-compartmental segmentation. Improvements in the quality and design of studies, including external validation, are required for the interpretability and generalizability of automated models.

Patient specific distortion detection and mitigation in MR images used for stereotactic radiosurgery

Objective. In MRI-based radiation therapy planning, mitigating patient-specific distortion with standard high bandwidth scans can result in unnecessary sacrifices of signal to noise ratio. This study investigates a technique for distortion detection and mitigation on a patient specific basis. Approach. Fast B0 mapping was performed using a previously developed technique for high-resolution, large dynamic range field mapping without the need for phase unwrapping algorithms. A phantom study was performed to validate the method. Distortion mitigation was validated by reducing geometric distortion with increased acquisition bandwidth and confirmed by both the B0 mapping technique and manual measurements. Images and contours from 25 brain stereotactic radiosurgery patients and 95 targets were analyzed to estimate the range of geometric distortions expected in the brain and to estimate bandwidth required to keep all treatment targets within the ±0.5 mm iso-distortion contour. Main Results. The phantom study showed, at 3 T, the technique can measure distortions with a mean absolute error of 0.12 mm (0.18 ppm), and a maximum error of 0.37 mm (0.6 ppm). For image acquisition at 3 T and 1.0 mm resolution, mean absolute distortion under 0.5 mm in patients required bandwidths from 109 to 200 Hz px−1 for patients with the least and most distortion, respectively. Maximum absolute distortion under 0.5 mm required bandwidths from 120 to 390 Hz px−1. Significance. The method for B0 mapping was shown to be valid and may be applied to assess distortion clinically. Future work will adapt the readout bandwidth to prospectively mitigate distortion with the goal to improve radiosurgery treatment outcomes by reducing healthy tissue exposure.

MRI biomarkers in neuro-oncology

The central role of MRI in neuro-oncology is undisputed. The technique is used, both in clinical practice and in clinical trials, to diagnose and monitor disease activity, support treatment decision-making, guide the use of focused treatments and determine response to treatment. Despite recent substantial advances in imaging technology and image analysis techniques, clinical MRI is still primarily used for the qualitative subjective interpretation of macrostructural features, as opposed to quantitative analyses that take into consideration multiple pathophysiological features. However, the field of quantitative imaging and imaging biomarker development is maturing. The European Imaging Biomarkers Alliance (EIBALL) and Quantitative Imaging Biomarkers Alliance (QIBA) are setting standards for biomarker development, validation and implementation, as well as promoting the use of quantitative imaging and imaging biomarkers by demonstrating their clinical value. In parallel, advanced imaging techniques are reaching the clinical arena, providing quantitative, commonly physiological imaging parameters that are driving the discovery, validation and implementation of quantitative imaging and imaging biomarkers in the clinical routine. Additionally, computational analysis techniques are increasingly being used in the research setting to convert medical images into objective high-dimensional data and define radiomic signatures of disease states. Here, I review the definition and current state of MRI biomarkers in neuro-oncology, and discuss the clinical potential of quantitative image analysis techniques.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Analysis of morphological characteristics of IDH-mutant/wildtype brain tumors using whole-lesion phenotype analysis

BACKGROUND

Although IDH-mutant tumors aggregate to the frontotemporal regions, the clustering pattern of IDH-wildtype tumors is less clear. As voxel-based lesion-symptom mapping (VLSM) has several limitations for solid lesion mapping, a new technique, whole-lesion phenotype analysis (WLPA), is developed. We utilize WLPA to assess spatial clustering of tumors with IDH mutation from The Cancer Genome Atlas and The Cancer Imaging Archive.

METHODS

The degree of tumor clustering segmented from T1 weighted images is measured to every other tumor by a function of lesion similarity to each other via the Hausdorff distance. Each tumor is ranked according to the degree to which its neighboring tumors show identical phenotypes, and through a permutation technique, significant tumors are determined. VLSM was applied through a previously described method.

RESULTS

A total of 244 patients of mixed-grade gliomas (WHO II-IV) are analyzed, of which 150 were IDH-wildtype and 139 were glioblastomas. VLSM identifies frontal lobe regions that are more likely associated with the presence of IDH mutation but no regions where IDH-wildtype was more likely to be present. WLPA identifies both IDH-mutant and -wildtype tumors exhibit statistically significant spatial clustering.

