1,721,037 research outputs found
IJCARS: IPCAI 2024 special issue—15th international conference on information processing in computer-assisted interventions 2024—part 1
No full textImage Analysis Techniques for Scoliosis Using Deep Learning
Full text linkFrontal spine radiographs are used in understanding and determining key aspects of scoliosis patients, such as bone age and degree of curvature. These properties affect proposed treatments, such as referral for surgery, as well as predicted outcomes. Variability in data interpretation and physician decisions support the utility of consistent, automated frameworks for image processing. Using radiographs both synthetically generated and from a collection of data from 28 different hospital sites, we explore three tasks on spine radiographs using convolutional neural networks (CNNs) and their potential applications: 1) segmentation of the spine from a given image, both as a whole and as individual vertebrae, 2) classification of the Risser sign measuring skeletal maturity, and 3) determination of Lenke classification describing curvature. We propose these methods as a framework that can provide a holistic under- standing of scoliosis severity and development in patients, and can also be added to and built upon in the future for other applications and data including Cobb and Risser angle with vertebral body segmentation
Enabling Cognitive Load Aware User Interfaces for Mixed Reality
Full text linkHuman-AI mixed reality systems are becoming ubiquitous from day-to-day intelligent personal assistants to specialized, high stakes AI-assisted decision making tools. While designed to improve the user experience, current systems lack the ability to adapt to changing user needs, imparting increased cognitive burden on users. Understanding and minimizing cognitive effort through adaptive design is critical to paving the way for widespread adoption of mixed reality technology. Recent approaches towards adaptive interfaces involve monitoring physiological signals through obtrusive and extraneous equipment. As eye-trackers are becoming more readily available, pupillometry provides an unobtrusive pathway to cognitive load estimation. However, assessment of cognitive load from pupillometry is challenging in unconstrained environments due confounding effects of the pupillary light reflex. Our approach aggregates human- and world-facing sensory data to disentangle the cognitive load induced pupil response from the pupillary light reflex. First, we design a user study to generate a dataset observing pupil diameter changes during an auditory N-back recall task under variable environmental conditions. Next we develop a data processing pipeline to address outliers and temporally align all target variables. Finally, we design a 3D-CNN architecture to achieve a proof-of-principle cognitive load estimation model
Evaluation of Augmented Reality for Collaborative Environments
Full text linkThe intersection of intelligent analytics and climbing is relatively nascent. Various forms of climbing have begun to grow exceedingly fast in recent years, with a combination of three sub-categories even having become adopted into the Olympic games (i.e. bouldering, speed climbing and lead climbing). With a growing community, injuries due to the inherent health risks of climbing will undoubtedly grow as well. We aim to address these health concerns by helping lay the groundwork for future preventive technologies that help climbers better understand and plan their routes.
Multiple works have applied mobile or projector-based augmented reality or tools such as computer vision and deep learning to help with problems such as climbing route difficulty assessment, games for user retention in the commercial setting and fall protection via wall monitoring. However, few if any, examine collaborative problems in climbing with real-time, augmented reality systems using modern, head-mounted displays.
To this end, we frame our examination of the climbing space as a collaborative, layout and design task, thereby targeting collaborative, route setting as the specific application space. We present ClimbAR, an open-source, collaborative, real-time, augmented reality application running natively on the Hololens 2 that allows climbers to virtually and collaboratively, set climbing holds in their physical environments. Due to the necessary infrastructure required to develop ClimbAR, we also present its core, Hololens 2 synchronization functionality as a separate, open-source platform called SynchronizAR. Finally, we present the qualitative results of demonstrating ClimbAR at two climbing gyms as well as the quantitative results of analyzing SynchronizAR's spatial alignment accuracy through two proto-user studies. We find an average rotational alignment error of 12.8338 degrees and an average translational alignment error of 0.0385 meters when using SynchronizAR for collaborative layout tasks involving two users
Evaluation of Augmented Reality for Collaborative Environments
Full text linkThe intersection of intelligent analytics and climbing is relatively nascent. Various forms of climbing have begun to grow exceedingly fast in recent years, with a combination of three sub-categories even having become adopted into the Olympic games (i.e. bouldering, speed climbing and lead climbing). With a growing community, injuries due to the inherent health risks of climbing will undoubtedly grow as well. We aim to address these health concerns by helping lay the groundwork for future preventive technologies that help climbers better understand and plan their routes.
Multiple works have applied mobile or projector-based augmented reality or tools such as computer vision and deep learning to help with problems such as climbing route difficulty assessment, games for user retention in the commercial setting and fall protection via wall monitoring. However, few if any, examine collaborative problems in climbing with real-time, augmented reality systems using modern, head-mounted displays.
