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

Radiomics analysis for the prediction of locoregional recurrence of locally advanced oropharyngeal cancer and hypopharyngeal cancer

PURPOSE

By radiomic analysis of the postcontrast CT images, this study aimed to predict locoregional recurrence (LR) of locally advanced oropharyngeal cancer (OPC) and hypopharyngeal cancer (HPC).

METHODS

A total of 192 patients with stage III-IV OPC or HPC from two independent cohort were randomly split into a training cohort with 153 cases and a testing cohort with 39 cases. Only primary tumor mass was manually segmented. Radiomic features were extracted using PyRadiomics, and then the support vector machine was used to build the radiomic model with fivefold cross-validation process in the training data set. For each case, a radiomics score was generated to indicate the probability of LR.

RESULTS

There were 94 patients with LR assigned in the progression group and 98 patients without LR assigned in the stable group. There was no significant difference of TNM staging, treatment strategies and common risk factors between these two groups. For the training data set, the radiomics model to predict LR showed 83.7% accuracy and 0.832 (95% CI 0.72, 0.87) area under the ROC curve (AUC). For the test data set, the accuracy and AUC slightly declined to 79.5% and 0.770 (95% CI 0.64, 0.80), respectively. The sensitivity/specificity of training and test data set for LR prediction were 77.6%/89.6%, and 66.7%/90.5%, respectively.

CONCLUSIONS

The image-based radiomic approach could provide a reliable LR prediction model in locally advanced OPC and HPC. Early identification of those prone to post-treatment recurrence would be helpful for appropriate adjustments to treatment strategies and post-treatment surveillance.

The specific viral composition in triple-negative breast cancer tissue shapes the specific tumor microenvironment characterized on pathological images

Numerous studies have shown that different subtypes of breast cancer (BC) have significant differences in terms of the tumor microbiome, host gene expression, and histopathological image, whereas the biological links between these cancer-associated indicators are still unknown. Here, we performed a comprehensive analysis with 610 patients of the four subtypes of BC with matched tissue microbiota, host transcriptome, and histopathological image samples. Correlation analysis showed that the composition of intratumoral viruses shaped the tumor microenvironment (TME) of patients with BC, and the TME was further reflected in the histopathological images. Of the four subtypes, patients with triple-negative breast cancer (TNBC) had unique intratumoral viral community composition, non-cancer cell infiltration in the TME, and histopathological image characteristics. Furthermore, we detected multiple virus-cell-image association axes in TNBC, in which tumor-associated macrophages (TAMs) have clinical prognostic implication. This study provides a comprehensive map of the associations between the intratumoral virome, TME, and histopathological image of TNBC, as well as insights into disease prognosis that can be crucial for precise therapeutic intervention strategies.

Machine learning for malignant versus benign focal liver lesions on US and CEUS: a meta-analysis

OBJECTIVES

To perform a meta-analysis of the diagnostic performance of learning (ML) algorithms (conventional and deep learning algorithms) for the classification of malignant versus benign focal liver lesions (FLLs) on US and CEUS.

METHODS

Available databases were searched for relevant published studies through September 2022. Studies met eligibility criteria if they evaluate the diagnostic performance of ML for the classification of malignant and benign focal liver lesions on US and CEUS. The pooled per-lesion sensitivities and specificities for each modality with 95% confidence intervals were calculated.

RESULTS

A total of 8 studies on US, 11 on CEUS, and 1 study evaluating both methods met the inclusion criteria with a total of 34,245 FLLs evaluated. The pooled sensitivity and specificity of ML for the malignancy classification of FLLs were 81.7% (95% CI, 77.2-85.4%) and 84.8% (95% CI, 76.0-90.8%) for US, compared to 87.1% (95% CI, 81.8-91.0%) and 87.0% (95% CI, 83.1-90.1%) for CEUS. In the subgroup analysis of studies that evaluated deep learning algorithms, the sensitivity and specificity of CEUS (n = 4) increased to 92.4% (95% CI, 88.5-95.0%) and 88.2% (95% CI, 81.1-92.9%).

CONCLUSIONS

The diagnostic performance of ML algorithms for the malignant classification of FLLs was high for both US and CEUS with overall similar sensitivity and specificity. The similar performance of US may be related to the higher prevalence of DL models in that group.

