Search

Purpose: This work presents FASTRL, a benchmark set of instrument manipulation tasks adapted to the domain of reinforcement learning and used in simulated surgical training. This benchmark enables and supports the design and training of human-centric reinforcement learning agents which assist and evaluate human trainees in surgical practice. Methods: Simulation tasks from the Fundamentals of Arthroscopic Surgery Training (FAST) program are adapted to the reinforcement learning setting for the purpose of training virtual agents that are capable of providing assistance and scoring to the surgical trainees. A skill performance assessment protocol is presented based on the trained virtual agents. Results: The proposed benchmark suite presents an API for training reinforcement learning agents in the context of arthroscopic skill training. The evaluation scheme based on both heuristic and learned reward functions robustly recovers the ground truth ranking on a diverse test set of human trajectories. Conclusion: The presented benchmark enables the exploration of a novel reinforcement learning-based approach to skill performance assessment and in-procedure assistance for simulated surgical training scenarios. The evaluation protocol based on the learned reward model demonstrates potential for evaluating the performance of surgical trainees in simulation. [ABSTRACT FROM AUTHOR]

Purpose: Segmentation of surgical scenes may provide valuable information for real-time guidance and post-operative analysis. However, in some surgical video frames there is unavoidable ambiguity, leading to incorrect predictions of class or missed detections. In this work, we propose a novel method that alleviates this problem by introducing a hierarchy and associated hierarchical inference scheme that allows broad anatomical structures to be predicted when fine-grained structures cannot be reliably distinguished. Methods: First, we formulate a multi-label segmentation loss informed by a hierarchy of anatomical classes and then train a network using this. Subsequently, we use a novel leaf-to-root inference scheme ("Hiera-Mix") to determine the trade-off between label confidence and granularity. This method can be applied to any segmentation model. We evaluate our method using a large laparoscopic cholecystectomy dataset with 65,000 labelled frames. Results: We observed an increase in per-structure detection F1 score for the critical structures, when evaluated across their sub-hierarchies, compared to the baseline method: 6.0% for the cystic artery and 2.9% for the cystic duct, driven primarily by increases in precision of 11.3% and 4.7%, respectively. This corresponded to visibly improved segmentation outputs, with better characterisation of the undissected area containing the critical structures and fewer inter-class confusions. For other anatomical classes, which did not stand to benefit from the hierarchy, performance was unimpaired. Conclusion: Our proposed hierarchical approach improves surgical scene segmentation in frames with ambiguity, by more suitably reflecting the model's parsing of the scene. This may be beneficial in applications of surgical scene segmentation, including recent advancements towards computer-assisted intra-operative guidance. [ABSTRACT FROM AUTHOR]

Purpose: Magnetic resonance imaging (MRI) is a common technique in image-guided neurosurgery (IGN). Recent research explores the integration of methods like ultrasound and tomography, among others, with hyperspectral (HS) imaging gaining attention due to its non-invasive real-time tissue classification capabilities. The main challenge is the registration process, often requiring manual intervention. This work introduces an automatic, markerless method for aligning HS images with MRI. Methods: This work presents a multimodal system that combines RGB-Depth (RGBD) and HS cameras. The RGBD camera captures the patient's facial geometry, which is used for registration with the preoperative MR through ICP. Once MR-depth registration is complete, the integration of HS data is achieved using a calibrated homography transformation. The incorporation of external tracking with a novel calibration method allows camera mobility from the registration position to the craniotomy area. This methodology streamlines the fusion of RGBD, HS and MR images within the craniotomy area. Results: Using the described system and an anthropomorphic phantom head, the system has been characterised by registering the patient's face in 25 positions and 5 positions resulted in a fiducial registration error of 1.88 ± 0.19 mm and a target registration error of 4.07 ± 1.28 mm, respectively. Conclusions: This work proposes a new methodology to automatically register MR and HS information with a sufficient accuracy. It can support the neurosurgeons to guide the diagnosis using multimodal data over an augmented reality representation. However, in its preliminary prototype stage, this system exhibits significant promise, driven by its cost-effectiveness and user-friendly design. [ABSTRACT FROM AUTHOR]

