All Publications

  • A Scoping Review of Artificial Intelligence Detection of Voice Pathology: Challenges and Opportunities. Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery Liu, G. S., Jovanovic, N., Sung, C. K., Doyle, P. C. 2024


    Survey the current literature on artificial intelligence (AI) applications for detecting and classifying vocal pathology using voice recordings, and identify challenges and opportunities for advancing the field forward.PubMed, EMBASE, CINAHL, and Scopus databases.A comprehensive literature search was performed following the Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews guidelines. Peer-reviewed journal articles in the English language were included if they used an AI approach to detect or classify pathological voices using voice recordings from patients diagnosed with vocal pathologies.Eighty-two studies were included in the review between the years 2000 and 2023, with an increase in publication rate from one study per year in 2012 to 10 per year in 2022. Seventy-two studies (88%) were aimed at detecting the presence of voice pathology, 24 (29%) at classifying the type of voice pathology present, and 4 (5%) at assessing pathological voice using the Grade, Roughness, Breathiness, Asthenia, and Strain scale. Thirty-six databases were used to collect and analyze speech samples. Fourteen articles (17%) did not provide information about their AI model validation methodology. Zero studies moved beyond the preclinical and offline AI model development stages. Zero studies specified following a reporting guideline for AI research.There is rising interest in the potential of AI technology to aid the detection and classification of voice pathology. Three challenges-and areas of opportunities-for advancing this research are heterogeneity of databases, lack of clinical validation studies, and inconsistent reporting.

    View details for DOI 10.1002/ohn.809

    View details for PubMedID 38738887

  • Estimation of Cochlear Implant Insertion Depth Using 2D-3D Registration of Postoperative X-Ray and Preoperative CT Images. Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology Liu, G. S., Cooperman, S. P., Neves, C. A., Blevins, N. H. 2024


    To improve estimation of cochlear implant (CI) insertion depth in postoperative skull x-rays using synthesized information from preoperative CT scans.Retrospective cohort.Tertiary referral center.Ten adult cochlear implant recipients with preoperative and postoperative temporal bone computed tomography (CT)scans and postoperative skull x-ray imaging.Postoperative x-rays and digitally reconstructed radiographs (DRR) from preoperative CTs were registered using 3D Slicer and MATLAB to enhance localization of the round window and modiolus. Angular insertion depth (AID) was estimated in unmodified and registration-enhanced x-rays and DRRs in the cochlear view. Linear insertion depth (LID) was estimated in registered images by two methods that localized the proximal CI electrode or segmented the cochlea. Ground truth assessments were made in postoperative CTs.Errors of insertion depth estimates were calculated relative to ground truth measurements and compared with paired t tests. Pearson correlation coefficient was used to assess inter-rater reliability of two reviewer's measurements of AID in unmodified x-rays.In postoperative x-rays, AID estimation errors were similar with and without registration enhancement (-1.3 ± 20.7° and -4.8 ± 24.9°, respectively; mean ± SD; p = 0.6). AID estimation in unmodified x-rays demonstrated strong interrater agreement (ρ = 0.79, p < 0.05) and interrater differences (-15.0 ± 35.3°) comparable to estimate errors. Registering images allowed measurement of AID in the cochlear view with estimation errors of 14.6 ± 30.6° and measurement of LID, with estimate errors that were similar between proximal electrode localization and cochlear segmentation methods (-0.9 ± 2.2 mm and -2.1 ± 2.7 mm, respectively; p = 0.3).2D-3D image registration allows measurement of AID in the cochlear view and LID using postoperative x-rays and preoperative CT imaging. The use of this technique may reduce the need for postimplantation CT studies to assess these metrics of CI electrode position. Further work is needed to improve the accuracy of AID assessment in the postoperative x-ray view with registered images compared with established methods.

