Nitish Thakor

Avisha Kumar, Kunal Kotkar, Kelly Jiang et al.

While deep learning has catalyzed breakthroughs across numerous domains, its broader adoption in clinical settings is inhibited by the costly and time-intensive nature of data acquisition and annotation. To further facilitate medical machine learning, we present an ultrasound dataset of 10,223 Brightness-mode (B-mode) images consisting of sagittal slices of porcine spinal cords (N=25) before and after a contusion injury. We additionally benchmark the performance metrics of several state-of-the-art object detection algorithms to localize the site of injury and semantic segmentation models to label the anatomy for comparison and creation of task-specific architectures. Finally, we evaluate the zero-shot generalization capabilities of the segmentation models on human ultrasound spinal cord images to determine whether training on our porcine dataset is sufficient for accurately interpreting human data. Our results show that the YOLOv8 detection model outperforms all evaluated models for injury localization, achieving a mean Average Precision (mAP50-95) score of 0.606. Segmentation metrics indicate that the DeepLabv3 segmentation model achieves the highest accuracy on unseen porcine anatomy, with a Mean Dice score of 0.587, while SAMed achieves the highest Mean Dice score generalizing to human anatomy (0.445). To the best of our knowledge, this is the largest annotated dataset of spinal cord ultrasound images made publicly available to researchers and medical professionals, as well as the first public report of object detection and segmentation architectures to assess anatomical markers in the spinal cord for methodology development and clinical applications.

Xianliang Ge, Yunxian Pan, Sujie Wang et al.

Intention decoding is an indispensable procedure in hands-free human-computer interaction (HCI). Conventional eye-tracking system using single-model fixation duration possibly issues commands ignoring users' real expectation. In the current study, an eye-brain hybrid brain-computer interface (BCI) interaction system was introduced for intention detection through fusion of multi-modal eye-track and ERP (a measurement derived from EEG) features. Eye-track and EEG data were recorded from 64 healthy participants as they performed a 40-min customized free search task of a fixed target icon among 25 icons. The corresponding fixation duration of eye-tracking and ERP were extracted. Five previously-validated LDA-based classifiers (including RLDA, SWLDA, BLDA, SKLDA, and STDA) and the widely-used CNN method were adopted to verify the efficacy of feature fusion from both offline and pseudo-online analysis, and optimal approach was evaluated through modulating the training set and system response duration. Our study demonstrated that the input of multi-modal eye-track and ERP features achieved superior performance of intention detection in the single trial classification of active search task. And compared with single-model ERP feature, this new strategy also induced congruent accuracy across different classifiers. Moreover, in comparison with other classification methods, we found that the SKLDA exhibited the superior performance when fusing feature in offline test (ACC=0.8783, AUC=0.9004) and online simulation with different sample amount and duration length. In sum, the current study revealed a novel and effective approach for intention classification using eye-brain hybrid BCI, and further supported the real-life application of hands-free HCI in a more precise and stable manner.

Rohan Ghosh, Siyi Tang, Mahdi Rasouli et al.

Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose.

Rohan Ghosh, Anupam Gupta, Andrei Nakagawa et al.

In this paper, we address the challenging problem of action recognition, using event-based cameras. To recognise most gestural actions, often higher temporal precision is required for sampling visual information. Actions are defined by motion, and therefore, when using event-based cameras it is often unnecessary to re-sample the entire scene. Neuromorphic, event-based cameras have presented an alternative to visual information acquisition by asynchronously time-encoding pixel intensity changes, through temporally precise spikes (10 micro-second resolution), making them well equipped for action recognition. However, other challenges exist, which are intrinsic to event-based imagers, such as higher signal-to-noise ratio, and a spatiotemporally sparse information. One option is to convert event-data into frames, but this could result in significant temporal precision loss. In this work we introduce spatiotemporal filtering in the spike-event domain, as an alternative way of channeling spatiotemporal information through to a convolutional neural network. The filters are local spatiotemporal weight matrices, learned from the spike-event data, in an unsupervised manner. We find that appropriate spatiotemporal filtering significantly improves CNN performance beyond state-of-the-art on the event-based DVS Gesture dataset. On our newly recorded action recognition dataset, our method shows significant improvement when compared with other, standard ways of generating the spatiotemporal filters.

Rohan Ghosh, Anupam Gupta, Siyi Tang et al.

Unlike conventional frame-based sensors, event-based visual sensors output information through spikes at a high temporal resolution. By only encoding changes in pixel intensity, they showcase a low-power consuming, low-latency approach to visual information sensing. To use this information for higher sensory tasks like object recognition and tracking, an essential simplification step is the extraction and learning of features. An ideal feature descriptor must be robust to changes involving (i) local transformations and (ii) re-appearances of a local event pattern. To that end, we propose a novel spatiotemporal feature representation learning algorithm based on slow feature analysis (SFA). Using SFA, smoothly changing linear projections are learnt which are robust to local visual transformations. In order to determine if the features can learn to be invariant to various visual transformations, feature point tracking tasks are used for evaluation. Extensive experiments across two datasets demonstrate the adaptability of the spatiotemporal feature learner to translation, scaling and rotational transformations of the feature points. More importantly, we find that the obtained feature representations are able to exploit the high temporal resolution of such event-based cameras in generating better feature tracks.

Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings et al.

This paper introduces a spiking hierarchical model for object recognition which utilizes the precise timing information inherently present in the output of biologically inspired asynchronous Address Event Representation (AER) vision sensors. The asynchronous nature of these systems frees computation and communication from the rigid predetermined timing enforced by system clocks in conventional systems. Freedom from rigid timing constraints opens the possibility of using true timing to our advantage in computation. We show not only how timing can be used in object recognition, but also how it can in fact simplify computation. Specifically, we rely on a simple temporal-winner-take-all rather than more computationally intensive synchronous operations typically used in biologically inspired neural networks for object recognition. This approach to visual computation represents a major paradigm shift from conventional clocked systems and can find application in other sensory modalities and computational tasks. We showcase effectiveness of the approach by achieving the highest reported accuracy to date (97.5\%$\pm$3.5\%) for a previously published four class card pip recognition task and an accuracy of 84.9\%$\pm$1.9\% for a new more difficult 36 class character recognition task.