Artificial intelligence for the classification of focal liver lesions in ultrasound - a systematic review

Focal liver lesions are detected in about 15% of abdominal ultrasound examinations. The diagnosis of frequent benign lesions can be determined reliably based on the characteristic B-mode appearance of cysts, hemangiomas, or typical focal fatty changes. In the case of focal liver lesions which remain unclear on B-mode ultrasound, contrast-enhanced ultrasound (CEUS) increases diagnostic accuracy for the distinction between benign and malignant liver lesions. Artificial intelligence describes applications that try to emulate human intelligence, at least in subfields such as the classification of images. Since ultrasound is considered to be a particularly examiner-dependent technique, the application of artificial intelligence could be an interesting approach for an objective and accurate diagnosis. In this systematic review we analyzed how artificial intelligence can be used to classify the benign or malignant nature and entity of focal liver lesions on the basis of B-mode or CEUS data. In a structured search on Scopus, Web of Science, PubMed, and IEEE, we found 52 studies that met the inclusion criteria. Studies showed good diagnostic performance for both the classification as benign or malignant and the differentiation of individual tumor entities. The results could be improved by inclusion of clinical parameters and were comparable to those of experienced investigators in terms of diagnostic accuracy. However, due to the limited spectrum of lesions included in the studies and a lack of independent validation cohorts, the transfer of the results into clinical practice is limited.

Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques

Hepatocellular Carcinoma (HCC) is the most frequent malignant liver tumor and the third cause of cancer-related deaths worldwide. For many years, the golden standard for HCC diagnosis has been the needle biopsy, which is invasive and carries risks. Computerized methods are due to achieve a noninvasive, accurate HCC detection process based on medical images. We developed image analysis and recognition methods to perform automatic and computer-aided diagnosis of HCC. Conventional approaches that combined advanced texture analysis, mainly based on Generalized Co-occurrence Matrices (GCM) with traditional classifiers, as well as deep learning approaches based on Convolutional Neural Networks (CNN) and Stacked Denoising Autoencoders (SAE), were involved in our research. The best accuracy of 91% was achieved for B-mode ultrasound images through CNN by our research group. In this work, we combined the classical approaches with CNN techniques, within B-mode ultrasound images. The combination was performed at the classifier level. The CNN features obtained at the output of various convolution layers were combined with powerful textural features, then supervised classifiers were employed. The experiments were conducted on two datasets, acquired with different ultrasound machines. The best performance, above 98%, overpassed our previous results, as well as representative state-of-the-art results.

Radiomics in Head and Neck Cancer Outcome Predictions

Head and neck cancer has great regional anatomical complexity, as it can develop in different structures, exhibiting diverse tumour manifestations and high intratumoural heterogeneity, which is highly related to resistance to treatment, progression, the appearance of metastases, and tumour recurrences. Radiomics has the potential to address these obstacles by extracting quantitative, measurable, and extractable features from the region of interest in medical images. Medical imaging is a common source of information in clinical practice, presenting a potential alternative to biopsy, as it allows the extraction of a large number of features that, although not visible to the naked eye, may be relevant for tumour characterisation. Taking advantage of machine learning techniques, the set of features extracted when associated with biological parameters can be used for diagnosis, prognosis, and predictive accuracy valuable for clinical decision-making. Therefore, the main goal of this contribution was to determine to what extent the features extracted from Computed Tomography (CT) are related to cancer prognosis, namely Locoregional Recurrences (LRs), the development of Distant Metastases (DMs), and Overall Survival (OS). Through the set of tumour characteristics, predictive models were developed using machine learning techniques. The tumour was described by radiomic features, extracted from images, and by the clinical data of the patient. The performance of the models demonstrated that the most successful algorithm was XGBoost, and the inclusion of the patients' clinical data was an asset for cancer prognosis. Under these conditions, models were created that can reliably predict the LR, DM, and OS status, with the area under the ROC curve (AUC) values equal to 0.74, 0.84, and 0.91, respectively. In summary, the promising results obtained show the potential of radiomics, once the considered cancer prognosis can, in fact, be expressed through CT scans.

Application of artificial intelligence using a novel EUS-based convolutional neural network model to identify and distinguish benign and malignant hepatic masses

BACKGROUND AND AIMS

Detection and characterization of focal liver lesions (FLLs) is key for optimizing treatment for patients who may have a primary hepatic cancer or metastatic disease to the liver. This is the first study to develop an EUS-based convolutional neural network (CNN) model for the purpose of identifying and classifying FLLs.

METHODS

A prospective EUS database comprising cases of FLLs visualized and sampled via EUS was reviewed. Relevant still images and videos of liver parenchyma and FLLs were extracted. Patient data were then randomly distributed for the purpose of CNN model training and testing. Once a final model was created, occlusion heatmap analysis was performed to assess the ability of the EUS-CNN model to autonomously identify FLLs. The performance of the EUS-CNN for differentiating benign and malignant FLLs was also analyzed.

RESULTS

A total of 210,685 unique EUS images from 256 patients were used to train, validate, and test the CNN model. Occlusion heatmap analyses demonstrated that the EUS-CNN model was successful in autonomously locating FLLs in 92.0% of EUS video assets. When evaluating any random still image extracted from videos or physician-captured images, the CNN model was 90% sensitive and 71% specific (area under the receiver operating characteristic [AUROC], 0.861) for classifying malignant FLLs. When evaluating full-length video assets, the EUS-CNN model was 100% sensitive and 80% specific (AUROC, 0.904) for classifying malignant FLLs.

