MyMedR

Displaying publications 1 - 20 of 98 in total

Abstract:

Sort:

Fulltext Screen Printed Carbon Electrode Based Electrochemical Immunosensor for the Detection of Dengue NS1 Antigen

Parkash O, Yean CY, Shueb RH

Diagnostics (Basel), 2014;4(4):165-80.
PMID: 26852684 DOI: 10.3390/diagnostics4040165

An electrochemical immunosensor modified with the streptavidin/biotin system on screen printed carbon electrodes (SPCEs) for the detection of the dengue NS1 antigen was developed in this study. Monoclonal anti-NS1 capture antibody was immobilized on streptavidin-modified SPCEs to increase the sensitivity of the assay. Subsequently, a direct sandwich enzyme linked immunosorbent assay (ELISA) format was developed and optimized. An anti-NS1 detection antibody conjugated with horseradish peroxidase enzyme (HRP) and 3,3,5,5'-tetramethybezidine dihydrochloride (TMB/H₂O₂) was used as an enzyme mediator. Electrochemical detection was conducted using the chronoamperometric technique, and electrochemical responses were generated at -200 mV reduction potential. The calibration curve of the immunosensor showed a linear response between 0.5 µg/mL and 2 µg/mL and a detection limit of 0.03 µg/mL. Incorporation of a streptavidin/biotin system resulted in a well-oriented antibody immobilization of the capture antibody and consequently enhanced the sensitivity of the assay. In conclusion, this immunosensor is a promising technology for the rapid and convenient detection of acute dengue infection in real serum samples.
Fulltext Association of Radiation Doses and Cancer Risks from CT Pulmonary Angiography Examinations in Relation to Body Diameter

Harun HH, Abdul Karim MK, Abbas Z, Abdul Rahman MA, Sabarudin A, Ng KH

Diagnostics (Basel), 2020 Sep 09;10(9).
PMID: 32917029 DOI: 10.3390/diagnostics10090681

In this study, we aimed to estimate the probability of cancer risk induced by CT pulmonary angiography (CTPA) examinations concerning effective body diameter. One hundred patients who underwent CTPA examinations were recruited as subjects from a single institution in Kuala Lumpur. Subjects were categorized based on their effective diameter size, where 19-25, 25-28, and >28 cm categorized as Groups 1, 2, and 3, respectively. The mean value of the body diameter of the subjects was 26.82 ± 3.12 cm, with no significant differences found between male and female subjects. The risk of cancer in breast, lung, and liver organs was 0.009%, 0.007%, and 0.005% respectively. The volume-weighted CT dose index (CTDIvol) was underestimated, whereas the size-specific dose estimates (SSDEs) provided a more accurate description of the radiation dose and the risk of cancer. CTPA examinations are considered safe but it is essential to implement a protocol optimized following the As Low as Reasonably Achievable (ALARA) principle.
Fulltext Establishment of CTPA Local Diagnostic Reference Levels with Noise Magnitude as a Quality Indicator in a Tertiary Care Hospital

Harun HH, Abdul Karim MK, Abd Rahman MA, Abdul Razak HR, Che Isa IN, Harun F

Diagnostics (Basel), 2020 Sep 09;10(9).
PMID: 32916913 DOI: 10.3390/diagnostics10090680

This study aimed to establish the local diagnostic reference levels (LDRLs) of computed tomography pulmonary angiography (CTPA) examinations based on body size with regard to noise magnitude as a quality indicator. The records of 127 patients (55 males and 72 females) who had undergone CTPAs using a 128-slice CT scanner were retrieved. The dose information, scanning acquisition parameters, and patient demographics were recorded in standardized forms. The body size of patients was categorized into three groups based on their anteroposterior body length: P1 (14-19 cm), P2 (19-24 cm), and P3 (24-31 cm), and the radiation dose exposure was statistically compared. The image noise was determined quantitatively by measuring the standard deviation of the region of interest (ROI) at five different arteries-the ascending and descending aorta, pulmonary trunk, and the left and right main pulmonary arteries. We observed that the LDRL values were significantly different between body sizes (p < 0.05), and the median values of the CT dose index volume (CTDIvol) for P1, P2, and P3 were 6.13, 8.3, and 21.40 mGy, respectively. It was noted that the noise reference values were 23.78, 24.26, and 23.97 HU for P1, P2, and P3, respectively, which were not significantly different from each other (p > 0.05). The CTDIvol of 9 mGy and dose length product (DLP) of 329 mGy∙cm in this study were lower than those reported by other studies conducted elsewhere. This study successfully established the LDRLs of a local healthcare institution with the inclusion of the noise magnitude, which is comparable with other established references.
Fulltext Microwave Breast Imaging Using Compressed Sensing Approach of Iteratively Corrected Delay Multiply and Sum Beamforming