A critical yet unpredictable complication following cataract surgery is intraocular lens dislocation. Postoperative stability is imperative, as even a tiny decentration of multifocal lenses or inadequate alignment of the torus in toric lenses due to postoperative rotation can lead to a significant drop in visual acuity. Investigating possible intraoperative indicators that can predict post-surgical instabilities of intraocular lenses can help prevent this complication. In this paper, we develop and evaluate the first fully automatic framework for the computation of lens unfolding delay, rotation, and instability during surgery. Adopting a combination of three types of CNNs, namely recurrent, region-based, and pixel-based, the proposed framework is employed to assess the possibility of predicting postoperative lens dislocation during cataract surgery. This is achieved via performing a large-scale study on the statistical differences between the behavior of different brands of intraocular lenses and aligning the results with expert surgeons’ hypotheses and observations about the lenses. We exploit a large-scale dataset of cataract surgery videos featuring four intraocular lens brands. Experimental results confirm the reliability of the proposed framework in evaluating the lens’ statistics during the surgery. The Pearson correlation and t-test results reveal significant correlations between lens unfolding delay and lens rotation and significant differences between the intra-operative rotations stability of four groups of lenses. These results suggest that the proposed framework can help surgeons select the lenses based on the patient’s eye conditions and predict post-surgical lens dislocation.

Background: In recent years, computer-assisted intervention and robot-assisted surgery are receiving increasing attention. The need for real-time identification and tracking of surgical tools and tool tips is constantly demanding. A series of researches focusing on surgical tool tracking and identification have been performed. However, the size of dataset, the sensitivity/precision, and the response time of these studies were limited. In this work, we developed and utilized an automated method based on Convolutional Neural Network (CNN) and You Only Look Once (YOLO) v3 algorithm to locate and identify surgical tools and tool tips covering five different surgical scenarios. Materials and methods: An algorithm of object detection was applied to identify and locate the surgical tools and tool tips. DarkNet-19 was used as Backbone Network and YOLOv3 was modified and applied for the detection. We included a series of 181 endoscopy videos covering 5 different surgical scenarios: pancreatic surgery, thyroid surgery, colon surgery, gastric surgery, and external scenes. A total amount of 25,333 images containing 94,463 targets were collected. Training and test sets were divided in a proportion of 2.5:1. The data sets were openly stored at the Kaggle database. Results: Under an Intersection over Union threshold of 0.5, the overall sensitivity and precision rate of the model were 93.02% and 89.61% for tool recognition and 87.05% and 83.57% for tool tip recognition, respectively. The model demonstrated the highest tool and tool tip recognition sensitivity and precision rate under external scenes. Among the four different internal surgical scenes, the network had better performances in pancreatic and colon surgeries and poorer performances in gastric and thyroid surgeries. Conclusion: We developed a surgical tool and tool tip recognition model based on CNN and YOLOv3. Validation of our model demonstrated satisfactory precision, accuracy, and robustness across different surgical scenes. [ABSTRACT FROM AUTHOR]

Purpose: Tissue deformation recovery is to reconstruct the change in shape and surface strain caused by tool-tissue interaction or respiration, which is essential for providing motion and shape information that benefits the improvement of the safety of minimally invasive surgery. The binocular vision-based approach is a practical candidate for deformation recovery as no extra devices are required. However, previous methods suffer from limitations such as the reliance on biomechanical priors and the vulnerability to the occlusion caused by surgical instruments. To address the issues, we propose a deformation recovery method incorporating mesh structures and scene flow. Methods: The method can be divided into three modules. The first one is the implementation of the two-step scene flow generation module to extract the 3D motion from the binocular sequence. Second, we propose a strain-based filtering method to denoise the original scene flow. Third, a mesh optimization model is proposed that strengthens the robustness to occlusion by employing contextual connectivity. Results: In a phantom and an in vivo experiment, the feasibility of the method in recovering surface deformation in the presence of tool-induced occlusion was demonstrated. Surface reconstruction accuracy was quantitatively evaluated by comparing the recovered mesh surface with the 3D scanned model in the phantom experiment. Results show that the overall error is 0.70 ± 0.55 mm. Conclusion: The method has been demonstrated to be capable of continuously recovering surface deformation using mesh representation with robustness to the occlusion caused by surgical forceps and promises to be suitable for the application in actual surgery. [ABSTRACT FROM AUTHOR]

