METHODS: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis.
RESULTS: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis.
CONCLUSIONS: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.
MATERIALS AND METHODS: This is prospective controlled trial. Peripheral venous blood sample is obtained from 20 patients with AAA and 36 normal control subjects. MMP-9 concentration levels were determined by an enzyme-linked immunosorbent assay and compared with subjects abdominal ultrasonography or computed tomography of abdomen.
RESULTS: Mean (± SE) MMP-9 was 23.94 ± 0.60 ng/mL in normal control subjects and 21.39 ± 1.03 ng/mL in patients with AAAs (p ← 0.05 versus normal control subjects). MMP-9 correlate significantly with AAA (p=0.004). There was no correlation of MMP-9 levels with age, gender, or other risk factors. The cutoff point is 12.54 for aorta size <3.0 cm. The sensitivity and specificity of MMP-9 were 60% and 64% respectively.
CONCLUSIONS: MMP-9 levels correlate significantly with AAA with a cutoff point of 12.54. However, the utility of MMP-9 as a diagnostic test is limited due to low sensitivity and specificity. An elevated MMP-9 has limited use to predict the presence of AAA (positive predictive value: 60%) and a normal MMP-9 level was insufficient to determine the absence of AAA (negative predictive value: 36.1%).
Methods: Histopathological examination of appendicectomies conducted between 2016 and 2017 in Melaka Hospital, Malaysia were traced and categorised into three groups: i) G1 (normal appendix), ii) G2 (acute appendicitis) and iii) G3 (perforated appendicitis). The reports were randomised and a total of 338 samples were collected. NLR values were compared between the three different groups and analysed.
Results: The median values of NLR for G1, G2 and G3 were 2.37, 5.25 and 9.27, respectively. We found a statistically significant difference in NLR between G1 and G2 (P < 0.001), and G2 and G3 (P < 0.001). The diagnostic values of NLR for acute appendicitis and perforated appendicitis were 3.11 (sensitivity: 75.23%, specificity: 68.70%) and 6.17 (sensitivity: 76.32%, specificity: 58.72%), respectively. There was a substantial correlation between NLR and disease severity, and a moderate correlation between NLR and duration of admission.
Conclusion: NLR, with a sensitivity of 75.23% and specificity of 68.70%, is a useful and reliable adjunct in diagnosing acute appendicitis. Hence, it will help in reducing the rate of negative appendicectomies.