Το ήπαρ είναι ένα πολύ σημαντικό όργανο του ανθρωπίνου σώματος το οποίο εκτελεί βασικές λειτουργί... more Το ήπαρ είναι ένα πολύ σημαντικό όργανο του ανθρωπίνου σώματος το οποίο εκτελεί βασικές λειτουργίες που σχετίζονται με την πέψη, τον μεταβολισμό, την ανοσία και την αποθήκευση θρεπτικών ουσιών στο σώμα. Οι ασθένειες του ήπατος μπορεί να οδηγήσουν σε ηπατική ανεπάρκεια η οποία, εάν δεν αντιμετωπιστεί, οδηγεί σε θάνατο. Ως εκ τούτου, η ακριβής διάγνωση για στοχευμένη θεραπεία των ασθενειών του ήπατος είναι μεγάλης σημασίας. Γενικά υπάρχουν δύο τύποι νόσων του ήπατος, οι εστιακές και οι διάχυτες. Εστιακές ηπατικές παθήσεις (ή Εστιακές Ηπατικές Αλλοιώσεις - ΕΗΑ) θεωρούνται ως ανωμαλίες του ηπατικού ιστού που είναι συγκεντρωμένες σε μια μικρή περιοχή, όπως ένας όγκος ή κύστη. Αυτές περαιτέρω κατηγοριοποιούνται σε καλοήθεις και κακοήθεις. Οι τελευταίες συνήθως οδηγούν στο θάνατο και συνεπώς ο ακριβής χαρακτηρισμός των ΕΗΑ ως κακοήθεις έχει μεγάλη σημασία. Η Διάχυτη Ασθένεια του Ήπατος (ή Χρόνια Ηπατική Νόσος - ΧΗΝ) κατανέμεται σχεδόν ομοιόμορφα σε όλο τον ηπατικό ιστό. Προκαλεί σταθερή και επαναλαμβανόμενη φλεγμονή στον ιστό του ήπατος ο οποίος αντικαθίσταται από συνδετικό ιστό (ίνωση), οδηγώντας προοδευτικά σε κίρρωση. Η κίρρωση είναι το τελικό στάδιο της νόσου, που οδηγεί σε ηπατική ανεπάρκεια ή Ηπατοκυτταρικό Καρκίνωμα (ΗΚΚ), μια κακοήθη ΕΗΑ, και τελικά στον θάνατο.Οι συνέπειες της εξελίξεως των ηπατικών παθήσεων καθιστούν την έγκαιρη και ακριβή διάγνωση πολύ σημαντική για την αντιμετώπισή τους. Η βιοψία ήπατος θεωρείται μέχρι και σήμερα εξέταση αναφοράς για την ακριβή διάγνωση των ηπατικών παθήσεων. Επειδή όμως είναι επεμβατική μέθοδος και συνεπώς έχει πιθανότητα επιπλοκών για τον ασθενή και αυξημένο κόστος, μη επεμβατικές προσεγγίσεις κυρίως στον τομέα της ιατρικής απεικονιστικής έχουν αναπτυχθεί και εξελίσσονται τα τελευταία χρόνια προκειμένου να αποτελούν μία έγκυρη εναλλακτική της βιοψίας ήπατος. Σκοπός της παρούσης διδακτορικής διατριβής ήταν η μελέτη και ανάπτυξη καινοτόμων αλγορίθμων επεξεργασίας και αναλύσεως εικόνων Υπερηχογραφίας και Πυρηνικού Μαγνητικού Συντονισμού (ΠΜΣ) για τη διαφορική διάγνωση των ηπατικών παθήσεων ούτως ώστε να μπορούν να αποτελούν χρήσιμες προσθήκες στο λογισμικό των αντίστοιχων απεικονιστικών ιατρικών μηχανημάτων. Μέσω των αλγορίθμων αυτών, η διαγνωστική απόδοση των Ακτινολόγων στις ηπατικές παθήσεις μπορεί να βελτιωθεί σημαντικά.Κατά τη διάρκεια της διατριβής αυτής, αναπτύχθηκαν τέσσερις καινοτόμοι αλγόριθμοι επεξεργασίας και αναλύσεως ιατρικών εικόνων των οποίων η απόδοση ξεπέρασε αυτές των αντίστοιχων προσεγγίσεων της βιβλιογραφίας.Λεπτομερέστερα, ο 1ος αλγόριθμος αφορά την διαφορική διάγνωση των ΕΗΑ μέσω επεξεργασίας και αναλύσεως βίντεο υπερηχογραφικής εικόνας από εξέταση με έκχυση σκιαγραφικού. Με τη χρήση του Συνεχούς Μετασχηματισμού Κυματιδίων (ΣΜΚ) (Continuous Wavelet Transform), υπολογίζονται η θέση της αλλοιώσεως και θέσεις των ορίων της από την εύρεση των ακροτάτων και των μηδενικών συντελεστών διελεύσεως (Zero Crossing Coefficients) της εικόνας που προκύπτει από τον Μετασχηματισμό Κυματιδίων. Από τη διαδικασία αυτή δημιουργείται μια αδρή εκτίμηση των ορίων της ΕΗΑ η οποία χρησιμοποιείται ως αρχικοποίηση ενός αλγορίθμου τμηματοποιήσεως Τυχαίων Μαρκοβιανών Πεδίων (Markov Random Fields) ο οποίος και δίνει τα τελικά ακριβή όρια της ΕΗΑ. Μέσω αυτής της διαδικασίας η ΕΗΑ παρακολουθείται από τον αλγόριθμο και εξάγονται με ακρίβεια τα όριά της σε όλες τις εικόνες του βίντεο που εμφανίζεται ανεξαρτήτως αλλαγής θέσεως, σχήματος ή φωτεινότητος εντός της. Για κάθε εικόνα που πραγματοποιείται η διαδικασία αυτή, υπολογίζεται οι μέσες τιμές της φωτεινότητας εντός της δομής και μιας μικρής περιοχής εκτός της και εξάγεται μία καμπύλη Φωτεινότητας – Χρόνου (Time – Intensity Curve). Κατόπιν εξάγονται χαρακτηριστικά από την καμπύλη αυτή τα οποία τοποθετούμενα σε ένα ταξινομητή Μηχανών Διανυσμάτων Υποστηρίξεως (ΜΔΥ) (Support Vector Machines) δίνουν τη διαφοροποίηση μεταξύ καλοήθους και κακοήθους ΕΗΑ.