arXiv subjects

Mahesh Raveendranatha Panicker

Publications and source records attributed to Mahesh Raveendranatha Panicker.

31 records · Page 2Linked to original sources

arXiv2022

A Nonlinear Beamforming for Enhanced Spatiotemporal Sensitivity in High Frame Rate Ultrasound Flow Imaging

Typically, an ultrasound flow imaging system employs the conventional delay and sum (DAS) beamformer due to its inherent low complexity. But the conventional DAS technique offers poor contrast, low imaging resolution, and limited spatiotemporal sensitivity. This article attempts to improve the spatiotemporal sensitivity of conventional flow imaging with a novel multiply and sum based nonlinear high-resolution (NLHR) beamforming approach. The major advantages of the proposed beamformer are the harmonic generation and the enhanced coherence in beamformed signals that improve the spatiotemporal sensitivity towards flow transients. We demonstrate the proposed beamformer for a directional cross-correlation as well as an autocorrelation based velocity estimator with simulated parabolic flow profiles of different velocities and flow directions, an in-vitro rotating disk dataset, and pulsatile flow experiments. The sensitivity of NLHR beamforming towards the flow transients is validated in-vitro with a sudden reversal of flow direction and air bubble tracking experiments. The comparison between the time-frequency plots of DAS and NLHR beamforming indicates that the impulsive spatiotemporal changes induced by the flow of air bubbles are clearly characterized by nonlinear beamforming than that of DAS beamforming. Furthermore, better spatiotemporal velocity tracking of a single air bubble and a clear distinguishability between the tracking of two proximal air bubbles are observed in-vitro. Preliminary studies on the in-vivo carotid data also show comparable, if not better, results than that of the DAS algorithm. Detailed results for each test case in simulation, phantom, and in-vivo studies are available as movies with the supplementary material and online.

eess.SP↗

arXiv2022

covEcho Resource constrained lung ultrasound image analysis tool for faster triaging and active learning

Lung ultrasound (LUS) is possibly the only medical imaging modality which could be used for continuous and periodic monitoring of the lung. This is extremely useful in tracking the lung manifestations either during the onset of lung infection or to track the effect of vaccination on lung as in pandemics such as COVID-19. There have been many attempts in automating the classification of severity of lung into various classes or automatic segmentation of various LUS landmarks and manifestations. However, all these approaches are based on training static machine learning models which require a significantly clinically annotated large dataset and are computationally heavy and most of the time non-real time. In this work, a real-time light weight active learning-based approach is presented for faster triaging in COVID-19 subjects in resource constrained settings. The tool, based on the you look only once (YOLO) network, has the capability of providing the quality of images based on the identification of various LUS landmarks, artefacts and manifestations, prediction of severity of lung infection, possibility of active learning based on the feedback from clinicians or on the image quality and a summarization of the significant frames which are having high severity of infection and high image quality for further analysis. The results show that the proposed tool has a mean average precision (mAP) of 66% at an Intersection over Union (IoU) threshold of 0.5 for the prediction of LUS landmarks. The 14MB lightweight YOLOv5s network achieves 123 FPS while running in a Quadro P4000 GPU. The tool is available for usage and analysis upon request from the authors.

eess.IV↗

arXiv2022

An Angle Independent Depth Aware Fusion Beamforming Approach for Ultrafast Ultrasound Flow Imaging

In the case of vector flow imaging systems, the most employed flow estimation techniques are the directional beamforming based cross correlation and the triangulation-based autocorrelation. However, the directional beamforming-based techniques require an additional angle estimator and are not reliable if the flow angle is not constant throughout the region of interest. On the other hand, estimates with triangulation-based techniques are prone to large bias and variance at low imaging depths due to limited angle for left and right apertures. In view of this, a novel angle independent depth aware fusion beamforming approach is proposed and evaluated in this paper. The hypothesis behind the proposed approach is that the peripheral flows are transverse in nature, where directional beamforming can be employed without the need of an angle estimator and the deeper flows being non-transverse and directional, triangulation-based vector flow imaging can be employed. In the simulation study, an overall 67.62% and 74.71% reduction in magnitude bias along with a slight reduction in the standard deviation are observed with the proposed fusion beamforming approach when compared to triangulation-based beamforming and directional beamforming, respectively, when implemented individually. The efficacy of the proposed approach is demonstrated with in-vivo experiments.

