35 research outputs found
Radio-clinical assessment of crista fenestra during pediatric cochlear implantation
No full textObjectives: This study aimed to assess the ability of preoperative computed tomography (CT) to predict the crista fenestra (CF) type during cochlear implantation and correlate these types with intraoperative findings. This may allow for precise preoperative planning with better surgical outcomes. Study design: A prospective observational study. Settings: The study was done in multiple tertiary centers between September 2021 and March 2024. Method: ology: We correlated the preoperative radiological type of the CF with the intraoperative CF type to evaluate the accuracy and sensitivity of the HRCT to predict the CF type. We also assessed the need for CF drilling in each case. Results: Our study included 154 patients who underwent CI. They were 90 (58.4 %) males and 64 (41.5 %) females with ages ranging from 2.1 to 7.6 years, with a mean of 4.69 ± 1.19. The intra-class correlation coefficient between both radiological evaluators was 0.985, which indicated a high agreement between them. The intraoperative surgical types of CF were significantly related to the radiological types as the Spearman correlation coefficient was 0.976, and the P-value was <0.001. Conclusions: Our study revealed that preoperative CT is a precise tool for predicting the intraoperative type of CF during cochlear implantation type with a sensitivity of 96.67 % and an accuracy of 94.17 %. Moreover, drilling of the CF is recommended in type A3 and type B
Game-like interactive exercise versus visual feedback in patients with chemotherapy induced peripheral neuropathy post mastectomy: A randomized comparative study
No full textBackground Chemotherapy-induced peripheral neuropathy (CIPN) is one of the most frequent side effects of antineoplastic agents, with a prevalence of 19 to 85%. In terms of clinical manifestations, CIPN is primarily a sensory neuropathy with motor and autonomic alterations of varying intensity and duration. CIPN consider as major problem for both cancer patients and survivors, as well as for their healthcare providers, possibly increasing the risk of falling. Objective: To evaluate the efficacy of game-like interactive exercise versus visual feedback training on the risk of falling and sensory integration in patients with chemotherapy-induced peripheral neuropathy after mastectomy. Methods: In this randomized comparative study, 30 female patients diagnosed with chemotherapy-induced peripheral neuropathy after mastectomy were randomly allocated into two equal groups; group (A) underwent game-like interactive exercise using the Biodex Balance System (BBS), while group (B) underwent a visual feedback training program using BBS. The treatment was applied for three sessions per week for four consecutive weeks. All subjects in both groups were assessed using the fall risk index and sensory integration test (sway index) in four sensory conditions at baseline and at the end of the study for both groups
Game-like Interactive Exercise Versus Visual Feedback in Patients with Chemotherapy Induced Peripheral Neuropathy Post Mastectomy: A Randomized Comparative Study
No full textBackground Chemotherapy-induced peripheral neuropathy (CIPN) is one of the most frequent side effects of antineoplastic agents, with a prevalence of 19 to 85%. In terms of clinical manifestations, CIPN is primarily a sensory neuropathy with motor and autonomic alterations of varying intensity and duration. CIPN consider as major problem for both cancer patients and survivors, as well as for their healthcare providers, possibly increasing the risk of falling. Objective: To evaluate the efficacy of game-like interactive exercise versus visual feedback training on the risk of falling and sensory integration in patients with chemotherapy-induced peripheral neuropathy after mastectomy. Methods: In this randomized comparative study, 30 female patients diagnosed with chemotherapy-induced peripheral neuropathy after mastectomy were randomly allocated into two equal groups; group (A) underwent game-like interactive exercise using the Biodex Balance System (BBS), while group (B) underwent a visual feedback training program using BBS. The treatment was applied for three sessions per week for four consecutive weeks. All subjects in both groups were assessed using the fall risk index and sensory integration test (sway index) in four sensory conditions at baseline and at the end of the study for both groups
Wafer classification using support vector machines