Ο 2ος και 3ος αλγόριθμος αφορούν την διάγνωση της ΧΗΝ μέσω επεξεργασίας και αναλύσεως ελαστογραφικής υπερηχογραφικής εικόνας. Οι αλγόριθμοι αυτοί εξάγουν αυτομάτως την έγχρωμη περιοχή με πληροφορία ελαστικότητας από την άχρωμη B-Mode εικόνα και εκτελούν μια διαδικασία μετατροπής έγχρωμων (RGB) τιμών σε τιμές ελαστικότητας. Κατόπιν αναλύουν όλη την περιοχή της ελαστικής πληροφορίας (2ος αλγόριθμος) και υποπεριοχές της (3ος αλγόριθμος) και εξάγουν χαρακτηριστικά υφής από αυτές από τα οποία, τα πιο σημαντικά, τοποθετούμενα σε ένα ταξινομητή ΜΔΥ δίνουν διαφοροποίηση μεταξύ υγιών ατόμων και ασθενών με ΧΗΝ.Τέλος, ο 4ος αλγόριθμος αφορά την διαφορική διάγνωση των ΕΗΑ μέσω επεξεργασίας και αναλύσεως εικόνων ΠΜΣ (MRI). Μέσω της χρήσεως του ΣΜΚ, της αναλύσεώς του σε πολλές κλίμακες (Multiscale Analysis), και του αλγορίθμου τμηματοποιήσεως Fuzzy C-Means (FCM), εντοπίζονται και εξάγονται με ακρίβεια τα όρια της κάθε ΕΗΑ. Κατόπιν εξάγονται χαρακτηριστικά υφής καθώς και μορφολογικά χαρακτηριστικά της δομής από τα οποία, τα πιο σημαντικά, εισάγονται σε έναν ταξινομητή Πιθανοτικών Νευρωνικών Δικτύων για…
Purpose: The design and implementation of a computer-based image analysis system employing the su... more Purpose: The design and implementation of a computer-based image analysis system employing the support vector machine (SVM) classifier system for the classification of Focal Liver Lesions (FLLs) on routine non-enhanced, T2-weighted Magnetic Resonance (MR) images. Materials and Methods: The study comprised 92 patients; each one of them has undergone MRI performed on a Magnetom Concerto (Siemens). Typical signs on dynamic contrast-enhanced MRI and biopsies were employed towards a three class categorization of the 92 cases: 40-benign FLLs, 25-Hepatocellular Carcinomas (HCC) within Cirrhotic liver parenchyma and 27-liver metastases from Non-Cirrhotic liver. Prior to FLLs classification an automated lesion segmentation algorithm based on Marcov Random Fields was employed in order to acquire each FLL Region of Interest. 42 texture features derived from the gray-level histogram, co-occurrence and run-length matrices and 12 morphological features were obtained from each lesion. Stepwise multi-linear regression analysis was utilized to avoid feature redundancy leading to a feature subset that fed the multiclass SVM classifier designed for lesion classification. SVM System evaluation was performed by means of leave-one-out method and ROC analysis. Results: Maximum accuracy for all three classes (90.0%) was obtained by means of the Radial Basis Kernel Function and three textural features (Inverse- Different-Moment, Sum-Variance and Long-Run-Emphasis) that describe lesion's contrast, variability and shape complexity. Sensitivity values for the three classes were 92.5%, 81.5% and 96.2% respectively, whereas specificity values were 94.2%, 95.3% and 95.5%. The AUC value achieved for the selected subset was 0.89 with 0.81 - 0.94 confidence interval. Conclusion: The proposed SVM system exhibit promising results that could be utilized as a second opinion tool to the radiologist in order to decrease the time/cost of diagnosis and the need for patients to undergo invasive examination.