eess.SP↗

arXiv2021

Subject Independent Emotion Recognition using EEG Signals Employing Attention Driven Neural Networks

In the recent past, deep learning-based approaches have significantly improved the classification accuracy when compared to classical signal processing and machine learning based frameworks. But most of them were subject-dependent studies which were not able to generalize on the subject-independent tasks due to the inter-subject variability present in EEG data. In this work, a novel deep learning framework capable of doing subject-independent emotion recognition is presented, consisting of two parts. First, an unsupervised Long Short-Term Memory (LSTM) with channel-attention autoencoder is proposed for getting a subject-invariant latent vector subspace i.e., intrinsic variables present in the EEG data of each individual. Secondly, a convolutional neural network (CNN) with attention framework is presented for performing the task of subject-independent emotion recognition on the encoded lower dimensional latent space representations obtained from the proposed LSTM with channel-attention autoencoder. With the attention mechanism, the proposed approach could highlight the significant time-segments of the EEG signal, which contributes to the emotion under consideration as validated by the results. The proposed approach has been validated using publicly available datasets for EEG signals such as DEAP dataset, SEED dataset and CHB-MIT dataset. The proposed end-to-end deep learning framework removes the requirement of different hand engineered features and provides a single comprehensive task agnostic EEG analysis tool capable of performing various kinds of EEG analysis on subject independent data.

cs.NE↗

arXiv2021

Hand-Drawn Electrical Circuit Recognition using Object Detection and Node Recognition

With the recent developments in neural networks, there has been a resurgence in algorithms for the automatic generation of simulation ready electronic circuits from hand-drawn circuits. However, most of the approaches in literature were confined to classify different types of electrical components and only a few of those methods have shown a way to rebuild the circuit schematic from the scanned image, which is extremely important for further automation of netlist generation. This paper proposes a real-time algorithm for the automatic recognition of hand-drawn electrical circuits based on object detection and circuit node recognition. The proposed approach employs You Only Look Once version 5 (YOLOv5) for detection of circuit components and a novel Hough transform based approach for node recognition. Using YOLOv5 object detection algorithm, a mean average precision (mAP0.5) of 98.2% is achieved in detecting the components. The proposed method is also able to rebuild the circuit schematic with 80% accuracy with a near-real time performance of 0.33s per schematic generation.

cs.CV↗

arXiv2021

Patch Based Transformation for Minimum Variance Beamformer Image Approximation Using Delay and Sum Pipeline

In the recent past, there have been several efforts in accelerating computationally heavy beamforming algorithms such as minimum variance distortionless response (MVDR) beamforming to achieve real-time performance comparable to the popular delay and sum (DAS) beamforming. This has been achieved using a variety of neural network architectures ranging from fully connected neural networks (FCNNs), convolutional neural networks (CNNs) and general adversarial networks (GANs). However most of these approaches are working with optimizations considering image level losses and hence require a significant amount of dataset to ensure that the process of beamforming is learned. In this work, a patch level U-Net based neural network is proposed, where the delay compensated radio frequency (RF) patch for a fixed region in space (e.g. 32x32) is transformed through a U-Net architecture and multiplied with DAS apodization weights and optimized for similarity with MVDR image of the patch. Instead of framing the beamforming problem as a regression problem to estimate the apodization weights, the proposed approach treats the non-linear transformation of the RF data space that can account for the data driven weight adaptation done by the MVDR approach in the parameters of the network. In this way, it is also observed that by restricting the input to a patch the model will learn the beamforming pipeline as an image non-linear transformation problem.

eess.SP↗

arXiv2021

Exploring Novel Pooling Strategies for Edge Preserved Feature Maps in Convolutional Neural Networks

With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of the anti-aliased CNN has been the application of Gaussian smoothing before the pooling operation to reduce the distortion due to aliasing thereby making CNNs shift invariant. Wavelet based approaches have also been proposed as a possibility of additional noise removal capability and gave interesting results for even segmentation tasks. However, all the approaches proposed completely remove the high frequency components under the assumption that they are noise. However, by removing high frequency components, the edges in the feature maps are also smoothed. In this work, an exhaustive analysis of the edge preserving pooling options for classification, segmentation and autoencoders are presented. Two novel pooling approaches are presented such as Laplacian-Gaussian Concatenation with Attention (LGCA) pooling and Wavelet based approximate-detailed coefficient concatenation with attention (WADCA) pooling. The results suggest that the proposed pooling approaches outperform the conventional pooling as well as blur pooling for classification, segmentation and autoencoders.

