arXiv subjects

Hassan Rivaz

Publications and source records attributed to Hassan Rivaz.

87 records · Page 5Linked to original sources

arXiv2021

Automatic 3D Ultrasound Segmentation of Uterus Using Deep Learning

On-line segmentation of the uterus can aid effective image-based guidance for precise delivery of dose to the target tissue (the uterocervix) during cervix cancer radiotherapy. 3D ultrasound (US) can be used to image the uterus, however, finding the position of uterine boundary in US images is a challenging task due to large daily positional and shape changes in the uterus, large variation in bladder filling, and the limitations of 3D US images such as low resolution in the elevational direction and imaging aberrations. Previous studies on uterus segmentation mainly focused on developing semi-automatic algorithms where require manual initialization to be done by an expert clinician. Due to limited studies on the automatic 3D uterus segmentation, the aim of the current study was to overcome the need for manual initialization in the semi-automatic algorithms using the recent deep learning-based algorithms. Therefore, we developed 2D UNet-based networks that are trained based on two scenarios. In the first scenario, we trained 3 different networks on each plane (i.e., sagittal, coronal, axial) individually. In the second scenario, our proposed network was trained using all the planes of each 3D volume. Our proposed schematic can overcome the initial manual selection of previous semi-automatic algorithm.

eess.IV↗

arXiv2021

Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images

Ultrasound is a non-invasive imaging modality that can be conveniently used to classify suspicious breast nodules and potentially detect the onset of breast cancer. Recently, Convolutional Neural Networks (CNN) techniques have shown promising results in classifying ultrasound images of the breast into benign or malignant. However, CNN inference acts as a black-box model, and as such, its decision-making is not interpretable. Therefore, increasing effort has been dedicated to explaining this process, most notably through GRAD-CAM and other techniques that provide visual explanations into inner workings of CNNs. In addition to interpretation, these methods provide clinically important information, such as identifying the location for biopsy or treatment. In this work, we analyze how adversarial assaults that are practically undetectable may be devised to alter these importance maps dramatically. Furthermore, we will show that this change in the importance maps can come with or without altering the classification result, rendering them even harder to detect. As such, care must be taken when using these importance maps to shed light on the inner workings of deep learning. Finally, we utilize Multi-Task Learning (MTL) and propose a new network based on ResNet-50 to improve the classification accuracies. Our sensitivity and specificity is comparable to the state of the art results.

eess.IV↗

arXiv2020

Virtual Source Synthetic Aperture for Accurate Lateral Displacement Estimation in Ultrasound Elastography

Ultrasound elastography is an emerging noninvasive imaging technique wherein pathological alterations can be visualized by revealing the mechanical properties of the tissue. Estimating tissue displacement in all directions is required to accurately estimate the mechanical properties. Despite capabilities of elastography techniques in estimating displacement in both axial and lateral directions, estimation of axial displacement is more accurate than lateral direction due to higher sampling frequency, higher resolution and having a carrier signal propagating in the axial direction. Among different ultrasound imaging techniques, Synthetic Aperture (SA) has better lateral resolution than others, but it is not commonly used for ultrasound elastography due to its limitation in imaging depth of field. Virtual source synthetic aperture (VSSA) imaging is a technique to implement synthetic aperture beamforming on the focused transmitted data to overcome limitation of SA in depth of field while maintaining the same lateral resolution as SA. Besides lateral resolution, VSSA has the capability of increasing sampling frequency in the lateral direction without interpolation. In this paper, we utilize VSSA to perform beamforming to enable higher resolution and sampling frequency in the lateral direction. The beamformed data is then processed using our recently published elastography technique, OVERWIND [1]. Simulation and experimental results show substantial improvement in estimation of lateral displacements.