Islam MT, Islam MT, Samsuzzaman M, Kibria S, Chowdhury MEH

Diagnostics (Basel), 2021 Mar 08;11(3).
PMID: 33800188 DOI: 10.3390/diagnostics11030470

Microwave imaging (MI) is a consistent health monitoring technique that can play a vital role in diagnosing anomalies in the breast. The reliability of biomedical imaging diagnosis is substantially dependent on the imaging algorithm. Widely used delay and sum (DAS)-based diagnosis algorithms suffer from some significant drawbacks. The delay multiply and sum (DMAS) is an improved method and has benefits over DAS in terms of greater contrast and better resolution. However, the main drawback of DMAS is its excessive computational complexity. This paper presents a compressed sensing (CS) approach of iteratively corrected DMAS (CS-ICDMAS) beamforming that reduces the channel calculation and computation time while maintaining image quality. The array setup for acquiring data comprised 16 Vivaldi antennas with a bandwidth of 2.70-11.20 GHz. The power of all the channels was calculated and low power channels were eliminated based on the compression factor. The algorithm involves data-independent techniques that eliminate multiple reflections. This can generate results similar to the uncompressed variants in a significantly lower time which is essential for real-time applications. This paper also investigates the experimental data that prove the enhanced performance of the algorithm.
Fulltext The Role of Breast Cancer Stem Cell-Related Biomarkers as Prognostic Factors

Ko CCH, Chia WK, Selvarajah GT, Cheah YK, Wong YP, Tan GC

Diagnostics (Basel), 2020 Sep 19;10(9).
PMID: 32961774 DOI: 10.3390/diagnostics10090721

Breast cancer is one of the leading causes of cancer-related deaths in women worldwide, and its incidence is on the rise. A small fraction of cancer stem cells was identified within the tumour bulk, which are regarded as cancer-initiating cells, possess self-renewal and propagation potential, and a key driver for tumour heterogeneity and disease progression. Cancer heterogeneity reduces the overall efficacy of chemotherapy and contributes to treatment failure and relapse. The cell-surface and subcellular biomarkers related to breast cancer stem cell (BCSC) phenotypes are increasingly being recognised. These biomarkers are useful for the isolation of BCSCs and can serve as potential therapeutic targets and prognostic tools to monitor treatment responses. Recently, the role of noncoding microRNAs (miRNAs) has extensively been explored as novel biomarker molecules for breast cancer diagnosis and prognosis with high specificity and sensitivity. An in-depth understanding of the biological roles of miRNA in breast carcinogenesis provides insights into the pathways of cancer development and its utility for disease prognostication. This review gives an overview of stem cells, highlights the biomarkers expressed in BCSCs and describes their potential role as prognostic indicators.
Fulltext The Role of Speckle Tracking Echocardiography in the Evaluation of Common Inherited Cardiomyopathies in Children and Adolescents: A Systematic Review

Dorobantu DM, Wadey CA, Amir NH, Stuart AG, Williams CA, Pieles GE

Diagnostics (Basel), 2021 Apr 01;11(4).
PMID: 33915862 DOI: 10.3390/diagnostics11040635

Speckle tracking echocardiography (STE) has gained importance in the evaluation of adult inherited cardiomyopathies, but its utility in children is not well characterized. We conducted a systematic review to evaluate the role of STE in pediatric inherited cardiomyopathies. PubMed, EMBASE, Web of Science, Scopus, CENTRAL and CINAHL databases were searched up to May 2020, for terms related to inherited cardiomyopathies and STE. Included were dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy (HCM), left ventricular non-compaction (LVNC) and arrhythmogenic cardiomyopathy (ACM). A total of 14 cohorts were identified, of which six were in DCM, four in HCM, three in LVNC and one in ACM. The most commonly reported STE measurements were left ventricular longitudinal strain (Sl), circumferential strain (Sc), radial strain (Sr) and rotation/torsion/twist. Sl, Sc and were abnormal in all DCM and LVNC cohorts, but not in all HCM. Apical rotation and twist/torsion were increased in HCM, and decreased in LVNC. Abnormal STE parameters were reported even in cohorts with normal non-STE systolic/diastolic measurements. STE in childhood cardiomyopathies can detect early changes which may not be associated with changes in cardiac function detectable by non-STE methods. Longitudinal and circumferential strain should be introduced in the cardiomyopathy echocardiography protocol, reflecting current practice in adults.
Fulltext Diagnostic and Prognostic Indications of Nasopharyngeal Carcinoma