The recent advancements in the surging field of Deep Learning (DL) have revolutionized every sphere of life, and the healthcare domain is no exception. The enormous success of DL models, particularly with image data, has led to the development of image-guided Robot Assisted Surgery (RAS) systems. By and large, the number of studies concerning image-driven computer assisted surgical systems using DL has increased exponentially. Additionally, the contemporary availability of surgical datasets has also boosted the DL applications in RAS. Inspired by the latest trends and contributions in surgery, this literature survey presents a summarized analysis of recent innovations of DL in image-guided RAS systems. After a thorough review, a sum of 184 articles are selected and grouped into four categories, based on the literature and the relevancy of the task in the articles, comprising 1) Surgical Tools, 2) Surgical Processes, 3) Surgical Surveillance, and 4) Surgical Performance. The survey also discusses publicly available surgical datasets and highlights the basics of the DL models. Furthermore, the legal, ethical, and technological challenges together with the intuitive predictions and recommendations related to the autonomous RAS systems are also presented. The study reveals that Convolutional Neural Network (CNN) is most widely adopted architecture, whereas, the JIGSAWS is most employed dataset in RAS. The study suggests fusing kinematic data along with image data, which produces better accuracy and precision, particularly in gesture and trajectory segmentation tasks. Additionally, CNN and long short term memory networks have shown remarkable performance, however, authors recommend employing these gigantic architectures only when simpler models have failed to produce satisfactory results. The simpler models, despite their limitations, are time and cost effective and yield considerable outcomes even on the smaller datasets.

Purpose: Automation of sub-tasks during robotic surgery is challenging due to the high variability of the surgical scenes intra- and inter-patients. For example, the pick and place task can be executed different times during the same operation and for distinct purposes. Hence, designing automation solutions that can generalise a skill over different contexts becomes hard. All the experiments are conducted using the Pneumatic Attachable Flexible (PAF) rail, a novel surgical tool designed for robotic-assisted intraoperative organ manipulation. Methods: We build upon previous open-source surgical Reinforcement Learning (RL) training environment to develop a new RL framework for manipulation skills, rlman. In rlman, contextual RL agents are trained to solve different aspects of the pick and place task using the PAF rail system. rlman is implemented to support both low- and high-dimensional state information to solve surgical sub-tasks in a simulation environment. Results: We use rlman to train state of the art RL agents to solve four different surgical sub-tasks involving manipulation skills using the PAF rail. We compare the results with state-of-the-art benchmarks found in the literature. We evaluate the ability of the agent to be able to generalise over different aspects of the targeted surgical environment. Conclusion: We have shown that the rlman framework can support the training of different RL algorithms for solving surgical sub-task, analysing the importance of context information for generalisation capabilities. We are aiming to deploy the trained policy on the real da Vinci using the dVRK and show that the generalisation of the trained policy can be transferred to the real world. [ABSTRACT FROM AUTHOR]

Augmented Reality (AR) can assist Laparoscopic Liver Resection (LLR) by registering a preoperative 3D model with laparoscopic images. Evaluating the accuracy of the registration methods requires measuring Target Registration Error (TRE). Previous work evaluates TRE on simulated, phantom and animal data but not on clinical data. Our contribution is a methodology for groundtruth acquisition using Laparoscopic Ultrasound (LUS) in clinical LLR, two evaluation criteria, a four-patient dataset and an evaluation of two existing registration methods. The LUS is coregistered with the laparoscope and its observations are made transferable to 3D laparoscope coordinates. The average position error in our LUS registered images is estimated to be about 1 mm, which is far better than the measured errors for the state-of-the-art registration methods, making our dataset relevant for their evaluation. We ran a preliminary evaluation of two registration methods. The dataset is available publicly at . [ABSTRACT FROM AUTHOR]