eess.IV↗

arXiv2020

Fast and Robust Localization of Surgical Array using Kalman Filter

Intraoperative tracking of surgical instruments is an inevitable task of computer-assisted surgery. An optical tracking system often fails to precisely reconstruct the dynamic location and pose of a surgical tool due to the acquisition noise and measurement variance. Embedding a Kalman Filter (KF) or any of its extensions such as extended and unscented Kalman filters with the optical tracker resolves this issue by reducing the estimation variance and regularizing the temporal behavior. However, the current rigid-body KF implementations are computationally burdensome and hence, takes long execution time which hinders real-time surgical tracking. This paper introduces a fast and computationally efficient implementation of linear KF to improve the measurement accuracy of an optical tracking system with high temporal resolution. Instead of the surgical tool as a whole, our KF framework tracks each individual fiducial mounted on it using a Newtonian model. In addition to simulated dataset, we validate our technique against real data obtained from a high frame-rate commercial optical tracking system. The proposed KF framework substantially stabilizes the tracking behavior in all of our experiments and reduces the mean-squared error (MSE) from the order of $10^{-2}$ $mm^{2}$ to $10^{-4}$ $mm^{2}$.

cs.RO↗

arXiv2020

Ultrasound Scatterer Density Classification Using Convolutional Neural Networks by Exploiting Patch Statistics

Quantitative ultrasound (QUS) can reveal crucial information on tissue properties such as scatterer density. If the scatterer density per resolution cell is above or below 10, the tissue is considered as fully developed speckle (FDS) or low-density scatterers (LDS), respectively. Conventionally, the scatterer density has been classified using estimated statistical parameters of the amplitude of backscattered echoes. However, if the patch size is small, the estimation is not accurate. These parameters are also highly dependent on imaging settings. In this paper, we propose a convolutional neural network (CNN) architecture for QUS, and train it using simulation data. We further improve the network performance by utilizing patch statistics as additional input channels. We evaluate the network using simulation data, experimental phantoms and in vivo data. We also compare our proposed network with different classic and deep learning models, and demonstrate its superior performance in classification of tissues with different scatterer density values. The results also show that the proposed network is able to work with different imaging parameters with no need for a reference phantom. This work demonstrates the potential of CNNs in classifying scatterer density in ultrasound images.

eess.IV↗

arXiv2020

Plane-Wave Ultrasound Beamforming Through Independent Component Analysis

Beamforming in plane-wave imaging (PWI) is an essential step in creating images with optimal quality. Adaptive methods estimate the apodization weights from echo traces acquired by several transducer elements. Herein, we formulate plane-wave beamforming as a blind source separation problem. The output of each transducer element is considered as a non-independent observation of the field. As such, beamforming can be formulated as the estimation of an independent component out of the observations. We then adapt the independent component analysis (ICA) algorithm to solve this problem and reconstruct the final image. The proposed method is evaluated on a set of simulation, real phantom, and in vivo data available from the PWI challenge in medical ultrasound. The performance of the proposed beamforming approach is also evaluated in different imaging settings. The proposed algorithm improves lateral resolution by as much as $36.5\%$ and contrast by $10\%$ as compared to the classical delay and sum. Moreover, results are compared with other well-known adaptive methods. Finally, the robustness of the proposed method to noise is investigated.

eess.IV↗

arXiv2020

Semi-Supervised Training of Optical Flow Convolutional Neural Networks in Ultrasound Elastography

Convolutional Neural Networks (CNN) have been found to have great potential in optical flow problems thanks to an abundance of data available for training a deep network. The displacement estimation step in UltraSound Elastography (USE) can be viewed as an optical flow problem. Despite the high performance of CNNs in optical flow, they have been rarely used for USE due to unique challenges that both input and output of USE networks impose. Ultrasound data has much higher high-frequency content compared to natural images. The outputs are also drastically different, where displacement values in USE are often smooth without sharp motions or discontinuities. The general trend is currently to use pre-trained networks and fine-tune them on a small simulation ultrasound database. However, realistic ultrasound simulation is computationally expensive. Also, the simulation techniques do not model complex motions, nonlinear and frequency-dependent acoustics, and many sources of artifact in ultrasound imaging. Herein, we propose an unsupervised fine-tuning technique which enables us to employ a large unlabeled dataset for fine-tuning of a CNN optical flow network. We show that the proposed unsupervised fine-tuning method substantially improves the performance of the network and reduces the artifacts generated by networks trained on computer vision databases.

