Neural Network Ensemble Based CAD System for Focal Liver Lesions from B-Mode Ultrasound

A neural network ensemble (NNE) based computer-aided diagnostic (CAD) system to assist radiologists in differential diagnosis between focal liver lesions (FLLs), including (1) typical and atypical cases of Cyst, hemangioma (HEM) and metastatic carcinoma (MET) lesions, (2) small and large hepatocellular carcinoma (HCC) lesions, along with (3) normal (NOR) liver tissue is proposed in the present work. Expert radiologists, visualize the textural characteristics of regions inside and outside the lesions to differentiate between different FLLs, accordingly texture features computed from inside lesion regions of interest (IROIs) and texture ratio features computed from IROIs and surrounding lesion regions of interests (SROIs) are taken as input. Principal component analysis (PCA) is used for reducing the dimensionality of the feature space before classifier design. The first step of classification module consists of a five class PCA-NN based primary classifier which yields probability outputs for five liver image classes. The second step of classification module consists of ten binary PCA-NN based secondary classifiers for NOR/Cyst, NOR/HEM, NOR/HCC, NOR/MET, Cyst/HEM, Cyst/HCC, Cyst/MET, HEM/HCC, HEM/MET and HCC/MET classes. The probability outputs of five class PCA-NN based primary classifier is used to determine the first two most probable classes for a test instance, based on which it is directed to the corresponding binary PCA-NN based secondary classifier for crisp classification between two classes. By including the second step of the classification module, classification accuracy increases from 88.7 % to 95 %. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in differential diagnosis of FLLs.     

Wavelet-packet-based texture analysis for differentiation between benign and malignant liver tumours in ultrasound images

The purpose of this study was to apply a novel method of multiscale echo texture analysis for distinguishing benign (hemangiomas) from malignant (hepatocellular carcinomas (HCCs) and metastases) focal liver lesions in B-mode ultrasound images. In this method, regions of interest (ROIs) extracted from within the lesions were decomposed into subimages by wavelet packets. Multiscale texture features that quantify homogeneity of the echogenicity were calculated from these subimages and were combined by an artificial neural network (ANN). A subset of the multiscale features was selected that yielded the highest performance in the classification of lesions measured by the area under the receiver operating characteristic curve (Az). In an analysis of 193 ROIs consisting of 50 hemangiomas, 87 hepatocellular carcinomas and 56 metastases, the multiscale features yielded a high A: value of 0.92 in distinguishing benign from malignant lesions, 0.93 in distinguishing hemangiomas from HCCs and 0.94 in distinguishing hemangiomas from metastases. Our new multiscale texture analysis method can effectively differentiate malignant from benign lesions, and thus has the potential to increase the accuracy of diagnosis of focal liver lesions in ultrasound images.     

A comparative study of computer-aided classification systems for focal hepatic lesions from B-mode ultrasound

Abstract

A comparative study of three computer-aided classification (CAC) systems for characterization of focal hepatic lesions (FHLs), such as cyst, hemangioma (HEM), hepatocellular carcinoma (HCC) and metastatic carcinoma (MET), along with normal (NOR) liver tissue is carried out in the present work. In order to develop efficient CAC systems a comprehensive and representative dataset consisting of B-mode ultrasound images with (1) typical and atypical cases of cyst, HEM and MET lesions, (2) small and large HCC lesions and (3) NOR liver cases have been used for designing K-nearest neighbour (KNN), probabilistic neural network (PNN) and a back propagation neural network (BPNN) classifiers. For differential diagnosis between atypical FHLs, expert radiologists often visualize the textural characteristics of regions inside and outside the lesion. Accordingly in the present work, texture features and texture ratio features are computed from regions inside and outside the lesions. A feature set consisting of 208 texture features (i.e. 104 texture features and 104 texture ratio features) is subjected to principal component analysis (PCA) for dimensionality reduction; it is observed that maximum accuracy of 87.7% is obtained for a PCA-BPNN-based CAC system in comparison to 86.1% and 85% as obtained by PCA-PNN and PCA-KNN-based CAC systems. The sensitivity of the proposed PCA-BPNN based CAC system for NOR, Cyst, HEM, HCC and MET cases is 82.5%, 96%, 93.3%, 90% and 82.2%, respectively. The sensitivity values with respect to typical, atypical, small HCC and large HCC cases are 85.9%, 88.1%, 100% and 87%, respectively. Keeping in view the comprehensive and representative dataset used for designing the classifier, the results obtained by the proposed PCA-BPNN-based CAC system are quite encouraging and indicate its usefulness to assist experienced radiologists for interpretation and diagnosis of FHLs.     