E A R ENS, Irekeola AA, Yean Yean C

Diagnostics (Basel), 2020 Aug 19;10(9).
PMID: 32825179 DOI: 10.3390/diagnostics10090611

Nasopharyngeal carcinoma (NPC) is a disease that is highly associated with the latent infection of Epstein-Barr virus. The absence of obvious clinical signs at the early stage of the disease has made early diagnosis practically impossible, thereby promoting the establishment and progression of the disease. To enhance the stride for a reliable and less invasive tool for the diagnosis and prognosis of NPC, we synopsize biomarkers belonging to the two most implicated biological domains (oncogenes and tumor suppressors) in NPC disease. Since no single biomarker is sufficient for diagnosis and prognosis, coupled with the fact that the known established methods such as methylation-specific polymerase chain reaction (PCR), multiplex methylation-specific PCR, microarray assays, etc., can only accommodate a few biomarkers, we propose a 10-biomarker panel (KIT, LMP1, PIKC3A, miR-141, and miR-18a/b (oncogenic) and p16, RASSF1A, DAP-kinase, miR-9, and miR-26a (tumor suppressors)) based on their diagnostic and prognostic values. This marker set could be explored in a multilevel or single unified assay for the diagnosis and prognosis of NPC. If carefully harnessed and standardized, it is hoped that the proposed marker set would help transform the diagnostic and prognostic realm of NPC, and ultimately, help prevent the life-threatening late-stage NPC disease.
Fulltext Laboratory Diagnosis of Paratyphoid Fever: Opportunity of Surface Plasmon Resonance

Alhaj-Qasem DM, Al-Hatamleh MAI, Irekeola AA, Khalid MF, Mohamud R, Ismail A, et al.

Diagnostics (Basel), 2020 Jun 28;10(7).
PMID: 32605310 DOI: 10.3390/diagnostics10070438

Paratyphoid fever is caused by the bacterium Salmonellaenterica serovar Paratyphi (A, B and C), and contributes significantly to global disease burden. One of the major challenges in the diagnosis of paratyphoid fever is the lack of a proper gold standard. Given the absence of a licensed vaccine against S. Paratyphi, this diagnostic gap leads to inappropriate antibiotics use, thus, enhancing antimicrobial resistance. In addition, the symptoms of paratyphoid overlap with other infections, including the closely related typhoid fever. Since the development and utilization of a standard, sensitive, and accurate diagnostic method is essential in controlling any disease, this review discusses a new promising approach to aid the diagnosis of paratyphoid fever. This advocated approach is based on the use of surface plasmon resonance (SPR) biosensor and DNA probes to detect specific nucleic acid sequences of S. Paratyphi. We believe that this SPR-based genoassay can be a potent alternative to the current conventional diagnostic methods, and could become a rapid diagnostic tool for paratyphoid fever.
Fulltext Nucleic Acid-Based Diagnostic Tests for the Detection SARS-CoV-2: An Update

Yu CY, Chan KG, Yean CY, Ang GY

Diagnostics (Basel), 2021 Jan 01;11(1).
PMID: 33401392 DOI: 10.3390/diagnostics11010053

The coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) began as a cluster of pneumonia cases in Wuhan, China before spreading to over 200 countries and territories on six continents in less than six months. Despite rigorous global containment and quarantine efforts to limit the transmission of the virus, COVID-19 cases and deaths have continued to increase, leaving devastating impacts on the lives of many with far-reaching effects on the global society, economy and healthcare system. With over 43 million cases and 1.1 million deaths recorded worldwide, accurate and rapid diagnosis continues to be a cornerstone of pandemic control. In this review, we aim to present an objective overview of the latest nucleic acid-based diagnostic tests for the detection of SARS-CoV-2 that have been authorized by the Food and Drug Administration (FDA) under emergency use authorization (EUA) as of 31 October 2020. We systematically summarize and compare the principles, technologies, protocols and performance characteristics of amplification- and sequencing-based tests that have become alternatives to the CDC 2019-nCoV Real-Time RT-PCR Diagnostic Panel. We highlight the notable features of the tests including authorized settings, along with the advantages and disadvantages of the tests. We conclude with a brief discussion on the current challenges and future perspectives of COVID-19 diagnostics.
Fulltext Thermostable Heptaplex PCR Assay for the Detection of Six Respiratory Bacterial Pathogens