eess.IV↗

arXiv2020

Automatic Frame Selection using CNN in Ultrasound Elastography

Ultrasound elastography is used to estimate the mechanical properties of the tissue by monitoring its response to an internal or external force. Different levels of deformation are obtained from different tissue types depending on their mechanical properties, where stiffer tissues deform less. Given two radio frequency (RF) frames collected before and after some deformation, we estimate displacement and strain images by comparing the RF frames. The quality of the strain image is dependent on the type of motion that occurs during deformation. In-plane axial motion results in high-quality strain images, whereas out-of-plane motion results in low-quality strain images. In this paper, we introduce a new method using a convolutional neural network (CNN) to determine the suitability of a pair of RF frames for elastography in only 5.4 ms. Our method could also be used to automatically choose the best pair of RF frames, yielding a high-quality strain image. The CNN was trained on 3,818 pairs of RF frames, while testing was done on 986 new unseen pairs, achieving an accuracy of more than 91%. The RF frames were collected from both phantom and in vivo data.

eess.IV↗

arXiv2020

Fine tuning U-Net for ultrasound image segmentation: which layers?

Fine-tuning a network which has been trained on a large dataset is an alternative to full training in order to overcome the problem of scarce and expensive data in medical applications. While the shallow layers of the network are usually kept unchanged, deeper layers are modified according to the new dataset. This approach may not work for ultrasound images due to their drastically different appearance. In this study, we investigated the effect of fine-tuning different layers of a U-Net which was trained on segmentation of natural images in breast ultrasound image segmentation. Tuning the contracting part and fixing the expanding part resulted in substantially better results compared to fixing the contracting part and tuning the expanding part. Furthermore, we showed that starting to fine-tune the U-Net from the shallow layers and gradually including more layers will lead to a better performance compared to fine-tuning the network from the deep layers moving back to shallow layers. We did not observe the same results on segmentation of X-ray images, which have different salient features compared to ultrasound, it may therefore be more appropriate to fine-tune the shallow layers rather than deep layers. Shallow layers learn lower level features (including speckle pattern, and probably the noise and artifact properties) which are critical in automatic segmentation in this modality.

eess.IV↗

arXiv2020

Breast lesion segmentation in ultrasound images with limited annotated data

Ultrasound (US) is one of the most commonly used imaging modalities in both diagnosis and surgical interventions due to its low-cost, safety, and non-invasive characteristic. US image segmentation is currently a unique challenge because of the presence of speckle noise. As manual segmentation requires considerable efforts and time, the development of automatic segmentation algorithms has attracted researchers attention. Although recent methodologies based on convolutional neural networks have shown promising performances, their success relies on the availability of a large number of training data, which is prohibitively difficult for many applications. Therefore, in this study we propose the use of simulated US images and natural images as auxiliary datasets in order to pre-train our segmentation network, and then to fine-tune with limited in vivo data. We show that with as little as 19 in vivo images, fine-tuning the pre-trained network improves the dice score by 21% compared to training from scratch. We also demonstrate that if the same number of natural and simulation US images is available, pre-training on simulation data is preferable.

eess.IV↗

arXiv2019

Automatic Frame Selection Using MLP Neural Network in Ultrasound Elastography

Ultrasound elastography estimates the mechanical properties of the tissue from two Radio-Frequency (RF) frames collected before and after tissue deformation due to an external or internal force. This work focuses on strain imaging in quasi-static elastography, where the tissue undergoes slow deformations and strain images are estimated as a surrogate for elasticity modulus. The quality of the strain image depends heavily on the underlying deformation, and even the best strain estimation algorithms cannot estimate a good strain image if the underlying deformation is not suitable. Herein, we introduce a new method for tracking the RF frames and selecting automatically the best possible pair. We achieve this by decomposing the axial displacement image into a linear combination of principal components (which are calculated offline) multiplied by their corresponding weights. We then use the calculated weights as the input feature vector to a multi-layer perceptron (MLP) classifier. The output is a binary decision, either 1 which refers to good frames, or 0 which refers to bad frames. Our MLP model is trained on in-vivo dataset and tested on different datasets of both in-vivo and phantom data. Results show that by using our technique, we would be able to achieve higher quality strain images compared to the traditional methods of picking up pairs that are 1, 2 or 3 frames apart. The training phase of our algorithm is computationally expensive and takes few hours, but it is only done once. The testing phase chooses the optimal pair of frames in only 1.9 ms.

eess.IV↗

arXiv2019

Fast Approximate Time-Delay Estimation in Ultrasound Elastography Using Principal Component Analysis