SVM-Based CAC System for B-Mode Kidney Ultrasound Images

The present study proposes a computer-aided classification (CAC) system for three kidney classes, viz. normal, medical renal disease (MRD) and cyst using B-mode ultrasound images. Thirty-five B-mode kidney ultrasound images consisting of 11 normal images, 8 MRD images and 16 cyst images have been used. Regions of interest (ROIs) have been marked by the radiologist from the parenchyma region of the kidney in case of normal and MRD cases and from regions inside lesions for cyst cases. To evaluate the contribution of texture features extracted from de-speckled images for the classification task, original images have been pre-processed by eight de-speckling methods. Six categories of texture features are extracted. One-against-one multi-class support vector machine (SVM) classifier has been used for the present work. Based on overall classification accuracy (OCA), features from ROIs of original images are concatenated with the features from ROIs of pre-processed images. On the basis of OCA, few feature sets are considered for feature selection. Differential evolution feature selection (DEFS) has been used to select optimal features for the classification task. DEFS process is repeated 30 times to obtain 30 subsets. Run-length matrix features from ROIs of images pre-processed by Lee’s sigma concatenated with that of enhanced Lee method have resulted in an average accuracy (in %) and standard deviation of 86.3 ± 1.6. The results obtained in the study indicate that the performance of the proposed CAC system is promising, and it can be used by the radiologists in routine clinical practice for the classification of renal diseases.     

STUDIES ON THE PROLIFERATIVE ACTIVITY OF DIETHYLNITROSAMINE-INDUCED HEPATOCELLULAR CARCINOMAS IN MONKEYS

In this study, synthetic phase fractions (SPFs) determined by flow cytometry and AgNOR counts were analysed in benign liver lesions (regenerative nodules and adenomas), hepatocellular carcinomas (HCCs), and lung metastases of a monkey hepatocarcinogenesis model to find out if AgNOR counts and SPFs can discriminate between malignant and non-malignant liver lesions. The average per cent SPF values and the AgNOR counts were significantly (P=0·001) increased in regenerative liver nodules (5·30 per cent; 4·96), adenomas (5·34 per cent; 3·46) and well-differentiated HCCs (6·75 per cent; 4·47), compared with the untreated control livers (3·18 per cent; 0·98), but the differences between these three groups were not significant. In the poorly differentiated HCC group, however, the average SPF value (9·60 per cent) and AgNOR count (7·14) were significantly higher than in any of the other liver lesions examined. A significant correlation was found between the SPF values and AgNOR counts on the one hand, and differentiation and cytological grade of the HCC samples on the other. The results of this study show that the SPF values and AgNOR counts are not reliable in differentiating between regenerating liver nodules, adenomas, and experimental well-differentiated HCCs. The SPF value, however, may serve as a prognostic factor in HCC, since it was found to be significantly higher in HCCs with lung metastasis than in those without. © 1997 by John Wiley & Sons, Ltd.     

Role of overexpression of MACC1 and/or FAK in predicting prognosis of hepatocellular carcinoma after liver transplantation

Background: Metastasis-associated in colon cancer-1 (MACC1) acts as a promoter of tumor metastasis; however, the predictive value of MACC1 for hepatocellular carcinoma (HCC) after liver transplantation (LT) remains unclear.Methods: We examined the expression of MACC1 and its target genes MET and FAK by quantitative PCR in 160 patients with HCC that was undergone LT.Results: The patients with MACC1^high or FAK^high in HCCs showed a significantly shorter overall survival and higher cumulative recurrence rates after liver transplantation (LT), compared with MACC1^low or FAK^low group. Multivariate analysis indicated that MACC1 alone or combination of MACC1/FAK was an independent prognostic factor for overall survival and cumulative recurrence.Conclusions: MACC1 or combination of MACC1/FAK could serve as a novel biomarker in predicting the prognosis of HCC after LT.     

