MyMedR

Displaying publications 1 - 20 of 53 in total

Abstract:

Sort:

Evaluation of a new predictive equation for automated calculation of size-specific dose estimate (SSDE) in CT imaging

Osman ND, Abdulkadir MK, Shuaib IL, Nasirudin RA

Radiography (Lond), 2024 Jan;30(1):237-244.
PMID: 38035439 DOI: 10.1016/j.radi.2023.11.012

INTRODUCTION: The adoption of size-specific dose estimate (SSDE) in clinical practice is still limited owing to the tedious and complex manual measurement of individual patient size for the clinical calculation of SSDE. Thus, the automation of SSDE is imperative. This study aims to evaluate a predictive equation for the automated calculation of SSDE.
METHODS: A user-friendly software was developed to accurately predict the individual size-specific dose estimation of paediatric patients undergoing computed tomography (CT) scans of the head, thorax, and abdomen. The software includes a calculation equation developed based on a novel SSDE prediction equation that used a population's pre-determined percentage difference between volume-weighted computed tomography dose index (CTDIvol) and SSDE with age. American Association of Physicists in Medicine (AAPM RPT 204) method (manual) and segmentation-based SSDE calculators (indoseCT and XXautocalc) were used to assess the proposed software predictions comparatively.
RESULTS: The results of this study show that the automated equation-based calculation of SSDE and the manual and segmentation-based calculation of SSDE are in good agreement for patients. The differences between the automated equation-based calculation of SSDE and the manual and segmentation-based calculation are less than 3%.
CONCLUSION: This study validated an accurate SSDE calculator that allows users to enter key input values and calculate SSDE.
IMPLICATION FOR PRACTICE: The automated equation-based SSDE software (PESSD) seems a promising tool for estimating individualised CT doses during CT scans.

Matched MeSH terms: Thorax
Assessment of breast dose and cancer risk for young females during CT chest and abdomen examinations

Tamam N, Sulieman A, Omer H, Toufig H, Alsaadi M, Salah H, et al.

Appl Radiat Isot, 2022 Dec;190:110452.
PMID: 36183658 DOI: 10.1016/j.apradiso.2022.110452

CT scanning deliver much higher radiation doses than planar radiological procedures, which puts patients to high risks. This study measures and evaluates patient doses during chest and abdomen computed tomography procedures. Particular attention is given to measuring the dose to the equivalent breast (mSv) and to estimate the associated risks of breast cancer to young female patients (15-35 years). Data was obtained from standard examinations from three hospitals. The measured values of CT dose indexes, CTDI (mGy) as well as exposure-related parameters were used for assessment. Breast and effective doses were extrapolated using a software. The results showed remarkable variations of the mean organ equivalent doses for similar CT examinations in the studied hospitals. This could be attributed to the variation in CT scanning imaging technique, and clinical indications. The average effective dose to the chest was 7.9 mSv (2.3-47.0 mSv) and for the abdomen the mean dose was 6.6 mSv, ranging from (3.3-27 mSv). The breast received equivalent doses from chest and abdomen procedures as follows: 10.2 (1.6-33 mSv) and 10.1(2.3-19 mS) Sv respectively. Each procedure yielded high risks of breast cancer for young females. Implementation of accurate referral criteria is recommended to avoid unnecessary breast radiation exposure.

Matched MeSH terms: Thorax
Fulltext Biomechanics Analysis of the Firefighters' Thorax Movement on Personal Protective Equipment during Lifting Task Using Inertial Measurement Unit Motion Capture

Yunus MNH, Jaafar MH, Mohamed ASA, Azraai NZ, Amil N, Zein RM

Int J Environ Res Public Health, 2022 Oct 31;19(21).
PMID: 36361112 DOI: 10.3390/ijerph192114232

