scholarly journals Computer-Assisted Detection of Cemento-Enamel Junction in Intraoral Ultrasonographs

2021 ◽  
Vol 11 (13) ◽  
pp. 5850
Author(s):  
Kim-Cuong T. Nguyen ◽  
Yuening Yan ◽  
Neelambar R. Kaipatur ◽  
Paul W. Major ◽  
Edmond H. Lou ◽  
...  
Keyword(s):  
Health Assessment ◽  
Computer Assisted ◽  
Ultrasound Images ◽  
Image Preprocessing ◽  
Human Volunteers ◽  
Computer Assisted Detection ◽  
The Mean ◽  
Bounding Boxes ◽  
Clinical Measurements ◽  
Dental Professionals

The cemento-enamel junction (CEJ) is an important reference point for various clinical measurements in oral health assessment. Identifying CEJ in ultrasound images is a challenging task for dentists. In this study, a computer-assisted detection method is proposed to identify the CEJ in ultrasound images, based on the curvature change of the junction outlining the upper edge of the enamel and cementum at the cementum–enamel intersection. The technique consists of image preprocessing steps for image enhancement, segmentation, and edge detection to locate the boundary of the enamel and cementum. The effects of the image preprocessing and the sizes of the bounding boxes enclosing the CEJ were studied. For validation, the algorithm was applied to 120 images acquired from human volunteers. The mean difference of the best performance between the proposed method and the two raters’ measurements was an average of 0.25 mm with reliability ≥ 0.98. The proposed method has the potential to assist dental professionals in CEJ identification on ultrasonographs to provide better patient care.

scholarly journals Artificial intelligence-supported lung cancer detection by multi-institutional readers with multi-vendor chest radiographs: a retrospective clinical validation study

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Daiju Ueda ◽  
Akira Yamamoto ◽  
Akitoshi Shimazaki ◽  
Shannon Leigh Walston ◽  
Toshimasa Matsumoto ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Lung Cancer ◽  
Ground Truth ◽  
Chest Radiographs ◽  
Initial Assessment ◽  
Computer Assisted ◽  
General Physicians ◽  
Computer Assisted Detection ◽  
Bounding Boxes ◽  
Sensitivity Specificity

Abstract Background We investigated the performance improvement of physicians with varying levels of chest radiology experience when using a commercially available artificial intelligence (AI)-based computer-assisted detection (CAD) software to detect lung cancer nodules on chest radiographs from multiple vendors. Methods Chest radiographs and their corresponding chest CT were retrospectively collected from one institution between July 2017 and June 2018. Two author radiologists annotated pathologically proven lung cancer nodules on the chest radiographs while referencing CT. Eighteen readers (nine general physicians and nine radiologists) from nine institutions interpreted the chest radiographs. The readers interpreted the radiographs alone and then reinterpreted them referencing the CAD output. Suspected nodules were enclosed with a bounding box. These bounding boxes were judged correct if there was significant overlap with the ground truth, specifically, if the intersection over union was 0.3 or higher. The sensitivity, specificity, accuracy, PPV, and NPV of the readers’ assessments were calculated. Results In total, 312 chest radiographs were collected as a test dataset, including 59 malignant images (59 nodules of lung cancer) and 253 normal images. The model provided a modest boost to the reader’s sensitivity, particularly helping general physicians. The performance of general physicians was improved from 0.47 to 0.60 for sensitivity, from 0.96 to 0.97 for specificity, from 0.87 to 0.90 for accuracy, from 0.75 to 0.82 for PPV, and from 0.89 to 0.91 for NPV while the performance of radiologists was improved from 0.51 to 0.60 for sensitivity, from 0.96 to 0.96 for specificity, from 0.87 to 0.90 for accuracy, from 0.76 to 0.80 for PPV, and from 0.89 to 0.91 for NPV. The overall increase in the ratios of sensitivity, specificity, accuracy, PPV, and NPV were 1.22 (1.14–1.30), 1.00 (1.00–1.01), 1.03 (1.02–1.04), 1.07 (1.03–1.11), and 1.02 (1.01–1.03) by using the CAD, respectively. Conclusion The AI-based CAD was able to improve the ability of physicians to detect nodules of lung cancer in chest radiographs. The use of a CAD model can indicate regions physicians may have overlooked during their initial assessment.

scholarly journals Ex vivo evaluation of a multilayered sealant patch for watertight dural closure: cranial and spinal models

2021 ◽  
Vol 32 (8) ◽  
Author(s):  
A. Kinaci ◽  
S. van Thoor ◽  
S. Redegeld ◽  
M. Tooren ◽  
T. P. C. van Doormaal
Keyword(s):  
Ex Vivo ◽  
Resistance Test ◽  
Burst Pressure ◽  
Cerebrospinal Fluid Leakage ◽  
Computer Assisted ◽  
Dural Defect ◽  
Test Results ◽  
Physiological Conditions ◽  
Dural Attachment ◽  
The Mean

