Ultrasonic tissue characterization for prostate diagnostics: spectral parameters vs. texture parameters

Differentiating benign from malignant mediastinal lymph nodes visible at EBUS using grey-scale textural analysis

BACKGROUND AND OBJECTIVE

Recent data suggest that grey-scale textural analysis on endobronchial ultrasound (EBUS) imaging can differentiate benign from malignant lymphadenopathy. The objective of studies was to evaluate grey-scale textural analysis and examine its clinical utility.

METHODS

Images from 135 consecutive clinically indicated EBUS procedures were evaluated retrospectively using MATLAB software (MathWorks, Natick, MA, USA). Manual node mapping was performed to obtain a region of interest and grey-scale textural features (range of pixel values and entropy) were analysed. The initial analysis involved 94 subjects and receiver operating characteristic (ROC) curves were generated. The ROC thresholds were then applied on a second cohort (41 subjects) to validate the earlier findings.

RESULTS

A total of 371 images were evaluated. There was no difference in proportions of malignant disease (56% vs 53%, P = 0.66) in the prediction (group 1) and validation (group 2) sets. There was no difference in range of pixel values in group 1 but entropy was significantly higher in the malignant group (5.95 vs 5.77, P = 0.03). Higher entropy was seen in adenocarcinoma versus lymphoma (6.00 vs 5.50, P < 0.05). An ROC curve for entropy gave an area under the curve of 0.58 with 51% sensitivity and 71% specificity for entropy greater than 5.94 for malignancy. In group 2, the entropy threshold phenotyped only 47% of benign cases and 20% of malignant cases correctly.

CONCLUSIONS

These findings suggest that use of EBUS grey-scale textural analysis for differentiation of malignant from benign lymphadenopathy may not be accurate. Further studies are required.

Optical differentiation between malignant and benign lymphadenopathy by grey scale texture analysis of endobronchial ultrasound convex probe images

BACKGROUND

Morphologic and sonographic features of endobronchial ultrasound (EBUS) convex probe images are helpful in predicting metastatic lymph nodes. Grey scale texture analysis is a well-established methodology that has been applied to ultrasound images in other fields of medicine. The aim of this study was to determine if this methodology could differentiate between benign and malignant lymphadenopathy of EBUS images.

METHODS

Lymph nodes from digital images of EBUS procedures were manually mapped to obtain a region of interest and were analyzed in a prediction set. The regions of interest were analyzed for the following grey scale texture features in MATLAB (version 7.8.0.347 [R2009a]): mean pixel value, difference between maximal and minimal pixel value, SEM pixel value, entropy, correlation, energy, and homogeneity. Significant grey scale texture features were used to assess a validation set compared with fluoro-D-glucose (FDG)-PET-CT scan findings where available.

RESULTS

Fifty-two malignant nodes and 48 benign nodes were in the prediction set. Malignant nodes had a greater difference in the maximal and minimal pixel values, SEM pixel value, entropy, and correlation, and a lower energy (P < .0001 for all values). Fifty-one lymph nodes were in the validation set; 44 of 51 (86.3%) were classified correctly. Eighteen of these lymph nodes also had FDG-PET-CT scan assessment, which correctly classified 14 of 18 nodes (77.8%), compared with grey scale texture analysis, which correctly classified 16 of 18 nodes (88.9%).

CONCLUSIONS

Grey scale texture analysis of EBUS convex probe images can be used to differentiate malignant and benign lymphadenopathy. Preliminary results are comparable to FDG-PET-CT scan.

Computer aided diagnosis of parotid gland lesions using ultrasonic multi-feature tissue characterization

In this article, an ultrasound based system for computer aided characterization of biologic tissue and its application to differential diagnosis of parotid gland lesions is proposed. Aiming at an automated differentiation between malignant and benign cases, the system is based on a supervised classification using tissue-describing features derived from ultrasound radio-frequency (RF) echo signals and image data. Standard diagnostic ultrasound equipment was employed to acquire ultrasound RF echo data from parotid glands of 138 patients. Lesions were manually demarcated as regions-of-interest (ROIs) in the B-mode images. Spectral ultrasound backscatter and attenuation parameters are estimated from diffraction corrected RF data, yielding spatially resolved parameter images. Histogram based statistical measures derived from the parameters distributions inside the ROI are used as tissue describing features. In addition, texture features and shape descriptors are extracted from demodulated ultrasound image data. The features are processed by a maximum likelihood classifier. An optimal set of 10 features was chosen by a sequential forward selection algorithm. The classifier's performance is evaluated using total cross validation and receiver operating characteristic (ROC) analysis. As a reference method, postoperative pathohistologic analysis was conducted and proved malignancy or prospective malignancy in 51 patients. The classification using the proposed system yielded an area under the ROC curve of 0.91, proving significant potential for differentiating between malignant and benign parotid gland lesions.