Back injury is a common musculoskeletal injury reported among firefighters (FFs) due to their nature of work and personal protective equipment (PPE). The nature of the work associated with heavy lifting tasks increases FFs' risk of back injury. This study aimed to assess the biomechanics movement of FFs on personal protective equipment during a lifting task. A set of questionnaires was used to identify the prevalence of musculoskeletal pain experienced by FFs. Inertial measurement unit (IMU) motion capture was used in this study to record the body angle deviation and angular acceleration of FFs' thorax extension. The descriptive analysis was used to analyze the relationship between the FFs' age and body mass index with the FFs' thorax movement during the lifting task with PPE and without PPE. Sixty-three percent of FFs reported lower back pain during work, based on the musculoskeletal pain questionnaire. The biomechanics analysis of thorax angle deviation and angular acceleration has shown that using FFs PPE significantly causes restricted movement and limited mobility for the FFs. As regards human factors, the FFs' age influences the angle deviation while wearing PPE and FFs' BMI influences the angular acceleration without wearing PPE during the lifting activity.

Matched MeSH terms: Thorax
Correlation between Hounsfield unit derived from head, thorax, abdomen, spine and pelvis CT and t-scores from DXA

Amin MFM, Zakaria WMW, Yahya N

Skeletal Radiol, 2021 Dec;50(12):2525-2535.
PMID: 34021364 DOI: 10.1007/s00256-021-03801-z

OBJECTIVES: CT examination can potentially be utilised for early detection of bone density changes with no additional procedure and radiation dose. We hypothesise that the Hounsfield unit (HU) measured from CT images is correlated to the t-scores derived from dual energy X-ray absorptiometry (DXA) in multiple anatomic regions.
MATERIALS & METHODS: Data were obtained retrospectively from all patients who underwent both CT examinations - brain (frontal bone), thorax (T7), abdomen (L3), spine (T7 & L3) or pelvis (left hip) - and DXA between 2014 and 2018 in our centre. To ensure comparability, the period between CT and DXA studies must not exceed one year. Correlations between HU values and t-scores were calculated using Pearson's correlation. Receiver operating characteristic (ROC) curves were generated, and the area under the curve (AUC) was used to determine threshold HU values for predicting osteoporosis.
RESULTS: The inclusion criteria were met by 1043 CT examinations (136 head, 537 thorax, 159 lumbar and 151 left hip). The left hip consistently provided the most robust correlations (r = 0.664-0.708, p thorax T7 and lumbar L3 showed average correlations (range of r values is 0.497-0.679, p 0.05.
CONCLUSION: HU values derived from the hip, T7 and L3 provided a good to moderate correlation to t-scores with a good prediction for osteoporosis. The suggested optimal thresholds may be used in clinical settings after external validations are performed.

Matched MeSH terms: Thorax
Fulltext Deep Mining Generation of Lung Cancer Malignancy Models from Chest X-ray Images

Horry M, Chakraborty S, Pradhan B, Paul M, Gomes D, Ul-Haq A, et al.

Sensors (Basel), 2021 Oct 07;21(19).
PMID: 34640976 DOI: 10.3390/s21196655

Lung cancer is the leading cause of cancer death and morbidity worldwide. Many studies have shown machine learning models to be effective in detecting lung nodules from chest X-ray images. However, these techniques have yet to be embraced by the medical community due to several practical, ethical, and regulatory constraints stemming from the "black-box" nature of deep learning models. Additionally, most lung nodules visible on chest X-rays are benign; therefore, the narrow task of computer vision-based lung nodule detection cannot be equated to automated lung cancer detection. Addressing both concerns, this study introduces a novel hybrid deep learning and decision tree-based computer vision model, which presents lung cancer malignancy predictions as interpretable decision trees. The deep learning component of this process is trained using a large publicly available dataset on pathological biomarkers associated with lung cancer. These models are then used to inference biomarker scores for chest X-ray images from two independent data sets, for which malignancy metadata is available. Next, multi-variate predictive models were mined by fitting shallow decision trees to the malignancy stratified datasets and interrogating a range of metrics to determine the best model. The best decision tree model achieved sensitivity and specificity of 86.7% and 80.0%, respectively, with a positive predictive value of 92.9%. Decision trees mined using this method may be considered as a starting point for refinement into clinically useful multi-variate lung cancer malignancy models for implementation as a workflow augmentation tool to improve the efficiency of human radiologists.

