CT Perfusion Map Synthesis from CTP Dynamic Images Using a Learned LSTM Generative Adversarial Network for Acute Ischemic Stroke Assessment.

Computed tomography perfusion (CTP) is a dynamic 4-dimensional imaging technique (3-dimensional volumes captured over approximately 1 min) in which cerebral blood flow is quantified by tracking the passage of a bolus of intravenous contrast with serial imaging of the brain. To diagnose and assess acute ischemic stroke, the standard method relies on summarizing acquired CTPs over the time axis to create maps that show different hemodynamic parameters, such as the timing of the bolus arrival and passage (Tmax and MTT), cerebral blood flow (CBF), and cerebral blood volume (CBV). However, producing accurate CTP maps requires the selection of an arterial input function (AIF), i.e. a time-concentration curve in one of the large feeding arteries of the brain, which is a highly error-prone procedure. Moreover, during approximately one minute of CT scanning, the brain is exposed to ionizing radiation that can alter tissue composition, and create free radicals that increase the risk of cancer. This paper proposes a novel end-to-end deep neural network that synthesizes CTP images to generate CTP maps using a learned LSTM Generative Adversarial Network (LSTM-GAN). Our proposed method can improve the precision and generalizability of CTP map extraction by eliminating the error-prone and expert-dependent AIF selection step. Further, our LSTM-GAN does not require the entire CTP time series and can produce CTP maps with a reduced number of time points. By reducing the scanning sequence from about 40 to 9 time points, the proposed method has the potential to minimize scanning time thereby reducing patient exposure to CT radiation. Our evaluations using the ISLES 2018 challenge dataset consisting of 63 patients showed that our model can generate CTP maps by using only 9 snapshots, without AIF selection, with an accuracy of 84.37 % .

Deep Learning using Pre-Brachytherapy MRI to Automatically Predict Applicator Induced Complex Uterine Deformation.

This novel deep-learning (DL) algorithm addresses the challenging task of predicting uterine shape and location when deformed from its natural anatomy by the presence of an intrauterine (tandem)/intravaginal (ring) applicator during brachytherapy (BT) treatment for locally advanced cervical cancer. Paired pelvic MRI datasets from 92 subjects, acquired without (pre-BT) and with (at-BT) applicators, were used. We propose a novel automated algorithm to segment the uterus in pre-BT MR images using a deep convolutional neural network (CNN) incorporated with autoencoders. The proposed neural net is based on a pre-trained CNN Inception V4 architecture. It predicts a compressed vector by applying a multi-layer autoencoder, which is then back-projected into the segmentation contour of the uterus. Following this, another transfer learning approach using a modified U-net model is employed to predict the at-BT uterus shape from pre-BT MRI. The complex and large deformations of the uterus are quantified using free form deformation method. The proposed algorithm yielded an average Dice Coefficient (DC) of 94.1±3.3 and an average Hausdorff Distance (HD) of 4.0±3.1 mm compared to the manually defined ground truth by expert clinicians. Further, the modified U-net prediction of the at-BT uterus resulted in a DC accuracy of 88.1±3.8 and HD of 5.8±3.6 mm. The mean uterine surface point-to-point displacement was 25.0 [10.0-62.5] mm from the pre-BT position. Our unique DL method can thus successfully predict tandem-deformed uterine shape and position from MR images taken before the BT implant procedure i.e. without the applicator in place. Clinical relevance-The proposed DL-based framework can be incorporated as an automatic prediction tool of uterine deformation due to applicator insertion for personalized BT treatments. It holds promise for more streamlined clinical/technical decision-making before BT applicator insertion resulting in improved dosimetric outcomes.

Test-retest validation of a cranial deformity index in unilateral coronal craniosynostosis.