Nik Zuraina NMN, Goni MD, Amalina KN, Hasan H, Mohamad S, Suraiya S

Diagnostics (Basel), 2021 Apr 22;11(5).
PMID: 33922299 DOI: 10.3390/diagnostics11050753

A thermostabilized, multiplex polymerase chain reaction (mPCR) assay was developed in this study for the detection of six respiratory bacterial pathogens. Specific primers were designed for an internal amplification control (IAC) and six target sequences from Klebsiella pneumoniae, Staphylococcus aureus, Streptococcus pneumoniae, Pseudomonas aeruginosa, Mycobacterium tuberculosis, and Haemophilus influenzae. The resultant seven-band positive amplification control (PAC) of this heptaplex PCR assay corresponded to 105 base pairs (bp) of IAC, 202 bp of K. pneumoniae, 293 bp of S. aureus, 349 bp of S. pneumoniae, 444 bp of P. aeruginosa, 505 bp of M. tuberculosis, and 582 bp of H. influenzae. Results found that 6% (w/v) of the stabilizer was optimum to preserve the functional conformation of Taq DNA polymerase enzyme. This assay was stable at ambient temperature for at least 6 months. The sensitivity and specificity of this assay were both 100% when testing on the intended target organisms (n = 119) and non-intended species (n = 57). The mPCR assay developed in this study enabled accurate, rapid, and simple detection of six respiratory bacteria.
Fulltext Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification

Haque F, Bin Ibne Reaz M, Chowdhury MEH, Srivastava G, Hamid Md Ali S, Bakar AAA, et al.

Diagnostics (Basel), 2021 Apr 28;11(5).
PMID: 33925190 DOI: 10.3390/diagnostics11050801

BACKGROUND: Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature.
METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms.
RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs.
CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.
Fulltext Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

Islam MJ, Ahmad S, Haque F, Reaz MBI, Bhuiyan MAS, Islam MR

Diagnostics (Basel), 2021 May 07;11(5).
PMID: 34067203 DOI: 10.3390/diagnostics11050843

A force-invariant feature extraction method derives identical information for all force levels. However, the physiology of muscles makes it hard to extract this unique information. In this context, we propose an improved force-invariant feature extraction method based on nonlinear transformation of the power spectral moments, changes in amplitude, and the signal amplitude along with spatial correlation coefficients between channels. Nonlinear transformation balances the forces and increases the margin among the gestures. Additionally, the correlation coefficient between channels evaluates the amount of spatial correlation; however, it does not evaluate the strength of the electromyogram signal. To evaluate the robustness of the proposed method, we use the electromyogram dataset containing nine transradial amputees. In this study, the performance is evaluated using three classifiers with six existing feature extraction methods. The proposed feature extraction method yields a higher pattern recognition performance, and significant improvements in accuracy, sensitivity, specificity, precision, and F1 score are found. In addition, the proposed method requires comparatively less computational time and memory, which makes it more robust than other well-known feature extraction methods.
Fulltext Detection of COVID-19 Virus on Surfaces Using Photonics: Challenges and Perspectives

Taha BA, Al Mashhadany Y, Bachok NN, Ashrif A Bakar A, Hafiz Mokhtar MH, Dzulkefly Bin Zan MS, et al.