Matched MeSH terms: Thorax
Radiomics approach for survival prediction in chronic obstructive pulmonary disease

Cho YH, Seo JB, Lee SM, Kim N, Yun J, Hwang JE, et al.

Eur Radiol, 2021 Oct;31(10):7316-7324.
PMID: 33847809 DOI: 10.1007/s00330-021-07747-7

OBJECTIVES: To apply radiomics analysis for overall survival prediction in chronic obstructive pulmonary disease (COPD), and evaluate the performance of the radiomics signature (RS).
METHODS: This study included 344 patients from the Korean Obstructive Lung Disease (KOLD) cohort. External validation was performed on a cohort of 112 patients. In total, 525 chest CT-based radiomics features were semi-automatically extracted. The five most useful features for survival prediction were selected by least absolute shrinkage and selection operation (LASSO) Cox regression analysis and used to generate a RS. The ability of the RS for classifying COPD patients into high or low mortality risk groups was evaluated with the Kaplan-Meier survival analysis and Cox proportional hazards regression analysis.
RESULTS: The five features remaining after the LASSO analysis were %LAA-950, AWT_Pi10_6th, AWT_Pi10_heterogeneity, %WA_heterogeneity, and VA18mm. The RS demonstrated a C-index of 0.774 in the discovery group and 0.805 in the validation group. Patients with a RS greater than 1.053 were classified into the high-risk group and demonstrated worse overall survival than those in the low-risk group in both the discovery (log-rank test, < 0.001; hazard ratio [HR], 5.265) and validation groups (log-rank test, < 0.001; HR, 5.223). For both groups, RS was significantly associated with overall survival after adjustments for patient age and body mass index.
CONCLUSIONS: A radiomics approach for survival prediction and risk stratification in COPD patients is feasible, and the constructed radiomics model demonstrated acceptable performance. The RS derived from chest CT data of COPD patients was able to effectively identify those at increased risk of mortality.
KEY POINTS: • A total of 525 chest CT-based radiomics features were extracted and the five radiomics features of %LAA-950, AWT_Pi10_6th, AWT_Pi10_heterogeneity, %WA_heterogeneity, and VA18mm were selected to generate a radiomics model. • A radiomics model for predicting survival of COPD patients demonstrated reliable performance with a C-index of 0.774 in the discovery group and 0.805 in the validation group. • Radiomics approach was able to effectively identify COPD patients with an increased risk of mortality, and patients assigned to the high-risk group demonstrated worse overall survival in both the discovery and validation groups.

Matched MeSH terms: Thorax
Fulltext Poland's syndrome mimicking traumatic chest injury

Ohn MH, Ohn KM

BMJ Case Rep, 2021 May 31;14(5).
PMID: 34059541 DOI: 10.1136/bcr-2020-241408

Poland's syndrome (PS) is a rare developmental anomaly that can manifest mild (pectoralis muscles involvement) to severe deformities (rib hypoplasia and hand deformities). We report a case of 69-year-old man who presented to the emergency department with a traumatic chest injury after a fall. It was initially thought to have a significant chest injury as the trauma survey revealed a palpable defect and tenderness in the right anterior chest wall. There was also a symbrachydactyly deformity in the right hand. CT of the chest showed lack of right pectoralis muscles, which were consistent with PS. This case highlights the importance of gathering detail history in adult trauma patients such as congenital disorder especially in the presence of bony deformity. With possibilities of several traumatic conditions in trauma patients eliminated, one can expand the non-traumatic differential, keeping in mind the possibility of a congenital disorder that can mimic traumatic chest injury.

Matched MeSH terms: Thorax
Single-stage open repair of severe asymmetric pectus excavatum and mitral valve replacement in connective tissue disease

Pau CP, Chong KS, Yakub MA, Khalil AA

Asian Cardiovasc Thorac Ann, 2021 May 04.
PMID: 33947231 DOI: 10.1177/02184923211014004

We present a 14-year-old boy with Loey-Dietz syndrome with severe mitral regurgitation, pectus excavatum and scoliosis. The Haller index was 25. The heart was displaced into the left hemithorax. The right inferior pulmonary vein was very close to the sternum and vertebral body. Single-stage surgery was performed. An osseo-myo-cutaneous pedicled flap was created by sterno-manubrial junction dislocation and rib resection with bilateral internal mammary arteries supplying the flap. Cardiopulmonary bypass and mitral valve replacement was performed. The defect was bridged with three straight plates. The flap was laid on top and anchored. Early outcome at three months was good.

