Purpose: Echocardiography is the most commonly used modality for assessing the heart in clinical practice. In an echocardiographic exam, an ultrasound probe samples the heart from different orientations and positions, thereby creating different viewpoints for assessing the cardiac function. The determination of the probe viewpoint forms an essential step in automatic echocardiographic image analysis.
Approach: In this study, convolutional neural networks are used for the automated identification of 14 different anatomical echocardiographic views (larger than any previous study) in a dataset of 8732 videos acquired from 374 patients. Differentiable architecture search approach was utilized to design small neural network architectures for rapid inference while maintaining high accuracy. The impact of the image quality and resolution, size of the training dataset, and number of echocardiographic view classes on the efficacy of the models were also investigated.
Results: In contrast to the deeper classification architectures, the proposed models had significantly lower number of trainable parameters (up to 99.9% reduction), achieved comparable classification performance (accuracy 88.4% to 96%, precision 87.8% to 95.2%, recall 87.1% to 95.1%) and real-time performance with inference time per image of 3.6 to 12.6 ms.
Conclusion: Compared with the standard classification neural network architectures, the proposed models are faster and achieve comparable classification performance. They also require less training data. Such models can be used for real-time detection of the standard views.
Barrett’s esophagus (BE) is a premalignant condition that has an increased risk to turn into esophageal adenocarcinoma. Classification and staging of the different changes (BE in particular) in the esophageal mucosa are challenging since they have a very similar appearance. Confocal laser endomicroscopy (CLE) is one of the newest endoscopy tools that is commonly used to identify the pathology type of the suspected area of the esophageal mucosa. However, it requires a well-trained physician to classify the image obtained from CLE. An automatic stage classification of esophageal mucosa is presented. The proposed model enhances the internal features of CLE images using an image filter that combines fractional integration with differentiation. Various features are then extracted on a multiscale level, to classify the mucosal tissue into one of its four types: normal squamous (NS), gastric metaplasia (GM), intestinal metaplasia (IM or BE), and neoplasia. These sets of features are used to train two conventional classifiers: support vector machine (SVM) and random forest. The proposed method was evaluated on a dataset of 96 patients with 557 images of different histopathology types. The SVM classifier achieved the best performance with 96.05% accuracy based on a leave-one-patient-out cross-validation. Additionally, the dataset was divided into 60% training and 40% testing; the model achieved an accuracy of 93.72% for the testing data using the SVM. The presented model showed superior performance when compared with four state-of-the-art methods. Accurate classification is essential for the intestinal metaplasia grade, which most likely develops into esophageal cancer. Not only does our method come to the aid of physicians for more accurate diagnosis by acting as a second opinion, but it also acts as a training method for junior physicians who need practice in using CLE. Consequently, this work contributes to an automatic classification that facilitates early intervention and decreases samples of required biopsy.
In this study, clinically produced multiphase CT volumetric data sets (pre-contrast, arterial and venous enhanced phase)
are drawn upon to transcend the intrinsic limitations of single phase data sets for the robust and accurate segmentation of
the liver in typically challenging cases. As an initial step, all other phase volumes are registered to either the arterial or
venous phase volume by a symmetric nonlinear registration method using mutual information as similarity metric. Once
registered, the multiphase CT volumes are pre-filtered to prepare for subsequent steps. Under the assumption that the
intensity vectors of different organs follow the Gaussian Mixture model (GMM), expectation maximization (EM) is then
used to classify the multiphase voxels into different clusters. The clusters for liver parenchyma, vessels and tumors are
combined together and provide the initial liver mask that is used to generate initial zeros level set. Conversely, the voxels
classified as non-liver will guide the speed image of the level sets in order to reduce leakage. Geodesic active contour
level set using the gradient vector flow (GVF) derived from one of the enhanced phase volumes is then performed to
further evolve the liver segmentation mask. Using EM clusters as the reference, the resulting liver mask is finally
morphologically post-processed to add missing clusters and reduce leakage. The proposed method has been tested on the
clinical data sets of ten patients with relatively complex and/or extensive liver cancer or metastases. A 95.8% dice
similarity index when compared to expert manual segmentation demonstrates the high performance and the robustness of
our proposed method - even for challenging cancer data sets - and confirms the potential of a more thorough
computational exploitation of currently available clinical data sets.