Diagnostics (Basel), 2021 Jun 19;11(6).
PMID: 34205401 DOI: 10.3390/diagnostics11061119

The propagation of viruses has become a global threat as proven through the coronavirus disease (COVID-19) pandemic. Therefore, the quick detection of viral diseases and infections could be necessary. This study aims to develop a framework for virus diagnoses based on integrating photonics technology with artificial intelligence to enhance healthcare in public areas, marketplaces, hospitals, and airfields due to the distinct spectral signatures from lasers' effectiveness in the classification and monitoring of viruses. However, providing insights into the technical aspect also helps researchers identify the possibilities and difficulties in this field. The contents of this study were collected from six authoritative databases: Web of Science, IEEE Xplore, Science Direct, Scopus, PubMed Central, and Google Scholar. This review includes an analysis and summary of laser techniques to diagnose COVID-19 such as fluorescence methods, surface-enhanced Raman scattering, surface plasmon resonance, and integration of Raman scattering with SPR techniques. Finally, we select the best strategies that could potentially be the most effective methods of reducing epidemic spreading and improving healthcare in the environment.
Fulltext Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation

Abdani SR, Zulkifley MA, Zulkifley NH

Diagnostics (Basel), 2021 Jun 17;11(6).
PMID: 34204479 DOI: 10.3390/diagnostics11061104

Pterygium is an eye condition that is prevalent among workers that are frequently exposed to sunlight radiation. However, most of them are not aware of this condition, which motivates many volunteers to set up health awareness booths to give them free health screening. As a result, a screening tool that can be operated on various platforms is needed to support the automated pterygium assessment. One of the crucial functions of this assessment is to extract the infected regions, which directly correlates with the severity levels. Hence, Group-PPM-Net is proposed by integrating a spatial pyramid pooling module (PPM) and group convolution to the deep learning segmentation network. The system uses a standard mobile phone camera input, which is then fed to a modified encoder-decoder convolutional neural network, inspired by a Fully Convolutional Dense Network that consists of a total of 11 dense blocks. A PPM is integrated into the network because of its multi-scale capability, which is useful for multi-scale tissue extraction. The shape of the tissues remains relatively constant, but the size will differ according to the severity levels. Moreover, group and shuffle convolution modules are also integrated at the decoder side of Group-PPM-Net by placing them at the starting layer of each dense block. The addition of these modules allows better correlation among the filters in each group, while the shuffle process increases channel variation that the filters can learn from. The results show that the proposed method obtains mean accuracy, mean intersection over union, Hausdorff distance, and Jaccard index performances of 0.9330, 0.8640, 11.5474, and 0.7966, respectively.
Fulltext Assessment of Potential Risk Factors and Skin Ultrasound Presentation Associated with Breast Cancer-Related Lymphedema in Long-Term Breast Cancer Survivors

Yusof KM, Avery-Kiejda KA, Ahmad Suhaimi S, Ahmad Zamri N, Rusli MEF, Mahmud R, et al.

Diagnostics (Basel), 2021 Jul 21;11(8).
PMID: 34441238 DOI: 10.3390/diagnostics11081303

Breast cancer has been reported to have the highest survival rate among various cancers. However, breast cancer survivors face several challenges following breast cancer treatment including breast cancer-related lymphedema (BCRL), sexual dysfunction, and psychological distress. This study aimed to investigate the potential risk factors of BCRL in long term breast cancer survivors. A total of 160 female breast cancer subjects were recruited on a voluntary basis and arm lymphedema was assessed through self-reporting of diagnosis, arm circumference measurement, and ultrasound examination. A total of 33/160 or 20.5% of the women developed BCRL with significantly higher scores for upper extremity disability (37.14 ± 18.90 vs. 20.08 ± 15.29, p < 0.001) and a lower score for quality of life (103.91 ± 21.80 vs. 115.49 ± 16.80, p = 0.009) as compared to non-lymphedema cases. Univariate analysis revealed that multiple surgeries (OR = 5.70, 95% CI: 1.21-26.8, p < 0.001), axillary lymph nodes excision (>10) (OR = 2.83, 95% CI: 0.94-8.11, p = 0.047), being overweight (≥25 kg/m2) (OR = 2.57, 95% CI: 1.04 - 6.38, p = 0.036), received fewer post-surgery rehabilitation treatment (OR = 2.37, 95% CI: 1.05-5.39, p = 0.036) and hypertension (OR = 2.38, 95% CI: 1.01-5.62, p = 0.043) were associated with an increased risk of BCRL. Meanwhile, multivariate analysis showed that multiple surgeries remained significant and elevated the likelihood of BCRL (OR = 5.83, 95% CI: 1.14-29.78, p = 0.034). Arm swelling was more prominent in the forearm area demonstrated by the highest difference of arm circumference measurement when compared to the upper arm (2.07 ± 2.48 vs. 1.34 ± 1.91 cm, p < 0.001). The total of skinfold thickness of the affected forearm was also significantly higher than the unaffected arms (p < 0.05) as evidenced by the ultrasound examination. The continuous search for risk factors in specific populations may facilitate the development of a standardized method to reduce the occurrence of BCRL and provide better management for breast cancer patients.
Fulltext An Artificial Intelligence-Enabled Pipeline for Medical Domain: Malaysian Breast Cancer Survivorship Cohort as a Case Study

Ganggayah MD, Dhillon SK, Islam T, Kalhor F, Chiang TC, Kalafi EY, et al.