CONCLUSIONS

This study demonstrated the capability of an EUS-CNN model to autonomously identify FLLs and to accurately classify them as either malignant or benign lesions.

Quantitative Ultrasound Image Analysis Helps in the Differentiation of Hepatocellular Carcinoma (HCC) From Borderline Lesions and Predicting the Histologic Grade of HCC and Microvascular Invasion

OBJECTIVES

Quantitative image analysis is one of the methods to overcome the lack of objectivity of ultrasound (US). The aim of this study was to clarify the correlation between the features from a US image analysis and the histologic grade and microvascular invasion (MVI) of hepatocellular carcinoma (HCC) and differentiation of HCC smaller than 2 cm from borderline lesions.

METHODS

We retrospectively analyzed grayscale US images with histopathologic evidence of HCC or a precancerous lesion using ImageJ version 1.47 software (National Institutes of Health, Bethesda, MD).

RESULTS

A total of 148 nodules were included (borderline lesion, n = 31; early HCC [eHCC], n = 3; well-differentiated HCC [wHCC], n = 16; moderately differentiated HCC [mHCC], n = 79; and poorly differentiated HCC [pHCC], n = 19). A multivariate analysis selected lower minimum gray values (odds ratio [OR], 0.431; P = .003) and a higher standard deviation (OR, 1.880; P = .019) as predictors of HCC smaller than 2 cm. Median (range) minimum gray values of borderline lesions, eHCC, wHCC, mHCC, and pHCC were 29 (0-103), 7 (0-47), 6 (0-60), 10 (0-53), and 2 (0-38), respectively, and gradually decreased from borderline lesions to pHCC (P < 0.001). The multivariate analysis showed a higher aspect ratio (OR, 2.170; P = .001) and lower minimum gray value (OR, 0.475; P = .043) as predictors of MVI. An anechoic area diagnosed by a subjective evaluation was correlated with the minimum gray value (P < .0001). The proportion of the anechoic area gradually increased from eHCC to pHCC (P = .031).

CONCLUSIONS

In a US image analysis, HCC smaller than 2 cm had features of greater heterogeneity and a lower minimum gray value than borderline lesions. Moderately differentiated HCC was smoother than borderline lesions, and the anechoic area correlated with histologic grading. Microvascular invasion was correlated with a slender shape and a lower minimum gray value.

Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods

Hepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, specific techniques for non-invasive, computerized HCC diagnosis are developed, by exploiting the information from ultrasound images. In this work, the possibility of performing the automatic diagnosis of HCC within B-mode ultrasound and Contrast-Enhanced Ultrasound (CEUS) images, using advanced machine learning methods based on Convolutional Neural Networks (CNN), was assessed. The recognition performance was evaluated separately on B-mode ultrasound images and on CEUS images, respectively, as well as on combined B-mode ultrasound and CEUS images. For this purpose, we considered the possibility of combining the input images directly, performing feature level fusion, then providing the resulted data at the entrances of representative CNN classifiers. In addition, several multimodal combined classifiers were experimented, resulted by the fusion, at classifier, respectively, at the decision levels of two different branches based on the same CNN architecture, as well as on different CNN architectures. Various combination methods, and also the dimensionality reduction method of Kernel Principal Component Analysis (KPCA), were involved in this process. These results were compared with those obtained on the same dataset, when employing advanced texture analysis techniques in conjunction with conventional classification methods and also with equivalent state-of-the-art approaches. An accuracy above 97% was achieved when our new methodology was applied.

Comparison of Deep-Learning and Conventional Machine-Learning Methods for the Automatic Recognition of the Hepatocellular Carcinoma Areas from Ultrasound Images

The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.

Wavelet-based Computationally-Efficient Computer-Aided Characterization of Liver Steatosis using Conventional B-mode Ultrasound Images

Hepatic steatosis occurs when lipids accumulate in the liver leading to steatohepatitis, which can evolve into cirrhosis and consequently may end with hepatocellular carcinoma. Several automatic classification algorithms have been proposed to detect liver diseases. However, some algorithms are manufacturer-dependent, while others require extensive calculations and consequently prolonged computational time. This may limit the development of real-time and manufacturer-independent computer-aided detection of liver steatosis. This work demonstrates the feasibility of a computationally-efficient and manufacturer-independent wavelet-based computer-aided liver steatosis detection system using conventional B-mode ultrasound (US) imaging. Seven features were extracted from the approximation part of the second-level wavelet packet transform (WPT) of US images. The proposed technique was tested on two datasets of ex-vivo mice livers with and without gelatin embedding, in addition to a third dataset of in-vivo human livers acquired using two different US machines. Using the gelatin-embedded mice liver dataset, the technique exhibited 98.8% accuracy, 97.8% sensitivity, and 100% specificity, and the frame classification time was reduced from 0.4814 s using original US images to 0.1444 s after WPT preprocessing. When the other mice liver dataset was used, the technique showed 85.74% accuracy, 84.4% sensitivity, and 88.5% specificity, and the frame classification time was reduced from 0.5612s to 0.2903 s. Using human liver image data, the best classifier exhibited 92.5% accuracy, 93.0% sensitivity, 91.0% specificity, and the classification time was reduced from 0.660 s to 0.146 s. This technique can be useful for developing computationally-efficient and manufacturer-independent noninvasive CAD systems for fatty liver detection.