Segmentation, Feature Extraction, and Multiclass Brain Tumor Classification

Multiclass brain tumor classification is performed by using a diversified dataset of 428 post-contrast T1-weighted MR images from 55 patients. These images are of primary brain tumors namely astrocytoma (AS), glioblastoma multiforme (GBM), childhood tumor-medulloblastoma (MED), meningioma (MEN), secondary tumor-metastatic (MET), and normal regions (NR). Eight hundred fifty-six regions of interest (SROIs) are extracted by a content-based active contour model. Two hundred eighteen intensity and texture features are extracted from these SROIs. In this study, principal component analysis (PCA) is used for reduction of dimensionality of the feature space. These six classes are then classified by artificial neural network (ANN). Hence, this approach is named as PCA-ANN approach. Three sets of experiments have been performed. In the first experiment, classification accuracy by ANN approach is performed. In the second experiment, PCA-ANN approach with random sub-sampling has been used in which the SROIs from the same patient may get repeated during testing. It is observed that the classification accuracy has increased from 77 to 91 %. PCA-ANN has delivered high accuracy for each class: AS—90.74 %, GBM—88.46 %, MED—85 %, MEN—90.70 %, MET—96.67 %, and NR—93.78 %. In the third experiment, to remove bias and to test the robustness of the proposed system, data is partitioned in a manner such that the SROIs from the same patient are not common for training and testing sets. In this case also, the proposed system has performed well by delivering an overall accuracy of 85.23 %. The individual class accuracy for each class is: AS—86.15 %, GBM—65.1 %, MED—63.36 %, MEN—91.5 %, MET—65.21 %, and NR—93.3 %. A computer-aided diagnostic system comprising of developed methods for segmentation, feature extraction, and classification of brain tumors can be beneficial to radiologists for precise localization, diagnosis, and interpretation of brain tumors on MR images.     

A case of hypervascular hyperplastic nodules in a patient with alcoholic liver cirrhosis

Most hypervascular nodules in a cirrhotic liver are hepatocellular carcinomas (HCCs); however, some are benign hypervascular hyperplastic nodules. We report a case of benign hypervascular hyperplastic nodules in a 41-year-old male patient without hepatitis B or C virus infection, with a history of alcohol abuse, and diagnosed with an aortic aneurysm. The dynamic computerized tomography of the liver demonstrated multiple nodular lesions on both liver lobes with arterial enhancement and delayed washout. The hepatic angiography showed multiple faint nodular staining of both lobes in the early arterial phase. Magnetic resonance imaging revealed numerous nodules showing high signals on T1 weighted images, with some nodules showing a low central signal portion. The clinical impression was HCC. The ultrasonography-guided liver biopsy, which was performed on the largest nodule (2.5 cm in size), revealed hepatocellular nodules with slightly increased cellularity, unpaired arteries, increased sinusoidal capillarization, and focal iron deposition. However, both cellular and cytological atypia were unremarkable. Although the clinical impression was HCC, the pathological diagnosis was hypervascular hyperplastic nodules in alcoholic cirrhosis. Differential diagnosis of hypervascular nodules in cirrhosis and HCC is difficult with imaging studies; thus, histological confirmation is mandatory.     

Extracellular matrix composition and integrin expression in early hepatocarcinogenesis in human cirrhotic liver

Extracellular matrix (ECM) plays a major role in cell differentiation, proliferation, and gene expression, both in physiological and in pathological conditions. Immunohistochemistry has been used to investigate modifications of ECM and related receptors, the integrins, in 26 small nodular lesions developed in human cirrhotic livers, on the basis that these lesions could represent sequential steps of hepatocarcinogenesis: the lesions were 16 macroregenerative nodules (MRNs), either of ordinary (n=5) or atypical (n=11) type, and ten small (<15 mm) hepatocellular carcinomas (HCCs). Data were compared with those obtained in the surrounding cirrhotic tissue, in large HCCs, and in normal liver. The results indicate similarities between ordinary MRNs and cirrhosis, on the one hand, and between atypical MRNs and small HCCs, on the other. Strong and homogeneous deposition of collagen type IV and laminin in sinusoids and overexpression of α6 integrin by sinusoidal cells and hepatocytes were especially noticeable in dysplastic areas characteristic of atypical MRNs, as in small HCCs. In addition, the staining of α 2 and α6 integrins in MRNs revealed the presence of widespread atypical ductular proliferation expanding from periportal and perinodular areas, containing epithelial cells with transitional (hepato-biliary) phenotype. These findings suggest a transition from atypical MRNs to small HCCs and a possible role for liver epithelial precursor cells (‘stem cells’) in the development and evolution of MRNs. © 1997 John Wiley & Sons, Ltd.     