The purpose of the present study was to employ a computer-aided diagnosis system that classifies ... more The purpose of the present study was to employ a computer-aided diagnosis system that classifies chronic liver disease (CLD) using ultrasound shear wave elastography (SWE) imaging, with a stiffness value-clustering and machine-learning algorithm. A clinical data set of 126 patients (56 healthy controls, 70 with CLD) was analyzed. First, an RGB-to-stiffness inverse mapping technique was employed. A five-cluster segmentation was then performed associating corresponding different-color regions with certain stiffness value ranges acquired from the SWE manufacturer-provided color bar. Subsequently, 35 features (7 for each cluster), indicative of physical characteristics existing within the SWE image, were extracted. A stepwise regression analysis toward feature reduction was used to derive a reduced feature subset that was fed into the support vector machine classification algorithm to classify CLD from healthy cases. The highest accuracy in classification of healthy to CLD subject discr...
Ultraschall in der Medizin - European Journal of Ultrasound, 2013
Purpose: This study compares two methods of liver elasticity determination, Shear Wave Elasticity... more Purpose: This study compares two methods of liver elasticity determination, Shear Wave Elasticity (SWE) and Trancient Elastography (VCTE). Images will be provided by a group of patients with chronic parechymal liver diseases which will be compared against histological liver biopsy findings of the same patients. Material and methods: SWE: All SWE measurements are performed in the right lobe of the liver using an appropriate intercostal space. Every patient is examined by two examiners, using the same methods, in order to estimate the Inter-Observer variability. Each examiner performs two measurements on each patient using the same method to estimate the Intra-Observer variability. VCTE: Anthropometric measurements at the time of SWE and TE should include information from patient's record about the type of liver disease and Histological evaluation of liver biopsies. Results: There was a statistically significant difference (p < 0,01) between elastography values of normal and diseased subjects with both VCTE and SWE methods. There was a good correlation when the values of the two methods were compared between each other and each one with the liver biopsy, where available. In addition, intra- and inter-observer variability was low with both methods, if the adequate strict protocol of study was applied. VCTE showed 82.3% sensitivity and 68.2% specificity in diagnosing liver cirrhosis at a cut-off value of 8.9 kPa.SWE showed 88.5% sensitivity and 74.2% specificity in diagnosing liver cirrhosis at a cut-off value of 8.9 kPa. Conclusion: Although patients are few, it was clearly shown that VCTE and SWE can definitely differentiate normal from fibrotic liver tissue. There is also differentiation with SWE between F1-F2 stages of fibrosis and F3-F4 appearing more evident comparing with discrimination offered by VCTE (Fibroscan). More patients are needed to investigate whether VCTE and SWE are able to differentiate between various stages of fibrotic liver disease.
PURPOSE To assess the role of an automated Computer Aided Diagnosis (CAD) system in differentiati... more PURPOSE To assess the role of an automated Computer Aided Diagnosis (CAD) system in differentiation of Healthy Subjects to Chronic Liver Disease (CLD) Patients in terms of liver fibrosis (F0-F4), using Ultrasound Shear Wave Elastography (SWE). METHODS Clinical Dataset consisted of 125 subjects, 55 Healthy (F0) whom condition was validated with Normal Biochemical Markers and clear Clinical History, and 70 with CLD (F1-F4) whom condition was validated with Liver Biopsy. For each subject an SWE examination on their liver right lobe was performed using Supersonic Imagine's Aixplorer ultrasound system, and an SC6-1 transducer. The examination was performed using preset default settings for Abdomen/Liver, and according to literature's suggested guidelines. An SWE image was then acquired, and a separation of the colored areas from the grayscale ones was performed. An RGB-to-Stiffness algorithm was consequently applied on the resulting image (Stiffness Box), using the nbuilt-in colormap, to replace RGB values to Stiffness values. A segmentation procedure was employed using thresholds that segment the image to 5 stiffness range clusters (0-6, 6-12, 12-18, 18-24, and 24-30 kPa), and extract 7 features from each cluster (Mean, Median, Standard Deviation, Sample Kurtosis, 10th Percentile, 90th Percentile, and Cluster's Pixel Percentage on the Stiffness Box) deriving 35 features for each SWE image. The computed feature set was then fed to a designed SVM classifier. SVM-model evaluation was performed by means of exhaustive search, and leave-one-out methods. RESULTS Maximum classification accuracy (85.6%) in distinguishing Healthy from chronic liver disease patients was obtained employing three features (Blue mean and Cyan median values, and Red maximum pixel number) with sensitivity and specificity values of 91.9% and 79.3% respectively. CONCLUSION The proposed CAD system accurately differentiates Healthy to CLD patients assisting in evaluating important factors for performing SWE examination, enriching its guidelines, and aiding clinicians in a more accurate diagnosis.
Nonalcoholic fatty liver disease (NAFLD) is dramatically increasing in parallel with the pandemic... more Nonalcoholic fatty liver disease (NAFLD) is dramatically increasing in parallel with the pandemic of type 2 diabetes. Here, the authors aimed to assess the performance of the most commonly used noninvasive, blood-based biomarkers for liver fibrosis (FibroTest, NAFLD fibrosis score, BARD score, and FIB-4 Index) in subjects with type 2 diabetes. Liver stiffness measurement was estimated by two-dimensional shear wave elastography Finally, the authors assessed the diagnostic role of ActiTest and NashTest 2 in liver fibrosis in the examined population.