Introduction: Rapid prototype modeling (RPM) has been used in medicine principally for bones - that are easily extracted from CT data sets - for planning orthopaedic, plastic or maxillo-facial interventions, and/or for designing custom prostheses and implants. Based on newly available technology, highly valuable multimodality approaches can now be applied to RPM, particularly for complex musculo-skeletal (MSK) tumors where multimodality often transcends CT alone. Methods: CT data sets are acquired for primary evaluation of MSK tumors in parallel with other modalities (e.g., MR, PET, SPECT). In our approach, CT is first segmented to provide bony anatomy for RPM and all other data sets are then registered to the CT reference. Parametric information relevant to the tumor's characterization is then extracted from the multimodality space and merged with the CT anatomy to produce a hybrid RPM-ready model. This model - that also accommodates digital multimodality visualization - is then produced on the latest generation of 3D printers, which permits both shapes and colors. Results: Multimodality models of complex MSK tumors have been physically produced on modern RPM equipment. This new approach has been found to be a clear improvement over the previously disconnected physical RPM and digital multimodality visualization. Conclusions: New technical developments keep opening doors to sophisticated medical applications that can directly impact the quality of patient care. Although this early work still deals with bones as base models for RPM, its use to encompass soft tissues is already envisioned for future approaches.
Following recent developments, most brain imaging modalities (MR, CT, SPECT, PET) can nowadays be registered and integrated in a manner almost simple enough for routine use. By design though, these modalities are still not able to match the principles and near real-time capabilities of the much simpler (but of lower spatial resolution) EEG, thus the need to integrate it as well, along with - for some patients - the more accurate invasive electrophysiology measurements taken directly in contact with brain structures. A standard control CT (or MR) is routinely performed after the implantation of invasive electrodes. After registration with the other modalities, the initial estimates of the electrodes' locations extracted from the CT (or MR) are iteratively improved by using a geometrical model of the electrodes' arrangement (grids, strips, etc.) And other optional constraints (morphology, etc.). Unlike the direct 3D pointing of each electrode in the surgical suite - which can still act as a complementary approach - this technique estimates the most likely location of the electrodes during monitoring and can also deal with non cortical arrangements (internal strips, depth electrodes, etc.). Although not always applicable to normal volunteers because of its invasive components, this integration further opens the door towards an improved understanding of a very complex biological system.
The Visible Human Slice Server started offering its slicing services at the end of June 1998. From that date until the end of May, more than 280,000 slices were extracted from the Visible Man, by layman interested in anatomy, by students and by specialists. The Slice Server is based one Bi-Pentium PC and 16 disks. It is a scaled down version of a powerful parallel server comprising 5 Bi-Pentium Pro PCs and 60 disks. The parallel server program was created thanks to a computer-aided parallelization framework, which takes over the task of creating a multi-threaded pipelined parallel program from a high-level parallel program description. On the full blown architecture, the parallel program enables the extraction and resampling of up to 5 color slices per second. Extracting 5 slice/s requires to access the disks and extract subvolumes of the Visible Human at an aggregate throughput of 105 MB/s. The publicly accessible server enables to extract slices having any orientation. The slice position and orientation can either be specified for each slice separately or as a position and orientation offered by a Java applet and possible future improvements. In the very near future, the Web Slice Server will offer additional services, such as the possibility to extract ruled surfaces and to extract animations incorporating slices perpendicular to a user defined trajectory.
Various biomedical imaging sensors, including ElectroMagnetic Tomography, are being combined to study, assess, and localized neurological (dys)function. The interest for this combination stems from the broad variety and complementarity of information brought out by (functional-) Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, Computed Tomodensitometry, Single Photon Emission Tomography, Positron Emission Tomography and ElectroMagnetic Tomography. Besides allowing morphology, metabolism and function to be studied simultaneously, this complementarity is also expected to show best when studying pathologies reflected by metabolic or electromagnetic dysfunctions. An example of clinical application for epilepsy assessment and surgery planning is presented, along with suggestions for further potential developments.
KEYWORDS: Positron emission tomography, Magnetic resonance imaging, Tissues, Head, Data modeling, Data acquisition, Imaging systems, Brain, Data processing, Mathematical modeling
In order to help in analyzing PET data and really take advantage of their metabolic content, a system was designed and implemented to align and process data from various medical imaging modalities, particularly (but not only) for brain studies. Although this system is for now mostly used for anatomical localization, multi-modality ROIs and pharmaco-kinetic modeling, more multi-modality protocols will be implemented in the future, not only to help in PET reconstruction data correction and semi-automated ROI definition, but also for helping in improving diagnostic accuracy along with surgery and therapy planning.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.