Matched MeSH terms: Thorax
Fulltext Aggressive scalp and sternal lesion: A presentation of rare case of metastatic eccrine carcinoma

Rownose CS, Mohamad Saupi MS, Sharif SZ, Lah NASN

Ann Med Surg (Lond), 2021 May;65:102322.
PMID: 33996055 DOI: 10.1016/j.amsu.2021.102322

Introduction: Ductal Eccrine carcinoma (DEC) is a rare primary cutaneous tumor that exhibits both squamous and adnexal ductal differentiation. Due to its rarity in clinical practice we present as case of DEC and a literature review on the latest management of this rare disease.
Case presentation: We report a case 41 years old female presented with lesion on the scalp and sternal mass, increasing in size with itchiness and erythematous for 6 months duration. Further CECT scan of brain and neck shows features of malignant left frontal scalp lesion with poor plane with overlying skin and underlying skull bone and CECT of thorax shows a large, irregular heterogeneously enhancing mass with necrotic center noted at right hilar within superior segment of right lower lobe, encasing right middle and lower lobe bronchi. Wedge biopsy of scalp lesion showed an intradermal lesion extensively infiltrating by malignant gland accompanied by desmoplasia and the tumor cells are seen extending into the surgical margins suggestive of ductal eccrine carcinoma.Clinical Discussion:This case highlights the importance and challenges in achieving early diagnosis coupled with the scarcity of information on these leads to difficulty in managing this patient.
Conclusion: In managing Ductal Eccrine Carcinoma tumor, standard method of treatment for has not been established. However, wide surgical excision is the treatment of choice for localized lesions. Regarding prognosis, there is conflicting data published which we describe in this article.

Matched MeSH terms: Thorax
The Cobblestone Heart

Tan WJ, Suz CS, Azza O, Zuki M

Med J Malaysia, 2021 03;76(2):241-244.
PMID: 33742636

Sarcoidosis is a chronic, multisystem disorder. A 38 years old lady presented at Hospital Raja Perempuan Zainab II, Kota Bharu ,Malaysia with cough and breathless for 2 months and constitutional symptoms of weight loss and loss of appetite. She was initially treated as smear negative pulmonary tuberculosis for 5 months. However, her clinical condition deteriorated with worsening New York Heart Association (NYHA) class 1 to class 3. Subsequently, workout of computed tomography( CT) thorax showed multiple perilymphatic distribution of nodules and multiple mediastinal lymphadenopathy coupled with pleura biopsy showed non caseating granuloma and cardiac magnetic resonance imaging (MRI) with positive late gadolinium enhancement revised the diagnosis of pulmonary sarcoidosis with cardiac involvement. Patient's functional status and cough improved with immunosuppresant was given in tapering dose fashion.

Matched MeSH terms: Thorax
Fulltext Kashima operation: an endoscopic phonosurgery by laser for bilateral vocal cord palsy

Alamgir Chowdhury, M., Farid Hossain Chowdhury, Khaled Bin Shahabuddin, Tofazzal Hossain, A.B.M., Shaila Kabir

Borneo Journal of Medical Sciences, 2021;15(1):31-35.
MyJurnal

Complete or partial restriction of the vocal cords usually occurs due to cancer, neurologic causes or mechanical causes like huge neck mass, trauma to the neck, viral infection, and sometimes iatrogenic during surgery. Bilateral vocal cord palsy is a severe condition that can lead to significant problems in breathing, speaking, and swallowing. If any patient presents with stridor, it requires urgent surgical airway management followed by specific treatment. A case of viral bilateral abductor vocal cord palsy in a 41-year-old female is reported here. The patient presented with stridor, and immediate tracheostomy was done. The stridor developed first 3 months earlier followed by cold and fever for a week. The stridor worsened gradually and leads to a state of commencing immediate tracheostomy. There was no history of trauma to the neck or any neck surgery. All basic laboratory blood test was within the normal limit. The laryngoscopic examination showed both vocal cords were immobile and almost median position with a small gap at the posterior commissure. Chest and neck plain X-ray along with computed tomography scan of neck was normal which ruled out the other causes of bilateral vocal cord palsy. The patient subsequently underwent successful left posterior cordectomy by laser, and decannulation of tracheostomy was done, known as Kashima operation.