Application of artificial intelligence to the management of urological cancer

PURPOSE

Artificial intelligence techniques, such as artificial neural networks, Bayesian belief networks and neuro-fuzzy modeling systems, are complex mathematical models based on the human neuronal structure and thinking. Such tools are capable of generating data driven models of biological systems without making assumptions based on statistical distributions. A large amount of study has been reported of the use of artificial intelligence in urology. We reviewed the basic concepts behind artificial intelligence techniques and explored the applications of this new dynamic technology in various aspects of urological cancer management.

MATERIALS AND METHODS

A detailed and systematic review of the literature was performed using the MEDLINE and Inspec databases to discover reports using artificial intelligence in urological cancer.

RESULTS

The characteristics of machine learning and their implementation were described and reports of artificial intelligence use in urological cancer were reviewed. While most researchers in this field were found to focus on artificial neural networks to improve the diagnosis, staging and prognostic prediction of urological cancers, some groups are exploring other techniques, such as expert systems and neuro-fuzzy modeling systems.

CONCLUSIONS

Compared to traditional regression statistics artificial intelligence methods appear to be accurate and more explorative for analyzing large data cohorts. Furthermore, they allow individualized prediction of disease behavior. Each artificial intelligence method has characteristics that make it suitable for different tasks. The lack of transparency of artificial neural networks hinders global scientific community acceptance of this method but this can be overcome by neuro-fuzzy modeling systems.

Sonohistology for the computerized differentiation of parotid gland tumors

A system for the computerized differentiation of parotid gland tumors is proposed. The parotid gland is the largest of the salivary glands. It is found in the subcutaneous tissue of the face, overlying the mandibular ramus and anterior and inferior to the external ear. The classification system is based on a multifeature tissue characterization approach, using fuzzy inference systems as higher-order classifiers. Baseband ultrasonic echo data were acquired during conventional ultrasound imaging examinations using standard ultrasound equipment. Several tissue-describing parameters were calculated within numerous small regions of interest to evaluate spectral and textural tissue properties. The parameters were processed by an adaptive network-based fuzzy inference system, using the results of conventional histology after parotidectomy as the "gold standard." The results of the classification are presented as a numerical score indicating the probability of a certain tumor or alteration for each parotid gland. The score can be presented to the physician during examination of the patient to improve the differentiation between various types of parotid gland tumors. The system was evaluated on n = 23 cases of patients undergoing radical parotidectomy. The receiver operating characteristic curve area is A(ROC) = 0.95 +/- 0.07 when using fourfold cross-validation over cases and differentiating between various benign parotid gland tumors and monomorphic adenoma.

Initial experiences with real-time elastography guided biopsies of the prostate

PURPOSE

Based on our first experiences with real-time elastography in the field of prostate diagnostics we evaluate its usefulness for biopsy guidance for prostate cancer detection.

MATERIALS AND METHODS

After imaging with conventional B-mode ultrasound in conjunction with real-time elastography 404 men underwent systematic sextant biopsy.

RESULTS

Overall prostate cancer was found in 151 of 404 cases (37.4%). In 127 of 151 cases (84.1%), prostate cancer was detected using real-time elastography as an additional diagnostic feature.

CONCLUSIONS

The results show that it is possible to detect prostate cancer with a high degree of sensitivity using real-time elastography in conjunction with conventional diagnostic methods for guided prostate biopsies.

A tutorial on the use of ROC analysis for computer-aided diagnostic systems

The application of the receiver operating characteristic (ROC) curve for computer-aided diagnostic systems is reviewed. A statistical framework is presented and different methods of evaluating the classification performance of computer-aided diagnostic systems, and, in particular, systems for ultrasonic tissue characterization, are derived. Most classifiers that are used today are dependent on a separation threshold, which can be chosen freely in many cases. The separation threshold separates the range of output values of the classification system into different target groups, thus conducting the actual classification process. In the first part of this paper, threshold specific performance measures, e.g., sensitivity and specificity, are presented. In the second part, a threshold-independent performance measure, the area under the ROC curve, is reviewed. Only the use of separation threshold-independent performance measures provides classification results that are overall representative for computer-aided diagnostic systems. The following text was motivated by the lack of a complete and definite discussion of the underlying subject in available textbooks, references and publications. Most manuscripts published so far address the theme of performance evaluation using ROC analysis in a manner too general to be practical for everyday use in the development of computer-aided diagnostic systems. Nowadays, the user of computer-aided diagnostic systems typically handles huge amounts of numerical data, not always distributed normally. Many assumptions made in more or less theoretical works on ROC analysis are no longer valid for real-life data. The paper aims at closing the gap between theoretical works and real-life data. The review provides the interested scientist with information needed to conduct ROC analysis and to integrate algorithms performing ROC analysis into classification systems while understanding the basic principles of classification.