- Browse by Subject
Browsing by Subject "Detection"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
Item COVID-19 and saliva: A primer for dental health care professionals(Wiley, 2020-08-23) Srinivasan, Mythily; Thyvalikakath, Thankam P.; Cook, Blaine N.; Zero, Domenick T.; Oral Pathology, Medicine and Radiology, School of DentistryTo contain the COVID‐19 pandemic, it is essential to find methods that can be used by a wide range of health care professionals to identify the virus. The less potential contagious nature of the collection process, the ease of collection and the convenience of frequent collection for real‐time monitoring makes saliva an excellent specimen for home‐based collection for epidemiological investigations. With respect to COVID‐19, the use of saliva offers the added advantages of greater sensitivity and potential for detection at an early stage of infection. However, the advantages from a diagnostic perspective also reflect the potential risk to dental professionals from saliva from infected patients. Although not validated in COVID‐19 patients, but by extension from studies of SARS‐CoV‐1 studies, it is suggested that using antimicrobial mouthrinses such as chlorhexidine, hydrogen peroxide or sodium hypochlorite solutions could reduce the viral load in saliva droplets and reduce the risk of direct transmission. Because large saliva droplets could deposit on inanimate surfaces, changing the personal protective equipment including the clinical gown, gloves, masks, protective eye wear and face shield between patients, as well as decontamination of the work surfaces in the clinic, could reduce the risk of indirect contact transmission.Item Detection and analyzing plane of non-cavitated approximal caries by cross-polarized optical coherence tomography (CP-OCT)(Elsevier, 2021-07) Xing, Haixia; Eckert, George J.; Ando, Masatoshi; Cariology, Operative Dentistry and Dental Public Health, School of DentistryObjective The objective was to assess the detection ability and the effect of analyzing plane of CP-OCT for non-cavitated approximal caries. Methods Thirty human extracted premolars were selected based on micro-computed tomography [μ-CT: μ- CT = 0: sound (n = 12), μ-CT = 1/2: caries into outer-/inner-half of enamel (n = 6 each), μ-CT = 3: caries into outer one-third of dentine (n = 6)]. Teeth were mounted in a custommade device to simulate approximal contact, and scanned from the marginal ridge above the contact area. CP-OCT images were analyzed by deepest caries extension from horizontal and coronal planes, and repeated 48-hrs later. Sensitivity, specificity,percent correct, area under the ROC curve (Az), intra-examiner repeatability and correlation with μ-CT were determined. Results Sensitivity/specificity/Az for Horizontalplane, Coronal-plane, and Deepest from both planes were 94percent/58percent/0.76,81percent/100percent/0.90, and 94 %/58 %/0.82. Coronal-plane had significantly higher specificity than Horizontal-plane and Deepest (p = 0.004) but Horizontal-plane and Deepest were not different (p = 1.00). Horizontal-plane had significantly lower Az than Deepest (p = 0.048), but Coronal-plane was not different than Horizontal-plane (p = 0.07) or Deepest (p = 0.20). Correlation coefficients were Horizontal-plane (0.53, p < 0.001), Coronal-plane (0.84, p < 0.001), and Deepest (0.66, p < 0.001). Conclusion Within the limitations of this study, CP-OCT could be used to detect non-cavitated approximal caries. Analysis using the Coronal-plane is superior to the Horizontal-plane. Clinical Significance: It is challenging to detect non-cavitated approximal caries clinically due to the adjacent tooth. CP-OCT is a nondestructive, no ionized-radiation caries detection technique. CP-OCT seems suitable to detect non-cavitated approximal caries and observing the Coronal-plane appears better than Horizontal-plane.Item Detection of artificial enamel caries-like lesions with a blue hydroxyapatite-binding porosity probe(Elsevier, 2023-08) Lippert, Frank; Eder, Jennifer S.; Eckert, George J.; Mangum, Jonathan; Hegarty, Kerry; Cariology, Operative Dentistry and Dental Public Health, School of DentistryObjectives This in vitro study investigated the ability of a blue protein-based hydroxyapatite porosity probe to selectively detect artificial enamel caries-like lesions of varying severities. Methods Artificial caries-like lesions were formed in enamel specimens using a hydroxyethylcellulose-containing lactic acid gel for 4/12/24/72 or 168 h. One untreated group was used as a control. The probe was applied for 2 min