Unilateral coronal craniosynostosis (UCS) affects many infants resulting in abnormalities affecting the forehead and orbits. As a result, the deformity caused by UCS is very noticeable and there are several surgical treatment options available to normalize the head shape. However, there is a lack of consistently used outcome measures, resulting in difficulty assessing surgical outcomes and on-going debate over optimal treatments. Current techniques to quantify deformity in UCS are cumbersome, provide limited information, or are based on subjective assessments. In this study, a cranial deformity index was developed to quantify abnormality at the frontal bones for UCS that is accessible, user-friendly, and generates objective surface distance measurements. The cranial deformity index is defined as the Euclidean distance at the point of the largest deviation between the deformed skull compared to a reference skull. In addition, the index was successfully used to quantify post-operative changes in a single case of UCS that underwent corrective surgery. The reproducibility of the index was assessed using test-retest reliability and was demonstrated to be highly reproducible (ICC = 0.93). A user-friendly measurement index that is based on open-source software may be a valuable tool for surgical teams. In addition, this information can augment the consultation experience for patients and their families.

Real-Time Lung Tumor Tracking Using a CUDA Enabled Nonrigid Registration Algorithm for MRI.

OBJECTIVE: This study intends to develop an accurate, real-time tumor tracking algorithm for the automated radiation therapy for cancer treatment using Graphics Processing Unit (GPU) computing. Although a previous moving mesh based tumor tracking approach has been shown to be successful in delineating the tumor regions from a sequence of magnetic resonance image, the algorithm is computationally intensive and its computation time on standard Central Processing Unit (CPU) processors is too slow to be used clinically especially for automated radiation therapy system. METHOD: A re-implementation of the algorithm on a low-cost parallel GPU-based computing platform is utilized to accelerate this computation at a speed that is amicable to clinical usages. Several components in the registration algorithm such as the computation of similarity metric are inherently parallel which fits well with the GPU parallel processing capabilities. Solving a partial differential equation numerically to generate the mesh deformation is one of the computationally intensive components which has been accelerated by utilizing a much faster shared memory on the GPU. RESULTS: Implemented on an NVIDIA Tesla K40c GPU, the proposed approach yielded a computational acceleration improvement of over 5 times its implementation on a CPU. The proposed approach yielded an average Dice score of 0.87 evaluated over 600 images acquired from six patients. CONCLUSION: This study demonstrated that the GPU computing approach can be used to accelerate tumor tracking for automated radiation therapy for mobile lung tumors. Clinical Impact: Accurately tracking mobile tumor boundaries in real-time is important to automate radiation therapy and the proposed study offers an excellent option for fast tumor region tracking for cancer treatment.

Microwave Imaging of Breast Tumor Using Time-Domain UWB Circular-SAR Technique.

This paper explores the competency of the time domain ultra-wideband (UWB)-circular synthetic aperture radar (CSAR) to image the breast and detect tumors. The image reconstruction is performed using a time domain global back projection technique adapted to the circular trajectory data acquisition. This paper also proposes a sectional image reconstruction method to compensate for the group velocity changes in different layers of a multilayer medium. Experiments on an advanced breast phantom examines the suitability of this technique for breast tumor imaging. The advanced breast phantom is designed based on a MRI of a real patient, fabricated using 3D printing technology, and filled with liquids that emulate normal and cancerous tissues. The measurement results, compared with MRI imaging of the phantom, demonstrate the suitability of the UWB-CSAR method for breast tumor imaging. This method can be a tool for early diagnosis as well as for treatment monitoring during chemotherapy or radiotherapy.

Remodeling of the Actin Network Associated with the Non-Structural Protein 1 (NS1) of West Nile Virus and Formation of NS1-Containing Tunneling Nanotubes.

The cellular response to the recombinant NS1 protein of West Nile virus (NS1WNV) was studied using three different cell types: Vero E6 simian epithelial cells, SH-SY5Y human neuroblastoma cells, and U-87MG human astrocytoma cells. Cells were exposed to two different forms of NS1WNV: (i) the exogenous secreted form, sNS1WNV, added to the extracellular milieu; and (ii) the endogenous NS1WNV, the intracellular form expressed in plasmid-transfected cells. The cell attachment and uptake of sNS1WNV varied with the cell type and were only detectable in Vero E6 and SH-SY5Y cells. Addition of sNS1WNV to the cell culture medium resulted in significant remodeling of the actin filament network in Vero E6 cells. This effect was not observed in SH-SY5Y and U-87MG cells, implying that the cellular uptake of sNS1WNV and actin network remodeling were dependent on cell type. In the three cell types, NS1WNV-expressing cells formed filamentous projections reminiscent of tunneling nanotubes (TNTs). These TNT-like projections were found to contain actin and NS1WNV proteins. Interestingly, similar actin-rich, TNT-like filaments containing NS1WNV and the viral envelope glycoprotein EWNV were also observed in WNV-infected Vero E6 cells.