This study examines how the introduction of TeachTown:Basics, a computer-assisted intervention for students with autism spectrum disorder, influenced teachers' use of other evidence-based practices. In a randomized controlled trial that enrolled 73 teachers nested within 58 schools, we used three-level hierarchical linear models to evaluate changes in teachers' use of evidence-based practices across the school year for those who received TeachTown:Basics versus those assigned to control. Both groups received training and implementation support to deliver three well-established evidence-based practices for autism spectrum disorder. Qualitative interviews were conducted with 25 teachers who used TeachTown:Basics to better understand their experience. Compared with teachers in the control group, teachers in the TeachTown:Basics group reported significantly less growth over the 9-month period in their use of evidence-based practices that require one-to-one instruction (p s < 0.05), but no difference in their reported use of evidence-based practices that do not involve one-to-one instruction (p = 0.637). Qualitative interviews indicated that teachers viewed TeachTown:Basics as an effective substitute for one-to-one instruction because it was less burdensome, despite the lack of support for TeachTown:Basics' effectiveness. Before introducing new practices, education leaders should carefully consider both evidence of effectiveness and the potential impact on the use of other evidence-based practices. Interventions for children with autism spectrum disorder are complex and often are not implemented successfully within schools. When new practices are introduced in schools, they often are layered on top of existing practices, with little attention paid to how introducing new practices affects the use of existing practices. This study evaluated how introducing a computer-assisted intervention, called TeachTown:Basics, affected the use of other evidence-based practices in autism support classrooms. We compared how often teachers reported using a set of evidence-based practices in classrooms that either had access to TeachTown:Basics or did not have the program. We found that teachers who had access to the computer-assisted intervention reported using the other evidence-based practices less often as the school year progressed. Teachers also reported that they liked the computer-assisted intervention, found it easy to use, and that it helped overcome challenges to implementing other evidence-based practices. This is important because the computer-assisted intervention did not improve child outcomes in a previous study and indicates that teachers may use interventions that are appealing and easier to implement, even when they do not have evidence to support their effectiveness. These findings support the idea of interventions' complexity and how well the intervention fits within the classroom affect how teachers use it and highlight the need to develop school-based interventions that both appeal to the practitioner and improve child outcomes. [ABSTRACT FROM AUTHOR]

The interest in computer-assisted interventions to promote literacy has increased over the years. In this study, we developed the Portuguese version of the GraphoGame Fluent and tested its effects on reading, spelling, and phonological awareness. Second graders struggling to read were randomly assigned to two groups: GraphoGame Fluent group (n = 15), which received a computer-assisted remedial reading intervention, or GraphoGame Math group (n = 15), which received a computer-assisted numeracy intervention. An additional, non-playing group, composed by second graders without reading difficulties, was formed (business-as-usual group, n = 15). Results showed clear benefits of GraphoGame on spelling and phonological awareness. After the intervention and one month later, the GraphoGame Fluent group displayed spelling and phonological awareness skills similar to the business-as-usual group, and above the GraphoGame Math group. Overall, these findings indicate that Portuguese struggling readers benefit from computer-assisted interventions that combine letter-sound correspondences with more complex orthographic patterns. [ABSTRACT FROM AUTHOR]

Objective: Computer-assisted interventions (CAIs) are popular for educating children with autism, but their effectiveness is not well established. This study evaluated the effectiveness of 1 CAI designed to improve children's language, cognitive, and academic skills, TeachTown: Basics, in a large urban school district.Method: Teachers (n = 59) in autism support classrooms and their consented students in kindergarten through second grade (n = 154) were randomized to TeachTown: Basics or waitlist control. Child outcome was measured at baseline and after 1 academic year using the Bracken Basic Concepts Scale-Receptive and Expressive versions and the Differential Ability Scales, Second Edition (DAS-II). Random effects regression models that included clustering of time within students and students within classrooms were used to test whether the change over time in each outcome differed between groups.Results: There were no statistically significant differences in outcomes for children who received TeachTown: Basics or treatment as usual. Increased time spent using TeachTown: Basics was associated with worse receptive language outcomes for children in the experimental group after 1 academic year. However, there was no association between minutes spent using TeachTown and changes in expressive language or DAS-II score.Conclusion: Despite growing enthusiasm for CAIs in autism treatment, the present findings indicate that CAI might not be effective at improving language and cognitive outcomes for children with autism spectrum disorder. The decision to implement CAIs in schools should be carefully balanced against the evidence for effectiveness of these programs. Schools might be better served by investing in treatment strategies with established evidence.Clinical Trial Registration Information: RCT of TeachTown in Autism Support Classrooms: Innovation and Exnovation; https://clinicaltrials.gov/; NCT02695693. [ABSTRACT FROM AUTHOR]