The purpose of the present study was to employ a computer-aided diagnosis system that classifies ... more The purpose of the present study was to employ a computer-aided diagnosis system that classifies chronic liver disease (CLD) using ultrasound shear wave elastography (SWE) imaging, with a stiffness value-clustering and machine-learning algorithm. A clinical data set of 126 patients (56 healthy controls, 70 with CLD) was analyzed. First, an RGB-to-stiffness inverse mapping technique was employed. A five-cluster segmentation was then performed associating corresponding different-color regions with certain stiffness value ranges acquired from the SWE manufacturer-provided color bar. Subsequently, 35 features (7 for each cluster), indicative of physical characteristics existing within the SWE image, were extracted. A stepwise regression analysis toward feature reduction was used to derive a reduced feature subset that was fed into the support vector machine classification algorithm to classify CLD from healthy cases. The highest accuracy in classification of healthy to CLD subject discr...
OBJECTIVES Nonalcoholic fatty liver disease (NAFLD) is the most widespread chronic liver disease ... more OBJECTIVES Nonalcoholic fatty liver disease (NAFLD) is the most widespread chronic liver disease type in the Western countries. Ultrasound (US) is used for NAFLD and hepatic steatosis (HS) grading. The most popular US method for NAFLD assessment is the hepatorenal index (HRI), but because of its limitations, other noninvasive methods have been developed. The Resona 7 US system has recently incorporated an US attenuation-related quantitative feature, liver ultrasound attenuation (LiSA), for HS estimation. The purpose of this study is to compare LiSA's and HRI's performance on NAFLD assessment. METHODS A total of 159 NAFLD patients having a magnetic resonance imaging-proton density fat fraction (MRI-PDFF) examination were examined by 2 radiologists, who performed LiSA and HRI measurements in the liver. Correlation of LiSA's and HRI's measurements with MRI-PDFF values was calculated through Pearson correlation coefficient (PCC). To further investigate the performance of LiSA and HRI, optimum cutoffs, provided by the literature, were used to correspond HS grades to MRI-PDFF results. Moreover, a receiver operating characteristic (ROC) analysis on LiSA measurements and steatosis grades was performed. RESULTS Magnetic resonance imaging-PDFF was better correlated with LiSA (PCC = 0.80) than HRI (PCC = 0.67). Receiver operating characteristic analysis showed better performance range for LiSA (77.8%-91.8%) than for HRI (72.8%-85.4%) on all HS grades for all studies used for corresponding MRI-PDFF values to HS grades. CONCLUSIONS The results indicate that LiSA is more accurate than HRI in HS differentiation and can lead to more accurate grading of HS on NAFLD patients.
Poster: "ECR 2015 / C-1378 / Automatic Segmentation of Focal Liver Lesions in MR Images by m... more Poster: "ECR 2015 / C-1378 / Automatic Segmentation of Focal Liver Lesions in MR Images by means of Marcov Random Fields with edge-driven Fuzzy C-means initialization" by: "I. Gatos1, S. Tsantis1, M. Karamesini2, A. Skouroliakou1, G. Kagadis3; 1Athens/GR, 2Kato Ahaia/GR, 3Patras/GR"
ABSTRACT The purpose of this study was to quantify liver elastic heterogeneity in Shear Wave Elas... more ABSTRACT The purpose of this study was to quantify liver elastic heterogeneity in Shear Wave Elastography (SWE) by using textural features and evaluating their diagnostic performance on differentiating healthy from chronic liver disease patients, taking biopsy results as the gold standard. Clinical material includes 16 healthy (F0) and 15 with Chronic Liver Disease (F1,F2,F3,F4) patients according to the Metavir staging system. All exams were performed using the Aixplorer ultrasound system with a SuperCurved SC6-1 transducer. From the SWE-QBox the RGB displayed elasticity data of Young&#39;s modulus were transformed from RGB color space into an elasticity matrix of gray tones, whose values varied from zero to the maximum elasticity measurement. Every pixel with no RGB-values was set to &#39;-1&#39; due to non-valid elasticity value for that pixel. From the elastogram map 185 textural features were computed (5 from the gray-tone histogram, 26 second order statistic features, extracted from the co-occurrence matrices and 10 features extracted from the run-length matrices over four directions (00,450,900,1350) and distances of (d=1,3,5,7,9) pixels). Stepwise multi-linear regression analysis was utilized to avoid feature redundancy leading to a feature subset feeding a Support Vector Machine (SVM) classifier. SVM-model evaluation was performed by means of the leave-one-out method. Maximum classification accuracy (93.5%) in distinguishing healthy from chronic liver disease patients was obtained employing three textural features (Standard Deviation, Sum-Variance, Contrast) that describe the elastogram&#39;s contrast, variability and complexity. Sensitivity and specificity values were 93.3% and 94.0% respectively. The proposed classification scheme can provide reproducibility and reliability of liver SWE application in clinical practice. It can also assist the interpretation of SWE measurements which is considered as a difficult task due to absence of guidelines in the literature and to decrease the time/cost of diagnosis and the need for patients to undergo invasive examination. This research has been co-financed by the European Union (European Social Fund ESF) and Greek national funds through the Operational Program &#39;Education and Lifelong Learning&#39; of the National Strategic Reference Framework (NSRF) Research Funding Program: ARCHIMEDES III. Investing in knowledge society through the European Social Fund.