A Fully Convolutional Deep Neural Network for Lung Tumor Boundary Tracking in MRI.

Delineation of lung tumor from adjacent tissue from a series of magnetic resonance images (MRI) poses many difficulties due to the image similarities of the region of interest and surrounding area as well as the influence of respiration. However, accurate segmentation of the tumor region is essential in planning a radiation therapy to prevent healthy tissues from receiving excessive radiation. The manual delineation of the entire MRI sequence is tedious, time-consuming and costly. This study investigates how one can perform automatic tracking of tumor boundaries during radiation therapy using convolutional neural networks. We proposed to use a convolutional neural network architecture with modified Dice metric as the cost function. The proposed approach was evaluated over 600 images in comparison to expert manual contours. The proposed method yielded an average Dice score of $0.91 \pm 0.03$ and Hausdorff distance of $2.88 \pm 0.86$ mm. The proposed approach outperformed recent state-of-the-art methods in terms of accuracy in the delineation of the mobile tumors.

Tracking tumor boundary using point correspondence for adaptive radio therapy.

BACKGROUND AND OBJECTIVE: Tracking mobile tumor regions during the treatment is a crucial part of image-guided radiation therapy because of two main reasons which negatively affect the treatment process: (1) a tiny error will lead to some healthy tissues being irradiated; and (2) some cancerous cells may survive if the beam is not accurately positioned as it may not cover the entire cancerous region. However, tracking or delineation of such a tumor region from magnetic resonance imaging (MRI) is challenging due to photometric similarities of the region of interest and surrounding area as well as the influence of motion in the organs. The purpose of this work is to develop an approach to track the center and boundary of tumor region by auto-contouring the region of interest in moving organs for radiotherapy. METHODS: We utilize a nonrigid registration method as well as a publicly available RealTITracker algorithm for MRI to delineate and track tumor regions from a sequence of MRI images. The location and shape of the tumor region in the MRI image sequence varies over time due to breathing. We investigate two approaches: the first one uses manual segmentation of the first frame during the pretreatment stage; and the second one utilizes manual segmentation of all the frames during the pretreatment stage. RESULTS: We evaluated the proposed approaches over a sequence of 600 images acquired from 6 patients. The method that utilizes all the frames in the pretreatment stage with moving mesh based registration yielded the best performance with an average Dice Score of 0.89 ±â€¯0.04 and Hausdorff Distance of 3.38 ±â€¯0.10 mm. CONCLUSIONS: This study demonstrates a promising boundary tracking tool for delineating the tumor region that can deal with respiratory movement and the constraints of adaptive radiation therapy.

Gesture segmentation and classification using affine speed and energy.

The characterization and analysis of hand gestures are challenging tasks with an important number of applications in human-computer interaction, machine vision and control, and medical gesture recognition. Specifically, several researchers have tried to develop objective evaluation methods of surgical skills for medical training. As a result, the adequate selection and extraction of similarities and differences between experts and novices have become an important challenge in this area. In particular, some of these works have shown that human movements performed during surgery can be described as a sequence of constant affine-speed trajectories. In this article, we will show that affine speed can be used to segment medical hand movements and present how the mechanical energy computed in the segment is analyzed to compare surgical skills. The position and orientation of the instrument end effectors are determined by six video photographic cameras. In addition, two laparoscopic instruments are capable of measuring simultaneously the forces and torques applied to the tool. Finally, we will report the results of these experiments and present a correlation between the mechanical energy values, dissipated during a procedure, and the surgical skills.

