MyMedR

Displaying all 6 publications

Abstract:

Sort:

3D axial-attention for lung nodule classification

Al-Shabi M, Shak K, Tan M

Int J Comput Assist Radiol Surg, 2021 Aug;16(8):1319-1324.
PMID: 34060010 DOI: 10.1007/s11548-021-02415-z

PURPOSE: In recent years, Non-Local-based methods have been successfully applied to lung nodule classification. However, these methods offer 2D attention or limited 3D attention to low-resolution feature maps. Moreover, they still depend on a convenient local filter such as convolution as full 3D attention is expensive to compute and requires a big dataset, which might not be available.
METHODS: We propose to use 3D Axial-Attention, which requires a fraction of the computing power of a regular Non-Local network (i.e., self-attention). Unlike a regular Non-Local network, the 3D Axial-Attention network applies the attention operation to each axis separately. Additionally, we solve the invariant position problem of the Non-Local network by proposing to add 3D positional encoding to shared embeddings.
RESULTS: We validated the proposed method on 442 benign nodules and 406 malignant nodules, extracted from the public LIDC-IDRI dataset by following a rigorous experimental setup using only nodules annotated by at least three radiologists. Our results show that the 3D Axial-Attention model achieves state-of-the-art performance on all evaluation metrics, including AUC and Accuracy.
CONCLUSIONS: The proposed model provides full 3D attention, whereby every element (i.e., pixel) in the 3D volume space attends to every other element in the nodule effectively. Thus, the 3D Axial-Attention network can be used in all layers without the need for local filters. The experimental results show the importance of full 3D attention for classifying lung nodules.
Lung nodule classification using deep Local-Global networks

Al-Shabi M, Lan BL, Chan WY, Ng KH, Tan M

Int J Comput Assist Radiol Surg, 2019 Oct;14(10):1815-1819.
PMID: 31020576 DOI: 10.1007/s11548-019-01981-7

PURPOSE: Lung nodules have very diverse shapes and sizes, which makes classifying them as benign/malignant a challenging problem. In this paper, we propose a novel method to predict the malignancy of nodules that have the capability to analyze the shape and size of a nodule using a global feature extractor, as well as the density and structure of the nodule using a local feature extractor.
METHODS: We propose to use Residual Blocks with a 3 × 3 kernel size for local feature extraction and Non-Local Blocks to extract the global features. The Non-Local Block has the ability to extract global features without using a huge number of parameters. The key idea behind the Non-Local Block is to apply matrix multiplications between features on the same feature maps.
RESULTS: We trained and validated the proposed method on the LIDC-IDRI dataset which contains 1018 computed tomography scans. We followed a rigorous procedure for experimental setup, namely tenfold cross-validation, and ignored the nodules that had been annotated by
Comparison of two-dimensional synthesized mammograms versus original digital mammograms: a quantitative assessment

Tan M, Al-Shabi M, Chan WY, Thomas L, Rahmat K, Ng KH

Med Biol Eng Comput, 2021 Feb;59(2):355-367.
PMID: 33447988 DOI: 10.1007/s11517-021-02313-1

This study objectively evaluates the similarity between standard full-field digital mammograms and two-dimensional synthesized digital mammograms (2DSM) in a cohort of women undergoing mammography. Under an institutional review board-approved data collection protocol, we retrospectively analyzed 407 women with digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) examinations performed from September 1, 2014, through February 29, 2016. Both FFDM and 2DSM images were used for the analysis, and 3216 available craniocaudal (CC) and mediolateral oblique (MLO) view mammograms altogether were included in the dataset. We analyzed the mammograms using a fully automated algorithm that computes 152 structural similarity, texture, and mammographic density-based features. We trained and developed two different global mammographic image feature analysis-based breast cancer detection schemes for 2DSM and FFDM images, respectively. The highest structural similarity features were obtained on the coarse Weber Local Descriptor differential excitation texture feature component computed on the CC view images (0.8770) and MLO view images (0.8889). Although the coarse structures are similar, the global mammographic image feature-based cancer detection scheme trained on 2DSM images outperformed the corresponding scheme trained on FFDM images, with area under a receiver operating characteristic curve (AUC) = 0.878 ± 0.034 and 0.756 ± 0.052, respectively. Consequently, further investigation is required to examine whether DBT can replace FFDM as a standalone technique, especially for the development of automated objective-based methods.
Fulltext A multi-country study on the impact of sex and age on oral features of COVID-19 infection in adolescents and young adults

Sabbagh HJ, Abdelaziz W, Quritum M, Alamoudi RA, AlKhateeb NAB, Abourdan J, et al.