Diagnostics (Basel), 2021 Aug 18;11(8).
PMID: 34441426 DOI: 10.3390/diagnostics11081492

Automated artificial intelligence (AI) systems enable the integration of different types of data from various sources for clinical decision-making. The aim of this study is to propose a pipeline to develop a fully automated clinician-friendly AI-enabled database platform for breast cancer survival prediction. A case study of breast cancer survival cohort from the University Malaya Medical Centre was used to develop and evaluate the pipeline. A relational database and a fully automated system were developed by integrating the database with analytical modules (machine learning, automated scoring for quality of life, and interactive visualization). The developed pipeline, iSurvive has helped in enhancing data management as well as to visualize important prognostic variables and survival rates. The embedded automated scoring module demonstrated quality of life of patients whereas the interactive visualizations could be used by clinicians to facilitate communication with patients. The pipeline proposed in this study is a one-stop center to manage data, to automate analytics using machine learning, to automate scoring and to produce explainable interactive visuals to enhance clinician-patient communication along the survivorship period to modify behaviours that relate to prognosis. The pipeline proposed can be modelled on any disease not limited to breast cancer.
Fulltext Residual-Shuffle Network with Spatial Pyramid Pooling Module for COVID-19 Screening

Zulkifley MA, Abdani SR, Zulkifley NH, Shahrimin MI

Diagnostics (Basel), 2021 Aug 19;11(8).
PMID: 34441431 DOI: 10.3390/diagnostics11081497

Since the start of the COVID-19 pandemic at the end of 2019, more than 170 million patients have been infected with the virus that has resulted in more than 3.8 million deaths all over the world. This disease is easily spreadable from one person to another even with minimal contact, even more for the latest mutations that are more deadly than its predecessor. Hence, COVID-19 needs to be diagnosed as early as possible to minimize the risk of spreading among the community. However, the laboratory results on the approved diagnosis method by the World Health Organization, the reverse transcription-polymerase chain reaction test, takes around a day to be processed, where a longer period is observed in the developing countries. Therefore, a fast screening method that is based on existing facilities should be developed to complement this diagnosis test, so that a suspected patient can be isolated in a quarantine center. In line with this motivation, deep learning techniques were explored to provide an automated COVID-19 screening system based on X-ray imaging. This imaging modality is chosen because of its low-cost procedures that are widely available even in many small clinics. A new convolutional neural network (CNN) model is proposed instead of utilizing pre-trained networks of the existing models. The proposed network, Residual-Shuffle-Net, comprises four stacks of the residual-shuffle unit followed by a spatial pyramid pooling (SPP) unit. The architecture of the residual-shuffle unit follows an hourglass design with reduced convolution filter size in the middle layer, where a shuffle operation is performed right after the split branches have been concatenated back. Shuffle operation forces the network to learn multiple sets of features relationship across various channels instead of a set of global features. The SPP unit, which is placed at the end of the network, allows the model to learn multi-scale features that are crucial to distinguish between the COVID-19 and other types of pneumonia cases. The proposed network is benchmarked with 12 other state-of-the-art CNN models that have been designed and tuned specially for COVID-19 detection. The experimental results show that the Residual-Shuffle-Net produced the best performance in terms of accuracy and specificity metrics with 0.97390 and 0.98695, respectively. The model is also considered as a lightweight model with slightly more than 2 million parameters, which makes it suitable for mobile-based applications. For future work, an attention mechanism can be integrated to target certain regions of interest in the X-ray images that are deemed to be more informative for COVID-19 diagnosis.
Fulltext Stability and Reproducibility of Radiomic Features Based Various Segmentation Technique on MR Images of Hepatocellular Carcinoma (HCC)