Baculovirus-assisted Reovirus Infection in Monolayer and Spheroid Cultures of Glioma cells.

The mammalian orthoreovirus Type 3 Dearing has great potential as oncolytic agent in cancer therapy. One of the bottlenecks that hampers its antitumour efficacy in vivo is the limited tumour-cell infection and intratumoural distribution. This necessitates strategies to improve tumour penetration. In this study we employ the baculovirus Autographa californica multiple nucleopolyhedrovirus as a tool to expand the reovirus' tropism and to improve its spread in three-dimensional tumour-cell spheroids. We generated a recombinant baculovirus expressing the cellular receptor for reovirus, the Junction Adhesion Molecule-A, on its envelope. Combining these Junction Adhesion Molecule-A-expressing baculoviruses with reovirus particles leads to the formation of biviral complexes. Exposure of the reovirus-resistant glioblastoma cell line U-118 MG to the baculovirus-reovirus complexes results in efficient reovirus infection, high reovirus yields, and significant reovirus-induced cytopathic effects. As compared to the reovirus-only incubations, the biviral complexes demonstrated improved penetration and increased cell killing of three-dimensional U-118 MG tumour spheroids. Our data demonstrate that reovirus can be delivered with increased efficiency into two- and three-dimensional tumour-cell cultures via coupling the reovirus particles to baculovirus. The identification of baculovirus' capacity to penetrate into tumour tissue opens novel opportunities to improve cancer therapy by improved delivery of oncolytic viruses into tumours.

Alpha-helicoidal HEAT-like Repeat Proteins (αRep) Selected as Interactors of HIV-1 Nucleocapsid Negatively Interfere with Viral Genome Packaging and Virus Maturation.

A new generation of artificial proteins, derived from alpha-helicoidal HEAT-like repeat protein scaffolds (αRep), was previously characterized as an effective source of intracellular interfering proteins. In this work, a phage-displayed library of αRep was screened on a region of HIV-1 Gag polyprotein encompassing the C-terminal domain of the capsid, the SP1 linker and the nucleocapsid. This region is known to be essential for the late steps of HIV-1 life cycle, Gag oligomerization, viral genome packaging and the last cleavage step of Gag, leading to mature, infectious virions. Two strong αRep binders were isolated from the screen, αRep4E3 (32 kDa; 7 internal repeats) and αRep9A8 (28 kDa; 6 internal repeats). Their antiviral activity against HIV-1 was evaluated in VLP-producer cells and in human SupT1 cells challenged with HIV-1. Both αRep4E3 and αRep9A8 showed a modest but significant antiviral effects in all bioassays and cell systems tested. They did not prevent the proviral integration reaction, but negatively interfered with late steps of the HIV-1 life cycle: αRep4E3 blocked the viral genome packaging, whereas αRep9A8 altered both virus maturation and genome packaging. Interestingly, SupT1 cells stably expressing αRep9A8 acquired long-term resistance to HIV-1, implying that αRep proteins can act as antiviral restriction-like factors.

Parallel implementation of a nonrigid image registration algorithm for lung tumor boundary tracking in quasi real-time MRI.

This study presents an accelerated implementation of a two-dimensional moving mesh point correspondence algorithm using a GPU for tracking mobile tumor boundaries during radiation therapy. Normal CPU implementation of this algorithm is computationally intensive and time-consuming which limits its clinical utility, hence the need for a faster GPU implementation. One of the computationally intensive parts of the registration algorithm involves numerically solving a partial differential equation. In this paper we demonstrate that the computational performance of the algorithms can be improved by utilizing a shared memory implementation on the GPU. Evaluations in comparison to 600 manually drawn contours showed that the proposed GPU-based tracking of the tumor boundaries yielded similar level of accuracy as the CPU based approach with improved computational efficiency.

Surgical gesture classification using Dynamic Time Warping and affine velocity.

