scholarly journals Adenomatous Hyperplasia of Thyroid Nodule Classification: Texture Feature Analysis Methodoloyof Ultrasound Images

This paper, explores to extract textural feature from ultrasound Adenomatous Hyperplasia thyroid nodule. The extracted texture feature will help the clinician to improve diagnostic accuracy. The Fine Needle Aspiration (FNA) and Histopathology report is the conventional diagnostic methodology. It is an invasive technique and patients are subjected to painful process. Non-invasive, non-contact and low cost imaging tool is essential to increase the clinical diagnostic accuracy. Ultrasound imaging is a potential non-invasive modality to capture Adenomatous Hyperplasia thyroid nodule. Adenomatous Hyperplasia thyroid nodule is the common inflammation in thyroid gland abnormality. The texture features, using Law’s Texture Energy Measures (Law’s TEM), Neighborhood Gray Tone Difference Matrix (NGTDM) and Statistical Feature Matrix (SFM) are extracted from normal and adenomatous hyperplasia of thyroid nodules. The normal and abnormal images are demarcated using T-test analysis. The extracted feature shows significant difference between normal and abnormal images with p value less than 0.001(p < 0.001). Hence the Law’s Texture Energy based feature may be used to identify the pathology in the thyroid ultrasound images.

Author(s):  
Alyaa Marzouk Soliman ◽  
Sherief Mohamed Abd-Elsalam ◽  
Amal Saeid ALBendary ◽  
Osama El. Sayed Negm

Background: All cirrhotic patients should be screened for oesophageal varices (OV) at the time of diagnosis. The development of a non-invasive method for the detection of OV is a vital issue in subjects with cirrhosis to decrease the need for invasive endoscopic procedures that can be costly. This work aimed to evaluate immature platelet fraction (IPF) as a non-invasive marker and predictor of OV. Methods: This cross-sectional study was carried out on 80 cirrhotic patients with esophageal varices diagnosed by upper endoscopy. They were divided into Group (1): 40 patients with cirrhosis with esophageal varices and Group (2): 40 patients with cirrhosis and without esophageal varices. All patients were subjected to the complete history taking, physical examination, routine laboratory investigations (Complete blood count, IPF, C-reactive protein, Liver and kidney function tests, Bone marrow aspiration for some cases, Ascetic sample analysis when applicable), Pelvic-Abdominal ultrasonography, Child Pugh score assessment, Upper GIT endoscopy. Results: There was a significant difference between the studied groups regarding IPF (p<0.001). At cutoff >12 IPF had (AUC= 0.993) with sensitivity of 97.5% and specificity of 97.5% for detection of esophageal varices. There was a significant negative correlation between IPF and platelets count (p- value < 0.001). There was a significant positive correlation between IPF and Child Pugh score (p- value <0.001). There was a highly significant positive correlation between IPF and CRP (p value <0.001). There was significant difference between the two groups as regards splenic longitudinal diameter (p<0.001). As regards platelet count, there was a significant difference between the two groups (p<0.001). It was significantly lower in Group 1. Conclusions: IPF is elevated in cirrhotic patients with naive esophageal varices than in cirrhotic patients without varices. IPF could be used as a noninvasive, easy to measure method for detection of the presence of esophageal varices at a cutoff level of >12.


2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi142-vi142
Author(s):  
Kaylie Cullison ◽  
Garrett Simpson ◽  
Danilo Maziero ◽  
Kolton Jones ◽  
Radka Stoyanova ◽  
...  

Abstract A dilemma in treating glioblastoma is that MRI after chemotherapy and radiation therapy (chemoRT) shows areas of presumed tumor growth in up to 50% of patients. These areas can represent true progression (TP), tumor growth with tumors non-responsive to treatment, or pseudoprogression (PP), edema and tumor necrosis with favorable treatment response. On imaging, TP and PP are usually not discernable. Patients in this study undergo six weeks of chemoRT on a combination MRI/RT device, receiving daily MRIs. The goal of this study is to explore the correlation of radiomics features with progression. The tumor lesion and surrounding areas of growth/edema were manually outlined as regions of interest (ROIs) for each daily T2-weighted MRI scan. The ROIs were used to calculate texture features: statistical features based on the gray-level co-occurrence matrix (GLCM), the gray-level zone size matrix (GLZSM), the gray-level run length matrix (GLRLM), and the neighborhood gray-tone difference matrix (NGTDM). Each of these matrix classes describe the probability of spatial relationships of gray levels occurring within the ROI. Daily texture features were averaged per week of treatment for each patient. Patient response was retrospectively defined as no progression (NP), TP, or PP. A Kruskal-Wallis test was performed to identify texture features that correlated most strongly with patient response. Forty texture features were calculated for 12 patients (19 treated, 7 excluded due to no T2 lesion or progression status unknown, 6 NP, 3 TP, 3 PP). There was a trend of more texture features correlating significantly with response in weeks 4-6 of treatment, compared to weeks 1-3. A particular texture feature, GLSZM Small Zone Low Gray-Level Emphasis, showed increasing difference between PP and TP over time, with significant difference during week 6 of treatment (p=0.0495). Future directions include correlating early outcomes with greater numbers of patients and daily multiparametric MRI.