Matched MeSH terms: Thorax
Vector competence of Malaysian Aedes aegypti to Zika virus and impact of sequential arbovirus infections

Ong NH, Chua CL, Liew JWK, Wan Sulaiman WY, Chan YF, Sam IC, et al.

Acta Trop, 2020 Aug;208:105472.
PMID: 32389451 DOI: 10.1016/j.actatropica.2020.105472

Zika virus (ZIKV) is a mosquito-borne flavivirus with global impact since 2015. Although ZIKV was first isolated from Aedes aegypti in Malaysia in 1965, not much is known about the competency of Malaysian Ae. aegypti to ZIKV. To date only 9 cases of ZIKV have been reported in Malaysia despite the abundance of mosquito vectors. This study aimed to determine the susceptibility of Ae. aegypti to ZIKV, and the impact of sequential infections in Ae. aegypti mosquitoes with DENV serotype 2 (DENV-2) followed by ZIKV. Field-caught urban Ae. aegypti were orally challenged with a Martinique strain of ZIKV, and midgut, head/thorax and saliva were collected at 3, 7 and 14 days post-infection (dpi). At 14 dpi, ZIKV-exposed mosquitoes had infection and dissemination rates of 59% (n=10/17) and 90% (n=9/10), respectively. Average titres of 3.9 and 4.4 log pfu infectious ZIKV were recovered in midgut and head/thorax, respectively. In sequential infection, prior exposure of Ae. aegypti to DENV did not affect the subsequent ZIKV infection in head/thorax albeit with a low sample size. In conclusion, Malaysian urban Ae. aegypti is susceptible to the contemporary Asian lineage of ZIKV. The established and continuous DENV circulation in Ae. aegypti did not suppress ZIKV emergence in Malaysia. Other factors contributing to low level of ZIKV circulation in Malaysia remain to be explored.

Matched MeSH terms: Thorax
Fulltext A case of primary pleural synovial sarcoma with endobronchial recurrence

Wan JL, Lam YF, Foong KW, Abdul Ghani N, Lachmanan K

Respirol Case Rep, 2020 Apr;8(3):e00547.
PMID: 32166036 DOI: 10.1002/rcr2.547

Primary pleural synovial sarcoma (PPSS) is an extremely rare malignancy without a known cause. The diagnosis is made after excluding metastasis from an extra-thoracic sarcoma. We report a case of a 67-year-old gentleman who presented with an incidental finding of a left lung mass on a routine chest X-ray. A computed tomography (CT) of the thorax and whole-body positron emission tomography (PET)-CT was done confirming a left lung mass with no other extra-thoracic involvement. A lobectomy was performed with a diagnostic and therapeutic intent. The histopathological examination and immunohistochemistry study revealed a pleural-based tumour with features suggestive of synovial sarcoma. Subsequently, he underwent post-operative radiotherapy. However, three months later, he developed an endobronchial recurrence, complicated by post-obstructive pneumonia resulting in his demise. This case highlights a rare form of malignancy with a rare site of recurrence.

Matched MeSH terms: Thorax
Psychometric evaluation of the shortened version of the Functional Difficulties Questionnaire to assess thoracic physical function

Katijjahbe MA, Denehy L, Granger CL, Royse A, Royse C, Logie S, et al.