cs.CV↗

arXiv2021

Physics Driven Domain Specific Transporter Framework with Attention Mechanism for Ultrasound Imaging

Most applications of deep learning techniques in medical imaging are supervised and require a large number of labeled data which is expensive and requires many hours of careful annotation by experts. In this paper, we propose an unsupervised, physics driven domain specific transporter framework with an attention mechanism to identify relevant key points with applications in ultrasound imaging. The proposed framework identifies key points that provide a concise geometric representation highlighting regions with high structural variation in ultrasound videos. We incorporate physics driven domain specific information as a feature probability map and use the radon transform to highlight features in specific orientations. The proposed framework has been trained on130 Lung ultrasound (LUS) videos and 113 Wrist ultrasound (WUS) videos and validated on 100 Lung ultrasound (LUS) videos and 58 Wrist ultrasound (WUS) videos acquired from multiple centers across the globe. Images from both datasets were independently assessed by experts to identify clinically relevant features such as A-lines, B-lines and pleura from LUS and radial metaphysis, radial epiphysis and carpal bones from WUS videos. The key points detected from both datasets showed high sensitivity (LUS = 99\% , WUS = 74\%) in detecting the image landmarks identified by experts. Also, on employing for classification of the given lung image into normal and abnormal classes, the proposed approach, even with no prior training, achieved an average accuracy of 97\% and an average F1-score of 95\% respectively on the task of co-classification with 3 fold cross-validation. With the purely unsupervised nature of the proposed approach, we expect the key point detection approach to increase the applicability of ultrasound in various examination performed in emergency and point of care.

eess.IV↗

arXiv2021

Unsupervised multi-latent space reinforcement learning framework for video summarization in ultrasound imaging

The COVID-19 pandemic has highlighted the need for a tool to speed up triage in ultrasound scans and provide clinicians with fast access to relevant information. The proposed video-summarization technique is a step in this direction that provides clinicians access to relevant key-frames from a given ultrasound scan (such as lung ultrasound) while reducing resource, storage and bandwidth requirements. We propose a new unsupervised reinforcement learning (RL) framework with novel rewards that facilitates unsupervised learning avoiding tedious and impractical manual labelling for summarizing ultrasound videos to enhance its utility as a triage tool in the emergency department (ED) and for use in telemedicine. Using an attention ensemble of encoders, the high dimensional image is projected into a low dimensional latent space in terms of: a) reduced distance with a normal or abnormal class (classifier encoder), b) following a topology of landmarks (segmentation encoder), and c) the distance or topology agnostic latent representation (convolutional autoencoders). The decoder is implemented using a bi-directional long-short term memory (Bi-LSTM) which utilizes the latent space representation from the encoder. Our new paradigm for video summarization is capable of delivering classification labels and segmentation of key landmarks for each of the summarized keyframes. Validation is performed on lung ultrasound (LUS) dataset, that typically represent potential use cases in telemedicine and ED triage acquired from different medical centers across geographies (India, Spain and Canada).

eess.IV↗

arXiv2021

Towards Fast Region Adaptive Ultrasound Beamformer for Plane Wave Imaging Using Convolutional Neural Networks

Automatic learning algorithms for improving the image quality of diagnostic B-mode ultrasound (US) images have been gaining popularity in the recent past. In this work, a novel convolutional neural network (CNN) is trained using time of flight corrected in-vivo receiver data of plane wave transmit to produce corresponding high-quality minimum variance distortion less response (MVDR) beamformed image. A comprehensive performance comparison in terms of qualitative and quantitative measures for fully connected neural network (FCNN), the proposed CNN architecture, MVDR and Delay and Sum (DAS) using the dataset from Plane wave Imaging Challenge in Ultrasound (PICMUS) is also reported in this work. The CNN architecture could leverage the spatial information and will be more region adaptive during the beamforming process. This is evident from the improvement seen over the baseline FCNN approach and conventional MVDR beamformer, both in resolution and contrast with an improvement of 6 dB in CNR using only zero-angle transmission over the baseline. With the observed reduction in the requirement of number of angles to produce similar image metrics would prove advantageous in providing a possibility for higher frame rates.