2020 ◽  
pp. 197140092095723
Author(s):  
Angela Guarnizo ◽  
Rafael Glikstein ◽  
Vered Tsehmaister-Abitbul ◽  
Ionut Busca ◽  
Samy El-Sayed ◽  
...  

Background and purpose Computed tomography virtual endoscopy (CT-VE) is a non-invasive technique which allows visualisation of intraluminal surfaces by tridimensional reconstruction of air/soft tissues. The aim of this study was to compare the diagnostic accuracy of CT-VE and flexible fibre-optic laryngoscopy (FFL) in identifying normal neck anatomic structures and pharyngeal and laryngeal lesions. Methods Forty-two patients with a history of neck cancer were assessed by two ENT surgeons using FFL and by one neuroradiologist using CT-VE in order to evaluate the visualisation of the epiglottis, vallecula, glossoepiglottic folds, pyriform sinuses, vocal cords and mass pathology. The visualisation of the structures in both modalities was assessed according to the following score: 0 = not visualised, 1 = partial visualisation, 2 = complete and clear visualisation. A weighted kappa coefficient was used to evaluate the inter-observer agreement. McNemar’s test was performed to compare the two diagnostic tests. Results The inter-observer agreement between FFL and CT-VE was fair in the assessment of the vocal cords ( k = 0.341); moderate in the assessment of the glossoepiglottic folds ( k = 0.418), epiglottis ( k = 0.513) and pyriform sinuses ( k = 0.477); and substantial in the assessment of the vallecula ( k = 0.618) and the tumour (0.740). McNemar’s test showed no significant difference between the two tests ( p<0.05). Conclusion CT-VE is a non-invasive technique with a diagnostic accuracy comparable to FFL in terms of visualisation of anatomical structures and pharyngeal and laryngeal lesions.


2018 ◽  
Vol 3 (1) ◽  
pp. 357-360 ◽  
Author(s):  
Bidur KC ◽  
Amit Thapa

Introduction: Though invasive intracranial devices are gold standard to calculate intracranial pressure (ICP); these are not without any complications. Non-invasive measurement of ICP by Ultrasonography could be a safe and portable technique.Objectives: The objective of the study was to measure and compare values of optic nerve sheath diameter of both eyes in healthy Nepalese adults.Methodology: A prospective cross-sectional study of healthy adult Nepalese volunteers was performed using a 7.5 MHz linear Ultrasound probe on the closed eyelids; optic nerve sheath diameter (ONSD) was measured 3 mm behind the globe in each eye.Results: Optic nerve sheath diameter (ONSD) of both eyes was measured in 100 healthy volunteers of age ranged from 15 to 75 years with a mean of 30.21 ± 14.05 years. There were 18 (18%) male and 82 (82%) female. ONSD for right eye ranged from 3.20 to 4.90 mm with mean of 4.10 ± 0.50 mm and left eye from 3.20 to 4.80 mm with mean of 4.22 ± 0.49 mm. P value for right and left eye ONSD (P = 0.06) and male and female (P = 0.12 and 0.85 for right and left ONSD respectively) were within normal limits. ONSD has no correlation with age (P = 0.27 and 0.27 for right and left ONSD respectively).Conclusion Mean of optic nerve sheath diameter (ONSD) is 4.10mm and 4.22 mm for right and left eye respectively. There is no statistical significant difference in mean of ONSD between right and left eye. BJHS 2018;3(1)5 : 357-360


2020 ◽  
Vol 11 (SPL4) ◽  
pp. 1240-1243
Author(s):  
Vasundhara S ◽  
Madhusudan Rao Bandlamudi

