I am a researcher with extensive experience in computer vision, medical image processing and simulation, currently working for Nuance. Previously, I have worked on motion management for radiotherapy, particularly the Elekta Clarity Prostate monitoring system. I have also worked in surgical simulation, specifically on the OssimTech SimOrtho orthopedic simulator and the Neurotouch neurosurgical simulator. My Masters work was on automated generalization of geographic data, so you will also find code and publications on those topics prior to 2002.
TorchXRayVision is an open source software library for working with chest X-ray datasets and deep... more TorchXRayVision is an open source software library for working with chest X-ray datasets and deep learning models. It provides a common interface and common pre-processing chain for a wide set of publicly available chest X-ray datasets. In addition, a number of classification and representation learning models with different architectures, trained on different data combinations, are available through the library to serve as baselines or feature extractors. https://github.com/mlmed/torchxrayvision NOT FOR MEDICAL USE
This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize ... more This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize well across multiple different datasets. We present evidence that the issue of generalization is not due to a shift in the images but instead a shift in the labels. We study the cross-domain performance, agreement between models, and model representations. We find interesting discrepancies between performance and agreement where models which both achieve good performance disagree in their predictions as well as models which agree yet achieve poor performance. We also test for concept similarity by regularizing a network to group tasks across multiple datasets together and observe variation across the tasks. All code is made available online and data is publicly available: this https URL
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020
Automatic and accurate segmentation of medical images is an important task due to the direct impa... more Automatic and accurate segmentation of medical images is an important task due to the direct impact of this procedure on both disease diagnosis and treatment. Segmentation of ultrasound (US) imaging is particularly challenging due to the presence of speckle noise. Recent deep learning approaches have demonstrated remarkable findings in image segmentation tasks, including segmentation of US images. However, many of the newly proposed structures are either task specific and suffer from poor generalization, or are computationally expensive. In this paper, we show that the receptive field plays a more significant role in the network's performance compared to the network's depth or the number of parameters. We further show that by controlling the size of the receptive field, a deep network can instead be replaced by a shallow network.
Image alignment refers to finding the best transformation from a fixed reference image to a new i... more Image alignment refers to finding the best transformation from a fixed reference image to a new image of a scene. This process is often guided by similarity measures between images, computed based on the image data. However, in time-critical applications state-of-the-art methods for computing similarity are too slow. Instead of using all the image data to compute similarity, one can use a subset of pixels to improve the speed, but often this comes at the cost of reduced accuracy. This makes the problem of image alignment a natural application domain for deliberation control using anytime algorithms. However, almost no research has been done in this direction. In this paper, we present anytime versions for the computation of two common image similarity measures: mean squared difference and mutual information. Off-line, we learn a performance profile specific to each measure, which is then used on-line to select the appropriate amount of pixels to process at each optimization step. Wh...
Image guidance of ear surgery would enable an ENT surgeon to navigate about the components of the... more Image guidance of ear surgery would enable an ENT surgeon to navigate about the components of the middle and inner ear, but the elaboration of anatomical models for this application is limited by the resolution of CT and its inability to distinguish among soft tissues. As a result, it is impossible to identify manually some tissues in clinical data, while visible tissues can only be identified with significant overhead. We propose a method for producing patient-specific description of the middle and inner ear on the basis of the minimally supervised registration of a high resolution model elaborated from micro-MR to patient CT, where the transformation among the model and the patient data is determined in a component-wise coarse-to-fine strategy. The first two stages feature a rough alignment on the basis of a few homologous point pairs, followed by a refinement based on a global affine transformation determined by mutual information. The middle stage involves a piecewise affine reg...
Image alignment refers to finding the best transformation from a fixed reference image to a new i... more Image alignment refers to finding the best transformation from a fixed reference image to a new image of a scene. This process is often guided by similarity measures between images, computed based on the image data. However, in time-critical applications state-of-the-art methods for computing similarity are too slow. Instead of using all the image data to compute similarity, one can use a subset of pixels to improve the speed, but often this comes at the cost of reduced accuracy. This makes the problem of image alignment a natural application domain for deliberation control using anytime algorithms. However, almost no research has been done in this direction. In this paper, we present anytime versions for the computation of two common image similarity measures: mean squared difference and mutual information. Off-line, we learn a performance profile specific to each measure, which is then used on-line to select the appropriate amount of pixels to process at each optimization step. Wh...
Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions ... more Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions of neural networks. Prediction explanation is important, especially in medical imaging, for avoiding the unintended consequences of deploying AI systems when false positive predictions can impact patient care. Thus, there is a pressing need to develop improved models for model explainability and introspection. Specific problem: A new approach is to transform input images to increase or decrease features which cause the prediction. However, current approaches are difficult to implement as they are monolithic or rely on GANs. These hurdles prevent wide adoption. Our approach: Given an arbitrary classifier, we propose a simple autoencoder and gradient update (Latent Shift) that can transform the latent representation of a specific input image to exaggerate or curtail the features used for prediction. We use this method to study chest X-ray classifiers and evaluate their performance. We cond...