Το ήπαρ είναι ένα πολύ σημαντικό όργανο του ανθρωπίνου σώματος το οποίο εκτελεί βασικές λειτουργί... more Το ήπαρ είναι ένα πολύ σημαντικό όργανο του ανθρωπίνου σώματος το οποίο εκτελεί βασικές λειτουργίες που σχετίζονται με την πέψη, τον μεταβολισμό, την ανοσία και την αποθήκευση θρεπτικών ουσιών στο σώμα. Οι ασθένειες του ήπατος μπορεί να οδηγήσουν σε ηπατική ανεπάρκεια η οποία, εάν δεν αντιμετωπιστεί, οδηγεί σε θάνατο. Ως εκ τούτου, η ακριβής διάγνωση για στοχευμένη θεραπεία των ασθενειών του ήπατος είναι μεγάλης σημασίας. Γενικά υπάρχουν δύο τύποι νόσων του ήπατος, οι εστιακές και οι διάχυτες. Εστιακές ηπατικές παθήσεις (ή Εστιακές Ηπατικές Αλλοιώσεις - ΕΗΑ) θεωρούνται ως ανωμαλίες του ηπατικού ιστού που είναι συγκεντρωμένες σε μια μικρή περιοχή, όπως ένας όγκος ή κύστη. Αυτές περαιτέρω κατηγοριοποιούνται σε καλοήθεις και κακοήθεις. Οι τελευταίες συνήθως οδηγούν στο θάνατο και συνεπώς ο ακριβής χαρακτηρισμός των ΕΗΑ ως κακοήθεις έχει μεγάλη σημασία. Η Διάχυτη Ασθένεια του Ήπατος (ή Χρόνια Ηπατική Νόσος - ΧΗΝ) κατανέμεται σχεδόν ομοιόμορφα σε όλο τον ηπατικό ιστό. Προκαλεί σταθερή και επαναλαμβανόμενη φλεγμονή στον ιστό του ήπατος ο οποίος αντικαθίσταται από συνδετικό ιστό (ίνωση), οδηγώντας προοδευτικά σε κίρρωση. Η κίρρωση είναι το τελικό στάδιο της νόσου, που οδηγεί σε ηπατική ανεπάρκεια ή Ηπατοκυτταρικό Καρκίνωμα (ΗΚΚ), μια κακοήθη ΕΗΑ, και τελικά στον θάνατο.Οι συνέπειες της εξελίξεως των ηπατικών παθήσεων καθιστούν την έγκαιρη και ακριβή διάγνωση πολύ σημαντική για την αντιμετώπισή τους. Η βιοψία ήπατος θεωρείται μέχρι και σήμερα εξέταση αναφοράς για την ακριβή διάγνωση των ηπατικών παθήσεων. Επειδή όμως είναι επεμβατική μέθοδος και συνεπώς έχει πιθανότητα επιπλοκών για τον ασθενή και αυξημένο κόστος, μη επεμβατικές προσεγγίσεις κυρίως στον τομέα της ιατρικής απεικονιστικής έχουν αναπτυχθεί και εξελίσσονται τα τελευταία χρόνια προκειμένου να αποτελούν μία έγκυρη εναλλακτική της βιοψίας ήπατος. Σκοπός της παρούσης διδακτορικής διατριβής ήταν η μελέτη και ανάπτυξη καινοτόμων αλγορίθμων επεξεργασίας και αναλύσεως εικόνων Υπερηχογραφίας και Πυρηνικού Μαγνητικού Συντονισμού (ΠΜΣ) για τη διαφορική διάγνωση των ηπατικών παθήσεων ούτως ώστε να μπορούν να αποτελούν χρήσιμες προσθήκες στο λογισμικό των αντίστοιχων απεικονιστικών ιατρικών μηχανημάτων. Μέσω των αλγορίθμων αυτών, η διαγνωστική απόδοση των Ακτινολόγων στις ηπατικές παθήσεις μπορεί να βελτιωθεί σημαντικά.Κατά τη διάρκεια της διατριβής αυτής, αναπτύχθηκαν τέσσερις καινοτόμοι αλγόριθμοι επεξεργασίας και αναλύσεως ιατρικών εικόνων των οποίων η απόδοση ξεπέρασε αυτές των αντίστοιχων προσεγγίσεων της βιβλιογραφίας.Λεπτομερέστερα, ο 1ος αλγόριθμος αφορά την διαφορική διάγνωση των ΕΗΑ μέσω επεξεργασίας και αναλύσεως βίντεο υπερηχογραφικής εικόνας από εξέταση με έκχυση σκιαγραφικού. Με τη χρήση του Συνεχούς Μετασχηματισμού Κυματιδίων (ΣΜΚ) (Continuous Wavelet Transform), υπολογίζονται η θέση της αλλοιώσεως και θέσεις των ορίων της από την εύρεση των ακροτάτων και των μηδενικών συντελεστών διελεύσεως (Zero Crossing Coefficients) της εικόνας που προκύπτει από τον Μετασχηματισμό Κυματιδίων. Από τη διαδικασία αυτή δημιουργείται μια αδρή εκτίμηση των ορίων της ΕΗΑ η οποία χρησιμοποιείται ως αρχικοποίηση ενός αλγορίθμου τμηματοποιήσεως Τυχαίων Μαρκοβιανών Πεδίων (Markov Random Fields) ο οποίος και δίνει τα τελικά ακριβή όρια της ΕΗΑ. Μέσω αυτής της διαδικασίας η ΕΗΑ παρακολουθείται από τον αλγόριθμο και εξάγονται με ακρίβεια τα όριά της σε όλες τις εικόνες του βίντεο που εμφανίζεται ανεξαρτήτως αλλαγής θέσεως, σχήματος ή φωτεινότητος εντός της. Για κάθε εικόνα που πραγματοποιείται η διαδικασία αυτή, υπολογίζεται οι μέσες τιμές της φωτεινότητας εντός της δομής και μιας μικρής περιοχής εκτός της και εξάγεται μία καμπύλη Φωτεινότητας – Χρόνου (Time – Intensity Curve). Κατόπιν εξάγονται χαρακτηριστικά από την καμπύλη αυτή τα οποία τοποθετούμενα σε ένα ταξινομητή Μηχανών Διανυσμάτων Υποστηρίξεως (ΜΔΥ) (Support Vector Machines) δίνουν τη διαφοροποίηση μεταξύ καλοήθους και κακοήθους ΕΗΑ.