    View details for DOI 10.1097/MAO.0000000000004100

    View details for PubMedID 38270174

  • End-to-end deep learning classification of vocal pathology using stacked vowels. Laryngoscope investigative otolaryngology Liu, G. S., Hodges, J. M., Yu, J., Sung, C. K., Erickson-DiRenzo, E., Doyle, P. C. 2023; 8 (5): 1312-1318


    Advances in artificial intelligence (AI) technology have increased the feasibility of classifying voice disorders using voice recordings as a screening tool. This work develops upon previous models that take in single vowel recordings by analyzing multiple vowel recordings simultaneously to enhance prediction of vocal pathology.Voice samples from the Saarbruecken Voice Database, including three sustained vowels (/a/, /i/, /u/) from 687 healthy human participants and 334 dysphonic patients, were used to train 1-dimensional convolutional neural network models for multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings. Three models were trained: (1) a baseline model that analyzed individual vowels in isolation, (2) a stacked vowel model that analyzed three vowels (/a/, /i/, /u/) in the neutral pitch simultaneously, and (3) a stacked pitch model that analyzed the /a/ vowel in three pitches (low, neutral, and high) simultaneously.For multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings, the stacked vowel model demonstrated higher performance compared with the baseline and stacked pitch models (F1 score 0.81 vs. 0.77 and 0.78, respectively). Specifically, the stacked vowel model achieved higher performance for class-specific classification of hyperfunctional dysphonia voice samples compared with the baseline and stacked pitch models (F1 score 0.56 vs. 0.49 and 0.50, respectively).This study demonstrates the feasibility and potential of analyzing multiple sustained vowel recordings simultaneously to improve AI-driven screening and classification of vocal pathology. The stacked vowel model architecture in particular offers promise to enhance such an approach.AI analysis of multiple vowel recordings can improve classification of voice pathologies compared with models using a single sustained vowel and offer a strategy to enhance AI-driven screening of voice disorders.3.

    View details for DOI 10.1002/lio2.1144

    View details for PubMedID 37899847

    View details for PubMedCentralID PMC10601590

  • Glomangiopericytoma Presenting as a Middle Ear Mass. The Laryngoscope Liu, G. S., Berry, G. J., Soltys, S. G., Blevins, N. H. 2023


    We describe an unusual case of glomangiopericytoma presenting as a mass filling the middle ear, enveloping the ossicles, and extending into the mastoid antrum without bony destruction. Management involved three surgeries and stereotactic radiosurgery, which achieved short-term local control with no evidence of disease on MRI imaging 12 months after radiation. Facial nerve function and hearing were preserved. This is the first report to our knowledge of a glomangiopericytoma presenting as a primary temporal bone lesion. Treatment with surgery and stereotactic radiosurgery for residual or recurrent disease is a reasonable approach to achieve local control and functional preservation. Laryngoscope, 2023.

    View details for DOI 10.1002/lary.30987

    View details for PubMedID 37615366

  • Automated Radiomic Analysis of Vestibular Schwannomas and Inner Ears Using Contrast-Enhanced T1-Weighted and T2-Weighted Magnetic Resonance Imaging Sequences and Artificial Intelligence. Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology Neves, C. A., Liu, G. S., El Chemaly, T., Bernstein, I. A., Fu, F., Blevins, N. H. 2023


    To objectively evaluate vestibular schwannomas (VSs) and their spatial relationships with the ipsilateral inner ear (IE) in magnetic resonance imaging (MRI) using deep learning.Cross-sectional study.A total of 490 adults with VS, high-resolution MRI scans, and no previous neurotologic surgery.MRI studies of VS patients were split into training (390 patients) and test (100 patients) sets. A three-dimensional convolutional neural network model was trained to segment VS and IE structures using contrast-enhanced T1-weighted and T2-weighted sequences, respectively. Manual segmentations were used as ground truths. Model performance was evaluated on the test set and on an external set of 100 VS patients from a public data set (Vestibular-Schwannoma-SEG).Dice score, relative volume error, average symmetric surface distance, 95th-percentile Hausdorff distance, and centroid locations.Dice scores for VS and IE volume segmentations were 0.91 and 0.90, respectively. On the public data set, the model segmented VS tumors with a Dice score of 0.89 ± 0.06 (mean ± standard deviation), relative volume error of 9.8 ± 9.6%, average symmetric surface distance of 0.31 ± 0.22 mm, and 95th-percentile Hausdorff distance of 1.26 ± 0.76 mm. Predicted VS segmentations overlapped with ground truth segmentations in all test subjects. Mean errors of predicted VS volume, VS centroid location, and IE centroid location were 0.05 cm3, 0.52 mm, and 0.85 mm, respectively.A deep learning system can segment VS and IE structures in high-resolution MRI scans with excellent accuracy. This technology offers promise to improve the clinical workflow for assessing VS radiomics and enhance the management of VS patients.