[A probability model for analyzing speckles in intravascular ultrasound images to facilitate image segmentation]

Ultrasonic image speckles result from the interference of the reflected signals by the scatters in the detected tissue. The physical characteristics of the speckles are closely correlated with the structures of the biological tissues, and the probability distribution of these speckles differs across different tissues. Based on the probability characteristics of intravascular ultrasound (IVUS) speckles, a Gamma mixture model and Gaussian mixture model are proposed to describe the calcified plaque, soft plaque and normal vascular regions on IVUS images. Using KS test, KL divergence and correlation coefficient analysis, we found that the probability distributions of the speckles generated by calcified plaques and normal blood vessels were better described by the Gaussian mixture model, while the speckles caused by soft plaques were described better by the Gamma mixture model. Based on this finding, we propose a probability mixture model combining neighborhood information for plaque segmentation on IVUS images. Compared with the existing probabilistic mixture model, the segmentation accuracy was greatly improved with a reduced noise.

Image texture features predict renal function decline in patients with autosomal dominant polycystic kidney disease

Magnetic resonance imaging (MRI) examinations provide high-resolution information about the anatomic structure of the kidneys and are used to measure total kidney volume (TKV) in patients with Autosomal Dominant Polycystic Kidney Disease (ADPKD). Height-adjusted TKV (HtTKV) has become the gold-standard imaging biomarker for ADPKD progression at early stages of the disease when estimated glomerular filtration rate (eGFR) is still normal. However, HtTKV does not take advantage of the wealth of information provided by MRI. Here we tested whether image texture features provide additional insights into the ADPKD kidney that may be used as complementary information to existing biomarkers. A retrospective cohort of 122 patients from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study was identified who had T2-weighted MRIs and eGFR values over 70 mL/min/1.73m² at the time of their baseline scan. We computed nine distinct image texture features for each patient. The ability of each feature to predict subsequent progression to CKD stage 3A, 3B, and 30% reduction in eGFR at eight-year follow-up was assessed. A multiple linear regression model was developed incorporating age, baseline eGFR, HtTKV, and three image texture features identified by stability feature selection (Entropy, Correlation, and Energy). Including texture in a multiple linear regression model (predicting percent change in eGFR) improved Pearson correlation coefficient from -0.51 (using age, eGFR, and HtTKV) to -0.70 (adding texture). Thus, texture analysis offers an approach to refine ADPKD prognosis and should be further explored for its utility in individualized clinical decision making and outcome prediction.

Segmentation of Breast Lesions in Ultrasound Images through Multiresolution Analysis Using Undecimated Discrete Wavelet Transform

Earliest detection and diagnosis of breast cancer reduces mortality rate of patients by increasing the treatment options. A novel method for the segmentation of breast ultrasound images is proposed in this work. The proposed method utilizes undecimated discrete wavelet transform to perform multiresolution analysis of the input ultrasound image. As the resolution level increases, although the effect of noise reduces, the details of the image also dilute. The appropriate resolution level, which contains essential details of the tumor, is automatically selected through mean structural similarity. The feature vector for each pixel is constructed by sampling intra-resolution and inter-resolution data of the image. The dimensionality of feature vectors is reduced by using principal components analysis. The reduced set of feature vectors is segmented into two disjoint clusters using spatial regularized fuzzy c-means algorithm. The proposed algorithm is evaluated by using four validation metrics on a breast ultrasound database of 150 images including 90 benign and 60 malignant cases. The algorithm produced significantly better segmentation results (Dice _coef = 0.8595, boundary displacement error = 9.796, d_vi = 1.744, and global consistency error = 0.1835) than the other three state of the art methods.

Feasibility Study of Texture Analysis Using Ultrasound Shear Wave Elastography to Predict Malignancy in Thyroid Nodules

Textural analysis of ultrasound shear wave elastography (SWE) was evaluated to discriminate benign and malignant thyroid nodules. Sixteen papillary thyroid cancers and 89 benign hyperplastic nodules in 105 patients underwent SWE using four static pre-compression levels. Fifteen gray level co-occurrence matrix textural features and six absolute SWE indices were computed from SWE images. Diagnostic performances of each SWE index for malignancy were calculated and compared using the area under the receiver operating characteristic curve (AUC), and optimal models were generated at each pre-compression level. The optimal model comprised two SWE textural features at the highest pre-compression level, which attained AUC, sensitivity and specificity of 0.973, 97.5% and 90.0%, respectively. By comparison, absolute SWE indices attained AUC of 0.709 as well as 18.8% sensitivity and 95.8% specificity. These preliminary results suggest SWE textural analysis can distinguish benign and malignant thyroid nodules and SWE spatial heterogeneity is greater in malignant nodules.