Ο 2ος και 3ος αλγόριθμος αφορούν την διάγνωση της ΧΗΝ μέσω επεξεργασίας και αναλύσεως ελαστογραφικής υπερηχογραφικής εικόνας. Οι αλγόριθμοι αυτοί εξάγουν αυτομάτως την έγχρωμη περιοχή με πληροφορία ελαστικότητας από την άχρωμη B-Mode εικόνα και εκτελούν μια διαδικασία μετατροπής έγχρωμων (RGB) τιμών σε τιμές ελαστικότητας. Κατόπιν αναλύουν όλη την περιοχή της ελαστικής πληροφορίας (2ος αλγόριθμος) και υποπεριοχές της (3ος αλγόριθμος) και εξάγουν χαρακτηριστικά υφής από αυτές από τα οποία, τα πιο σημαντικά, τοποθετούμενα σε ένα ταξινομητή ΜΔΥ δίνουν διαφοροποίηση μεταξύ υγιών ατόμων και ασθενών με ΧΗΝ.Τέλος, ο 4ος αλγόριθμος αφορά την διαφορική διάγνωση των ΕΗΑ μέσω επεξεργασίας και αναλύσεως εικόνων ΠΜΣ (MRI). Μέσω της χρήσεως του ΣΜΚ, της αναλύσεώς του σε πολλές κλίμακες (Multiscale Analysis), και του αλγορίθμου τμηματοποιήσεως Fuzzy C-Means (FCM), εντοπίζονται και εξάγονται με ακρίβεια τα όρια της κάθε ΕΗΑ. Κατόπιν εξάγονται χαρακτηριστικά υφής καθώς και μορφολογικά χαρακτηριστικά της δομής από τα οποία, τα πιο σημαντικά, εισάγονται σε έναν ταξινομητή Πιθανοτικών Νευρωνικών Δικτύων για…
Purpose: The design and implementation of a computer-based image analysis system employing the su... more Purpose: The design and implementation of a computer-based image analysis system employing the support vector machine (SVM) classifier system for the classification of Focal Liver Lesions (FLLs) on routine non-enhanced, T2-weighted Magnetic Resonance (MR) images. Materials and Methods: The study comprised 92 patients; each one of them has undergone MRI performed on a Magnetom Concerto (Siemens). Typical signs on dynamic contrast-enhanced MRI and biopsies were employed towards a three class categorization of the 92 cases: 40-benign FLLs, 25-Hepatocellular Carcinomas (HCC) within Cirrhotic liver parenchyma and 27-liver metastases from Non-Cirrhotic liver. Prior to FLLs classification an automated lesion segmentation algorithm based on Marcov Random Fields was employed in order to acquire each FLL Region of Interest. 42 texture features derived from the gray-level histogram, co-occurrence and run-length matrices and 12 morphological features were obtained from each lesion. Stepwise multi-linear regression analysis was utilized to avoid feature redundancy leading to a feature subset that fed the multiclass SVM classifier designed for lesion classification. SVM System evaluation was performed by means of leave-one-out method and ROC analysis. Results: Maximum accuracy for all three classes (90.0%) was obtained by means of the Radial Basis Kernel Function and three textural features (Inverse- Different-Moment, Sum-Variance and Long-Run-Emphasis) that describe lesion's contrast, variability and shape complexity. Sensitivity values for the three classes were 92.5%, 81.5% and 96.2% respectively, whereas specificity values were 94.2%, 95.3% and 95.5%. The AUC value achieved for the selected subset was 0.89 with 0.81 - 0.94 confidence interval. Conclusion: The proposed SVM system exhibit promising results that could be utilized as a second opinion tool to the radiologist in order to decrease the time/cost of diagnosis and the need for patients to undergo invasive examination.