    View details for DOI 10.1097/MAO.0000000000003959

    View details for PubMedID 37464458

  • Signal to noise ratio quantifies the contribution of spectral channels to classification of human head and neck tissues ex vivo using deep learning and multispectral imaging. Journal of biomedical optics Liu, G. S., Shenson, J. A., Farrell, J. E., Blevins, N. H. 2023; 28 (1): 016004


    Significance: Accurate identification of tissues is critical for performing safe surgery. Combining multispectral imaging (MSI) with deep learning is a promising approach to increasing tissue discrimination and classification. Evaluating the contributions of spectral channels to tissue discrimination is important for improving MSI systems.Aim: Develop a metric to quantify the contributions of individual spectral channels to tissue classification in MSI.Approach: MSI was integrated into a digital operating microscope with three sensors and seven illuminants. Two convolutional neural network (CNN) models were trained to classify 11 head and neck tissue types using white light (RGB) or MSI images. The signal to noise ratio (SNR) of spectral channels was compared with the impact of channels on tissue classification performance as determined using CNN visualization methods.Results: Overall tissue classification accuracy was higher with use of MSI images compared with RGB images, both for classification of all 11 tissue types and binary classification of nerve and parotid ( p < 0.001 ). Removing spectral channels with SNR > 20 reduced tissue classification accuracy.Conclusions: The spectral channel SNR is a useful metric for both understanding CNN tissue classification and quantifying the contributions of different spectral channels in an MSI system.

    View details for DOI 10.1117/1.JBO.28.1.016004

    View details for PubMedID 36726664

  • Benign Ectopic Thyroid in the Lateral (Level II) Neck Compartment. Cureus Liu, G. S., Berry, G. J., Desai, K., Megwalu, U. C. 2022; 14 (2): e22140


    Ectopic thyroid most commonly presents in the midline and is typically associated with the absence of an orthotopic thyroid. Less commonly, ectopic thyroid can present in the lateral neck, typically with a coexisting orthotopic thyroid and abnormal pathology in either the ectopic or orthotopic thyroid tissue. This paper describes a rare case of a benign, ectopic thyroid in the lateral neck (level II) associated with a normal, benign orthotopic thyroid. This report illustrates clinical pearls for the management of this unusual entity.

    View details for DOI 10.7759/cureus.22140

    View details for PubMedID 35308702

    View details for PubMedCentralID PMC8920790

  • Deep learning classification of inverted papilloma malignant transformation using 3D convolutional neural networks and magnetic resonance imaging. International forum of allergy & rhinology Liu, G. S., Yang, A., Kim, D., Hojel, A., Voevodsky, D., Wang, J., Tong, C. C., Ungerer, H., Palmer, J. N., Kohanski, M. A., Nayak, J. V., Hwang, P. H., Adappa, N. D., Patel, Z. M. 2022


    Distinguishing benign inverted papilloma (IP) tumors from those that have undergone malignant transformation to squamous cell carcinoma (IP-SCC) is important but challenging to do preoperatively. Magnetic resonance imaging (MRI) can help differentiate these two entities, however no established method exists that can automatically synthesize all potentially relevant MRI image features to distinguish IP and IP-SCC. We explored a deep learning approach, using 3-dimensional convolutional neural networks (CNNs), to address this challenge.Retrospective chart reviews were performed at two institutions to create a dataset of preoperative MRIs with corresponding surgical pathology reports. The MRI dataset included all available MRI sequences in the axial plane, which were used to train, validate, and test three CNN models. Saliency maps were generated to visualize areas of MRIs with greatest influence on predictions.A total of 90 patients with IP (n = 64) or IP-SCC (n = 26) tumors were identified, with a total of 446 images of distinct MRI sequences for IP (n = 329) or IP-SCC (n = 117). The best CNN model, All-Net, demonstrated a sensitivity of 66.7%, specificity of 81.5%, overall accuracy of 77.9%, and ROC-AUC of 0.80 ([0.682 - 0.898], 95% confidence interval) for test classification performance. The other two models, Small-All-Net and Elastic-All-Net, showed similar performances.A deep learning approach with 3-dimensional CNNs can distinguish IP and IP-SCC with moderate test classification performance. Although CNNs demonstrate promise to enhance the prediction of IP-SCC using MRIs, more data is needed before they can reach the predictive value already established by human MRI evaluation. This article is protected by copyright. All rights reserved.