Haniff NSM, Abdul Karim MK, Osman NH, Saripan MI, Che Isa IN, Ibahim MJ

Diagnostics (Basel), 2021 Aug 30;11(9).
PMID: 34573915 DOI: 10.3390/diagnostics11091573

Hepatocellular carcinoma (HCC) is considered as a complex liver disease and ranked as the eighth-highest mortality rate with a prevalence of 2.4% in Malaysia. Magnetic resonance imaging (MRI) has been acknowledged for its advantages, a gold technique for diagnosing HCC, and yet the false-negative diagnosis from the examinations is inevitable. In this study, 30 MR images from patients diagnosed with HCC is used to evaluate the robustness of semi-automatic segmentation using the flood fill algorithm for quantitative features extraction. The relevant features were extracted from the segmented MR images of HCC. Four types of features extraction were used for this study, which are tumour intensity, shape feature, textural feature and wavelet feature. A total of 662 radiomic features were extracted from manual and semi-automatic segmentation and compared using intra-class relation coefficient (ICC). Radiomic features extracted using semi-automatic segmentation utilized flood filling algorithm from 3D-slicer had significantly higher reproducibility (average ICC = 0.952 ± 0.009, p < 0.05) compared with features extracted from manual segmentation (average ICC = 0.897 ± 0.011, p > 0.05). Moreover, features extracted from semi-automatic segmentation were more robust compared to manual segmentation. This study shows that semi-automatic segmentation from 3D-Slicer is a better alternative to the manual segmentation, as they can produce more robust and reproducible radiomic features.
Fulltext RT-LAMP CRISPR-Cas12/13-Based SARS-CoV-2 Detection Methods

Selvam K, Najib MA, Khalid MF, Mohamad S, Palaz F, Ozsoz M, et al.

Diagnostics (Basel), 2021 Sep 08;11(9).
PMID: 34573987 DOI: 10.3390/diagnostics11091646

Coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), has attracted public attention. The gold standard for diagnosing COVID-19 is reverse transcription-quantitative polymerase chain reaction (RT-qPCR). However, RT-qPCR can only be performed in centralized laboratories due to the requirement for advanced laboratory equipment and qualified workers. In the last decade, clustered regularly interspaced short palindromic repeats (CRISPR) technology has shown considerable promise in the development of rapid, highly sensitive, and specific molecular diagnostic methods that do not require complicated instrumentation. During the current COVID-19 pandemic, there has been growing interest in using CRISPR-based diagnostic techniques to develop rapid and accurate assays for detecting SARS-CoV-2. In this work, we review and summarize reverse-transcription loop-mediated isothermal amplification (RT-LAMP) CRISPR-based diagnostic techniques for detecting SARS-CoV-2.
Fulltext Neoteric Algorithm Using Cell Population Data (VCS Parameters) as a Rapid Screening Tool for Haematological Disorders

Ambayya A, Sathar J, Hassan R

Diagnostics (Basel), 2021 Sep 09;11(9).
PMID: 34573992 DOI: 10.3390/diagnostics11091652

Hitherto, there has been no comprehensive study on the usefulness of cell population data (CPD) parameters as a screening tool in the discrimination of non-neoplastic and neoplastic haematological disorders. Hence, we aimed to develop an algorithm derived from CPD parameters to enable robust screening of neoplastic from non-neoplastic samples and subsequently to aid in differentiating various neoplastic haematological disorders. In this study, the CPD parameters from 245 subtypes of leukaemia and lymphoma were compared against 1103 non-neoplastic cases, and those CPD parameters that were vigorous discriminants were selected for algorithm development. We devised a novel algorithm: [(SD-V-NE*MN-UMALS-LY*SD-AL2-MO)/MN-C-NE] to distinguish neoplastic from non-neoplastic cases. Following that, the single parameter MN-AL2-NE was used as a discriminant to rule out reactive cases from neoplastic cases. We then assessed CPD parameters that were useful in delineating leukaemia subtypes as follows: AML (SD-MALS-NE and SD-UMALS-NE), APL (MN-V-NE and SD-V-MO), ALL (MN-MALS-NE and MN-LMALS-NE) and CLL (SD-C-MO). Prospective studies were carried out to validate the algorithm and single parameter, MN-AL2-NE. We propose these CPD parameter-based discriminant strategies to be adopted as an initial screening and flagging system in the preliminary evaluation of leukocyte morphology.

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links