TorchXRayVision is an open source software library for working with chest X-ray datasets and deep... more TorchXRayVision is an open source software library for working with chest X-ray datasets and deep learning models. It provides a common interface and common pre-processing chain for a wide set of publicly available chest X-ray datasets. In addition, a number of classification and representation learning models with different architectures, trained on different data combinations, are available through the library to serve as baselines or feature extractors. https://github.com/mlmed/torchxrayvision NOT FOR MEDICAL USE
This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize ... more This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize well across multiple different datasets. We present evidence that the issue of generalization is not due to a shift in the images but instead a shift in the labels. We study the cross-domain performance, agreement between models, and model representations. We find interesting discrepancies between performance and agreement where models which both achieve good performance disagree in their predictions as well as models which agree yet achieve poor performance. We also test for concept similarity by regularizing a network to group tasks across multiple datasets together and observe variation across the tasks. All code is made available online and data is publicly available: this https URL
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020
Automatic and accurate segmentation of medical images is an important task due to the direct impa... more Automatic and accurate segmentation of medical images is an important task due to the direct impact of this procedure on both disease diagnosis and treatment. Segmentation of ultrasound (US) imaging is particularly challenging due to the presence of speckle noise. Recent deep learning approaches have demonstrated remarkable findings in image segmentation tasks, including segmentation of US images. However, many of the newly proposed structures are either task specific and suffer from poor generalization, or are computationally expensive. In this paper, we show that the receptive field plays a more significant role in the network's performance compared to the network's depth or the number of parameters. We further show that by controlling the size of the receptive field, a deep network can instead be replaced by a shallow network.
Image alignment refers to finding the best transformation from a fixed reference image to a new i... more Image alignment refers to finding the best transformation from a fixed reference image to a new image of a scene. This process is often guided by similarity measures between images, computed based on the image data. However, in time-critical applications state-of-the-art methods for computing similarity are too slow. Instead of using all the image data to compute similarity, one can use a subset of pixels to improve the speed, but often this comes at the cost of reduced accuracy. This makes the problem of image alignment a natural application domain for deliberation control using anytime algorithms. However, almost no research has been done in this direction. In this paper, we present anytime versions for the computation of two common image similarity measures: mean squared difference and mutual information. Off-line, we learn a performance profile specific to each measure, which is then used on-line to select the appropriate amount of pixels to process at each optimization step. Wh...
Image guidance of ear surgery would enable an ENT surgeon to navigate about the components of the... more Image guidance of ear surgery would enable an ENT surgeon to navigate about the components of the middle and inner ear, but the elaboration of anatomical models for this application is limited by the resolution of CT and its inability to distinguish among soft tissues. As a result, it is impossible to identify manually some tissues in clinical data, while visible tissues can only be identified with significant overhead. We propose a method for producing patient-specific description of the middle and inner ear on the basis of the minimally supervised registration of a high resolution model elaborated from micro-MR to patient CT, where the transformation among the model and the patient data is determined in a component-wise coarse-to-fine strategy. The first two stages feature a rough alignment on the basis of a few homologous point pairs, followed by a refinement based on a global affine transformation determined by mutual information. The middle stage involves a piecewise affine reg...
Image alignment refers to finding the best transformation from a fixed reference image to a new i... more Image alignment refers to finding the best transformation from a fixed reference image to a new image of a scene. This process is often guided by similarity measures between images, computed based on the image data. However, in time-critical applications state-of-the-art methods for computing similarity are too slow. Instead of using all the image data to compute similarity, one can use a subset of pixels to improve the speed, but often this comes at the cost of reduced accuracy. This makes the problem of image alignment a natural application domain for deliberation control using anytime algorithms. However, almost no research has been done in this direction. In this paper, we present anytime versions for the computation of two common image similarity measures: mean squared difference and mutual information. Off-line, we learn a performance profile specific to each measure, which is then used on-line to select the appropriate amount of pixels to process at each optimization step. Wh...
Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions ... more Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions of neural networks. Prediction explanation is important, especially in medical imaging, for avoiding the unintended consequences of deploying AI systems when false positive predictions can impact patient care. Thus, there is a pressing need to develop improved models for model explainability and introspection. Specific problem: A new approach is to transform input images to increase or decrease features which cause the prediction. However, current approaches are difficult to implement as they are monolithic or rely on GANs. These hurdles prevent wide adoption. Our approach: Given an arbitrary classifier, we propose a simple autoencoder and gradient update (Latent Shift) that can transform the latent representation of a specific input image to exaggerate or curtail the features used for prediction. We use this method to study chest X-ray classifiers and evaluate their performance. We cond...
Uploads
Papers by Rupert Brooks