Medical Applications

Behavioral Analysis of Turbulent Exhale Flows
Authors: Shane Transue, Sayed Mohsin Reza, Ann C. Halbower, Min-Hyung Choi

Description: Dense exhale flow through carbon-dioxide spectral imaging introduces a pivotal trajectory within non-contact respiratory analysis that consolidates several pulmonary evaluations into a single coherent monitoring process. Due to technical limitations and the limited exploration of respiratory analysis through this non-contact technique, this method has not been fully utilized to extract high-level respiratory behaviors through turbulent exhale analysis. In this work, we present a structural foundation for respiratory analysis of turbulent exhale flows through the visualization of dense carbon-dioxide density distributions using precisely refined thermal imaging device to target high-resolution respiratory modeling. We achieve spatial and temporal high-resolution flow reconstructions through the cooperative development of a thermal camera dedicated to respiratory analysis to drastically improve the precision of current exhale imaging methods. We then model turbulent exhale behaviors using a heuristic volumetric flow reconstruction process to generate sparse flow exhale models. Together these contributions allow us to target the acquisition of numerous respiratory behaviors including, breathing rate, exhale strength and capacity, towards insights into lung functionality and tidal volume estimation.
Download Links: [ PDF ] [ YouTube ] [ YouTube2 ]
Non-Contact Comprehensive Breathing Analysis using Thermal Thin Medium
Authors: Breawn Schoun, Shane Transue, Ann C. Halbower, Min-Hyung Choi

Description: Respiration monitoring methods that are both accurate and comfortable are highly sought after in the medical field. No existing method of respiration monitoring perfectly satisfies both of these criteria; each method is a trade-off between comfort and accuracy. Contact methods, which require placing sensors directly on the patient's body, provide reliable measurements, but are uncomfortable for the patient, which alters their natural breathing behaviors. Conversely, non-contact methods monitor respiration remotely and comfortably, but with lower accuracy. We present a method of respiratory analysis that is non-contact, but also measures the exhaled air of a human subject directly through a medium-based exhale visualization technique. In this method, we place a thin medium perpendicular to the exhaled airflow of an individual, and use a thermal camera to record the heat signature from the exhaled breath on the opposite side of the material. Breathing rate and respiratory behaviors are extracted from the thermal data in real time. Our proposed respiration monitoring technique accurately reports breathing rate, and provides other information not obtainable through other non-contact methods. This method can be implemented as a small low-cost device for ease of use in a clinical environment.
Download Links: [ PDF ] [ YouTube ]
Thermal-Depth Fusion for Occluded Body Skeletal Posture Estimation
Authors: Shane Transue, Phuc Nguyen, Tam Vu, Min-Hyung Choi

Description: Reliable occluded skeletal posture estimation is a fundamentally challenging problem for ision-based monitoring techniques. This is due to several imaging related challenges introduced by existing depth-based pose estimation techniques that fail to provide accurate joint position estimates when the line of sight between the imaging device and the patient is obscured by an occluding material. In this work, we present a new method of estimating skeletal posture in occluded applications using both depth and thermal imaging through volumetric modeling and introduce a new occluded ground-truth tracking method inspired by modern motion capture solutions. Using this integrated volumetric model, we utilize Convolutional Neural Networks to characterize and identify volumetric thermal distributions that match trained skeletal posture estimates which includes disconnected skeletal definitions and allows correct posture estimation in highly ambiguous cases. We demonstrate this approach by correctly identifying common sleep postures that present challenging cases for current skeletal joint estimations, obtaining an average classification accuracy of ~94.45%.
Download Links: [ PDF ] [ IEEE Xplore ] [ YouTube ]
WiKiSpiro: Non-contact Respiration volume Monitoring during Sleep
Authors: Phuc Nguyen, Shane Transue, Min-Hyung Choi, Ann C. Halbower, Tam Vu

Description: Respiration volume has been widely used as an important indication for diagnosis and treatment of pulmonary diseases and other health care related issues such as critically ill patients neonatal ventilation, post-operative monitoring and various others. Most of existing technologies for respiration volume monitoring require physical contact with the human body. While wireless-based approaches have also been discussed in the literature, there are still limitations in terms of estimation accuracy and time efficiency preventing these approaches from being realized in practice. In this paper, we present an automated, wireless-based, vision-supervised system, called WiKiSpiro, for monitoring an individual’s respiration volume. In particular, we present a system design encompassing a wireless device, motion tracking and control system, and a set of methods to accurately derive breathing volume from the reflected signal and to address challenges caused by body movement and posture changes. We present our preliminary results of WikiSpiro, and identify possible challenges for future research and development.
Download Links: [ PDF ] [ ACM Digital Library ] [ YouTube ]
Real-time Tidal Volume Estimation using Iso-surface Reconstruction
Authors: Shane Transue, Phuc Nguyen, Tam Vu, Min-Hyung Choi