BMC Oral Health, 2022 Nov 19;22(1):513.
PMID: 36402969 DOI: 10.1186/s12903-022-02515-5

BACKGROUND: Oral diseases are features of COVID-19 infection. There is, however, little known about oral diseases associated with COVID-19 in adolescents and young adults (AYA). Therefore, the aim of this study was to assess oral lesions' association with COVID-19 infection in AYA; and to identify if sex and age will modify these associations.
METHODOLOGY: Data was collected for this cross-sectional study between August 2020 and January 2021 from 11-to-23 years old participants in 43-countries using an electronic validated questionnaire developed in five languages. Data collected included information on the dependent variables (the presence of oral conditions- gingival inflammation, dry mouth, change in taste and oral ulcers), independent variable (COVID-19 infection) and confounders (age, sex, history of medical problems and parents' educational level). Multilevel binary logistic regression was used for analysis.
RESULTS: Complete data were available for 7164 AYA, with 7.5% reporting a history of COVID-19 infection. A significantly higher percentage of participants with a history of COVID-19 infection than those without COVID-19 infection reported having dry mouth (10.6% vs 7.3%, AOR = 1.31) and taste changes (11.1% vs 2.7%, AOR = 4.11). There was a significant effect modification in the association between COVID-19 infection and the presence of dry mouth and change in taste by age and sex (P = 0.02 and
Fulltext Anxiety among Adolescents and Young Adults during COVID-19 Pandemic: A Multi-Country Survey

Sabbagh HJ, Abdelaziz W, Alghamdi W, Quritum M, AlKhateeb NA, Abourdan J, et al.

Int J Environ Res Public Health, 2022 Aug 24;19(17).
PMID: 36078253 DOI: 10.3390/ijerph191710538

(1) Background: Adolescents-and-young-adults (AYA) are prone to anxiety. This study assessed AYA's level of anxiety during the COVID-19 pandemic; and determined if anxiety levels were associated with country-income and region, socio-demographic profile and medical history of individuals. (2) Methods: A survey collected data from participants in 25 countries. Dependent-variables included general-anxiety level, and independent-variables included medical problems, COVID-19 infection, age, sex, education, and country-income-level and region. A multilevel-multinomial-logistic regression analysis was conducted to determine the association between dependent, and independent-variables. (3) Results: Of the 6989 respondents, 2964 (42.4%) had normal-anxiety, and 2621 (37.5%), 900 (12.9%) and 504 (7.2%) had mild, moderate and severe-anxiety, respectively. Participants from the African region (AFR) had lower odds of mild, moderate and severe than normal-anxiety compared to those from the Eastern-Mediterranean-region (EMR). Also, participants from lower-middle-income-countries (LMICs) had higher odds of mild and moderate than normal-anxiety compared to those from low-income-countries (LICs). Females, older-adolescents, with medical-problems, suspected-but-not-tested-for-COVID-19, and those with friends/family-infected with COVID-19 had significantly greater odds of different anxiety-levels. (4) Conclusions: One-in-five AYA had moderate to severe-anxiety during the COVID-19-pandemic. There were differences in anxiety-levels among AYAs by region and income-level, emphasizing the need for targeted public health interventions based on nationally-identified priorities.
Fulltext Oral manifestations in young adults infected with COVID-19 and impact of smoking: a multi-country cross-sectional study

El Tantawi M, Sabbagh HJ, Alkhateeb NA, Quritum M, Abourdan J, Qureshi N, et al.

PeerJ, 2022;10:e13555.
PMID: 35860046 DOI: 10.7717/peerj.13555

BACKGROUND: Oral manifestations and lesions could adversely impact the quality of people's lives. COVID-19 infection may interact with smoking and the impact on oral manifestations is yet to be discovered.
OBJECTIVES: The aim of this study was to assess the self-reported presence of oral lesions by COVID-19-infected young adults and the differences in the association between oral lesions and COVID-19 infection in smokers and non-smokers.
METHODS: This cross-sectional multi-country study recruited 18-to-23-year-old adults. A validated questionnaire was used to collect data on COVID-19-infection status, smoking and the presence of oral lesions (dry mouth, change in taste, and others) using an online platform. Multi-level logistic regression was used to assess the associations between the oral lesions and COVID-19 infection; the modifying effect of smoking on the associations.
RESULTS: Data was available from 5,342 respondents from 43 countries. Of these, 8.1% reported COVID-19-infection, 42.7% had oral manifestations and 12.3% were smokers. A significantly greater percentage of participants with COVID-19-infection reported dry mouth and change in taste than non-infected participants. Dry mouth (AOR=, 9=xxx) and changed taste (AOR=, 9=xxx) were associated with COVID-19- infection. The association between COVID-19-infection and dry mouth was stronger among smokers than non-smokers (AOR = 1.26 and 1.03, p = 0.09) while the association with change in taste was stronger among non-smokers (AOR = 1.22 and 1.13, p = 0.86).
CONCLUSION: Dry mouth and changed taste may be used as an indicator for COVID-19 infection in low COVID-19-testing environments. Smoking may modify the association between some oral lesions and COVID-19-infection.