The purpose of the present study was to employ a computer-aided diagnosis system that classifies ... more The purpose of the present study was to employ a computer-aided diagnosis system that classifies chronic liver disease (CLD) using ultrasound shear wave elastography (SWE) imaging, with a stiffness value-clustering and machine-learning algorithm. A clinical data set of 126 patients (56 healthy controls, 70 with CLD) was analyzed. First, an RGB-to-stiffness inverse mapping technique was employed. A five-cluster segmentation was then performed associating corresponding different-color regions with certain stiffness value ranges acquired from the SWE manufacturer-provided color bar. Subsequently, 35 features (7 for each cluster), indicative of physical characteristics existing within the SWE image, were extracted. A stepwise regression analysis toward feature reduction was used to derive a reduced feature subset that was fed into the support vector machine classification algorithm to classify CLD from healthy cases. The highest accuracy in classification of healthy to CLD subject discr...
Ultraschall in der Medizin - European Journal of Ultrasound, 2013
Purpose: This study compares two methods of liver elasticity determination, Shear Wave Elasticity... more Purpose: This study compares two methods of liver elasticity determination, Shear Wave Elasticity (SWE) and Trancient Elastography (VCTE). Images will be provided by a group of patients with chronic parechymal liver diseases which will be compared against histological liver biopsy findings of the same patients. Material and methods: SWE: All SWE measurements are performed in the right lobe of the liver using an appropriate intercostal space. Every patient is examined by two examiners, using the same methods, in order to estimate the Inter-Observer variability. Each examiner performs two measurements on each patient using the same method to estimate the Intra-Observer variability. VCTE: Anthropometric measurements at the time of SWE and TE should include information from patient's record about the type of liver disease and Histological evaluation of liver biopsies. Results: There was a statistically significant difference (p < 0,01) between elastography values of normal and diseased subjects with both VCTE and SWE methods. There was a good correlation when the values of the two methods were compared between each other and each one with the liver biopsy, where available. In addition, intra- and inter-observer variability was low with both methods, if the adequate strict protocol of study was applied. VCTE showed 82.3% sensitivity and 68.2% specificity in diagnosing liver cirrhosis at a cut-off value of 8.9 kPa.SWE showed 88.5% sensitivity and 74.2% specificity in diagnosing liver cirrhosis at a cut-off value of 8.9 kPa. Conclusion: Although patients are few, it was clearly shown that VCTE and SWE can definitely differentiate normal from fibrotic liver tissue. There is also differentiation with SWE between F1-F2 stages of fibrosis and F3-F4 appearing more evident comparing with discrimination offered by VCTE (Fibroscan). More patients are needed to investigate whether VCTE and SWE are able to differentiate between various stages of fibrotic liver disease.
PURPOSE To assess the role of an automated Computer Aided Diagnosis (CAD) system in differentiati... more PURPOSE To assess the role of an automated Computer Aided Diagnosis (CAD) system in differentiation of Healthy Subjects to Chronic Liver Disease (CLD) Patients in terms of liver fibrosis (F0-F4), using Ultrasound Shear Wave Elastography (SWE). METHODS Clinical Dataset consisted of 125 subjects, 55 Healthy (F0) whom condition was validated with Normal Biochemical Markers and clear Clinical History, and 70 with CLD (F1-F4) whom condition was validated with Liver Biopsy. For each subject an SWE examination on their liver right lobe was performed using Supersonic Imagine's Aixplorer ultrasound system, and an SC6-1 transducer. The examination was performed using preset default settings for Abdomen/Liver, and according to literature's suggested guidelines. An SWE image was then acquired, and a separation of the colored areas from the grayscale ones was performed. An RGB-to-Stiffness algorithm was consequently applied on the resulting image (Stiffness Box), using the nbuilt-in colormap, to replace RGB values to Stiffness values. A segmentation procedure was employed using thresholds that segment the image to 5 stiffness range clusters (0-6, 6-12, 12-18, 18-24, and 24-30 kPa), and extract 7 features from each cluster (Mean, Median, Standard Deviation, Sample Kurtosis, 10th Percentile, 90th Percentile, and Cluster's Pixel Percentage on the Stiffness Box) deriving 35 features for each SWE image. The computed feature set was then fed to a designed SVM classifier. SVM-model evaluation was performed by means of exhaustive search, and leave-one-out methods. RESULTS Maximum classification accuracy (85.6%) in distinguishing Healthy from chronic liver disease patients was obtained employing three features (Blue mean and Cyan median values, and Red maximum pixel number) with sensitivity and specificity values of 91.9% and 79.3% respectively. CONCLUSION The proposed CAD system accurately differentiates Healthy to CLD patients assisting in evaluating important factors for performing SWE examination, enriching its guidelines, and aiding clinicians in a more accurate diagnosis.
Nonalcoholic fatty liver disease (NAFLD) is dramatically increasing in parallel with the pandemic... more Nonalcoholic fatty liver disease (NAFLD) is dramatically increasing in parallel with the pandemic of type 2 diabetes. Here, the authors aimed to assess the performance of the most commonly used noninvasive, blood-based biomarkers for liver fibrosis (FibroTest, NAFLD fibrosis score, BARD score, and FIB-4 Index) in subjects with type 2 diabetes. Liver stiffness measurement was estimated by two-dimensional shear wave elastography Finally, the authors assessed the diagnostic role of ActiTest and NashTest 2 in liver fibrosis in the examined population.
