MyMedR

Displaying all 3 publications

Abstract:

Sort:

Development of a multi-fusion convolutional neural network (MF-CNN) for enhanced gastrointestinal disease diagnosis in endoscopy image analysis

Hossain T, Shamrat FMJM, Zhou X, Mahmud I, Mazumder MSA, Sharmin S, et al.

PeerJ Comput Sci, 2024;10:e1950.
PMID: 38660192 DOI: 10.7717/peerj-cs.1950

Gastrointestinal (GI) diseases are prevalent medical conditions that require accurate and timely diagnosis for effective treatment. To address this, we developed the Multi-Fusion Convolutional Neural Network (MF-CNN), a deep learning framework that strategically integrates and adapts elements from six deep learning models, enhancing feature extraction and classification of GI diseases from endoscopic images. The MF-CNN architecture leverages truncated and partially frozen layers from existing models, augmented with novel components such as Auxiliary Fusing Layers (AuxFL), Fusion Residual Block (FuRB), and Alpha Dropouts (αDO) to improve precision and robustness. This design facilitates the precise identification of conditions such as ulcerative colitis, polyps, esophagitis, and healthy colons. Our methodology involved preprocessing endoscopic images sourced from open databases, including KVASIR and ETIS-Larib Polyp DB, using adaptive histogram equalization (AHE) to enhance their quality. The MF-CNN framework supports detailed feature mapping for improved interpretability of the model's internal workings. An ablation study was conducted to validate the contribution of each component, demonstrating that the integration of AuxFL, αDO, and FuRB played a crucial part in reducing overfitting and efficiency saturation and enhancing overall model performance. The MF-CNN demonstrated outstanding performance in terms of efficacy, achieving an accuracy rate of 99.25%. It also excelled in other key performance metrics with a precision of 99.27%, a recall of 99.25%, and an F1-score of 99.25%. These metrics confirmed the model's proficiency in accurate classification and its capability to minimize false positives and negatives across all tested GI disease categories. Furthermore, the AUC values were exceptional, averaging 1.00 for both test and validation sets, indicating perfect discriminative ability. The findings of the P-R curve analysis and confusion matrix further confirmed the robust classification performance of the MF-CNN. This research introduces a technique for medical imaging that can potentially transform diagnostics in gastrointestinal healthcare facilities worldwide.
Clinical presentation of post-COVID pain and its impact on quality of life in long COVID patients: a cross-sectional household survey of SARS-CoV-2 cases in Bangladesh

Kabir MF, Yin KN, Jeffree MS, Ahmedy FB, Zainudin MF, Htwe O, et al.

BMC Infect Dis, 2024 Apr 04;24(1):375.
PMID: 38575878 DOI: 10.1186/s12879-024-09267-3

BACKGROUND: Pain is one of the prevalent Long COVID Symptoms (LCS). Pain interferes with the quality of life (QoL) and induces disease burden.
PURPOSE: The study aimed to elicit the clinical presentation of pain and determine the relationships between QoL and pain in LCS.
METHODS: This household cross-sectional study of 12,925 SARS-CoV-2 cases between July and December 2021 was carried out in eight administrative divisions of Bangladesh. Stratified random sampling from the cases retrieved from the Ministry of Health was employed. Symptom screening was performed through COVID-19 Yorkshire Rehabilitation Scale, and long COVID was diagnosed according to World Health Organization (WHO) criteria. The analyses were conducted using IBM SPSS (Version 20.00).
RESULTS: The prevalence of pain in long COVID was between 01 and 3.1% in the studied population. The study also found five categories of pain symptoms as LCS in Bangladesh: muscle pain 3.1% (95% CI; 2.4-3.8), chest pain 2.4% (95% CI; 1.8-3.1), joint pain 2.8% (95% CI; 2.2-2.3), headache 3.1% (95% CI; 2.4-3.8), and abdominal pain 0.3% (95% CI; 0.01-0.5). People with LCS as pain, multiple LCS, and longer duration of LCS had significantly lower quality of life across all domains of the WHOQOL-BREF (P
Fulltext Symptom response and episodic disability of long COVID in people with spinal cord injury: A case-control study

Kabir MF, Nyein Yin K, Htwe O, Saffree Jeffree M, Binti Ahmedy F, Faizal Zainudin M, et al.

PLoS One, 2024;19(6):e0304824.
PMID: 38941308 DOI: 10.1371/journal.pone.0304824

BACKGROUND: Spinal cord injury (SCI) is a consequence of significant disability and health issues globally, and long COVID represents the symptoms of neuro-musculoskeletal, cardiovascular and respiratory complications.
PURPOSE: This study aimed to identify the symptom responses and disease burden of long COVID in individuals with spinal cord injury.
METHODS: This case-control study was conducted on patients with SCI residing at a specialised rehabilitation centre in Bangladesh. Forty patients with SCI with and without long COVID symptoms (LCS) were enrolled in this study at a 1:1 ratio according to WHO criteria.
RESULT: Twelve LCS were observed in patients with SCI, including fatigue, musculoskeletal pain, memory loss, headache, respiratory problems, anxiety, depression, insomnia, problem in ADL problem in work, palpitation, and weakness. The predictors of developing long COVID include increasing age (p<0.002), increasing BMI (p<0.03), and longer duration of spinal cord injury (p<0.004). A significant difference (p<0.01) in overall years of healthy life lost due to disability (YLD) for non-long COVID cases was 2.04±0.596 compared to long COVID (LC) cases 1.22±2.09 was observed.
CONCLUSION: Bangladeshi patients of SCI presented 12 long COVID symptoms and have a significant disease burden compared to non long COVID cases.

Filters

Please provide feedback to Administrator ([email protected])

External Links