CONCLUSION

WLPA may provide additional statistical power when compared with VLSM without making several potentially erroneous assumptions. WLPA identifies tumors most likely to exhibit particular phenotypes, rather than producing anatomical maps, and may be used in conjunction with VLSM to understand the relationship between tumor morphology and biologically relevant tumor phenotypes.

A web-based brain metastases segmentation and labeling platform for stereotactic radiosurgery

PURPOSE

Stereotactic radiosurgery (SRS) has become a standard of care for patients' with brain metastases (BMs). However, the manual multiple BMs delineation can be time-consuming and could create an efficiency bottleneck in SRS workflow. There is a clinical need for automatic delineation and quantitative evaluation tools. In this study, building on our previous developed deep learning-based segmentation algorithms, we developed a web-based automated BMs segmentation and labeling platform to assist the SRS clinical workflow.

METHOD

This platform was developed based on the Django framework, including a web client and a back-end server. The web client enables interactions as database access, data import, and image viewing. The server performs the segmentation and labeling tasks including: skull stripping; deep learning-based BMs segmentation; and affine registration-based BMs labeling. Additionally, the client can display BMs contours with corresponding atlas labels, and allows further postprocessing tasks including: (a) adjusting window levels; (b) displaying/hiding specific contours; (c) removing false-positive contours; (d) exporting contours as DICOM RTStruct files; etc. RESULTS: We evaluated this platform on 10 clinical cases with BMs number varied from 12-81 per case. The overall operation took about 4-5 min per patient. The segmentation accuracy was evaluated between the manual contour and automatic segmentation with several metrics. The averaged center of mass shift was 1.55 ± 0.36 mm, the Hausdorff distance was 2.98 ± 0.63 mm, the mean of surface-to-surface distance (SSD) was 1.06 ± 0.31 mm, and the standard deviation of SSD was 0.80 ± 0.16 mm. In addition, the initial averaged false-positive over union (FPoU) and false-negative rate (FNR) were 0.43 ± 0.19 and 0.15 ± 0.10 respectively. After case-specific postprocessing, the averaged FPoU and FNR were 0.19 ± 0.10 and 0.15 ± 0.10 respectively.

CONCLUSION

The evaluated web-based BMs segmentation and labeling platform can substantially improve the clinical efficiency compared to manual contouring. This platform can be a useful tool for assisting SRS treatment planning and treatment follow-up.

Advanced Imaging of Brain Metastases: From Augmenting Visualization and Improving Diagnosis to Evaluating Treatment Response

Early detection of brain metastases and differentiation from other neuropathologies is crucial. Although biopsy is often required for definitive diagnosis, imaging can provide useful information. After treatment commences, imaging is also performed to assess the efficacy of treatment. Contrast-enhanced magnetic resonance imaging (MRI) is the traditional imaging method for the evaluation of brain metastases, as it provides information about lesion size, morphology, and macroscopic properties. Newer MRI sequences have been developed to increase the conspicuity of detecting enhancing metastases. Other advanced MRI techniques, that have the capability to probe beyond the anatomic structure, are available to characterize micro-structures, cellularity, physiology, perfusion, and metabolism. Artificial intelligence provides powerful computational tools for detection, segmentation, classification, prediction, and prognosis. We highlight and review a few advanced MRI techniques for the assessment of brain metastases-specifically for (1) diagnosis, including differentiating between malignancy types and (2) evaluation of treatment response, including the differentiation between radiation necrosis and disease progression.

Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning

This work aimed to investigate whether automated classifiers belonging to feature-based and deep learning may approach brain metastases segmentation successfully. Support Vector Machine and V-Net Convolutional Neural Network are selected as representatives of the two approaches. In the experiments, we consider several configurations of the two methods to segment brain metastases on contrast-enhanced T1-weighted magnetic resonance images. Performances were evaluated and compared under critical conditions imposed by the clinical radiotherapy domain, using in-house dataset and public dataset created for the Multimodal Brain Tumour Image Segmentation (BraTS) challenge. Our results showed that the feature-based and the deep network approaches are promising for the segmentation of Magnetic Resonance Imaging (MRI) brain metastases achieving both an acceptable level of performance. Experimental results also highlight different behaviour between the two methods. Support vector machine (SVM) improves performance with a smaller training set, but it is unable to manage a high level of heterogeneity in the data and requires post-processing refinement stages. The V-Net model shows good performances when trained on multiple heterogeneous cases but requires data augmentations and transfer learning procedures to optimise its behaviour. The paper illustrates a software package implementing an integrated set of procedures for active support in segmenting brain metastases within the radiotherapy workflow.

Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI

BACKGROUND

Detecting and segmenting brain metastases is a tedious and time-consuming task for many radiologists, particularly with the growing use of multisequence 3D imaging.

PURPOSE

To demonstrate automated detection and segmentation of brain metastases on multisequence MRI using a deep-learning approach based on a fully convolution neural network (CNN).

STUDY TYPE

Retrospective.

POPULATION

In all, 156 patients with brain metastases from several primary cancers were included.

FIELD STRENGTH

1.5T and 3T. [Correction added on May 24, 2019, after first online publication: In the preceding sentence, the first field strength listed was corrected.] SEQUENCE: Pretherapy MR images included pre- and postgadolinium T₁ -weighted 3D fast spin echo (CUBE), postgadolinium T₁ -weighted 3D axial IR-prepped FSPGR (BRAVO), and 3D CUBE fluid attenuated inversion recovery (FLAIR).

ASSESSMENT

The ground truth was established by manual delineation by two experienced neuroradiologists. CNN training/development was performed using 100 and 5 patients, respectively, with a 2.5D network based on a GoogLeNet architecture. The results were evaluated in 51 patients, equally separated into those with few (1-3), multiple (4-10), and many (>10) lesions.

STATISTICAL TESTS

Network performance was evaluated using precision, recall, Dice/F1 score, and receiver operating characteristic (ROC) curve statistics. For an optimal probability threshold, detection and segmentation performance was assessed on a per-metastasis basis. The Wilcoxon rank sum test was used to test the differences between patient subgroups.

RESULTS

The area under the ROC curve (AUC), averaged across all patients, was 0.98 ± 0.04. The AUC in the subgroups was 0.99 ± 0.01, 0.97 ± 0.05, and 0.97 ± 0.03 for patients having 1-3, 4-10, and >10 metastases, respectively. Using an average optimal probability threshold determined by the development set, precision, recall, and Dice score were 0.79 ± 0.20, 0.53 ± 0.22, and 0.79 ± 0.12, respectively. At the same probability threshold, the network showed an average false-positive rate of 8.3/patient (no lesion-size limit) and 3.4/patient (10 mm³ lesion size limit).

DATA CONCLUSION

A deep-learning approach using multisequence MRI can automatically detect and segment brain metastases with high accuracy.

LEVEL OF EVIDENCE

3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020;51:175-182.

Real-Time Whole-Brain Radiation Therapy: A Single-Institution Experience

PURPOSE

To demonstrate the feasibility of a real-time whole-brain radiation therapy (WBRT) workflow, taking advantage of contemporary radiation therapy capabilities and seeking to optimize clinical workflow for WBRT.

METHODS AND MATERIALS

We developed a method incorporating the linear accelerator's on-board imaging system for patient simulation, used cone-beam computed tomography (CBCT) data for treatment planning, and delivered the first fraction of prescribed therapy, all during the patient's initial appointment. Simulation was performed in the linear accelerator vault. An acquired CBCT data set was used for scripted treatment planning protocol, providing inversely planned, automated treatment plan generation. The osseous boundaries of the brain were auto-contoured to create a target volume. Two parallel-opposed beams using field-in-field intensity modulate radiation therapy covered this target to the user-defined inferior level (C1 or C2). The method was commissioned using an anthropomorphic head phantom and verified using 100 clinically treated patients.

RESULTS

Whole-brain target heterogeneity was within 95%-107% of the prescription dose, and target coverage compared favorably to standard, manually created 3-dimensional plans. For the commissioning CBCT datasets, the secondary monitor unit verification and independent 3-dimensional dose distribution comparison for computed and delivered doses were within 2% agreement relative to the scripted auto-plans. On average, time needed to complete the entire process was 35.1 ± 10.3 minutes from CBCT start to last beam delivered.

CONCLUSIONS

The real-time WBRT workflow using integrated on-site imaging, planning, quality assurance, and delivery was tested and deemed clinically feasible. The design necessitates a synchronized team consisting of physician, physicist, dosimetrist, and therapists. This work serves as a proof of concept of real-time planning and delivery for other treatment sites.

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.