AbstractCerebrospinal fluid leakage is a frequent complication after cranial and spinal surgery. To prevent this complication and seal the dura watertight, we developed Liqoseal, a dural sealant patch comprising a watertight polyesterurethane layer and an adhesive layer consisting of poly(DL-lactide-co-ε-caprolactone) copolymer and multiarmed N-hydroxylsuccinimide functionalized polyethylene glycol. We compared acute burst pressure and resistance to physiological conditions for 72 h of Liqoseal, Adherus, Duraseal, Tachosil, and Tisseel using computer-assisted models and fresh porcine dura. The mean acute burst pressure of Liqoseal in the cranial model (145 ± 39 mmHg) was higher than that of Adherus (87 ± 47 mmHg), Duraseal (51 ± 42 mmHg) and Tachosil (71 ± 16 mmHg). Under physiological conditions, cranial model resistance test results showed that 2 of 3 Liqoseal sealants maintained dural attachment during 72 hours as opposed to 3 of 3 for Adherus and Duraseal and 0 of 3 for Tachosil. The mean burst pressure of Liqoseal in the spinal model (233 ± 81 mmHg) was higher than that of Tachosil (123 ± 63 mmHg) and Tisseel (23 ± 16 mmHg). Under physiological conditions, spinal model resistance test results showed that 2 of 3 Liqoseal sealants maintained dural attachment for 72 hours as opposed to 3 of 3 for Adherus and 0 of 3 for Duraseal and Tachosil. This novel study showed that Liqoseal is capable of achieving a strong watertight seal over a dural defect in ex vivo models.

scholarly journals AB0189 ASSESSMENT OF POWER DOPPLER SYNOVITIS IN RHEUMATOID ARTHRITIS PATIENTS WITH CLINICAL REMISSION

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 1394.2-1394
Author(s):  
R. Fakhfakh ◽  
N. El Amri ◽  
K. Baccouche ◽  
H. Zeglaoui ◽  
E. Bouajina
Keyword(s):  
Rheumatoid Arthritis ◽  
Functional Capacity ◽  
Clinical Remission ◽  
Power Doppler ◽  
Health Assessment ◽  
Disease Flare ◽  
Synovial Hypertrophy ◽  
The Mean ◽  
Grade 3 ◽  
Subclinical Synovitis

Background:Ultrasound-detected synovitis, mainly synovial Doppler signal, has shown predictive value in relation to radiographic damage progression and disease flare or relapse in rheumatoid arthritis (RA) patients with clinical remission.Objectives:The aim of the study was to analyze the correlation between power Doppler scores and clinical/laboratory and radiographic data in clinical remission RA patients.Methods:Cross-sectional study including patients with RA in clinical remission defined by: DAS28ESR ≤ 2.6, without disease flare or changes in therapy in the previous 6 months. Each patient underwent ultrasound: B-mode and PD assessments of 36 joints and 20 tendons in the Rheumatology Department over a period of 6 month. Synovitis and tenosynovitis were defined and scored according to the Outcome Measures in Rheumatology Clinical Trials (OMERACT). Radiological measurements included the modified Sharp/van der Heijde method (SHS). Functional capacity was assessed by the Health Assessment Questionnaire (HAQ).Results:Thirty two patients were enrolled, the mean age was 53.7±13.4 and 75% were female. The mean disease duration was 15 years ± 8.8. Subclinical synovitis were the most frequent in wrist (56.3%), 2ndmetacarpophalangeal joints (28.1%) and 2ndmetatarsophalangeal joints (29%). The mean subclinical synovitis/ tenosynovitis numbers was 4±3.1 per patient. Synovial hypertrophy and B mode tenosynovitis were detected in 93.8%: 71.3% had a grade = 2 and 9.8% had a grade= 3. Total B mode score was correlated only with the SHS score in the feet (r: 0.4, p: 0.03). PD signal was detected in 62.5% of patients: 37.5% had a grade =2 and 9.4% had a grade= 3. Total PD score was correlated with DAS28 (r:0.42, p:0.02), the SHS score in the hands (r:0.39, p:0.03) and in the feet (r:0.5, p:0.007), synovial hypertrophy (r:0.6, p:0.0001) and HAQ (r:0.32, p:0.06). No correlation was found with CDAI, SDAI, swollen joint counts, tender joint counts, patient global health assessment, erythrocyte sedimentation rate, C-reactive protein, rheumatoid factor and anti-cyclic citrullinated peptide, biologic treatment.Conclusion:Synovial hypertrophy and PD signal were frequent in RA remission. PD signal was associated with RA activity, radiologic damage and functional capacity.References:[1]Yan Geng & Jingjing Han & Xuerong Deng and al. Presence of power Doppler synovitis in rheumatoid arthritis patients with synthetic and/or biological disease-modifying anti-rheumatic drug-induced clinical remission: experience from a Chinese cohort. Clinical Rheumatology 2014. DOI 10.1007/s10067-014-2634-yDisclosure of Interests:None declared

scholarly journals Automated and Computer-Assisted Detection, Classification, and Diagnosis of Diabetic Retinopathy

2020 ◽  
Vol 26 (4) ◽  
pp. 544-550 ◽  
Author(s):  
Michael D. Abràmoff ◽  
Theodore Leng ◽  
Daniel S.W. Ting ◽  
Kyu Rhee ◽  
Mark B. Horton ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Computer Assisted ◽  
Computer Assisted Detection
Sign in / Sign up

Export Citation Format

Share Document