    View details for DOI 10.1002/alr.22958

    View details for PubMedID 34989484

  • Multispectral Imaging for Automated Tissue Identification of Normal Human Surgical Specimens. Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery Shenson, J. A., Liu, G. S., Farrell, J., Blevins, N. H. 2020: 194599820941013


    OBJECTIVE: Safe surgery requires the accurate discrimination of tissue intraoperatively. We assess the feasibility of using multispectral imaging and deep learning to enhance surgical vision by automated identification of normal human head and neck tissues.STUDY DESIGN: Construction and feasibility testing of novel multispectral imaging system for surgery.SETTING: Academic university hospital.SUBJECTS AND METHODS: Multispectral images of fresh-preserved human cadaveric tissues were captured with our adapted digital operating microscope. Eleven tissue types were sampled, each sequentially exposed to 6 lighting conditions. Two convolutional neural network machine learning models were developed to classify tissues based on multispectral and white-light color images (ARRInet-M and ARRInet-W, respectively). Blinded otolaryngology residents were asked to identify tissue specimens from white-light color images, and their performance was compared with that of the ARRInet models.RESULTS: A novel multispectral imaging system was developed with minimal adaptation to an existing digital operating microscope. With 81.8% accuracy in tissue identification of full-size images, the multispectral ARRInet-M classifier outperformed the white-light-only ARRInet-W model (45.5%) and surgical residents (69.7%). Challenges with discrimination occurred with parotid vs fat and blood vessels vs nerve.CONCLUSIONS: A deep learning model using multispectral imaging outperformed a similar model and surgical residents using traditional white-light imaging at the task of classifying normal human head and neck tissue ex vivo. These results suggest that multispectral imaging can enhance surgical vision and augment surgeons' ability to identify tissues during a procedure.

    View details for DOI 10.1177/0194599820941013

    View details for PubMedID 32838646

  • Prospective Evaluation of the Safety and Efficacy of THRIVE for Children Undergoing Airway Evaluation. Pediatric quality & safety Okland, T. S., Liu, G. S., Caruso, T. J., Sidell, D. R. 2020; 5 (5): e348


    Transnasal Humidified Rapid-Insufflation Ventilatory Exchange (THRIVE) is a humidified high-flow nasal cannula capable of extending apneic time. Although THRIVE is assumed to stent upper airway soft tissues, this has not been objectively evaluated. Also, there are no prior studies providing safety and efficacy data for those patients undergoing upper airway evaluation using THRIVE.This report is a prospective study of the safety and efficacy of THRIVE in pediatric patients younger than 18 years old undergoing drug-induced sleep endoscopy. We positioned a flexible laryngoscope to view the larynx, and photographs were taken with no THRIVE flow (control) and with THRIVE flow at 10 and 20 liters per minute (LPM). Upper airway patency was measured using epiglottis to posterior pharynx distance, laryngeal inlet area, and modified Cormack-Lehane score at the trialed parameters. Vomiting and aspiration were our primary safety endpoints.Eleven patients (6 women) with a mean age of 5.3 ± 2.1 years (2-8 years; SD, 2.05) were enrolled. Measurements of upper airway patency showed a significant THRIVE flow-associated increase in epiglottis to posterior pharynx distance (105 ± 54 at 10 L/min and 199 ± 67 at 20 L/min; P = 0.007) and nonsignificant increase of laryngeal inlet area (206 ± 148 at 10 L/min and 361 ± 190 at 20 L/min; P = 0.07). Cormack-Lehane score improved significantly at higher THRIVE volumes (P = 0.006).THRIVE appears to safely improve upper airway patency during sleep endoscopy in the pediatric patient. In this study, we objectively document the flow-dependent increase in laryngeal patency associated with THRIVE.