Minimally Invasive Surgery (MIS) has become widespread as an important surgical technique due to its advantages related to pain relief and short recovery time periods. However, this approach implies the acquisition of special surgical skills, which represents a challenge in the objective assessment of surgical gestures. In this way, several studies shown that kinematics and kinetic analysis of hand movement is a valuable assessment tool of basic surgical skills in MIS. In addition, recent researches proved that human motion performed during surgery can be described as a sequence of constant affine velocity movements. In this paper, we present a novel method to classify gestures based on an affine velocity analysis of 3D motion and an implementation of the Dynamic Time Warping algorithm. In particular, affine velocity calculation correlates kinematics and geometrical variables such as curvature, torsion, and euclidean velocity, reducing the dimension of the conventional 3D problem. In this way, using the simplicity of dynamic time warping algorithm allows us to perform an accurate classification, easier to implement and understand. Experimental validation of the algorithm is presented based on the position and orientation data of a laparoscope instrument, determiMinimally Invasive Surgery (MIS) has become widespread as an important surgical technique due to its advantages related to pain relief and short recovery time periods. However, this approach implies the acquisition of special surgical skills, which represents a challenge in the objective assessment of surgical gestures. In this way, several studies shown that kinematics and kinetic analysis of hand movement is a valuable assessment tool of basic surgical skills in MIS. In addition, recent researches proved that human motion performed during surgery can be described as a sequence of constant affine velocity movements. In this paper, we present a novel method to classify gestures based on an affine velocity analysis of 3D motion and an implementation of the Dynamic Time Warping algorithm. In particular, affine velocity calculation correlates kinematics and geometrical variables such as curvature, torsion, and euclidean velocity, reducing the dimension of the conventional 3D problem. In this way, using the simplicity of dynamic time warping algorithm allows us to perform an accurate classification, easier to implement and understand. Experimental validation of the algorithm is presented based on the position and orientation data of a laparoscope instrument, determined by six cameras. Results show the advantages of the proposed method compared to conventional Multidimensional Dynamic Time Warping to classify surgical gestures in MIS.ned by six cameras. Results show the advantages of the proposed method compared to conventional Multidimensional Dynamic Time Warping to classify surgical gestures in MIS.

PUMA gene delivery to synoviocytes reduces inflammation and degeneration of arthritic joints.

In rheumatoid arthritis (RA), the proliferation of fibroblast-like synoviocytes (FLS) is the cause of chronic inflammation in joints and of joint damage. Delivery of the pro-apoptotic gene PUMA to FLS via human adenovirus type 5 (HAdV5) vectors has been tested as a therapeutic approach, but efficiency is hampered by low transduction, as FLS do not express HAdV5 receptors on the cell surface. Here we show that efficient transduction of PUMA in FLS can be achieved by conjugating HAdV5 to a baculovirus, which binds to the cell surface via the envelope glycoprotein Gp64. Intra-articular injection in an adjuvant-induced rat model of RA induces apoptosis of FLS, leading to significant decrease in joint inflammation, joint damage, and bone loss with improvement in joint function and mobility. Our results demonstrate the therapeutic potential of PUMA gene therapy as a local treatment in various forms of arthritis in which abnormal FLS proliferation is implicated.Proliferation of synoviocytes contributes to joint damage in rheumatoid arthritis. Here the authors show that targeting of these cells by a vector, consisting of a baculovirus conjugated to an adenovirus carrying the pro-apoptotic gene PUMA, has therapeutic efficacy in a rat arthritis model.

Three-dimensional morphological changes of the temporomandibular joint and functional effects after mandibulotomy.