and unbound probe rinsed off with deionized water. Surface color changes were determined spectrophotometrically (L*a*b* color space) and with digital photography. Lesions were characterized using quantitative light-induced fluorescence (QLF), Vickers surface microhardness, and transverse microradiography (TMR). Data were analyzed using one-way ANOVA. Results Digital photography did not reveal any discoloration in unaffected enamel. However, all lesions stained blue with color intensity positively correlated with demineralization times. The color data reflected similar trends: lesions became significantly darker (L* decreased) and bluer (b* decreased), while overall color differences (ΔE) increased significantly after probe application (4-h lesion, mean±standard deviation: ΔL*=-2.6 ± 4.1/Δb*=0.1 ± 0.8/ΔE=5.5 ± 1.3 vs. 168-h lesion: ΔL*=-17.3 ± 1.1/Δb*=-6.0 ± 0.6/ΔE=18.7 ± 1.1). TMR analysis revealed distinct differences in integrated mineral loss (ΔZ) and lesion depth (L) between demineralization times (4-h lesion: ΔZ=391±190 vol%min × µm/L = 18.1 ± 10.9 µm vs. 168-h lesion: ΔZ=3606±499 vol%min × µm/L = 111.9 ± 13.9 µm). QLF and microhardness were also able to differentiate between demineralization times. L and ΔZ strongly correlated (Pearson correlation coefficient [r]) with Δb* (L vs. Δb*: r=-0.90/ΔZ vs. Δb*: r=-0.90), ΔE (r = 0.85/r = 0.81), and ΔL* (r=-0.79/r=-0.73). Conclusion Considering the limitations of this study, the blue protein-based hydroxyapatite-binding porosity probe appears to be sufficiently sensitive to distinguish between unaffected enamel and artificial caries-like lesions. Clinical significance Early detection of enamel caries lesions remains one of the most critical aspects in the diagnosis and management of dental caries. This study highlighted the potential of a novel porosity probe in detecting artificial caries-like demineralization by objective means.Item Exploration of Deep Learning Applications on an Autonomous Embedded Platform (Bluebox 2.0)(2019-12) Katare, Dewant; El-Sharkawy, Mohamed; Rizkalla, Maher; Kim, Dongsoo StephenAn Autonomous vehicle depends on the combination of latest technology or the ADAS safety features such as Adaptive cruise control (ACC), Autonomous Emergency Braking (AEB), Automatic Parking, Blind Spot Monitor, Forward Collision Warning or Avoidance (FCW or FCA), Lane Departure Warning. The current trend follows incorporation of these technologies using the Artificial neural network or Deep neural network, as an imitation of the traditionally used algorithms. Recent research in the field of deep learning and development of competent processors for autonomous or self-driving car have shown amplitude of prospect, but there are many complexities for hardware deployment because of limited resources such as memory, computational power, and energy. Deployment of several mentioned ADAS safety feature using multiple sensors and individual processors, increases the integration complexity and also results in the distribution of the system, which is very pivotal for autonomous vehicles. This thesis attempts to tackle two important adas safety feature: Forward collision Warning, and Object Detection using the machine learning and Deep Neural Networks and there deployment in the autonomous embedded platform. 1. A machine learning based approach for the forward collision warning system in an autonomous vehicle. 2. 3-D object detection using Lidar and Camera which is primarily based on Lidar Point Clouds. The proposed forward collision warning model is based on the forward facing automotive radar providing the sensed input values such as acceleration, velocity and separation distance to a classifier algorithm which on the basis of supervised learning model, alerts the driver of possible collision. Decision Tress, Linear Regression, Support Vector Machine, Stochastic Gradient Descent, and a Fully Connected Neural Network is used for the prediction purpose. The second proposed methods uses object detection architecture, which combines the 2D object detectors and a contemporary 3D deep learning techniques. For this approach, the 2D object detectors is used first, which proposes a 2D bounding box on the images or video frames. Additionally a 3D object detection technique is used where the point clouds are instance segmented and based on raw point clouds density a 3D bounding box is predicted across the previously segmented objects.Item HPV-related oropharyngeal cancer: a review on burden of the disease and opportunities for prevention and early detection(Taylor & Francis, 