Time delay estimation (TDE) is a critical and challenging step in all ultrasound elastography methods. A growing number of TDE techniques require an approximate but robust and fast method to initialize solving for TDE. Herein, we present a fast method for calculating an approximate TDE between two radio frequency (RF) frames of ultrasound. Although this approximate TDE can be useful for several algorithms, we focus on GLobal Ultrasound Elastography (GLUE), which currently relies on Dynamic Programming (DP) to provide this approximate TDE. We exploit Principal Component Analysis (PCA) to find the general modes of deformation in quasi-static elastography, and therefore call our method PCA-GLUE. PCA-GLUE is a data-driven approach that learns a set of TDE principal components from a training database in real experiments. In the test phase, TDE is approximated as a weighted sum of these principal components. Our algorithm robustly estimates the weights from sparse feature matches, then passes the resulting displacement field to GLUE as initial estimates to perform a more accurate displacement estimation. PCA-GLUE is more than ten times faster than DP in estimation of the initial displacement field and yields similar results.

eess.IV↗

arXiv2019

Ultrasound segmentation using U-Net: learning from simulated data and testing on real data

Segmentation of ultrasound images is an essential task in both diagnosis and image-guided interventions given the ease-of-use and low cost of this imaging modality. As manual segmentation is tedious and time consuming, a growing body of research has focused on the development of automatic segmentation algorithms. Deep learning algorithms have shown remarkable achievements in this regard; however, they need large training datasets. Unfortunately, preparing large labeled datasets in ultrasound images is prohibitively difficult. Therefore, in this study, we propose the use of simulated ultrasound (US) images for training the U-Net deep learning segmentation architecture and test on tissue-mimicking phantom data collected by an ultrasound machine. We demonstrate that the trained architecture on the simulated data is transferrable to real data, and therefore, simulated data can be considered as an alternative training dataset when real datasets are not available. The second contribution of this paper is that we train our U- Net network on envelope and B-mode images of the simulated dataset, and test the trained network on real envelope and B- mode images of phantom, respectively. We show that test results are superior for the envelope data compared to B-mode image.

eess.IV↗

arXiv2019

Evaluation of MRI to ultrasound registration methods for brain shift correction: The CuRIOUS2018 Challenge

In brain tumor surgery, the quality and safety of the procedure can be impacted by intra-operative tissue deformation, called brain shift. Brain shift can move the surgical targets and other vital structures such as blood vessels, thus invalidating the pre-surgical plan. Intra-operative ultrasound (iUS) is a convenient and cost-effective imaging tool to track brain shift and tumor resection. Accurate image registration techniques that update pre-surgical MRI based on iUS are crucial but challenging. The MICCAI Challenge 2018 for Correction of Brain shift with Intra-Operative UltraSound (CuRIOUS2018) provided a public platform to benchmark MRI-iUS registration algorithms on newly released clinical datasets. In this work, we present the data, setup, evaluation, and results of CuRIOUS 2018, which received 6 fully automated algorithms from leading academic and industrial research groups. All algorithms were first trained with the public RESECT database, and then ranked based on test dataset of 10 additional cases with identical data curation and annotation protocols as the RESECT database. The article compares the results of all participating teams and discusses the insights gained from the challenge, as well as future work.

eess.IV↗

arXiv2018

Global Ultrasound Elastography Using Convolutional Neural Network

Displacement estimation is very important in ultrasound elastography and failing to estimate displacement correctly results in failure in generating strain images. As conventional ultrasound elastography techniques suffer from decorrelation noise, they are prone to fail in estimating displacement between echo signals obtained during tissue distortions. This study proposes a novel elastography technique which addresses the decorrelation in estimating displacement field. We call our method GLUENet (GLobal Ultrasound Elastography Network) which uses deep Convolutional Neural Network (CNN) to get a coarse time-delay estimation between two ultrasound images. This displacement is later used for formulating a nonlinear cost function which incorporates similarity of RF data intensity and prior information of estimated displacement. By optimizing this cost function, we calculate the finer displacement by exploiting all the information of all the samples of RF data simultaneously. The Contrast to Noise Ratio (CNR) and Signal to Noise Ratio (SNR) of the strain images from our technique is very much close to that of strain images from GLUE. While most elastography algorithms are sensitive to parameter tuning, our robust algorithm is substantially less sensitive to parameter tuning.

eess.IV↗