Radiomics: a new application from established techniques

The increasing use of biomarkers in cancer have led to the concept of personalized medicine for patients. Personalized medicine provides better diagnosis and treatment options available to clinicians. Radiological imaging techniques provide an opportunity to deliver unique data on different types of tissue. However, obtaining useful information from all radiological data is challenging in the era of "big data". Recent advances in computational power and the use of genomics have generated a new area of research termed Radiomics. Radiomics is defined as the high throughput extraction of quantitative imaging features or texture (radiomics) from imaging to decode tissue pathology and creating a high dimensional data set for feature extraction. Radiomic features provide information about the gray-scale patterns, inter-pixel relationships. In addition, shape and spectral properties can be extracted within the same regions of interest on radiological images. Moreover, these features can be further used to develop computational models using advanced machine learning algorithms that may serve as a tool for personalized diagnosis and treatment guidance.

Evolution-based hierarchical feature fusion for ultrasonic liver tissue characterization

This paper presents an evolution-based hierarchical feature fusion system that selects the dominant features among multiple feature vectors for ultrasonic liver tissue characterization. After extracting the spatial gray-level dependence matrices, multiresolution fractal feature vectors and multiresolution energy feature vectors, the system utilizes evolution-based algorithms to select features. In each feature space, features are selected independently to compile a feature subset. As the features of different feature vectors contain complementary information, a feature fusion process is used to combine the subsets generated from different vectors. Features are then selected from the fused feature vector to form a fused feature subset. The selected features are used to classify ultrasonic images of liver tissue into three classes: hepatoma, cirrhosis, and normal liver. Experiment results show that the classification accuracy of the fused feature subset is superior to that derived by using individual feature subsets. Moreover, the findings demonstrate that the proposed algorithm is capable of selecting discriminative features among multiple feature vectors to facilitate the early detection of hepatoma and cirrhosis via ultrasonic liver imaging.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

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.

Characterization of primary and secondary malignant liver lesions from B-mode ultrasound

Characterization of hepatocellular carcinomas (HCCs) and metastatic carcinomas (METs) from B-mode ultrasound presents a daunting challenge for radiologists due to their highly overlapping appearances. The differential diagnosis between HCCs and METs is often carried out by observing the texture of regions inside the lesion and the texture of background liver on which the lesion has evolved. The present study investigates the contribution made by texture patterns of regions inside and outside of the lesions for binary classification between HCC and MET lesions. The study is performed on 51 real ultrasound liver images with 54 malignant lesions, i.e., 27 images with 27 solitary HCCs (13 small HCCs and 14 large HCCs) and 24 images with 27 MET lesions (12 typical cases and 15 atypical cases). A total of 120 within-lesion regions of interest and 54 surrounding lesion regions of interest are cropped from 54 lesions. Subsequently, 112 texture features (56 texture features and 56 texture ratio features) are computed by statistical, spectral, and spatial filtering based texture features extraction methods. A two-step methodology is used for feature set optimization, i.e., feature pruning by removal of nondiscriminatory features followed by feature selection by genetic algorithm-support vector machine (SVM) approach. The SVM classifier is designed based on optimum features. The proposed computer-aided diagnostic system achieved the overall classification accuracy of 91.6 % with sensitivity of 90 % and 93.3 % for HCCs and METs, respectively. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in diagnosing liver malignancies.

SVM-based characterization of liver ultrasound images using wavelet packet texture descriptors

A system to characterize normal liver, cirrhotic liver and hepatocellular carcinoma (HCC) evolved on cirrhotic liver is proposed in this paper. The study is performed with 56 real ultrasound images (15 normal, 16 cirrhotic and 25 HCC liver images) taken from 56 subjects. A total of 180 nonoverlapping regions of interest (ROIs), i.e. 60 from each image class, are extracted by an experienced participating radiologist. The multiresolution wavelet packet texture descriptors, i.e. mean, standard deviation and energy features, are computed from all 180 ROIs by using various compact support wavelet filters including Haar, Daubechies (db4 and db6), biorthogonal (bior3.1,bior3.3 and bior4.4), symlets (sym3 and sym5) and coiflets (coif1 and coif2). It is observed that a combined texture descriptor feature vector of length 48 consisting of 16 mean, 16 standard deviation and 16 energy features estimated from all 16 subband feature images (wavelet packets) obtained by second-level decomposition with two-dimensional wavelet packet transform by using Haar wavelet filter gives the best characterization performance of 86.6 %. Feature selection by genetic algorithm-support vector machine method increased the classification accuracy to 88.8 % with sensitivity of 90 % for detecting normal and cirrhotic cases and sensitivity of 86.6 % for HCC cases. Considering limited sensitivity of B-mode ultrasound for detecting HCCs evolved on cirrhotic liver, the sensitivity of 86.6 % for HCC lesions obtained by the proposed computer-aided diagnostic system is quite promising and suggests that the proposed system can be used in a clinical environment to support radiologists in lesion interpretation.