Description: Breathing volume measurement has long been an important physiological indication widely used for the diagnosis and treatment of pulmonary diseases. However, most of existing breathing volume monitoring techniques require either physical contact with the patient or are prohibitively expensive. In this paper we present an automated and inexpensive non-contact, vision-based method for monitoring an individual's tidal volume, which is extracted from a three-dimensional (3D) chest surface reconstruction from a single depth camera. In particular, formulating the respiration monitoring process as a 3D space-time volumetric representation, we introduce a real-time surface reconstruction algorithm to generate omni-direction deformation states of a patient's chest while breathing, which reflects the change in tidal volume over time. These deformation states are then used to estimate breathing volume through a per-patient correlation metric acquired through a Bayesian-network learning process. Through prototyping and implementation, our results indicate that we have achieved 92.2% to 94.19% accuracy in the tidal volume estimations through the experimentation based on the proposed vision-based method.
Download Links: [ PDF ] [ IEEE Xplore ] [ YouTube ]
Fast Volume Preservation for a Mass-Spring System

Authors: Min Hong, Sunwha Jung, Min-Hyung Choi, Samuel Welch

Description: This article presents a new method to model fast volume preservation of a mass-spring system to achieve a realistic and efficient deformable object animation, without using internal volumetric meshing. With this method the simulated behavior is comparable to a finite-element-method-based model at a fraction of the computational cost.
Download Links: [ PDF ]
Volume-Preserved Human Organs for Surgical Simulation

Authors: Sunwha Jung, Min Hong, Min-Hyung Choi

Description: One of the challenging problems in surgical simulation is to reduce the computational cost to achieve interactive refresh rates for both haptic and visualization devices, while maintaining reasonable behavioural realism. Since human organs are predominantly based on water, they preserve overall volume during deformation. Therefore, representing the volume-preserved behaviour in dynamic system is essential to deliver realistic organ reaction in surgical simulation. Many existing methods for modeling and simulation of human organs often neglect the volume preservation due to its computational complexities. Otherwise, some previous volume preservation methods alter the material properties, resulting in hardened and unnatural dynamic behaviour. This paper presents a novel method to model human organs with volume preservation. It keeps the material properties intact and requires virtually no additional computation cost to address both computational efficiency and visual realism. Our method incorporates an implicit volume constraint on a simple mass-spring system. Experiments show that the object level volume is well maintained even under high pressure. Proposed method makes a realistic human organ simulation possible at an interactive rate with almost no additional computational cost.
Download Links: [ PDF ]
Integrated Term Weighting, Visualization, and User Interface Development for Bioinformation Retrieval

Authors: Min Hong, Anis Karimpour-fard, Steve Russell, Lawrence Hunter

Description: This project implements an integrated biological information website that classifies technical documents, learns about users' interests, and offers intuitive interactive visualization to navigate vast information spaces. The effective use of modern software engineering principles, system environments, and development approaches is demonstrated. Straightforward yet powerful document characterization strategies are illustrated, helpful visualization for effective knowledge transfer is shown, and current user interface methodologies are applied. A specific success of note is the collaboration of disparately skilled specialists to deliver a flexible integrated prototype in a rapid manner that meets user acceptance and performance goals. The domain chosen for the demonstration is breast cancer, using a corpus of abstracts from publications obtained online from Medline. The terms in the abstracts are extracted by word stemming and a stop list, and are encoded in vectors. A TF-IDF technique is implemented to calculate similarity scores between a set of documents and a query. Polysemy and synonyms are explicitly addressed. Groups of related and useful documents are identified using interactive visual displays such as a spiral graph that represents of the overall similarity of documents. K-means clustering of the similarities among a document set is used to display a 3-D relationship map. User identities are established and updated by observing the patterns of terms used in their queries, and from login site locations. Explicit considerations of changing user category profiles, site stakeholders, information modeling, and networked technologies are pointed out.
Download Links: [ PDF ]