The purpose of the present study was to employ a computer-aided diagnosis system that classifies ... more The purpose of the present study was to employ a computer-aided diagnosis system that classifies chronic liver disease (CLD) using ultrasound shear wave elastography (SWE) imaging, with a stiffness value-clustering and machine-learning algorithm. A clinical data set of 126 patients (56 healthy controls, 70 with CLD) was analyzed. First, an RGB-to-stiffness inverse mapping technique was employed. A five-cluster segmentation was then performed associating corresponding different-color regions with certain stiffness value ranges acquired from the SWE manufacturer-provided color bar. Subsequently, 35 features (7 for each cluster), indicative of physical characteristics existing within the SWE image, were extracted. A stepwise regression analysis toward feature reduction was used to derive a reduced feature subset that was fed into the support vector machine classification algorithm to classify CLD from healthy cases. The highest accuracy in classification of healthy to CLD subject discr...
OBJECTIVES Nonalcoholic fatty liver disease (NAFLD) is the most widespread chronic liver disease ... more OBJECTIVES Nonalcoholic fatty liver disease (NAFLD) is the most widespread chronic liver disease type in the Western countries. Ultrasound (US) is used for NAFLD and hepatic steatosis (HS) grading. The most popular US method for NAFLD assessment is the hepatorenal index (HRI), but because of its limitations, other noninvasive methods have been developed. The Resona 7 US system has recently incorporated an US attenuation-related quantitative feature, liver ultrasound attenuation (LiSA), for HS estimation. The purpose of this study is to compare LiSA's and HRI's performance on NAFLD assessment. METHODS A total of 159 NAFLD patients having a magnetic resonance imaging-proton density fat fraction (MRI-PDFF) examination were examined by 2 radiologists, who performed LiSA and HRI measurements in the liver. Correlation of LiSA's and HRI's measurements with MRI-PDFF values was calculated through Pearson correlation coefficient (PCC). To further investigate the performance of LiSA and HRI, optimum cutoffs, provided by the literature, were used to correspond HS grades to MRI-PDFF results. Moreover, a receiver operating characteristic (ROC) analysis on LiSA measurements and steatosis grades was performed. RESULTS Magnetic resonance imaging-PDFF was better correlated with LiSA (PCC = 0.80) than HRI (PCC = 0.67). Receiver operating characteristic analysis showed better performance range for LiSA (77.8%-91.8%) than for HRI (72.8%-85.4%) on all HS grades for all studies used for corresponding MRI-PDFF values to HS grades. CONCLUSIONS The results indicate that LiSA is more accurate than HRI in HS differentiation and can lead to more accurate grading of HS on NAFLD patients.
Poster: "ECR 2015 / C-1378 / Automatic Segmentation of Focal Liver Lesions in MR Images by m... more Poster: "ECR 2015 / C-1378 / Automatic Segmentation of Focal Liver Lesions in MR Images by means of Marcov Random Fields with edge-driven Fuzzy C-means initialization" by: "I. Gatos1, S. Tsantis1, M. Karamesini2, A. Skouroliakou1, G. Kagadis3; 1Athens/GR, 2Kato Ahaia/GR, 3Patras/GR"
ABSTRACT The purpose of this study was to quantify liver elastic heterogeneity in Shear Wave Elas... more ABSTRACT The purpose of this study was to quantify liver elastic heterogeneity in Shear Wave Elastography (SWE) by using textural features and evaluating their diagnostic performance on differentiating healthy from chronic liver disease patients, taking biopsy results as the gold standard. Clinical material includes 16 healthy (F0) and 15 with Chronic Liver Disease (F1,F2,F3,F4) patients according to the Metavir staging system. All exams were performed using the Aixplorer ultrasound system with a SuperCurved SC6-1 transducer. From the SWE-QBox the RGB displayed elasticity data of Young&#39;s modulus were transformed from RGB color space into an elasticity matrix of gray tones, whose values varied from zero to the maximum elasticity measurement. Every pixel with no RGB-values was set to &#39;-1&#39; due to non-valid elasticity value for that pixel. From the elastogram map 185 textural features were computed (5 from the gray-tone histogram, 26 second order statistic features, extracted from the co-occurrence matrices and 10 features extracted from the run-length matrices over four directions (00,450,900,1350) and distances of (d=1,3,5,7,9) pixels). Stepwise multi-linear regression analysis was utilized to avoid feature redundancy leading to a feature subset feeding a Support Vector Machine (SVM) classifier. SVM-model evaluation was performed by means of the leave-one-out method. Maximum classification accuracy (93.5%) in distinguishing healthy from chronic liver disease patients was obtained employing three textural features (Standard Deviation, Sum-Variance, Contrast) that describe the elastogram&#39;s contrast, variability and complexity. Sensitivity and specificity values were 93.3% and 94.0% respectively. The proposed classification scheme can provide reproducibility and reliability of liver SWE application in clinical practice. It can also assist the interpretation of SWE measurements which is considered as a difficult task due to absence of guidelines in the literature and to decrease the time/cost of diagnosis and the need for patients to undergo invasive examination. This research has been co-financed by the European Union (European Social Fund ESF) and Greek national funds through the Operational Program &#39;Education and Lifelong Learning&#39; of the National Strategic Reference Framework (NSRF) Research Funding Program: ARCHIMEDES III. Investing in knowledge society through the European Social Fund.
Uploads