结合快速傅里叶变换的肝实质病变特征量化检测

目的：探讨针对高频超声图像下的肝实质病变特征进行量化检测的可行性。方法：收集47例轻、中、重度乙型肝炎肝硬化患者（轻度肝硬化组、中度肝硬化组、重度肝硬化组）及20名健康志愿者（正常对照组）的肝脏二维高频超声图像,采用快速傅里叶变换与图像形态学处理相结合的方法对肝实质进行处理,自动检测肝实质形态特征并量化提取病变特征数据,并通过评分策略对病变特征进行详细分类。结果：该评分策略所得数据在轻度、中度、重度肝硬化、正常对照组中差异具有统计学意义（P<0.001）。在多重比较中,与正常对照组比较,组间差异均具有统计学意义,与轻度、中度肝硬化组比较,除重度肝硬化组组间差异不显著外,其余均具有统计学意义（P<0.05）。结论：利用快速傅里叶变换可有效提取出符合医生视角的肝实质纹理特征并进行量化,为进一步对肝硬化分级诊断提供数据支撑。     

Computerized Breast Mass Detection Using Multi-Scale Hessian-Based Analysis for Dynamic Contrast-Enhanced MRI

This study aimed to investigate a computer-aided system for detecting breast masses using dynamic contrast-enhanced magnetic resonance imaging for clinical use. Detection performance of the system was analyzed on 61 biopsy-confirmed lesions (21 benign and 40 malignant lesions) in 34 women. The breast region was determined using the demons deformable algorithm. After the suspicious tissues were identified by kinetic feature (area under the curve) and the fuzzy c-means clustering method, all breast masses were detected based on the rotation-invariant and multi-scale blob characteristics. Subsequently, the masses were further distinguished from other detected non-tumor regions (false positives). Free-response operating characteristics (FROC) curve and detection rate were used to evaluate the detection performance. Using the combined features, including blob, enhancement, morphologic, and texture features with 10-fold cross validation, the mass detection rate was 100 % (61/61) with 15.15 false positives per case and 91.80 % (56/61) with 4.56 false positives per case. In conclusion, the proposed computer-aided detection system can help radiologists reduce inter-observer variability and the cost associated with detection of suspicious lesions from a large number of images. Our results illustrated that breast masses can be efficiently detected and that enhancement and morphologic characteristics were useful for reducing non-tumor regions.     

基于超声影像组学的原发性肝细胞癌分级预测

目的:针对原发性肝细胞癌（HCC）肿瘤分级预测难题，提出一种基于灰阶超声成像的影像组学预测模型。方法:首先，由超声医生对肿瘤区域进行手动分割，其次，采用影像组学方法对肿瘤区域提取形状、一阶统计、纹理特征，计算特征间Pearson相关系数剔除冗余特征，最后通过单变量分析筛选得到特征子集，采用LASSO构建HCC分级预测模型；利用留一法计算模型的受试者操作特性曲线下的面积（AUC）评估模型对HCC分级的预测能力。结果:利用43例经手术病理证实的HCC患者的灰阶超声图像构建HCC分级预测模型，所建模型由6个与分级高度相关的影像特征组成，模型具有较强的预测能力（AUC=0.76）。结论:基于灰阶超声成像的影像特征与HCC分级高度相关，所建影像组学模型能够较好地预测HCC分级。     

Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers

OBJECTIVES: The aim of the present study is to define an optimally performing computer-aided diagnosis (CAD) architecture for the classification of liver tissue from non-enhanced computed tomography (CT) images into normal liver (C1), hepatic cyst (C2), hemangioma (C3), and hepatocellular carcinoma (C4). To this end, various CAD architectures, based on texture features and ensembles of classifiers (ECs), are comparatively assessed. MATERIALS AND METHODS: Number of regions of interests (ROIs) corresponding to C1-C4 have been defined by experienced radiologists in non-enhanced liver CT images. For each ROI, five distinct sets of texture features were extracted using first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. Two different ECs were constructed and compared. The first one consists of five multilayer perceptron neural networks (NNs), each using as input one of the computed texture feature sets or its reduced version after genetic algorithm-based feature selection. The second EC comprised five different primary classifiers, namely one multilayer perceptron NN, one probabilistic NN, and three k-nearest neighbor classifiers, each fed with the combination of the five texture feature sets or their reduced versions. The final decision of each EC was extracted by using appropriate voting schemes, while bootstrap re-sampling was utilized in order to estimate the generalization ability of the CAD architectures based on the available relatively small-sized data set. RESULTS: The best mean classification accuracy (84.96%) is achieved by the second EC using a fused feature set, and the weighted voting scheme. The fused feature set was obtained after appropriate feature selection applied to specific subsets of the original feature set. CONCLUSIONS: The comparative assessment of the various CAD architectures shows that combining three types of classifiers with a voting scheme, fed with identical feature sets obtained after appropriate feature selection and fusion, may result in an accurate system able to assist differential diagnosis of focal liver lesions from non-enhanced CT images.     

Computerized Determination Scheme for Histological Classification of Breast Mass Using Objective Features Corresponding to Clinicians’ Subjective Impressions on Ultrasonographic Images

It is often difficult for clinicians to decide correctly on either biopsy or follow-up for breast lesions with masses on ultrasonographic images. The purpose of this study was to develop a computerized determination scheme for histological classification of breast mass by using objective features corresponding to clinicians’ subjective impressions for image features on ultrasonographic images. Our database consisted of 363 breast ultrasonographic images obtained from 363 patients. It included 150 malignant (103 invasive and 47 noninvasive carcinomas) and 213 benign masses (87 cysts and 126 fibroadenomas). We divided our database into 65 images (28 malignant and 37 benign masses) for training set and 298 images (122 malignant and 176 benign masses) for test set. An observer study was first conducted to obtain clinicians’ subjective impression for nine image features on mass. In the proposed method, location and area of the mass were determined by an experienced clinician. We defined some feature extraction methods for each of nine image features. For each image feature, we selected the feature extraction method with the highest correlation coefficient between the objective features and the average clinicians’ subjective impressions. We employed multiple discriminant analysis with the nine objective features for determining histological classification of mass. The classification accuracies of the proposed method were 88.4 % (76/86) for invasive carcinomas, 80.6 % (29/36) for noninvasive carcinomas, 86.0 % (92/107) for fibroadenomas, and 84.1 % (58/69) for cysts, respectively. The proposed method would be useful in the differential diagnosis of breast masses on ultrasonographic images as diagnosis aid.     

Quantitative Ultrasound Analysis for Classification of BI-RADS Category 3 Breast Masses

The accuracy of an ultrasound (US) computer-aided diagnosis (CAD) system was evaluated for the classification of BI-RADS category 3, probably benign masses. The US database used in this study contained 69 breast masses (21 malignant and 48 benign masses) that at blinded retrospective interpretation were assigned to BI-RADS category 3 by at least one of five radiologists. For computer-aided analysis, multiple morphology (shape, orientation, margin, lesions boundary, and posterior acoustic features) and texture (echo patterns) features based on BI-RADS lexicon were implemented, and the binary logistic regression model was used for classification. The receiver operating characteristic curve analysis was used for statistical analysis. The area under the curve (Az) of morphology, texture, and combined features were 0.90, 0.75, and 0.95, respectively. The combined features achieved the best performance and were significantly better than using texture features only (0.95 vs. 0.75, p value?=?0.0163). The cut-off point at the sensitivity of 86 % (18/21), 95 % (20/21), and 100 % (21/21) achieved the specificity of 90 % (43/48), 73 % (35/48), and 33 % (16/48), respectively. In conclusion, the proposed CAD system has the potential to be used in upgrading malignant masses misclassified as BI-RADS category 3 on US by the radiologists.     