Clin Rehabil, 2020 Jan;34(1):132-140.
PMID: 31610700 DOI: 10.1177/0269215519879476

OBJECTIVE: The aim of this study was to investigate the psychometric properties of the shortened version of the Functional Difficulties Questionnaire (FDQ).
DESIGN: This is a multisite observational study.
SETTING: The study was conducted in four tertiary care hospitals in Australia.
SUBJECTS: A total of 225 participants, following cardiac surgery, were involved in the study.
INTERVENTION: Participants completed the original 13-item FDQ and other measures of physical function, pain and health-related quality of life.
METHOD: Item reduction was utilized to develop the shortened version. Reliability was evaluated using intraclass correlation coefficients (ICCs), the smallest detectable change and Bland-Altman plots. The validity and responsiveness were evaluated using correlation. Anchor and distribution-based calculation was used to calculate the minimal clinical important difference (MCID).
RESULTS: Item reduction resulted in the creation of a 10-item shortened version of the questionnaire (FDQ-s). Within the cohort of cardiac surgery patient, the mean (SD) for the FDQ-s was 38.7 (19.61) at baseline; 15.5 (14.01) at four weeks and 7.9 (12.01) at three months. Validity: excellent internal consistency (Cronbach's α > 0.90) and fair-to-excellent construct validity (>0.4). Reliability: internal consistency was excellent (Cronbach's α > 0.8). The FDQ-s had excellent test-retest reliability (ICC = 0.89-0.92). Strong responsiveness overtime was demonstrated with large effect sizes (Cohen's d > 1.0). The MCID of the FDQ-s was calculated between 4 and 10 out of 100 (in cm).
CONCLUSION: The FDQ-s demonstrated robust psychometric properties as a measurement tool of physical function of the thoracic region following cardiac surgery.

Matched MeSH terms: Thorax/physiopathology*
Fulltext Vanishing lung syndrome Masquerading as bilateral pneumothorax: A case report

Muhamad NI, Mohd Nawi SN, Yusoff BM, Ab Halim NA, Mohammad N, Wan Ghazali WS

Respir Med Case Rep, 2020;31:101276.
PMID: 33209576 DOI: 10.1016/j.rmcr.2020.101276

Vanishing lung syndrome (VLS) is a rare condition characterized by giant emphysematous bullae. It is frequently misdiagnosed as pneumothorax. We describe a case of a 30-year-old male who presented with shortness of breath, reduced effort tolerance, and pleuritic chest pain for three months. He was initially diagnosed with bilateral pneumothorax based on clinical examination and chest radiograph findings. However, further imaging with a high resolution computed tomography (HRCT) of the thorax confirmed bilateral giant emphysematous bullae. Our patient subsequently underwent video-assisted thoracoscopic surgery (VATS) and bullectomy. In this report, we discuss the clinical presentations, radiological features, and the management of VLS. We also highlight the differentiating features of VLS from a pneumothorax.

Matched MeSH terms: Pneumothorax; Thorax
Fulltext Spontaneous oesophageal perforation: a case report

Shu Ann Hon, Jan Jan Chai, Lian Thai Lee, Qin Jian Low

Malaysian Journal of Medicine and Health Sciences, 2020;16(2):326-328.
MyJurnal

A 49-year-old gentleman presented with epigastric pain for one day associated with one episode of vomiting and dyspnoea. Respiratory examination showed reduced breath sound over his left lower zone. He was treated as left spontaneous pneumothorax and left lung empyema requiring left chest tube insertion and intravenous antibiotics. His left pleural fluid biochemistry result was exudative while its centrifuge showed empyema. In ward, we noticed food material draining from his left chest tube during feeding. An urgent contrast enhanced computed tomography (CECT) thorax showed a left oesophageal-pleural fistula with possible broncho-oesophageal fistula. During oesoph- agogastroduodenoscopy (OGDS), air bubbles were seen in his left under-water chest drainage during air-insufflation of the oesophagus. The revised diagnosis was Boerhaave syndrome. He was treated with an esophageal stent to cover the perforation and a left lung decortication via video assisted thoracoscopic surgery (VATS) for his left empyema. He improved and was discharged well.

Matched MeSH terms: Pneumothorax; Thorax
Lo, the ever confounding nipple shadow!

Boo WH, Chan YC

Malays Fam Physician, 2020;15(3):79-82.
PMID: 33329866

The discovery of a solitary pulmonary nodule (SPN) on chest imaging can be alarming for both the clinician and the patient. In the absence of a uniform guideline, managing SPN is nothing short of challenging for primary care physicians (PCPs). We present a case here of a patient presenting with prolonged cough who also displayed unilateral SPN on her chest radiograph. Through further examination, this presence was later shown to be a nipple shadow simulating SPN, and the patient was spared unnecessary testing and psychological distress.