Health care delivery is being transformed by the use of computer technology, and integrated physical health with mental and behavioral health care are national priorities. This study examined the basic computer skills and computer preferences of inner-city hospitalized medical patients in a design study of a web-based alcohol screening and brief intervention program prototype. Participants were 26 patients observed going through the program prototype using both a laptop computer and mouse, and an iPad. The majority of patients were able to do all the basic laptop and basic iPad skills to complete the program prototype, including older patients (aged 50 years or older) and patients with a high school degree or less. Patient computer preference was 3:1 for the use of an iPad versus a laptop computer, and the majority of patients preferred to complete a web-based versus an in-person brief intervention health program. Inner-city hospitalized medical patients appear able to complete and may be receptive to web-based alcohol screening and brief intervention programs. [ABSTRACT FROM AUTHOR]

Accurate localization and analyses of functional liver segments are crucial in devising various surgical procedures, including hepatectomy. To this end, they require the extraction of a liver from computed tomography, and then the identification of resection correspondence between individuals. The first part is usually impeded by inherent deficiencies, as present in medical images, and vast anatomical variations across subjects. While the model-based approach is found viable to tackle both issues, it is often undermined by an inadequate number of labeled samples, to capture all plausible variations. To address segmentation problems by balancing between accuracy, resource consumption, and data availability, this paper presents an efficient method for liver segmentation based on a graph-cut algorithm. One of its main novelties is the incorporation of a feature preserving a metric for boundary separation. Intuitive anatomical constraints are imposed to ensure valid extraction. The second part involves the symmetric conformal parameterization of the extracted liver surface onto a genus-0 domain. Provided with a few landmarks specified on two livers, we demonstrated that, by using a modified Beltrami differential, not only could they be non-rigidly registered, but also the hepatectomy on one liver could be envisioned on another. The merits of the proposed scheme were elucidated by both visual and numerical assessments on a standard MICCAI SLIVER07 dataset.

Abstract Background The number of children diagnosed with autism has rapidly outpaced the capacities of many public school systems to serve them, especially under-resourced, urban school districts. The intensive nature of evidence-based autism interventions, which rely heavily on one-to-one delivery, has caused schools to turn to computer-assisted interventions (CAI). There is little evidence regarding the feasibility, effectiveness, and implementation of CAI in public schools. While CAI has the potential to increase instructional time for students with autism, it may also result in unintended consequences such as reduction in the amount of interpersonal (as opposed to computerized) instruction students receive. The purpose of this study is to test the effectiveness of one such CAI—TeachTown—its implementation, and its effects on teachers’ use of other evidence-based practices. Methods This study protocol describes a type II hybrid cluster randomized effectiveness-implementation trial. We will train and coach 70 teachers in autism support classrooms in one large school district in the use of evidence-based practices for students with autism. Half of the teachers then will be randomly selected to receive training and access to TeachTown: Basics, a CAI for students with autism, for the students in their classrooms. The study examines: (1) the effectiveness of TeachTown for students with autism; (2) the extent to which teachers implement TeachTown the way it was designed (i.e., fidelity); and (3) whether its uptake increases or reduces the use of other evidence-based practices. Discussion This study will examine the implementation of new technology for children with ASD in public schools and will be the first to measure the effectiveness of CAI. As importantly, the study will investigate whether adding a new technology on top of existing practices increases or decreases their use. This study presents a unique method to studying both the implementation and exnovation of evidence-based practices for children with autism in school settings. Trial registration NCT02695693 . Retrospectively registered on July 8, 2016.

Pressure injuries represent a major concern in many nations. These wounds result from prolonged pressure on the skin, which mainly occur among elderly and disabled patients. If retrieving quantitative information using invasive methods is the most used method, it causes significant pain and discomfort to the patients and may also increase the risk of infections. Hence, developing non-intrusive methods for the assessment of pressure injuries would represent a highly useful tool for caregivers and a relief for patients. Traditional methods rely on findings retrieved solely from 2D images. Thus, bypassing the 3D information deriving from the deep and irregular shape of this type of wounds leads to biased measurements. In this paper, we propose an end-to-end system which uses a single 2D image and a 3D mesh of the pressure injury, acquired using the Structure Sensor, and outputs all the necessary findings such as: external segmentation of the wound as well as its real-world measurements (depth, area, volume, major axis and minor axis). More specifically, a first block composed of a Mask RCNN model uses the 2D image to output the segmentation of the external boundaries of the wound. Then, a second block matches the 2D and 3D views to segment the wound in the 3D mesh using the segmentation output and generates the aforementioned real-world measurements. Experimental results showed that the proposed framework can not only output refined segmentation with 87% precision, but also retrieves reliable measurements, which can be used for medical assessment and healing evaluation of pressure injuries.