To this end, we frame our examination of the climbing space as a collaborative, layout and design task, thereby targeting collaborative, route setting as the specific application space. We present ClimbAR, an open-source, collaborative, real-time, augmented reality application running natively on the Hololens 2 that allows climbers to virtually and collaboratively, set climbing holds in their physical environments. Due to the necessary infrastructure required to develop ClimbAR, we also present its core, Hololens 2 synchronization functionality as a separate, open-source platform called SynchronizAR. Finally, we present the qualitative results of demonstrating ClimbAR at two climbing gyms as well as the quantitative results of analyzing SynchronizAR's spatial alignment accuracy through two proto-user studies. We find an average rotational alignment error of 12.8338 degrees and an average translational alignment error of 0.0385 meters when using SynchronizAR for collaborative layout tasks involving two users
Mixed Reality for Precision in Joint Replacement Surgeries: Bridging the Gap from Planning to Execution
No full textThe precision of surgical interventions, particularly in orthopedic surgeries, faces notable challenges due to the discrepancy between detailed pre-operative plans and their execution during surgery. This gap stems from the inability of traditional methods to provide direct guidance intra-operatively and adapt to real-time variations and anatomical shifts. These methods, which rely heavily on the surgeon's experience and manual alignment of tools with anatomical landmarks, often result in inconsistent outcomes. The difference in performance between novice and experienced surgeons highlights this issue, emphasizing the need for techniques that can bridge this gap effectively. In this context, mixed reality (MR) technologies, especially optical see-through head-mounted displays (OST-HMDs), have been identified as a potential solution to bridge this gap by overlaying digital information directly onto the surgical field. Nonetheless, the effective integration of MR into surgical workflows encounters several impediments.
This dissertation endeavors to address a subset of these challenges through a comprehensive research approach designed to enhance MR-guided joint replacement surgeries. To start with, we assess the capability of depth sensing technologies, including Time-of-Flight (ToF) cameras and stereo RGB cameras, to facilitate marker-less registration. This is a pivotal step for achieving an accurate alignment of virtual and physical spaces. Although these technologies hold potential, their application is restrained by factors like sensor accuracy under varying lighting conditions and occlusion issues. To overcome these limitations, we introduced novel methodologies aimed at enhancing the precision of the registration processes, including the development of a continuous drift correction mechanism and the implementation of near-infrared fluorescent markers for robust tracking of anatomical features.
Through comprehensive evaluations, including comparative analyses with traditional methods and FDA-cleared non-MR guiding solutions, our research demonstrates the viability and improved accuracy of the proposed solutions in MR-guided orthopedic surgeries. This research suggests that MR technologies could enhance surgical precision, potentially reduce operation times, and ultimately improve patient outcomes. While these benefits are promising, ongoing development and clinical validations are necessary to fully realize the potential of MR in diverse surgical applications
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Towards Interpretable Machine Learning in Medical Image Analysis
No full textOver the past few years, ML has demonstrated human expert level performance in many medical image analysis tasks. However, due to the black-box nature of classic deep ML models, translating these models from the bench to the bedside to support the corresponding stakeholders in the desired tasks brings substantial challenges. One solution is interpretable ML, which attempts to reveal the working mechanisms of complex models. From a human-centered design perspective, interpretability is not a property of the ML model but an affordance, i.e., a relationship between algorithm and user. Thus, prototyping and user evaluations are critical to attaining solutions that afford interpretability. Following human-centered design principles in highly specialized and high stakes domains, such as medical image analysis, is challenging due to the limited access to end users. This dilemma is further exacerbated by the high knowledge imbalance between ML designers and end users. To overcome the predicament, we first define 4 levels of clinical evidence that can be used to justify the interpretability to design ML models. We state that designing ML models with 2 levels of clinical evidence: 1) commonly used clinical evidence, such as clinical guidelines, and 2) iteratively developed clinical evidence with end users are more likely to design models that are indeed interpretable to end users. In this dissertation, we first address how to design interpretable ML in medical image analysis that affords interpretability with these two different levels of clinical evidence. We further highly recommend formative user research as the first step of the interpretable model design to understand user needs and domain requirements. We also indicate the importance of empirical user evaluation to support transparent ML design choices to facilitate the adoption of human-centered design principles. All these aspects in this dissertation increase the likelihood that the algorithms afford interpretability and enable stakeholders to capitalize on the benefits of interpretable ML. In detail, we first propose neural symbolic reasoning to implement public clinical evidence into the designed models for various routinely performed clinical tasks. We utilize the routinely applied clinical taxonomy for abnormality classification in chest x-rays. We also establish a spleen injury grading system by strictly following the clinical guidelines for symbolic reasoning with the detected and segmented salient clinical features.
Then, we propose the entire interpretable pipeline for UM prognostication with cytopathology images. We first perform formative user research and found that pathologists believe cell composition is informative for UM prognostication. Thus, we build a model to analyze cell composition directly. Finally, we conduct a comprehensive user study to assess the human factors of human-machine teaming with the designed model, e.g., whether the proposed model indeed affords interpretability to pathologists. The human-centered design process is proven to be truly interpretable to pathologists for UM prognostication. All in all, this dissertation introduces a comprehensive human-centered design for interpretable ML solutions in medical image analysis that affords interpretability to end users
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