A method was developed and validated for low-level detection of glucose. The method involves quantitation of glucose though derivitisation with PABA and HPLC-DAD analysis. A selective and novel method has been optimised for evaluation of blood glucose levels in blood Serum and saliva biological matrices by R.P-H.P.L.C. The principle analyte was eluted with the conditions of mobile phase having the 50m.M Sodium acetate: Acetonitrile (60:40%, v./v.) using the Phenomax-C.18  (250 x 4.6 mm, 3.5m.) analytical column with the 1.0 ml/min flow rate and 10µl sample volume at 254 nm in a photodiode array detector. The retention times of was 3.4 min within the total run time of 05 min. The curve indicates the correlation coefficient (r2) was superior by having the value 0.998 with a linear range of 40 µg/ml- 600.0 µg/ml. Based on the results obtained in the validation, the developed method was susceptible, accurate, linear and economical. Due to the short time of the chromatographic program, more samples can be analysed within a short period.  Data obtained were subjected to statistical analysis using t-test. Highly significant P-value (P<0.05) was obtained between the serum blood glucose and salivary glucose level. A distinct difference was observed in the salivary glucose between the control and diabetic group. The method was met all the predefined acceptance criteria.  Diabetes mellitus is a globally widespread disease. As the salivary collection is painless and non-invasive, in this study, an attempt has been made to diagnose diabetes mellitus by estimating the salivary glucose level in comparison with serum blood glucose level. Hence the developed method can be used as an index of diabetes mellitus.


2017 ◽  
Vol 21 (2) ◽  
pp. 106-111 ◽  
Author(s):  
Gaspare Carta ◽  
Patrizia Palermo ◽  
Chiara Pasquale ◽  
Valeria Conte ◽  
Ruggero Pulcinella ◽  
...  

2021 ◽  
Vol In Press (In Press) ◽  
Author(s):  
Sepideh Abdollahi ◽  
Pantea Izadi ◽  
Shahla Noori Ardebili ◽  
Samaneh Chegeni ◽  
Mir Saead Yekaninejad

Background: Endometriosis is one of the common gynecological diseases and can lead to pelvic pain, dysmenorrhea, dyspareunia, and infertility in women. Thus, accurate and early diagnosis is a pivotal issue and an essential need for managing this disorder. At the present, the gold standard diagnostic method for endometriosis is laparoscopic surgery that is an invasive method and can lead to delay in diagnosis. Thus, there is an immediate necessity to search for non-invasive diagnostic biomarkers, such as blood-based ones. Objectives: Matrix metalloproteinase-9 (MMP-9) and vascular endothelial growth factor-A (VEGF-A) have essential roles in the pathogenesis of endometriosis. Therefore, in this study, we evaluated the plasma mRNA levels of MMP-9 and VEGF-A, as potential non-invasive diagnostic biomarkers for endometriosis. Methods: This study included 48 women (24 cases and 24 controls) who underwent laparoscopy for suspected endometriosis. Preoperative plasma samples were collected, and after RNA extraction, the levels of MMP-9 and VEGF-A mRNAs were determined by reverse transcription-quantitative polymerase chain reaction (RT-qPCR). Results: Plasma MMP-9 mRNA level was statistically higher in endometriosis patients compared with the control group (P value = 0.01). However, plasma VEGF-A mRNA level did not show a significant difference between the two groups (P value =0.5). Conclusions: It seems that the plasma level of MMP-9 mRNA in endometriosis patients is significantly higher than in non-endometriosis women. This finding can provide new insights regarding this mRNA’s applicability as a non-invasive diagnostic biomarker for discovering new cases of endometriosis (newly diagnosed). According to our results, despite the suggested role of VEGF-A in endometriosis pathogenesis, it seems that the plasma level of VEGF-A mRNA does not have the potential to be used as a non-invasive diagnostic biomarker.


