“…The performances of machine-learning algorithms, including the CNNs, heavily depend on their hyperparameter settings [37]. Accordingly, some of the BM-segmentation studies, such as [10] and [11], provided a set of analyses on parameter tuning. The introduced framework's performance also relies on proper setup of multiple parameters, including (1) edge length and the block count of CropNet, (2) random gamma correction range, and (3) elastic deformation parameters, which were found empirically and individually.…”
Section: Discussionmentioning
confidence: 99%
“…sensitivity vs average number of false-positive detections per patient -AFP) at various output threshold settings (~0 -low likelihood and ~1 -high likelihood of metastasis). Accordingly, state-of-art approaches[10] [11][15] follow a similar reporting methodology.…”
Brain Metastases (BM) complicate 20-40% of cancer cases. BM lesions can present as punctate (1 mm) foci, requiring high-precision Magnetic Resonance Imaging (MRI) in order to prevent inadequate or delayed BM treatment. However, BM lesion detection remains challenging partly due to their structural similarities to normal structures (e.g., vasculature). We propose a BMdetection framework using a single-sequence gadoliniumenhanced T1-weighted 3D MRI dataset. The framework focuses on detection of smaller (< 15 mm) BM lesions and consists of: (1) candidate-selection stage, using Laplacian of Gaussian approach for highlighting parts of a MRI volume holding higher BM occurrence probabilities, and (2) detection stage that iteratively processes cropped region-of-interest volumes centered by candidates using a custom-built 3D convolutional neural network ("CropNet"). Data is augmented extensively during training via a pipeline consisting of random gamma correction and elastic deformation stages; the framework thereby maintains its invariance for a plausible range of BM shape and intensity representations. This approach is tested using five-fold cross-validation on 217 datasets from 158 patients, with training and testing groups randomized per patient to eliminate learning bias. The BM database included lesions with a mean diameter of ~5.4 mm and a mean volume of ~160 mm 3 . For 90% BM-detection sensitivity, the framework produced on average 9.12 falsepositive BM detections per patient (standard deviation of 3.49); for 85% sensitivity, the average number of falsepositives declined to 5.85. Comparative analysis showed that the framework produces comparable BM-detection accuracy with the state-of-art approaches validated for significantly larger lesions.Index Terms-magnetic resonance imaging, brain metastases, convolutional neural networks, deep learning, scale-space representations, computer-aided detection, medical image analysis.
“…The performances of machine-learning algorithms, including the CNNs, heavily depend on their hyperparameter settings [37]. Accordingly, some of the BM-segmentation studies, such as [10] and [11], provided a set of analyses on parameter tuning. The introduced framework's performance also relies on proper setup of multiple parameters, including (1) edge length and the block count of CropNet, (2) random gamma correction range, and (3) elastic deformation parameters, which were found empirically and individually.…”
Section: Discussionmentioning
confidence: 99%
“…sensitivity vs average number of false-positive detections per patient -AFP) at various output threshold settings (~0 -low likelihood and ~1 -high likelihood of metastasis). Accordingly, state-of-art approaches[10] [11][15] follow a similar reporting methodology.…”
Brain Metastases (BM) complicate 20-40% of cancer cases. BM lesions can present as punctate (1 mm) foci, requiring high-precision Magnetic Resonance Imaging (MRI) in order to prevent inadequate or delayed BM treatment. However, BM lesion detection remains challenging partly due to their structural similarities to normal structures (e.g., vasculature). We propose a BMdetection framework using a single-sequence gadoliniumenhanced T1-weighted 3D MRI dataset. The framework focuses on detection of smaller (< 15 mm) BM lesions and consists of: (1) candidate-selection stage, using Laplacian of Gaussian approach for highlighting parts of a MRI volume holding higher BM occurrence probabilities, and (2) detection stage that iteratively processes cropped region-of-interest volumes centered by candidates using a custom-built 3D convolutional neural network ("CropNet"). Data is augmented extensively during training via a pipeline consisting of random gamma correction and elastic deformation stages; the framework thereby maintains its invariance for a plausible range of BM shape and intensity representations. This approach is tested using five-fold cross-validation on 217 datasets from 158 patients, with training and testing groups randomized per patient to eliminate learning bias. The BM database included lesions with a mean diameter of ~5.4 mm and a mean volume of ~160 mm 3 . For 90% BM-detection sensitivity, the framework produced on average 9.12 falsepositive BM detections per patient (standard deviation of 3.49); for 85% sensitivity, the average number of falsepositives declined to 5.85. Comparative analysis showed that the framework produces comparable BM-detection accuracy with the state-of-art approaches validated for significantly larger lesions.Index Terms-magnetic resonance imaging, brain metastases, convolutional neural networks, deep learning, scale-space representations, computer-aided detection, medical image analysis.
“…While the current benchmark for brain metastases segmentation employs MRI imaging only [1,6], CT imaging is an essential reference for clinical treatment planning due to its spatial accuracy. We thus proposed a deep learning framework using multimodal imaging (MRI+CT) and ensemble neural networks for brain metastases detection and segmentation.…”
Section: Deep Learning Frameworkmentioning
confidence: 99%
“…DeepMedic DeepMedic [4] is originally designed for brain tumor segmentation on multi-channel MRI and also had been applied to BMs [1,6]. It consists of multiple parallel pathways-one branch takes small patches from full resolution images as input and the others utilizes subsampled-version of the images.…”
Section: Deep Learning Frameworkmentioning
confidence: 99%
“…However, such manually contouring process can be very time-consuming and suffer from large inter and intra-reader variability [11]. Driven by the ever-increasing capability of deep learning, automated segmentation of BMs using neural networks has been recently proposed [1,6]. Previous works on computer-aided segmentation of BMs used only MRI as an imaging input.…”
Stereotactic radiosurgery (SRS), which delivers high doses of irradiation in a single or few shots to small targets, has been a standard of care for brain metastases. While very effective, SRS currently requires manually intensive delineation of tumors. In this work, we present a deep learning approach for automated detection and segmentation of brain metastases using multimodal imaging and ensemble neural networks. In order to address small and multiple brain metastases, we further propose a volume-aware Dice loss which optimizes model performance using the information of lesion size. This work surpasses current benchmark levels and demonstrates a reliable AI-assisted system for SRS treatment planning for multiple brain metastases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.