Loss of parental-specific methylation at the IGF2 locus in human hepatocellular carcinoma

Significant production of the growth factor IGF2 has been reported in human hepatocellular carcinomas (HCCs). Disturbances associated with changes in methylation at this locus or affecting the 11p15.5 imprinting domain as a whole can be postulated in HCCs. In the present study, the methylation status of differentially methylated regions of the imprinted genes TSSC5, LIT1, and IGF2, which span the 11p15 domain, was analysed in 71 liver tissues from virus-associated and non-virus-associated HCCs compared with six normal liver tissues. Altered methylation of TSSC5 and LIT1 was observed in only 6% and 8% of HCCs, respectively, compared with 89% at the IGF2 locus, suggesting that these loci were not concomitantly dysregulated. These observations suggest that loss of parental-specific methylation at the IGF2 locus may be specifically associated with HCC, whether virus-associated or non-virus-associated, and arising in cirrhotic or non-cirrhotic livers.     

In situ detection of telomerase enzymatic activity in human hepatocellular carcinogenesis

Telomerase enzymatic activity has been detected in most human malignant tumours including hepatocellular carcinoma. In order to assess the cellular source, the topographic distribution, and the chronology of telomerase re-expression during human liver carcinogenesis, an in situ technique derived from the standard TRAP (telomeric repeat amplification protocol) assay was set up that allowed the detection of telomerase enzyme activity at the cellular level on frozen liver tissue sections. In situ TRAP (ISTRAP) was performed on 27 hepatocellular carcinomas (HCCs) and 57 non-tumour livers, including normal liver without HCC, liver samples adjacent to tumour with and without hepatic cirrhosis, and biopsies of chronic hepatitis. In HCC, telomerase was detected in the nuclei of liver tumour cells in 23/27 cases (85%), with a heterogeneous distribution within the tumour. This signal was also detected in clusters of hepatocytes in 16/26 (61%) samples of liver adjacent to HCC, in 10/23 (43%) cases of chronic viral hepatitis without adjacent HCC, and in scattered nuclei of 2/8 histologically normal livers. Comparison of the results obtained with ISTRAP and standard TRAP assays on tissue extracts suggests a gain in sensitivity with the in situ technique. This study confirms that telomerase is expressed in most HCCs and suggests that focal telomerase reactivation is an early event during human liver carcinogenesis. ISTRAP is a sensitive technique that allows the study of telomerase expression in the morphological context.     

A computer-aided temporal and dynamic subtraction technique of the liver for detection of small hepatocellular carcinomas on abdominal CT images

It is often difficult for radiologists to identify small hepatocellular carcinomas (HCCs) due to insufficient contrast enhancement. Therefore, we have developed a new computer-aided temporal and dynamic subtraction technique to enhance small HCCs, after automatically selecting images set at the same anatomical position from the present (non-enhanced and arterial-phase CT images) and previous images. The present study was performed with CT images from 14 subjects. First, we used template-matching based on similarities in liver shape between the present (non-enhanced and arterial-phase CT images) and previous arterial-phase CT images at the same position. Temporal subtraction images were then obtained by subtraction of the previous image from the present image taken at the same position of the liver. Dynamic subtraction images were also obtained by subtraction of non-enhanced CT images from arterial-phase CT images taken at the same position of the liver. Twenty-one of 22 nodules (95.5%) with contrast enhancement were visualized in temporal and dynamic subtraction images. Compared with present arterial-phase CT images, increases of 150% and 140% in nodule-to-liver contrast were observed on dynamic and temporal subtraction images, respectively. These subtraction images may be useful as reference images in the detection of small moderately differentiated HCCs.     

Fibrolamellar hepatocellular carcinoma: a case report with cytological features in a sixteen-year-old girl

We report a case of a 16-yr-old girl with a liver tumor revealed by thrombophlebitis of the left leg. On physical examination the patient was found to have painless hepatomegaly. Ultrasound and CAT scan showed a large tumor of the left portion of the liver, measuring 14 cm in diameter. Cytological preparations were touch imprints of the biopsy fragments obtained under ultrasound guidance. Cytological examination using May-Grünwald Giemsa stain revealed highly cellular smears containing large tumor cells with a round nucleus, prominent nucleoli, and abundant granular basophilic cytoplasm. Cytological features were those of fibrolamellar hepatocellular carcinoma, confirmed by histological examination of the biopsy sample as well as the surgical specimen obtained after wide excision of the lesion following ineffective neoadjuvant chemotherapy.