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

Abstract

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.

Artificial intelligence in neuroimaging of brain tumors: reality or still promise?

“…Federated learning provides an effective method to train an AI algorithm across multiple institutions without sharing raw imaging data and has been successfully applied to glioma segmentation, combining data from more than 60 institutions worldwide [27]. To date, commercial AI tools for fully automated segmentation are becoming available for glioblastoma [28 && ] and brain metastasis [29]. These tools can be used for imaging assessment during clinical trials and can also be integrated with picture archiving and communication system (PACS) as part of clinical radiology workflow.…”

Segmentation of Brain Metastases Using Background Layer Statistics (BLAST)

“…Supervised methods, such as those based on deep convolutional neural networks, have recently garnered attention, showing excellent performance in brain tumor segmentation tasks, [3][4][5] with 1 algorithm now FDA-cleared. 6 These supervised methods, however, require large numbers of (manual) labels for training, which is a time-consuming and costly process and can be prone to bias introduced by the training set. Additionally, optimal performance of deep learning (DL) algorithms across multiple institutions commonly requires retraining with additional site-specific data (distributions).…”