Prostate tissue characterization/classification in 144 patient population using wavelet and higher order spectra features from transrectal ultrasound images

In this work, we have proposed an on-line computer-aided diagnostic system called "UroImage" that classifies a Transrectal Ultrasound (TRUS) image into cancerous or non-cancerous with the help of non-linear Higher Order Spectra (HOS) features and Discrete Wavelet Transform (DWT) coefficients. The UroImage system consists of an on-line system where five significant features (one DWT-based feature and four HOS-based features) are extracted from the test image. These on-line features are transformed by the classifier parameters obtained using the training dataset to determine the class. We trained and tested six classifiers. The dataset used for evaluation had 144 TRUS images which were split into training and testing sets. Three-fold and ten-fold cross-validation protocols were adopted for training and estimating the accuracy of the classifiers. The ground truth used for training was obtained using the biopsy results. Among the six classifiers, using 10-fold cross-validation technique, Support Vector Machine and Fuzzy Sugeno classifiers presented the best classification accuracy of 97.9% with equally high values for sensitivity, specificity and positive predictive value. Our proposed automated system, which achieved more than 95% values for all the performance measures, can be an adjunct tool to provide an initial diagnosis for the identification of patients with prostate cancer. The technique, however, is limited by the limitations of 2D ultrasound guided biopsy, and we intend to improve our technique by using 3D TRUS images in the future.

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

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.

Abdominal tumor characterization and recognition using superior-order cooccurrence matrices, based on ultrasound images

The noninvasive diagnosis of the malignant tumors is an important issue in research nowadays. Our purpose is to elaborate computerized, texture-based methods for performing computer-aided characterization and automatic diagnosis of these tumors, using only the information from ultrasound images. In this paper, we considered some of the most frequent abdominal malignant tumors: the hepatocellular carcinoma and the colonic tumors. We compared these structures with the benign tumors and with other visually similar diseases. Besides the textural features that proved in our previous research to be useful in the characterization and recognition of the malignant tumors, we improved our method by using the grey level cooccurrence matrix and the edge orientation cooccurrence matrix of superior order. As resulted from our experiments, the new textural features increased the malignant tumor classification performance, also revealing visual and physical properties of these structures that emphasized the complex, chaotic structure of the corresponding tissue.

Automated classification of liver disorders using ultrasound images

This paper presents a novel approach for detection of Fatty liver disease (FLD) and Heterogeneous liver using textural analysis of liver ultrasound images. The proposed system is able to automatically assign a representative region of interest (ROI) in a liver ultrasound which is subsequently used for diagnosis. This ROI is analyzed using Wavelet Packet Transform (WPT) and a number of statistical features are obtained. A multi-class linear support vector machine (SVM) is then used for classification. The proposed system gives an overall accuracy of ~95% which clearly illustrates the efficacy of the system.

Comparison of multiresolution features for texture classification of carotid atherosclerosis from B-mode ultrasound

In this paper, a multiresolution approach is suggested for texture classification of atherosclerotic tissue from B-mode ultrasound. Four decomposition schemes, namely, the discrete wavelet transform, the stationary wavelet transform, wavelet packets (WP), and Gabor transform (GT), as well as several basis functions, were investigated in terms of their ability to discriminate between symptomatic and asymptomatic cases. The mean and standard deviation of the detail subimages produced for each decomposition scheme were used as texture features. Feature selection included 1) ranking the features in terms of their divergence values and 2) appropriately thresholding by a nonlinear correlation coefficient. The selected features were subsequently input into two classifiers using support vector machines (SVM) and probabilistic neural networks. WP analysis and the coiflet 1 produced the highest overall classification performance (90% for diastole and 75% for systole) using SVM. This might reflect WP's ability to reveal differences in different frequency bands, and therefore, characterize efficiently the atheromatous tissue. An interesting finding was that the dominant texture features exhibited horizontal directionality, suggesting that texture analysis may be affected by biomechanical factors (plaque strains).

INTRODUCING TYPE-2 FUZZY SETS FOR IMAGE TEXTURE MODELING

In this paper, the texture property "coarseness" is modeled by means of type-2 fuzzy sets, relating representative coarseness measures (our reference set) with the human perception of this texture property. The type-2 approach allows to face both the imprecision in the interpretation of the measure value and the uncertainty about the coarseness degree associated with a measure value. In our study, a wide variety of measures is analyzed, and assessments about coarseness perception are collected from pools. This information is used to obtain type-2 fuzzy sets where the secondary fuzzy sets are modeled by means of triangular membership functions fitted to the collected data.