No full textIncreasing yield is a primary concern to integrated circuit manufacturing companies as it dictates the readiness of a new process for high volume manufacturing. In order to expedite the process of discovering yield issues, companies have started looking for ways to perform early prediction for such issues. This paper suggests the use of the support vector machines (SVMs) for early wafer classification. The choice of SVM is motivated by the model's ability to effectively classify multivariate, multimodal, and inseparable data points. This model uses multidimensional hyperplanes to separate and classify wafers into low-yield and high-yield classes. This paper includes a proposal for how the classification model can be applied for yield classification and how it can be adaptively updated in a manufacturing environment. We show how the values for the SVM parameters can be selected for best yield classification. Furthermore, performance evaluation is conducted on real manufacturing data, comparing the proposed SVM classifier to state of the art. Results show that in all cases, SVM consistently outperforms other methods with and without adaptive model updates. The experiments also show that all classifiers' performances depend on yield thresholds. It is also shown that the classification model can be built and executed using a reduced set without compromising its accuracy. © 1988-2012 IEEE.Abe S., 2005, SUPPORT VECTOR MACHI; Boser B, 1992, P 5 ANN WORKSH COMP, V5, P144, DOI DOI 10.1145-130385.130401; Botros Y, 2003, P SOC PHOTO-OPT INS, V5044, P121, DOI 10.1117-12.485311; Botros Y., 2003, P AEC APC S 4; Chapelle O, 2002, MACH LEARN, V46, P131, DOI 10.1023-A:1012450327387; Chin W. W., 2010, HDB PARTIAL LEAST SQ; Dasarathy B. V., 1991, NEAREST NEIGHBOR NN; Dupret Y., 2005, P IEEE SEM ADV SEM M, P118; Fayed A., 2003, P AEC APC S 25 SEP; Fenner J., 2000, P AEC APC S 12 SEP, VXII; Hajj H., 1998, P FLEX AUT INT MAN C; Hajj H., 2006, P AEC APC S 18, VXVIII; Hajj H, 2007, P SOC PHOTO-OPT INS, V6730, pQ7300, DOI 10.1117-12.746844; Hall M., 2000, P 17 INT C MACH LEAR, P359; Han J., 2001, DATA MINING CONCEPTS; He QP, 2008, P AMER CONTR CONF, P1606, DOI 10.1109-ACC.2008.4586721; He QP, 2007, IEEE T SEMICONDUCT M, V20, P345, DOI 10.1109-TSM.2007.907607; Khan AA, 2008, J PROCESS CONTR, V18, P961, DOI 10.1016-j.jprocont.2008.04.014; Kittler R., 2000, P INT C MOD AN SEM M, P270; Li TS, 2006, J INTELL MANUF, V17, P355, DOI 10.1007-s10845-005-0008-7; Lin TH, 2009, IEEE T SEMICONDUCT M, V22, P204, DOI 10.1109-TSM.2008.2011185; MACGREGOR JF, 1995, CONTROL ENG PRACT, V3, P403, DOI 10.1016-0967-0661(95)00014-L; May G. S., 2006, FUNDAMENTALS SEMICON; Moore G. E., 1975, P IEEE INT EL DEV M, P11; Moyne J, 2001, RUN TO RUN CONTROL S; Moyne JR, 2007, IEEE T SEMICONDUCT M, V20, P408, DOI 10.1109-TSM.2007.907617; Quinlan J. R., 1993, C4 5 PROGRAMS MACHIN; SPECHT DF, 1991, IEEE T NEURAL NETWOR, V2, P568, DOI 10.1109-72.97934; Wong A. Y., 1996, Proceedings. 1996 IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems (Cat. No.96TB100081), DOI 10.1109-DFTVS.1996.57201274
Author Correction: COVID-19 infection segmentation using hybrid deep learning and image processing techniques
No full textArabic speech recognition using end‐to‐end deep learning
No full textAbstract Arabic automatic speech recognition (ASR) methods with diacritics have the ability to be integrated with other systems better than Arabic ASR methods without diacritics. In this work, the application of state‐of‐the‐art end‐to‐end deep learning approaches is investigated to build a robust diacritised Arabic ASR. These approaches are based on the Mel‐Frequency Cepstral Coefficients and the log Mel‐Scale Filter Bank energies as acoustic features. To the best of our knowledge, end‐to‐end deep learning approach has not been used in the task of diacritised Arabic automatic speech recognition. To fill this gap, this work presents a new CTC‐based ASR, CNN‐LSTM, and an attention‐based end‐to‐end approach for improving diacritisedArabic ASR. In addition, a word‐based language model is employed to achieve better results. The end‐to‐end approaches applied in this work are based on state‐of‐the‐art frameworks, namely ESPnet and Espresso. Training and testing of these frameworks are performed based on the Standard Arabic Single Speaker Corpus (SASSC), which contains 7 h of modern standard Arabic speech. Experimental results show that the CNN‐LSTM with an attention framework outperforms conventional ASR and the Joint CTC‐attention ASR framework in the task of Arabic speech recognition. The CNN‐LSTM with an attention framework could achieve a word error rate better than conventional ASR and the Joint CTC‐attention ASR by 5.24% and 2.62%, respectively
Virtual reality-based exercises to improve balance and hand grip strength in patients with hemiparesis caused by an electrical burn: A randomized controlled study
No full textThere are many complications after an electrical burn injury, including neuromuscular defects, paresis or paralysis, Gillian barre syndrome, transverse myelitis, or amyotrophic lateral sclerosis. The aim of this study was to investigate the effect of virtual reality-based exercises on balance and hand grip strength in post electrical burn-induced hemiparetic patients. A randomized control trial pre- and post-experimental design with intra-rater reliability and inter-rater agreement was undertaken. Thirty post-electrical burn-induced hemiparetic patients (19 males and 11 females, aged 15 to 25 years) were randomly allocated into two equal groups (group A and B). Group A (n = 15) received virtual reality-based exercise in addition to the conventional physical therapy program. Group B (n = 15) received conventional physical therapy program only. The treatment was applied 3 sessions per week for 12 consecutive weeks. Posture stability