    View details for DOI 10.1097/pq9.0000000000000348

    View details for PubMedID 34616964

    View details for PubMedCentralID PMC8483875

  • Using Nasal Self-Esteem to Predict Revision in Cosmetic Rhinoplasty. Aesthetic surgery journal Okland, T. S., Patel, P. n., Liu, G. S., Most, S. P. 2020


    It would be useful if existing tools or outcomes measures could predict which patients are at greater risk of revision surgery following rhinoplasty.We aim to determine if a single question assessing nasal self-esteem could be used to predict which patients are at greatest risk of revision surgery following rhinoplasty.Retrospective chart review of 148 patients who underwent cosmetic rhinoplasty. Results of pre- and postoperative Standardized Cosmesis and Health Nasal Outcomes Survey (SCHNOS) questionnaires, and rates of revision or patient-initiated revision discussions (RD) were collected. Patients were stratified based on answers to SCHNOS Question five (SQ5), "Decreased mood and self-esteem due to my nose."Of the 148 patients included in the analysis, 72.9% were women, and the mean age was 30.9 (15-59, SD 10.3) years. Those patients who selected 4 or 5 on SQ5 had an overall revision rate of 16.7% and 18.8%, respectively, and a RD rate of 27.8% and 31.25%, respectively. Those patients who selected 0 through 3 on SQ5 had an overall revision rate of 0%, and an overall RD rate of 10.4%. Only SQ5 was predictive of revision and RD on logistic regression analysis (p = 0.0484 and p = 0.0257) after Bonferroni correction.SQ5 appears to offer a useful adjunct to guide surgical management of the cosmetic rhinoplasty patient. Those patients who reported worse nasal self-esteem and associated mood preoperatively were more likely to request and undergo revision.

    View details for DOI 10.1093/asj/sjaa252

    View details for PubMedID 32856710

  • Hypotympanic Sound Baffle for Amelioration of Pulsatile Tinnitus due to Carotid and Jugular Bulb Dehiscence. Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology Liu, G. S., Blevins, N. H., Vaisbuch, Y. n. 2019; 40 (7): 920–26


    To share our experience with treating pulsatile tinnitus by insulating a dehiscent carotid artery with a hypotympanic sound baffle, and compare outcomes with a similar resurfacing approach for jugular bulb wall anomalies.Retrospective case series.Tertiary academic medical center.Adult patients with troublesome pulsatile tinnitus with radiologic evidence of carotid artery dehiscence or jugular bulb wall anomaly within the temporal bone.Hypotympanic exposure of vessel followed by resurfacing using hydroxyapatite cement (carotid dehiscence) or autologous tissue (jugular bulb wall anomalies).Alleviation or reduction of pulsatile tinnitus.Two patients presented with unilateral, debilitating pulsatile tinnitus and history and imaging consistent with carotid dehiscence and underwent hypotympanic resurfacing with hydroxyapatite cement. Both had considerable initial improvement of tinnitus, and 40% resolution of tinnitus with improved quality of life at an average follow-up of 13.5 months. Two patients with jugular bulb dehiscence/diverticulum treated by resurfacing had complete elimination of symptoms at an average follow up of 17.3 months. There were no major adverse outcomes (permanent hearing loss, vascular injury, or intracranial hypertension).Creation of a hypotympanic sound baffle offers promise as a means of reducing pulsatile tinnitus emanating from a dehiscent carotid artery transmitted to the tympanum, with substantial improvement in reported functional ability. Treatment of venous etiologies of pulsatile tinnitus with similar techniques demonstrates higher success rates, which may be attributable to incomplete resurfacing of carotid artery dehiscence along its extent towards the petrous apex due to safety concerns.

    View details for DOI 10.1097/MAO.0000000000002293

    View details for PubMedID 31295200

  • Systematic Review of Temporal Bone-Resurfacing Techniques for Pulsatile Tinnitus Associated with Vascular Wall Anomalies. Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery Liu, G. S., Boursiquot, B. C., Blevins, N. H., Vaisbuch, Y. n. 2019: 194599818823205


    To systematically review literature evidence on temporal bone-resurfacing techniques for pulsatile tinnitus (PT) associated with vascular wall anomalies.We searched PubMed, Embase, and the Cochrane Database. The period covered was from 1962 to 2018.We included studies in all languages that reported resurfacing outcomes for patients with PT and radiographic evidence or direct visualization of sigmoid sinus wall anomaly, jugular bulb wall anomaly, or dehiscent or aberrant internal carotid artery.Of 954 citations retrieved in database searches and 5 citations retrieved from reference lists, 20 studies with a total of 141 resurfacing cases involving 138 patients were included. Resurfacing outcomes for arterial sources of PT showed 3 of 5 cases (60%) with complete resolution and 2 (40%) with partial resolution. Jugular bulb sources of PT showed 11 of 14 cases (79%) with complete resolution and 1 (7%) with partial resolution. Sigmoid sinus sources of PT showed 91 of 121 cases (75%) with complete resolution and 12 (10%) with partial resolution. Symptoms occurred more in females and on the right side. Most cases (94%) used hard-density materials for resurfacing. Material density did not appear to be associated with resurfacing outcomes. Use of autologous materials was associated with improved outcomes for arterial sources resurfacing. Major complications involving sigmoid sinus thrombosis or compression were reported in 4% of cases without long-term morbidity or mortality.Resurfacing surgery is likely effective and well tolerated for select patients with PT associated with various vascular wall anomalies.