Tendinopathy discrimination by use of spatial frequency parameters in ultrasound B-mode images

The structural characteristics of a healthy tendon are related to the anisotropic speckle patterns observed in ultrasonic images. This speckle orientation is disrupted upon damage to the tendon structure as observed in patients with tendinopathy. Quantification of the structural appearance of tendon shows promise in creating a tool for diagnosing, prognosing, or measuring changes in tendon organization over time. The current work describes a first step taken towards this goal-classification of Achilles tendon images into tendinopathy and control categories. Eight spatial frequency parameters were extracted from regions of interest on tendon images, filtered and classified using linear discriminant analysis. Resulting algorithms had better than 80% accuracy in categorizing tendon image kernels as tendinopathy or control. Tendon images categorized wrongly provided for an interesting clinical association between incorrect classification of tendinopathy kernels as control and the symptom and clinical time history based inclusion criteria. To assess intersession reliability of image acquisition, the first 10 subjects were imaged twice during separate sessions. Test-retest of repeated measures was excellent (tau = 0.996, ICC = (2, 1) = 0.73 with one outlier) indicating a general consistency in imaging techniques.

Automatic classification of focal lesions in ultrasound liver images using principal component analysis and neural networks

Ultrasound Medical Imaging is currently the most popular modality for diagnostic application. This imaging technique has been used for the detecting abnormalities associated with abdominal organs like liver, kidney, uterus etc. In this paper, the possibilities of automatic classification of the ultrasound liver images into four classes-Normal, Cyst, Benign and Malignant masses, using texture features are explored. These texture features are extracted using the various statistical and spectral methods. The optimal feature selection process is carried out manually to pick the best discriminating features from the extracted texture parameters. Also, the method of principal component analysis is used to extract the principal features or directions of maximum information from the data set there by automatically selecting the optimal features. Using these optimal features, a final combined feature set is formed and is employed for classification of the liver lesions into respective classes. K-means clustering and neural network based automatic classifiers are employed in this process. The classifier design and its performance are studied. This paper summarizes the various statistical and spectral texture parameter extraction processes, optimal feature selection techniques and automated classification procedures involved in our work.

The effects of sampling rate on the texture separability of ultrasound images

Ultrasound machine has been a useful diagnosis tool for several decades, and many researches tried to use computerized algorithms to help physicians diagnose diseases according to the ultrasound texture patterns. However, the effects of sampling format and the sampling rate on the texture feature were not treated properly. In this paper, the authors try to evaluate the effects of the scan conversion done at imaging stage and the sampling rate used at the texture feature extraction stage. They demonstrate the indispensability of considering sampling format and sampling rate according to the feature used, and their proposed method would improve the separability of texture feature for coarse and homogeneous ultrasound images.

Texture analysis of perimenopausal and post-menopausal endometrial tissue in grayscale transvaginal ultrasonography

The aim of this study was to investigate the feasibility of texture analysis in characterizing endometrial tissue as depicted in two-dimensional (2D) grayscale transvaginal ultrasonography. Digital transvaginal ultrasound endometrial images were acquired from 65 perimenopausal and post-menopausal women prior to gynaecological operations; histology revealed 15 malignant and 50 benign cases. Images were processed with a wavelet-based contrast enhancement technique. Three regions of interest (ROIs) were identified (endometrium, endometrium plus adjacent myometrium, layer containing endometrial-myometrial interface) on each original and processed image. 32 textural features were extracted from each ROI employing first and second order statistics texture analysis algorithms. Textural features-based models were generated for differentiating benign from malignant endometrial tissue using stepwise logistic regression analysis. Models' performance was evaluated by means of receiver operating characteristic (ROC) analysis. The best logistic regression model comprised seven textural features extracted from the ROIs determined on the processed images; three features were extracted from the endometrium, while four features were extracted from the layer containing the endometrial-myometrial interface. The area under the ROC curve (A(z)) was 0.956+/-0.038, providing 86.0% specificity at 93.3% sensitivity using the cut-off level of 0.5 for probability of malignancy. Texture analysis of 2D grayscale transvaginal ultrasound images can effectively differentiate malignant from benign endometrial tissue and may contribute to computer-aided diagnosis of endometrial cancer.