BACKGROUND: The midline and paramedian mandibulotomy are surgical procedures that divide the mandibular bone into two halves and disconnects the condylar heads of the TMJ from each other. This study aimed to prospectively evaluate the temporomandibular joint (TMJ) functional and morphological changes after mandibulotomy using a reconstructed 3D models of the TMJ. METHODS: Sixteen adult patients diagnosed with oral and oropharyngeal tumors with planned surgical mandibulotomy (test group, 9 patients) or transoral (control group, seven patients) treatments were included in the study. MRI and CBCT images were obtained immediately preceeding surgery and 6-8 weeks after surgery. Using the MRI-CBCT registered images, TMJ tissues were segmented at the two occasions by the same operator and 3D models were reconstructed for morphological assessment. Changes across time were measured using the volume overlap and Hausdorff distance of the disc and condyle 3D models. Disc-condyle relationship was measured using point-based and color map analysis. To assess the early functional changes, the Jaw function limitation scale (JFLS) and the maximum mouth opening were measured. Two-sample Hotelling T2 t-test was performed to determine the significance of the morphological and clinical outcomes' differences between the two groups. RESULTS: The two-sample Hotelling T2 t-test showed significant differences (T2 (df1,df2) = 0.97 (5,26), p <0.01) between the mean values of all outcomes among the 2 groups. The change in disc displacement was significantly different between the two groups (p <0.05). However, the condylar displacement was not significantly different between the two groups (p =0.3). The average of the JFLS score was five times larger after mandibulotomy, and was 2 times larger after transoral surgery (p < 0.01). Patients showed decrease in the average of the maximum interincisal mouth opening by 11 mm after mandibulotomy, and by 5.4 mm after transoral surgery. CONCLUSION: The quantitative assessment of the TMJ showed minimal changes of the condylar position and variable degrees of articular disc displacement associated with the paramedian split mandibulotomy. As well, limited jaw functions and vertical mouth opening were noticed more in the mandibultomy group compared to the transoral group in 6- weeks after surgery.

Depth Perception of Surgeons in Minimally Invasive Surgery.

Minimally invasive surgery (MIS) poses visual challenges to the surgeons. In MIS, binocular disparity is not freely available for surgeons, who are required to mentally rebuild the 3-dimensional (3D) patient anatomy from a limited number of monoscopic visual cues. The insufficient depth cues from the MIS environment could cause surgeons to misjudge spatial depth, which could lead to performance errors thus jeopardizing patient safety. In this article, we will first discuss the natural human depth perception by exploring the main depth cues available for surgeons in open procedures. Subsequently, we will reveal what depth cues are lost in MIS and how surgeons compensate for the incomplete depth presentation. Next, we will further expand our knowledge by exploring some of the available solutions for improving depth presentation to surgeons. Here we will review the innovative approaches (multiple 2D camera assembly, shadow introduction) and devices (3D monitors, head-mounted devices, and auto-stereoscopic monitors) for 3D image presentation from the past few years.

Transfer of the Cystic Fibrosis Transmembrane Conductance Regulator to Human Cystic Fibrosis Cells Mediated by Extracellular Vesicles.

Cystic fibrosis (CF) is a genetic disease caused by mutations in the CF transmembrane conductance regulator (CFTR) gene, resulting in a deficiency in chloride channel activity. In this study, extracellular vesicles (EVs), microvesicles, and exosomes were used as vehicles to deliver exogenous CFTR glycoprotein and its encoding mRNA (mRNA(GFP-CFTR)) to CF cells to correct the CFTR chloride channel function. We isolated microvesicles and exosomes from the culture medium of CFTR-positive Calu-3 cells, or from A549 cells transduced with an adenoviral vector overexpressing a GFP-tagged CFTR (GFP-CFTR). Both microvesicles and exosomes had the capacity to package and deliver the GFP-CFTR glycoprotein and mRNA(GFP-CFTR) to target cells in a dose-dependent manner. Homologous versus heterologous EV-to-cell transfer was studied, and it appeared that the cellular uptake of EVs was significantly more efficient in homologous transfer. The incubation of CF15 cells, a nasal epithelial cell line homozygous for the ΔF508 CFTR mutation, with microvesicles or exosomes loaded with GFP-CFTR resulted in the correction of the CFTR function in CF cells in a dose-dependent manner. A time-course analysis of EV-transduced CF cells suggested that CFTR transferred as mature glycoprotein was responsible for the CFTR-associated channel activity detected at early times posttransduction, whereas GFP-CFTR translated from exogenous mRNA(GFP-CFTR) was responsible for the CFTR function at later times. Collectively, this study showed the potential application of microvesicles and exosomes as vectors for CFTR transfer and functional correction of the genetic defect in human CF cells.