    View details for PubMedID 30667295

  • Thyroid cancer risk in airline cockpit and cabin crew: a meta-analysis. Cancers of the head & neck Liu, G. S., Cook, A. n., Richardson, M. n., Vail, D. n., Holsinger, F. C., Oakley-Girvan, I. n. 2018; 3: 7


    Airline crew are exposed to ionizing radiation as part of their occupation and have a documented increased risk of melanoma and cataracts. However, whether their occupation predisposes them to an increased risk of thyroid cancer is not established. The purpose of this systematic review and meta-analysis was to assess the risk of thyroid cancer in airline cockpit and cabin crew compared with the general population.The MEDLINE database accessed via PubMed and Cochrane Database were searched. We included cohort studies reporting the standardized incidence ratio (SIR) or standardized mortality ratio (SMR) of thyroid cancers in any flight-based occupation.Of the 1777 citations retrieved in PubMed, eight studies with a total of 243,088 aircrew members and over 3,334,114 person-years of follow-up were included in this meta-analysis. No relevant studies were identified on Cochrane Database. The overall summary SIR of participants in any flight-based occupation was 1.11 (95% CI, 0.79-1.57; p = 0.613; 6 records). The summary SIR for cockpit crew was 1.21 (95% CI, 0.75-1.95; p = 0.383; 4 records) and the summary SIR for cabin crew was 1.00 (95% CI, 0.60-1.66; p = 0.646; 2 records). The overall summary standardized mortality ratio for airline crew was 1.19 (95% CI, 0.59-2.39; p = 0.773; 2 records).Airline crew were not found to have a significantly elevated risk of thyroid cancer incidence or mortality relative to the general population. Future research should capitalize on the growing occupational cohort dataset and employ innovative methods to quantify lifetime radiation exposure to further assess thyroid cancer risk in airline crew.

    View details for PubMedID 31093360

  • The effect of antibiotics on protein diffusion in the Escherichia coli cytoplasmic membrane PLOS ONE Liu, G. S., Bratton, B. P., Gital, Z., Shaevitz, J. W. 2017; 12 (10): e0185810


    Accumulating evidence suggests that molecular motors contribute to the apparent diffusion of molecules in cells. However, current literature lacks evidence for an active process that drives diffusive-like motion in the bacterial membrane. One possible mechanism is cell wall synthesis, which involves the movement of protein complexes in the cell membrane circumferentially around the cell envelope and may generate currents in the lipid bilayer that advectively transport other transmembrane proteins. We test this hypothesis in Escherichia coli using drug treatments that slow cell wall synthesis and measure their effect on the diffusion of the transmembrane protein mannitol permease using fluorescence recovery after photobleaching. We found no clear decrease in diffusion in response to vancomycin and no decrease in response to mecillinam treatment. These results suggest that cell wall synthesis is not an active contributor to mobility in the cytoplasmic membrane.

    View details for DOI 10.1371/journal.pone.0185810

    View details for Web of Science ID 000412163100047

    View details for PubMedID 28977034

    View details for PubMedCentralID PMC5627921

  • ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography BIOMEDICAL OPTICS EXPRESS Liu, G. S., Zhu, M. H., Kim, J., Raphael, P., Applegate, B. E., Oghalai, J. S. 2017; 8 (10): 4579–94


    Detection of endolymphatic hydrops is important for diagnosing Meniere's disease, and can be performed non-invasively using optical coherence tomography (OCT) in animal models as well as potentially in the clinic. Here, we developed ELHnet, a convolutional neural network to classify endolymphatic hydrops in a mouse model using learned features from OCT images of mice cochleae. We trained ELHnet on 2159 training and validation images from 17 mice, using only the image pixels and observer-determined labels of endolymphatic hydrops as the inputs. We tested ELHnet on 37 images from 37 mice that were previously not used, and found that the neural network correctly classified 34 of the 37 mice. This demonstrates an improvement in performance from previous work on computer-aided classification of endolymphatic hydrops. To the best of our knowledge, this is the first deep CNN designed for endolymphatic hydrops classification.