Abstract This study reports on the effectiveness of an early reading intervention, based on current research on early reading acquisition, and aligned to Norwegian orthography. Thirteen schools were randomly assigned to one of two interventions or a control condition. First grade students (n = 744) were screened at school entry, and children at risk of reading difficulties (n = 140) were identified. At-risk students in schools allocated for intervention received comprehensive teacher-led instruction also containing an individually-delivered computer component. The only difference between the two interventions was whether the computer application had adaptive learning features. Both interventions had significant impact on reading and spelling with no significant difference between the two different intervention conditions. Findings indicate that Norwegian children identified to be at-risk at school entry can profit from intensive intervention that combines training in letter knowledge with explicit instruction in phonetic decoding and word recognition, free spelling, connected text reading and shared reading. Highlights • A multi-component reading intervention for students at risk for RD is proposed. • The proposed intervention is evaluated in a sample of Norwegian first graders. • Intervention students outperform controls on reading and spelling after treatment. • Adaptive and fixed computer applications are evaluated and found equally effective. • At-risk children receiving intervention showed parallel growth with not-at-risk. [ABSTRACT FROM AUTHOR]

Background: The number of children diagnosed with autism has rapidly outpaced the capacities of many public school systems to serve them, especially under resourced, urban school districts. The intensive nature of evidencebased autism interventions, which rely heavily on one to one delivery, has caused schools to turn to computerassisted interventions (CAI). There is little evidence regarding the feasibility, effectiveness, and implementation of CAI in public schools. While CAI has the potential to increase instructional time for students with autism, it may also result in unintended consequences such as reduction in the amount of interpersonal (as opposed to computerized) instruction students receive. The purpose of this study is to test the effectiveness of one such CAI TeachTown its implementation, and its effects on teachers use of other evidence based practices. Methods: This study protocol describes a type II hybrid cluster randomized effectiveness implementation trial. We will train and coach 70 teachers in autism support classrooms in one large school district in the use of evidencebased practices for students with autism. Half of the teachers then will be randomly selected to receive training and access to TeachTown: Basics, a CAI for students with autism, for the students in their classrooms. The study examines: (1) the effectiveness of TeachTown for students with autism; (2) the extent to which teachers implement TeachTown the way it was designed (i.e., fidelity); and (3) whether its uptake increases or reduces the use of other evidence based practices. Discussion: This study will examine the implementation of new technology for children with ASD in public schools and will be the first to measure the effectiveness of CAI. As importantly, the study will investigate whether adding a new technology on top of existing practices increases or decreases their use. This study presents a unique method to studying both the implementation and exnovation of evidence-based practices for children with autism in school settings. [ABSTRACT FROM AUTHOR]

The early days of the field of medical image computing (MIC) and computer-assisted intervention (CAI), when publishing a strong self-contained methodological algorithm was enough to produce impact, are over. As a community, we now have substantial responsibility to translate our scientific progresses into improved patient care. In the field of computer-assisted interventions, the emphasis is also shifting from the mere use of well-known established imaging modalities and position trackers to the design and combination of innovative sensing, elaborate computational models and fine-grained clinical workflow analysis to create devices with unprecedented capabilities. The barriers to translating such devices in the complex and understandably heavily regulated surgical and interventional environment can seem daunting. Whether we leave the translation task mostly to our industrial partners or welcome, as researchers, an important share of it is up to us. We argue that embracing the complexity of surgical and interventional sciences is mandatory to the evolution of the field. Being able to do so requires large-scale infrastructure and a critical mass of expertise that very few research centres have. In this paper, we emphasise the need for a holistic approach to computer-assisted interventions where clinical, scientific, engineering and regulatory expertise are combined as a means of moving towards clinical impact. To ensure that the breadth of infrastructure and expertise required for translational computer-assisted intervention research does not lead to a situation where the field advances only thanks to a handful of exceptionally large research centres, we also advocate that solutions need to be designed to lower the barriers to entry. Inspired by fields such as particle physics and astronomy, we claim that centralised very large innovation centres with state of the art technology and health technology assessment capabilities backed by core support staff and open interoperability standards need to be accessible to the wider computer-assisted intervention research community. [ABSTRACT FROM AUTHOR]