Accuracy of magnetic resonance imaging-cone beam computed tomography rigid registration of the head: an in-vitro study.

OBJECTIVE: To evaluate the performance of cross-modality image registration procedure between magnetic resonance imaging (MRI) and cone beam computed tomography (CBCT). METHODS: In vitro diagnostic MRI and CBCT images of 5 cadaver swine heads were obtained prospectively. Five radiopaque fiducial markers were attached to each cadaver skull by using resin screws. Automatic MRI-CBCT rigid registrations were performed. The specimens were then scanned using a 3-dimensional (3-D) laser scanner. The 3-D coordinate points for the centroid of the attached fiducial markers from laser scan were identified and considered ground truth. The distances between marker centroids were measured with MRI, CBCT, and MRI-CBCT. Accuracy was calculated by using repeated measures analysis of variance and mean difference values. The registration method was repeated 10 times for each specimen in MRI to measure the average error. RESULTS: There was no significant difference (P > .05) in mean distances of the markers between all images and the ground truth. The distances' mean difference between MRI, CBCT, and MRI-CBCT and the ground truth were 0.2 ± 1.1 mm, 0.3 ± 1.0 mm, 0.2 ± 1.2 mm, respectively. The detected method error ranged between 0.06 mm and 0.1 mm. CONCLUSION: The cross-modality image registration algorithm is accurate for head MRI-CBCT registration.

Lung tumor boundary tracking in MRI with moving mesh correspondences for adaptive radio therapy.

Delineation of lung tumor regions from magnetic resonance imaging (MRI) poses many difficulties due to MR signal similarities of the region of interest and surrounding area as well as the influence of respiration. However, accurate segmentation of the tumor region is of utmost importance in planning a radiation therapy since a small error can result in some healthy tissues to receive excessive radiation. This study presents a semi-automated method to delineate lung tumor regions from a sequence of MRIs. The proposed method uses a non-rigid image registration framework to propagate the boundaries of the tumor region in MRI acquired during a radiation treatment stage, given manual segmentation on frames acquired during pretreatment stage. We investigate two approaches: 1) the first one utilizes manual segmentation of the first frame during the pretreatment stage; and 2) the second one utilizes manual segmentation of all the frames during the pretreatment stage. We evaluated the proposed approaches over a sequence of 400 images acquired from 4 patients. The proposed method based on the utilization of all the frames yielded a Dice score of 0.90 ± 0.04 and a Hausdorff distance of 1.17 ± 0.35 pixels (2.83 ± 0.79 mm) in comparison to expert manual segmentation.

Three-Dimensional Eye Tracking in a Surgical Scenario.

INTRODUCTION: Eye tracking has been widely used in studying the eye behavior of surgeons in the past decade. Most eye-tracking data are reported in a 2-dimensional (2D) fashion, and data for describing surgeons' behaviors on stereoperception are often missed. With the introduction of stereoscopes in laparoscopic procedures, there is an increasing need for studying the depth perception of surgeons under 3D image-guided surgery. METHODS: We developed a new algorithm for the computation of convergence points in stereovision by measuring surgeons' interpupillary distance, the distance to the view target, and the difference between gaze locations of the 2 eyes. To test the feasibility of our new algorithm, we recruited 10 individuals to watch stereograms using binocular disparity and asked them to develop stereoperception using a cross-eyed viewing technique. Participants' eye motions were recorded by the Tobii eye tracker while they performed the trials. Convergence points between normal and stereo-viewing conditions were computed using the developed algorithm. RESULTS: All 10 participants were able to develop stereovision after a short period of training. During stereovision, participants' eye convergence points were 14 ± 1 cm in front of their eyes, which was significantly closer than the convergence points under the normal viewing condition (77 ± 20 cm). CONCLUSION: By applying our method of calculating convergence points using eye tracking, we were able to elicit the eye movement patterns of human operators between the normal and stereovision conditions. Knowledge from this study can be applied to the design of surgical visual systems, with the goal of improving surgical performance and patient safety.