2019-05-07) Timbang, Mary Roz; Sim, Michael W.; Bewley, Arnaud F.; Farwell, D. Gregory; Mantravadi, Avinash; Moore, Michael G.; Otolaryngology -- Head and Neck Surgery, School of MedicineThe incidence of oropharyngeal cancer (OPC) related to infection with human papillomavirus (HPV) is rising, making it now the most common HPV-related malignancy in the United States. These tumors present differently than traditional mucosal head and neck cancers, and those affected often lack classic risk factors such as tobacco and alcohol use. Currently, there are no approved approaches for prevention and early detection of disease, thus leading many patients to present with advanced cancers requiring intense surgical or nonsurgical therapies resulting in significant side effects and cost to the health-care system. In this review, we outline the evolving epidemiology of HPV-related OPC. We also summarize the available evidence corresponding to HPV-related OPC prevention, including efficacy and safety of the HPV vaccine in preventing oral HPV infections. Finally, we describe emerging techniques for identifying and screening those who may be at high risk for developing these tumors.Item Kidney Health for Everyone Everywhere - From Prevention to Detection and Equitable Access to Care(Medknow Publications, 2020-03) Li, Philip Kam-Tao; Garcia-Garcia, Guillermo; Lui, Siu-Fai; Andreoli, Sharon; Fung, Winston Wing-Shing; Hradsky, Anne; Kumaraswami, Latha; Liakopoulos, Vassilios; Rakhimova, Ziyoda; Saadi, Gamal; Strani, Luisa; Ulasi, Ifeoma; Kalantar-Zadeh, Kamyar; World Kidney Day Steering Committee; Medicine, School of MedicineThe global burden of chronic kidney disease (CKD) is rapidly increasing with a projection of becoming the 5th most common cause of years of life lost globally by 2040. Aggravatingly, CKD is a major cause of catastrophic health expenditure. The costs of dialysis and transplantation consume up to 3% of the annual healthcare budget in high-income countries. Crucially, however, the onset and progression of CKD is often preventable. In 2020, the World Kidney Day campaign highlights the importance of preventive interventions - be it primary, secondary or tertiary. This complementing article focuses on outlining and analyzing measures that can be implemented in every country to promote and advance CKD prevention. Primary prevention of kidney disease should focus on the modification of risk factors and addressing structural abnormalities of the kidney and urinary tracts, as well as exposure to environmental risk factors and nephrotoxins. In persons with pre-existing kidney disease, secondary prevention, including blood pressure optimization and glycemic control, should be the main goal of education and clinical interventions. In patients with advanced CKD, management of co-morbidities such as uremia and cardiovascular disease is a highly recommended preventative intervention to avoid or delay dialysis or kidney transplantation. Political efforts are needed to proliferate the preventive approach. While national policies and strategies for non-communicable diseases might be present in a country, specific policies directed toward education and awareness about CKD screening, management and treatment are often lacking. Hence, there is an urgent need to increase the awareness of the importance of preventive measures throughout populations, professionals and policy makers.Item Large-scale annotated dataset for cochlear hair cell detection and classification(bioRxiv, 2023-09-01) Buswinka, Christopher J.; Rosenberg, David B.; Simikyan, Rubina G.; Osgood, Richard T.; Fernandez, Katharine; Nitta, Hidetomi; Hayashi, Yushi; Liberman, Leslie W.; Nguyen, Emily; Yildiz, Erdem; Kim, Jinkyung; Jarysta, Amandine; Renauld, Justine; Wesson, Ella; Thapa, Punam; Bordiga, Pierrick; McMurtry, Noah; Llamas, Juan; Kitcher, Siân R.; López-Porras, Ana I.; Cui, Runjia; Behnammanesh, Ghazaleh; Bird, Jonathan E.; Ballesteros, Angela; Vélez-Ortega, A. Catalina; Edge, Albert S. B.; Deans, Michael R.; Gnedeva, Ksenia; Shrestha, Brikha R.; Manor, Uri; Zhao, Bo; Ricci, Anthony J.; Tarchini, Basile; Basch, Martin; Stepanyan, Ruben S.; Landegger, Lukas D.; Rutherford, Mark; Liberman, M. Charles; Walters, Bradley J.; Kros, Corné J.; Richardson, Guy P.; Cunningham, Lisa L.; Indzhykulian, Artur A.; Otolaryngology -- Head and Neck Surgery, School of MedicineOur sense of hearing is mediated by cochlear hair cells, localized within the sensory epithelium called the organ of Corti. There are two types of hair cells in the cochlea, which are organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains a few thousands of hair cells, and their survival is essential for our perception of sound because they are terminally differentiated and do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. However, the sheer number of cells along the cochlea makes manual quantification impractical. Machine learning can be used to overcome this challenge by automating the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, human, pig and guinea pig cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 90'000 hair cells, all of which have been manually identified and annotated as one of two cell types: inner hair cells and outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to supply other groups within the hearing research community with the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.Item Retrospective, observational, cross-sectional study of detection of recurrent Barrett's esophagus and dysplasia in post-ablation patients with adjunctive use of wide-area transepithelial sample (WATS-3D)(Hellenic Society of Gastroenterology, 2022) Fatima, Hala; Wajid, Maryiam; Hamade, Nour; Han, Yan; Kessler, William; Dewitt, John; Rex, Douglas; Imperiale, Thomas; Medicine, School of MedicineBackground: Barrett's esophagus (BE) and dysplasia are often missed by Seattle protocol biopsies (SPB). Wide-area transepithelial sampling with 3-dimensional computer-assisted analysis (WATS-3D) with SPB improves detection in treatment-naïve patients. We aimed to determine to what extent WATS-3D adds to SPB in the detection of non-dysplastic BE (NDBE) and dysplasia in patients undergoing post-endoscopic eradication therapy (EET). Methods: This retrospective, observational, cross-sectional study included patients who presented for post-EET surveillance with SPB and WATS-3D sampling from April 2019 to February 2020. BE patients with no previous EET were excluded. For the outcomes of NDBE and any dysplastic/neoplastic finding, we calculated both relative and absolute increases in yield by WATS-3D over SBP. Results: In 78 patients [mean age 68±10.4 years, 66 (84.6%) male], the prevalence of NDBE, any dysplastic/neoplastic finding, and any abnormality (NDBE or dysplasia/neoplasia) were 53.85%, 10.26%, and 55.13%. The absolute increase in yield of NDBE with WATS-3D over SPB was 26.9% (95% confidence interval [CI] 17.95-37.18%), with the number needed to treat (NNT) 3.71 (95%CI 2.69-5.57) and a relative increase in yield of 100% (95%CI 53.33-188.25%). For dysplasia/neoplasia, the absolute increase in yield was 6.4% (95%CI 1.28-12.82%), NNT 15.6 (95%CI 7.8-78.0), and relative increase of 167% (95%CI 33.33%-infinity). For any abnormal finding, the absolute increase in yield was 26.9% (95%CI 16.67-37.18%), NNT 3.71 (95%CI 2.69-6.00), and relative increase in yield 95% (95%CI 50-176.92%). Conclusions: WATS-3D with SPB improves the detection of residual/recurrent BE and dysplasia in post-ablation BE. However, randomized controlled trials are needed to validate these findings.Item Understanding metric-related pitfalls in image analysis validation(ArXiv, 2023-09-25) Reinke, Annika; Tizabi, Minu D.; Baumgartner, Michael; Eisenmann, Matthias; Heckmann-Nötzel, Doreen; Kavur, A. Emre; Rädsch, Tim; Sudre, Carole H.; Acion, Laura; Antonelli, Michela; Arbel, Tal; Bakas, Spyridon; Benis, Arriel; Blaschko, Matthew B.; Buettner, Florian; Cardoso, M. Jorge; Cheplygina, Veronika; Chen, Jianxu; Christodoulou, Evangelia; Cimini, Beth A.; Collins, Gary S.; Farahani, Keyvan; Ferrer, Luciana; Galdran, Adrian; Van Ginneken, Bram; Glocker, Ben; Godau, Patrick; Haase, Robert; Hashimoto, Daniel A.; Hoffman, Michael M.; Huisman, Merel; Isensee, Fabian; Jannin, Pierre; Kahn, Charles E.; Kainmueller, Dagmar; Kainz, Bernhard; Karargyris, Alexandros; Karthikesalingam, Alan; Kenngott, Hannes; Kleesiek, Jens; Kofler, Florian; Kooi, Thijs; Kopp-Schneider, Annette; Kozubek, Michal; Kreshuk, Anna; Kurc, Tahsin; Landman, Bennett A.; Litjens, Geert; Madani, Amin; Maier-Hein, Klaus; Martel, Anne L.; Mattson, Peter; Meijering, Erik; Menze, Bjoern; Moons, Karel G. M.; Müller, Henning; Nichyporuk, Brennan; Nickel, Felix; Petersen, Jens; Rafelski, Susanne M.; Rajpoot, Nasir; Reyes, Mauricio; Riegler, Michael A.; Rieke, Nicola; Saez-Rodriguez, Julio; Sánchez, Clara I.; Shetty, Shravya; Summers, Ronald M.; Taha, Abdel A.; Tiulpin, Aleksei; Tsaftaris, Sotirios A.; Van Calster, Ben; Varoquaux, Gaël; Yaniv, Ziv R.; Jäger, Paul F.; Maier-Hein, Lena; Pathology and Laboratory Medicine, School of MedicineValidation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.