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
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 JOURNAL OF MEDICAL SCIENCE
2022; 14 (2)
View details for DOI 10.7759/cureus.22140
View details for Web of Science ID 000755197000018
Benign Ectopic Thyroid in the Lateral (Level II) Neck Compartment.
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
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
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
Using Nasal Self-Esteem to Predict Revision in Cosmetic Rhinoplasty.
Aesthetic surgery journal
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
Prospective Evaluation of the Safety and Efficacy of THRIVE for Children Undergoing Airway Evaluation.
Pediatric quality & safety
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
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
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
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
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
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
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
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
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
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
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