Matched MeSH terms: Thorax
Fulltext COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings

Che Azemin MZ, Hassan R, Mohd Tamrin MI, Md Ali MA

Int J Biomed Imaging, 2020;2020:8828855.
PMID: 32849861 DOI: 10.1155/2020/8828855

The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing.

Matched MeSH terms: Thorax
Fulltext Optimised genetic algorithm-extreme learning machine approach for automatic COVID-19 detection

Albadr MAA, Tiun S, Ayob M, Al-Dhief FT, Omar K, Hamzah FA

PLoS One, 2020;15(12):e0242899.
PMID: 33320858 DOI: 10.1371/journal.pone.0242899

The coronavirus disease (COVID-19), is an ongoing global pandemic caused by severe acute respiratory syndrome. Chest Computed Tomography (CT) is an effective method for detecting lung illnesses, including COVID-19. However, the CT scan is expensive and time-consuming. Therefore, this work focus on detecting COVID-19 using chest X-ray images because it is widely available, faster, and cheaper than CT scan. Many machine learning approaches such as Deep Learning, Neural Network, and Support Vector Machine; have used X-ray for detecting the COVID-19. Although the performance of those approaches is acceptable in terms of accuracy, however, they require high computational time and more memory space. Therefore, this work employs an Optimised Genetic Algorithm-Extreme Learning Machine (OGA-ELM) with three selection criteria (i.e., random, K-tournament, and roulette wheel) to detect COVID-19 using X-ray images. The most crucial strength factors of the Extreme Learning Machine (ELM) are: (i) high capability of the ELM in avoiding overfitting; (ii) its usability on binary and multi-type classifiers; and (iii) ELM could work as a kernel-based support vector machine with a structure of a neural network. These advantages make the ELM efficient in achieving an excellent learning performance. ELMs have successfully been applied in many domains, including medical domains such as breast cancer detection, pathological brain detection, and ductal carcinoma in situ detection, but not yet tested on detecting COVID-19. Hence, this work aims to identify the effectiveness of employing OGA-ELM in detecting COVID-19 using chest X-ray images. In order to reduce the dimensionality of a histogram oriented gradient features, we use principal component analysis. The performance of OGA-ELM is evaluated on a benchmark dataset containing 188 chest X-ray images with two classes: a healthy and a COVID-19 infected. The experimental result shows that the OGA-ELM achieves 100.00% accuracy with fast computation time. This demonstrates that OGA-ELM is an efficient method for COVID-19 detecting using chest X-ray images.

Matched MeSH terms: Thorax/physiopathology; Thorax/virology
Fulltext Eye tracker as an implied social presence: awareness of being eye-tracked induces social-norm-based looking behaviour

Wong HK, Stephen ID

J Eye Mov Res, 2019 Aug 05;12(2).
PMID: 33828723 DOI: 10.16910/jemr.12.2.5

Human behaviour is not only influenced by the physical presence of others, but also implied social presence. This study examines the impact of awareness of being eye-tracked on eye movement behaviour in a laboratory setting. During a classic yes/no face recognition task, participants were made to believe that their eye movements were recorded (or not recorded) by eye trackers. Their looking patterns with and without the awareness of being eye-tracked were compared while perceiving social (faces, faces-and-bodies) and non-social (inanimate objects) video stimuli. Area-of-interest (AOI) analysis revealed that misinformed participants (who were not aware that their eye movements were being recorded) looked more at the body (chest and waist) compared to informed participants (who believed they were being eye-tracked), whereas informed participants fixated longer on the mouth and shorter on the eyes of female models than misinformed participants did. These findings highlight the potential impact of an awareness of being eye tracked on one's eye movement pattern when perceiving a social stimulus. We conclude that even within laboratory settings an eye tracker may function as an implied social presence that leads individuals to modify their eye movement behaviour according to socially-derived inhibitory norms.

Matched MeSH terms: Thorax

Filters

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

External Links