Author(s):  
Puja Bharti ◽  
Deepti Mittal ◽  
Rupa Ananthasivan

Chronic liver diseases are fifth leading cause of fatality in developing countries. Early diagnosis is important for timely treatment and to salvage life. Ultrasound imaging is frequently used to examine abnormalities of liver. However, ambiguity lies in visual interpretation of liver stages on ultrasound images. This difficult visualization problem can be solved by analysing extracted textural features from images. Grey-level difference matrix, a texture feature extraction method, can provide information about roughness of liver surface, sharpness of liver borders and echotexture of liver parenchyma. In this article, the behaviour of variants of grey-level difference matrix in characterizing liver stages is investigated. The texture feature sets are extracted by using variants of grey-level difference matrix based on two, three, five and seven neighbouring pixels. Thereafter, to take the advantage of complementary information from extracted feature sets, feature fusion schemes are implemented. In addition, hybrid feature selection (combination of ReliefF filter method and sequential forward selection wrapper method) is used to obtain optimal feature set in characterizing liver stages. Finally, a computer-aided system is designed with the optimal feature set to classify liver health in terms of normal, chronic liver, cirrhosis and hepatocellular carcinoma evolved over cirrhosis. In the proposed work, experiments are performed to (1) identify the best approximation of derivative (forward, central or backward); (2) analyse the performance of individual feature sets of variants of grey-level difference matrix; (3) obtain optimal feature set by exploiting the complementary information from variants of grey-level difference matrix and (4) analyse the performance of proposed method in comparison with existing feature extraction methods. These experiments are carried out on database of 754 segmented regions of interest formed by clinically acquired ultrasound images. The results show that classification accuracy of 94.5% is obtained by optimal feature set having complementary information from variants of grey-level difference matrix.


2021 ◽  
Vol 75 (2) ◽  
pp. 143-148
Author(s):  
Seyed Mohsen Dehghani ◽  
Sadegh Mohammadi ◽  
Iraj Shahramian ◽  
Fateme Parooie ◽  
Hadi Mirzaie ◽  
...  

Introduction: Liver function test is a part of safe and aff ordable routine blood biochemical tests and provides useful information for the diagnosis and management of liver dysfunction. In this study we evaluated the value of the R factor in distinguishing between intrahepatic and extrahepatic causes of infant cholestasis. Methods: Receiver operating characteristic (ROC) analysis was performed to evaluate the diagnostic value of the R factor in each group in comparison with liver biopsy as the gold standard of diagnosis. The data were analyzed using SPSS statistical software and P < 0.05 indicated a significant difference. Results: The study included 37 neonatal hepatitis patients (group A) and 25 biliary atresia patients (group B). The R factor was calculated using the (ALT patient/ULN)/(ALP patient/ULN) formula; ROC analysis revealed that if the R factor was ≤ 0.09 the patient diagnosis would be biliary atresia with high sensitivity (92%) (p-value = 0.001). The corresponding specificity, positive predictive value (PPV), negative predictive value (NPV), diagnostic accuracy and area under the ROC curve (AUC) were 75.7%, 72%, 93%, 82% and 0.87, respectively. Conclusion: The study revealed that the R factor is a good diagnostic marker for differentiating between the most common intrahepatic and extrahepatic causes of infant cholestasis and has good diagnostic accuracy, sensitivity, specificity, PPV and NPV, in comparison with liver biopsy as the gold standard of diagnosis.


QJM ◽  
2020 ◽  
Vol 113 (Supplement_1) ◽  
Author(s):  
W F Ezzat ◽  
A M Askoura ◽  
A N Elshazly ◽  
H Y Falah

Abstract Background The first case of fungal sinusitis was reported in 1885. This fungal disease occurred rarely until the past decade, when a worldwide increase in its incidence occurred. Till one decade back bacteria was implicated as pathogen in most form of chronic rhinosinusitis (CRS). Fungi were thought to be responsible for few specific forms, sine 1999, when ponikau and associates claimed that fungi were responsible for nearly all cases of CRS. Their study demonstrated the presence of fungi & eosinophils from nose & paranasal sinuses from ∼96 % cases of CRS. Aim of the Work The aim of the work was to detect the presence of fungal biofilm, in patients with fungal sinusitis trying to find its role in recurrence of fungal sinus infection, resistance to medical treatment and occurrence of intra orbital and intracranial complications. Patients and Methods The study consisted of 20 different cases of fungal sinusitis controlled by 10 cases of non fungal sinusitis. Control cases were divided into 5 cases of chronic sinusitis with nasal polyposis and 5 cases of deviated septum with no evidence of sinusitis undergoing nasal surgery. Results Using statistical analysis, there was evidence of pressure of fungal biofilm in different cases of fungal sinusitis whether primary or recurrent, also whether invasive or non invasive. Comparing cases with controls, There was statistically significant difference between them as regard Biofilm (p-value: &lt; 0.001) with incidence reaching (70 %) in cases while (0%) in controls. By applying risk analysis for biofilm, we used relative risk (p value = 0.0001) which is statistically significant indicating higher risk of positive biofilm in cases of fungal sinusitis, also by Using odds ratio (p value= 0.0002) which is statistically significant indicating higher risk of positive biofilm in cases of fungal sinusitis. Conclusion The study showed the presence of fungal biofilm in different cases of fungal siunsitis whether primary or recurrent, also whether invasive or non invasive.


Sign in / Sign up

Export Citation Format

Share Document