Objective: To assess the impact of a computer-assisted Screening, Brief Intervention, and Referral to Treatment (SBIRT) on daily consumption of alcohol by patients with hazardous drinking disorder detected after systematic screening during their admission to an emergency department (ED).Design: Two-arm, parallel group, multicentre, randomized controlled trial with a centralised computer-generated randomization procedure.Setting: Four EDs in university hospitals located in the Paris area in France.Participants: Patients admitted in the ED for any reason, with hazardous drinking disorder detected after systematic screening (i.e., Alcohol Use Disorder Identification Test score ≥5 for women and 8 for men OR self-reported alcohol consumption by week ≥7 drinks for women and 14 for men).Interventions: The experimental intervention was computer-assisted SBIRT and the comparator was a placebo-controlled intervention (i.e., a computer-assisted education program on nutrition). Interventions were administered in the ED and followed by phone reinforcements at 1 and 3 months.Main Outcome Measure: The primary outcome was the mean number of alcohol drinks per day in the previous week, at 12 months. Results From May 2005 to February 2011, 286 patients were randomized to the computer-assisted SBIRT and 286 to the comparator intervention. The two groups did not differ in the primary outcome, with an adjusted mean difference of 0.12 (95% confidence interval, -0.88 to 1.11).Conclusions: There was no additional benefit of the computer-assisted alcohol SBIRT as compared with the computer-assisted education program on nutrition among patients with hazardous drinking disorder detected by systematic screening during their admission to an ED. [ABSTRACT FROM AUTHOR]

Purpose : In recent years, selective retina laser treatment (SRT), a sub-threshold therapy method, avoids widespread damage to all retinal layers by targeting only a few. While these methods facilitate faster healing, their lack of visual feedback during treatment represents a considerable shortcoming as induced lesions remain invisible with conventional imaging and make clinical use challenging. To overcome this, we present a new strategy to provide location-specific and contact-free automatic feedback of SRT laser applications. Methods : We leverage time-resolved optical coherence tomography (OCT) to provide informative feedback to clinicians on outcomes of location-specific treatment. By coupling an OCT system to SRT treatment laser, we visualize structural changes in the retinal layers as they occur via time-resolved depth images. We then propose a novel strategy for automatic assessment of such time-resolved OCT images. To achieve this, we introduce novel image features for this task that when combined with standard machine learning classifiers yield excellent treatment outcome classification capabilities. Results : Our approach was evaluated on both ex vivo porcine eyes and human patients in a clinical setting, yielding performances above 95 % accuracy for predicting patient treatment outcomes. In addition, we show that accurate outcomes for human patients can be estimated even when our method is trained using only ex vivo porcine data. Conclusion : The proposed technique presents a much needed strategy toward noninvasive, safe, reliable, and repeatable SRT applications. These results are encouraging for the broader use of new treatment options for neovascularization-based retinal pathologies. [ABSTRACT FROM AUTHOR]

Background: The aim of this paper is to provide a general discussion, algorithm, and actual working programs of the deformation method for fast simulation of biological tissue formed by fibers and fluid. In order to demonstrate the benefit of the clinical applications software, we successfully used our computational program to deform a 3D breast image acquired from patients, using a 3D scanner, in a real hospital environment. Results: The method implements a quasi-static solution for elastic global deformations of objects. Each pair of vertices of the surface is connected and defines an elastic fiber. The set of all the elastic fibers defines a mesh of smaller size than the volumetric meshes, allowing for simulation of complex objects with less computational effort. The behavior similar to the stress tensor is obtained by the volume conservation equation that mixes the 3D coordinates. Step by step, we show the computational implementation of this approach. Conclusions: As an example, a 2D rectangle formed by only 4 vertices is solved and, for this simple geometry, all intermediate results are shown. On the other hand, actual implementations of these ideas in the form of working computer routines are provided for general 3D objects, including a clinical application. [ABSTRACT FROM AUTHOR]