High antinoise photoacoustic tomography based on a modified filtered backprojection algorithm with combination wavelet

How to extract the weak photoacoustic signals from the collected signals with high noise is the key to photoacoustic signal processing. We have developed a modified filtered backprojection algorithm based on combination wavelet for high antinoise photoacoustic tomography. A Q-switched-Nd: yttrium-aluminum-garnet laser operating at 532 nm is used as light source. The laser has a pulse width of 7 ns and a repetition frequency of 20 Hz. A needle polyvinylidene fluoride hydrophone with diameter of 1 mm is used to capture photoacoustic signals. The modified algorithm is successfully applied to imaging vascular network of a chick embryo chorioallantoic membrane in situ and brain structure of a rat brain in vivo, respectively. In the reconstructed images, almost all of the capillary vessels and the vascular ramifications of the chick embryo chorioallantoic membrane are accurately resolved, and the detailed brain structures of the rat brain organization are clearly identified with the skull and scalp intact. The experimental results demonstrate that the modified algorithm has much higher antinoise capacity, and can greatly improve the reconstruction image quality. The spatial resolution of the reconstructed images can reach 204 microm. The modified filtered back-projection algorithm based on the combination wavelet has the potential in the practical high-noise signal processing for deeply penetrating photoacoustic tomography.

Neighborhood-pixels algorithm combined with Sono-CT in the diagnosis of cirrhosis: an experimental study

The goal was to investigate the role of neighborhood-pixels algorithm (NPA) in analyzing the echogram of experimental cirrhosis and the value of high frequency real-time compound imaging (Sono-CT) in improving texture analysis. A cirrhosis model was established by subcutaneously injecting CCl(4) in 80 rats. The total group of rats were divided into a control group and four treatment groups (treated for 6, 8, 10 and 12, weeks respectively). The texture of hepatic-echograms was analyzed using a "neighborhood-pixels" algorithm. Images were obtained under conventional imaging mode and Sono-CT, respectively. The second texture parameter (FP(2)) was estimated and compared in different groups and under different modes. FP(2) increased gradually with the time of treatment and group differences were significant (p < 0.01). In these groups, FP(2) was higher under Sono-CT than under conventional condition (p < 0.01) and group differences in FP(2) under both conditions were significant (p < 0.01). Thus, FP(2) measured by neighborhood-pixels algorithm can reflect the dynamic change of the texture of echogram of cirrhosis in rats and Sono-CT can improve texture analysis by neighborhood-pixels algorithm, thus facilitating the early diagnosis of cirrhosis.

Ultrasound image segmentation: a survey

This paper reviews ultrasound segmentation paper methods, in a broad sense, focusing on techniques developed for medical B-mode ultrasound images. First, we present a review of articles by clinical application to highlight the approaches that have been investigated and degree of validation that has been done in different clinical domains. Then, we present a classification of methodology in terms of use of prior information. We conclude by selecting ten papers which have presented original ideas that have demonstrated particular clinical usefulness or potential specific to the ultrasound segmentation problem.

Diagnosis of hepatic tumors with texture analysis in nonenhanced computed tomography images

RATIONALE AND OBJECTIVES

Computed tomography (CT) after iodinated contrast agent injection is highly accurate for diagnosis of hepatic tumors. However, iodinating may have problems of renal toxicity and allergic reaction. We aimed to evaluate the potential role of the computer-aided diagnosis (CAD) with texture analysis in the differential of hepatic tumors on nonenhanced CT.

MATERIALS AND METHODS

This study evaluated 164 liver lesions (80 malignant tumors and 84 hemangiomas). The suspicious tumor region in the digitized CT image was manually selected and extracted as a circular subimage. Proposed preprocessing adjustments for subimages were used to equalize the information needed for a differential diagnosis. The autocovariance texture features of subimage were extracted and a support vector machine classifier identified the tumor as benign or malignant.

RESULTS

The accuracy of the proposed diagnosis system for classifying malignancies is 81.7%, the sensitivity is 75.0%, the specificity is 88.1%, the positive predictive value is 85.7%, and the negative predictive value is 78.7%.

CONCLUSIONS

This system differentiates benign from malignant hepatic tumors with relative high accuracy and is therefore clinically useful to reduce patients needed for iodinated contrast agent injection in CT examination. Because the support vector machine is trainable, it could be further optimized if a larger set of tumor images is to be supplied.

Wavelet Analysis of Cutaneous Blood Flow in Melanocytic Skin Lesions

Laser Doppler flowmetry (LDF) is frequently used to study the microcirculation. Usually LDF time series are analyzed by conventional linear methods, mainly Fourier analysis. The aim of this study was to observe dynamic blood perfusion of the skin in malignant and benign melanocytic skin lesions. Wavelet transformation was performed on each LDF time series in order to calculate a vasomotion field. First, the differences in vasomotion between healthy and pigmented skin were evaluated visually on six different time scales of the vasomotion field. In order to quantify the findings, vasomotion scale variance (VSV) was calculated for each scale plane of the vasomotion field. These VSV were compared using contrast DeltaVSV to determine the difference between healthy skin and a pigmented skin lesion in the same patient. After the measurements, the skin lesions were excised and examined histologically. We found that wavelet analysis of LDF time series is a specific, sensitive method for the in vivo identification of malignant melanoma. It is a non-invasive procedure and takes minimal time to be carried out.