eess.SP↗

arXiv2021

An Approach Towards Physics Informed Lung Ultrasound Image Scoring Neural Network for Diagnostic Assistance in COVID-19

Ultrasound is fast becoming an inevitable diagnostic tool for regular and continuous monitoring of the lung with the recent outbreak of COVID-19. In this work, a novel approach is presented to extract acoustic propagation-based features to automatically highlight the region below pleura, which is an important landmark in lung ultrasound (LUS). Subsequently, a multichannel input formed by using the acoustic physics-based feature maps is fused to train a neural network, referred to as LUSNet, to classify the LUS images into five classes of varying severity of lung infection to track the progression of COVID-19. In order to ensure that the proposed approach is agnostic to the type of acquisition, the LUSNet, which consists of a U-net architecture is trained in an unsupervised manner with the acoustic feature maps to ensure that the encoder-decoder architecture is learning features in the pleural region of interest. A novel combination of the U-net output and the U-net encoder output is employed for the classification of severity of infection in the lung. A detailed analysis of the proposed approach on LUS images over the infection to full recovery period of ten confirmed COVID-19 subjects shows an average five-fold cross-validation accuracy, sensitivity, and specificity of 97%, 93%, and 98% respectively over 5000 frames of COVID-19 videos. The analysis also shows that, when the input dataset is limited and diverse as in the case of COVID-19 pandemic, an aided effort of combining acoustic propagation-based features along with the gray scale images, as proposed in this work, improves the performance of the neural network significantly and also aids the labelling and triaging process.

eess.IV↗

arXiv2021

Learning the Imaging Landmarks: Unsupervised Key point Detection in Lung Ultrasound Videos

Lung ultrasound (LUS) is an increasingly popular diagnostic imaging modality for continuous and periodic monitoring of lung infection, given its advantages of non-invasiveness, non-ionizing nature, portability and easy disinfection. The major landmarks assessed by clinicians for triaging using LUS are pleura, A and B lines. There have been many efforts for the automatic detection of these landmarks. However, restricting to a few pre-defined landmarks may not reveal the actual imaging biomarkers particularly in case of new pathologies like COVID-19. Rather, the identification of key landmarks should be driven by data given the availability of a plethora of neural network algorithms. This work is a first of its kind attempt towards unsupervised detection of the key LUS landmarks in LUS videos of COVID-19 subjects during various stages of infection. We adapted the relatively newer approach of transporter neural networks to automatically mark and track pleura, A and B lines based on their periodic motion and relatively stable appearance in the videos. Initial results on unsupervised pleura detection show an accuracy of 91.8% employing 1081 LUS video frames.

eess.IV↗

arXiv2021

Domain Specific Transporter Framework to Detect Fractures in Ultrasound

Ultrasound examination for detecting fractures is ideally suited for Emergency Departments (ED) as it is relatively fast, safe (from ionizing radiation), has dynamic imaging capability and is easily portable. High interobserver variability in manual assessment of ultrasound scans has piqued research interest in automatic assessment techniques using Deep Learning (DL). Most DL techniques are supervised and are trained on large numbers of labeled data which is expensive and requires many hours of careful annotation by experts. In this paper, we propose an unsupervised, domain specific transporter framework to identify relevant keypoints from wrist ultrasound scans. Our framework provides a concise geometric representation highlighting regions with high structural variation in a 3D ultrasound (3DUS) sequence. We also incorporate domain specific information represented by instantaneous local phase (LP) which detects bone features from 3DUS. We validate the technique on 3DUS videos obtained from 30 subjects. Each ultrasound scan was independently assessed by three readers to identify fractures along with the corresponding x-ray. Saliency of keypoints detected in the image\ are compared against manual assessment based on distance from relevant features.The transporter neural network was able to accurately detect 180 out of 250 bone regions sampled from wrist ultrasound videos. We expect this technique to increase the applicability of ultrasound in fracture detection.

eess.IV↗