    View details for PubMedID 29082086

  • Computer-aided detection and quantification of endolymphatic hydrops within the mouse cochlea in vivo using optical coherence tomography JOURNAL OF BIOMEDICAL OPTICS Liu, G. S., Kim, J., Applegate, B. E., Oghalai, J. S. 2017; 22 (7): 76002


    Diseases that cause hearing loss and/or vertigo in humans such as Meniere’s disease are often studied using animal models. The volume of endolymph within the inner ear varies with these diseases. Here, we used a mouse model of increased endolymph volume, endolymphatic hydrops, to develop a computer-aided objective approach to measure endolymph volume from images collected

    View details for PubMedID 28687821

  • Explaining the Coincidence Rule for Estimating Respiratory Compensation in Metabolic Acid-Base Disorders ANNALS OF INTERNAL MEDICINE Liu, G. S., Bhalla, V. 2017; 166 (8): 610-610

    View details for DOI 10.7326/L16-0470

    View details for Web of Science ID 000399304000033

    View details for PubMedID 28384697

  • Superresolution microscope image reconstruction by spatiotemporal object decomposition and association: application in resolving t-tubule structure in skeletal muscle OPTICS EXPRESS Sun, M., Huang, J., Bunyak, F., Gumpper, K., De, G., Sermersheim, M., Liu, G., Lin, P., Palaniappan, K., Ma, J. 2014; 22 (10): 12160-12176


    One key factor that limits resolution of single-molecule superresolution microscopy relates to the localization accuracy of the activated emitters, which is usually deteriorated by two factors. One originates from the background noise due to out-of-focus signals, sample auto-fluorescence, and camera acquisition noise; and the other is due to the low photon count of emitters at a single frame. With fast acquisition rate, the activated emitters can last multiple frames before they transiently switch off or permanently bleach. Effectively incorporating the temporal information of these emitters is critical to improve the spatial resolution. However, majority of the existing reconstruction algorithms locate the emitters frame by frame, discarding or underusing the temporal information. Here we present a new image reconstruction algorithm based on tracklets, short trajectories of the same objects. We improve the localization accuracy by associating the same emitters from multiple frames to form tracklets and by aggregating signals to enhance the signal to noise ratio. We also introduce a weighted mean-shift algorithm (WMS) to automatically detect the number of modes (emitters) in overlapping regions of tracklets so that not only well-separated single emitters but also individual emitters within multi-emitter groups can be identified and tracked. In combination with a maximum likelihood estimator method (MLE), we are able to resolve low to medium density of overlapping emitters with improved localization accuracy. We evaluate the performance of our method with both synthetic and experimental data, and show that the tracklet-based reconstruction is superior in localization accuracy, particularly for weak signals embedded in a strong background. Using this method, for the first time, we resolve the transverse tubule structure of the mammalian skeletal muscle.

    View details for DOI 10.1364/OE.22.012160

    View details for Web of Science ID 000336957700078

    View details for PubMedID 24921337

    View details for PubMedCentralID PMC4162352

  • IS THE BEDSIDE TIMED VIBRATION TEST RELIABLE? MUSCLE & NERVE Botez, S. A., Liu, G., Logigian, E., Herrmann, D. N. 2009; 39 (2): 221-223


    The timed vibration test (TVT) is an easy-to-perform bedside sensory test; however, its reliability is not well established at sites commonly used for clinical testing. We evaluated intra- and interrater reliability of the TVT in a healthy control cohort of 25 adult volunteers and assessed the influence of neurologic training on TVT. Intrarater [intraclass correlation coefficient (ICC) range 0.79-0.92] and interrater (ICC range 0.0.82-0.95) reliability of TVT was high at different sites, which suggests that TVT is a reliable bedside examination when performed using a standardized protocol.

    View details for DOI 10.1002/mus.21143

    View details for Web of Science ID 000262837700012

    View details for PubMedID 19145659