and hand grip strength were measured by the Biodex balance system and handheld dynamometer, respectively. Data was collected prior to the first treatment and at the end of the 12-week trial and all statistical calculations were done using the computer program IBM SPSS. A statistically significant increase in the overall stability index and the power of hand grip strength was observed in both groups after treatment (p < 0.05), especially in group A, which received VR - based exercise training. Thus, group A showed a greater improvement in postural stability and hand grip strength than group B (p < 0.05). Virtual reality-based exercises as well as conventional physical therapy program were effective in improving posture stability and hand grip strength in post electrical burn-induced hemiparetic patients
Virtual reality-based exercises to improve balance and hand grip strength in patients with hemiparesis caused by an electrical burn: A randomized controlled study
No full textThere are many complications after an electrical burn injury, including neuromuscular defects, paresis or paralysis, Gillian barre syndrome, transverse myelitis, or amyotrophic lateral sclerosis. The aim of this study was to investigate the effect of virtual reality-based exercises on balance and hand grip strength in post electrical burn-induced hemiparetic patients. A randomized control trial pre- and post-experimental design with intra-rater reliability and inter-rater agreement was undertaken. Thirty post-electrical burn-induced hemiparetic patients (19 males and 11 females, aged 15 to 25 years) were randomly allocated into two equal groups (group A and B). Group A (n = 15) received virtual reality-based exercise in addition to the conventional physical therapy program. Group B (n = 15) received conventional physical therapy program only. The treatment was applied 3 sessions per week for 12 consecutive weeks. Posture stability and hand grip strength were measured by the Biodex balance system and handheld dynamometer, respectively. Data was collected prior to the first treatment and at the end of the 12-week trial and all statistical calculations were done using the computer program IBM SPSS. A statistically significant increase in the overall stability index and the power of hand grip strength was observed in both groups after treatment (p < 0.05), especially in group A, which received VR - based exercise training. Thus, group A showed a greater improvement in postural stability and hand grip strength than group B (p < 0.05). Virtual reality-based exercises as well as conventional physical therapy program were effective in improving posture stability and hand grip strength in post electrical burn-induced hemiparetic patients
Vascular endothelial growth factor and subclinical atherosclerosis by carotid ultrasonography in Egyptian patients with Behçet’s disease
No full textAbstractAim of the workThis study aimed to investigate serum levels of vascular endothelial growth factor (VEGF) and to measure common carotid intima media thickness (cc-IMT) in Egyptian patients with Behçet’s disease (BD) to evaluate their relations to disease activity and different clinical manifestations.Patients and methodsSeventy patients with BD and 70 healthy controls participated in this study. Behçet’s disease patients were subjected to detailed history taking, thorough clinical examination, disease activity assessment using the BD Current Activity Form (BDCAF) and laboratory investigation. Vascular endothelial growth factor levels were measured using ELISA. The carotid arteries were assessed for cc-IMT and plaques with a carotid high-resolution B-mode ultrasound.ResultsThe mean cc-IMT showed a significant difference in BD patients compared to controls (p<0.011). Three BD patients had plaques (4.3%). There were significant correlations of cc-IMT with disease duration (p<0.001), systolic blood pressure (BP) (p=0.029), diastolic BP (p=0.041), total cholesterol (p<0.001) and LDL (p<0.001) and insignificant correlation with BDCAF (p=0.054). There was a significant elevation of VEGF levels (p<0.001) in BD patients compared to controls. VEGF levels showed significant correlations with ESR (p=0.14), CRP (p<0.001) and BDCAF (P=0.02), while there was an insignificant correlation with cc-IMT (p=0.107).ConclusionBD patients have ultrasonographic evidence of subclinical atherosclerosis which was associated with increasing age, longer disease duration, elevated systolic and diastolic BP, total cholesterol and LDL. Elevated VEGF showed statistically significant positive correlations with BDCAF and thus can be used as a marker of disease activity and/or therapeutic targets in BD patients
Correction: Epidemiology and outcomes of early-onset AKI in COVID-19-related ARDS in comparison with non-COVID-19-related ARDS: insights from two prospective global cohort studies (Critical Care, (2023), 27, 1, (3), 10.1186/s13054-022-04294-5)
No full textFollowing publication of the original article [1], the authors identified that the collaborating authors part of the collaborating author group CCCC Consortium was missing. The collaborating author group is available and included as Additional file 1 in this article