Purpose: Percutaneous needle insertions are increasingly used for diagnosis and treatment of abdominal lesions. The challenging part of computed tomography (CT)-guided punctures is the transfer of the insertion trajectory planned in the CT image to the patient. Conventionally, this often results in several needle repositionings and control CT scans. To address this issue, several navigation systems for percutaneous needle insertions have been presented; however, none of them has thus far become widely accepted in clinical routine. Their benefit for the patient could not exceed the additional higher costs and the increased complexity in terms of bulky tracking systems and specialized markers for registration and tracking. Methods: We present the first markerless and trackerless navigation concept for real-time patient localization and instrument guidance. It has specifically been designed to be integrated smoothly into the clinical workflow and does not require markers or an external tracking system. The main idea is the utilization of a range imaging device that allows for contactless and radiation-free acquisition of both range and color information used for patient localization and instrument guidance. Results: A first feasibility study in phantom and porcine models yielded a median targeting accuracy of 6.9 and 19.4 mm, respectively. Conclusions: Although system performance remains to be improved for clinical use, expected advances in camera technology as well as consideration of respiratory motion and automation of the individual steps will make this approach an interesting alternative for guiding percutaneous needle insertions. [ABSTRACT FROM AUTHOR]

Four groups of poor readers were identified among a population of students with learning disabilities attending a special class in secondary school: normal readers; specific poor decoders; specific poor comprehenders, and general poor readers (deficits in both decoding and comprehension). These students were then trained with a software program designed to encourage either their word decoding skills or their text comprehension skills. After 5 weeks of training, we observed that the students experiencing word reading deficits and trained with the decoding software improved primarily in the reading fluency task while those exhibiting comprehension deficits and trained with the comprehension software showed improved performance in listening and reading comprehension. But interestingly, the latter software also led to improved performance on the word recognition task. This result suggests that, for these students, training interventions focused at the text level and its comprehension might be more beneficial for reading in general (i.e., for the two components of reading) than word-level decoding trainings. [ABSTRACT FROM AUTHOR]

Purpose: Malignant neoplasms of the liver are among the most frequent cancers worldwide. Given the diversity of options for liver cancer therapy, the choice of treatment depends on various parameters including patient condition, tumor size and location, liver function, and previous interventions. To address this issue, we present the first approach to treatment strategy planning based on holistic processing of patient-individual data, practical knowledge (i.e., case knowledge), and factual knowledge (e.g., clinical guidelines and studies). Methods: The contributions of this paper are as follows: (1) a formalized dynamic patient model that incorporates all the heterogeneous data acquired for a specific patient in the whole course of disease treatment; (2) a concept for formalizing factual knowledge; and (3) a technical infrastructure that enables storing, accessing, and processing of heterogeneous data to support clinical decision making. Results: Our patient model, which currently covers 602 patient-individual parameters, was successfully instantiated for 184 patients. It was sufficiently comprehensive to serve as the basis for the formalization of a total of 72 rules extracted from studies on patients with colorectal liver metastases or hepatocellular carcinoma. For a subset of 70 patients with these diagnoses, the system derived an average of $$37 \pm 15$$ assertions per patient. Conclusion: The proposed concept paves the way for holistic treatment strategy planning by enabling joint storing and processing of heterogeneous data from various information sources. [ABSTRACT FROM AUTHOR]

Patients with semantic dementia (SD) can improve their naming ability through cognitive intervention, with good retention 1 month later. Beyond this time, improvements often fade, yet no studies have investigated how to maintain performance. Nine SD patients completed a 2-month word training program and were then monitored over 6 months: firstly for 2 months without training, followed by a further 4 months, where additional training was provided to revise words, if required. All patients improved their naming immediately postintervention (P<0.001). After 2 months without practice, significant declines occurred in 4 patients. To sustain at least 80% of their postintervention performance 6 months later, 4 patients required minimal revision (<10 sessions over the period), 2 required regular weekly or biweekly revision sessions, with the remaining 3 patients requiring no revision sessions. During this period, group results indicated some decline in words that were initially known, but were not trained. Improvements in naming can be sustained in SD patients, with the support of less intense, but ongoing revision. Training words that are still known appears to help prolong memory of these words. [ABSTRACT FROM AUTHOR]

The overall purpose of the present study was to examine the relationship between self-image and different reading abilities among pupils with reading difficulties in grade 2. The purpose was also to examine whether there were any differences between typical readers and pupils with reading difficulties with regard to self-image. The empirical material consists of 130 pupils who were tested at five different test sessions with different reading-related tests. Their self-image was tested twice at an interval of nearly a school year The results showed that there were differences between pupils with reading difficulties and typical readers with regard to the self-image level, where pupils with reading disabilities had a significantly lower self-image than typical readers. Among pupils with reading disabilities those with a low self-image showed significantly less improvement in word decoding and reading comprehension than students with a typical self-image. [ABSTRACT FROM AUTHOR]