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.     

Automatic segmentation of breast lesions on ultrasound

In this paper we present a computationally efficient segmentation algorithm for breast masses on sonography that is based on maximizing a utility function over partition margins defined through gray-value thresholding of a preprocessed image. The performance of the segmentation algorithm is evaluated on a database of 400 cases in two ways. Of the 400 cases, 124 were complex cysts, 182 were benign solid lesions, and 94 were malignant lesions. In the first evaluation, the computer-delineated margins were compared to manually delineated margins. At an overlap threshold of 0.40, the segmentation algorithm correctly delineated 94% of the lesions. In the second evaluation, the performance of our computer-aided diagnosis method on the computer-delineated margins was compared to the performance of our method on the manually delineated margins. Round robin evaluation yielded Az values of 0.90 and 0.87 on the manually delineated margins and the computer-delineated margins, respectively, in the task of distinguishing between malignant and nonmalignant lesions.     

Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses in Breast DCE-MRI

Our purpose in this study was to develop a computer-aided diagnosis (CAD) scheme for distinguishing between benign and malignant breast masses in dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI). Our database consisted 90 DCE-MRI examinations, each of which contained four sequential phase images; this database included 28 benign masses and 62 malignant masses. In our CAD scheme, we first determined 11 objective features of masses by taking into account the image features and the dynamic changes in signal intensity that experienced radiologists commonly use for describing masses in DCE-MRI. Quadratic discriminant analysis (QDA) was employed to distinguish between benign and malignant masses. As the input of the QDA, a combination of four objective features was determined among the 11 objective features according to a stepwise method. These objective features were as follows: (i) the change in signal intensity from 2 to 5 min; (ii) the change in signal intensity from 0 to 2 min; (iii) the irregularity of the shape; and (iv) the smoothness of the margin. Using this approach, the classification accuracy, sensitivity, and specificity were shown to be 85.6 % (77 of 90), 87.1 % (54 of 62), and 82.1 % (23 of 28), respectively. Furthermore, the positive and negative predictive values were 91.5 % (54 of 59) and 74.2 % (23 of 31), respectively. Our CAD scheme therefore exhibits high classification accuracy and is useful in the differential diagnosis of masses in DCE-MRI images.     

Semi-Automatic Region-of-Interest Segmentation Based Computer-Aided Diagnosis of Mass Lesions from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Based Breast Cancer Screening

Cancer screening with magnetic resonance imaging (MRI) is currently recommended for very high risk women. The high variability in the diagnostic accuracy of radiologists analyzing screening MRI examinations of the breast is due, at least in part, to the large amounts of data acquired. This has motivated substantial research towards the development of computer-aided diagnosis (CAD) systems for breast MRI which can assist in the diagnostic process by acting as a second reader of the examinations. This retrospective study was performed on 184 benign and 49 malignant lesions detected in a prospective MRI screening study of high risk women at Sunnybrook Health Sciences Centre. A method for performing semi-automatic lesion segmentation based on a supervised learning formulation was compared with the enhancement threshold based segmentation method in the context of a computer-aided diagnostic system. The results demonstrate that the proposed method can assist in providing increased separation between malignant and radiologically suspicious benign lesions. Separation between malignant and benign lesions based on margin measures improved from a receiver operating characteristic (ROC) curve area of 0.63 to 0.73 when the proposed segmentation method was compared with the enhancement threshold, representing a statistically significant improvement. Separation between malignant and benign lesions based on dynamic measures improved from a ROC curve area of 0.75 to 0.79 when the proposed segmentation method was compared to the enhancement threshold, also representing a statistically significant improvement. The proposed method has potential as a component of a computer-aided diagnostic system.     

Usefulness of positron tomography (PET) in lung cancer

Lung carcinoma is one on the leading causes of death from cancer in all parts of the world. The frequency of this tumor is increasing; at present, accounts for approximately 25% of all cancer deaths. The majority of lung cancers are initially detected on chest radiographs, but many benign lesions have radiologic characteristics similar to malignant lesions. Computed tomography (CT) is most frequently used to provide additional anatomic and morphologic information on lesions, but it is limited in distinguishing between benign and malignant abnormalities. Fluorodeoxyglucose-Positron emission tomography (PET-FDG) imaging provides physiologic and metabolic information that characterizes lesions indeterminate by CT, is used clinically to-differentiate benign from malignant focal pulmonary abnormalities, to stage mediastinal and extrathoracic metastases, and to identify recurrence. It is the gold standard that define the therapeutic strategy.     

Clinical study for classification of benign, dysplastic, and malignant oral lesions using autofluorescence spectroscopy

Autofluorescence spectroscopy shows promising results for detection and staging of oral (pre-)malignancies. To improve staging reliability, we develop and compare algorithms for lesion classification. Furthermore, we examine the potential for detecting invisible tissue alterations. Autofluorescence spectra are recorded at six excitation wavelengths from 172 benign, dysplastic, and cancerous lesions and from 97 healthy volunteers. We apply principal components analysis (PCA), artificial neural networks, and red/green intensity ratio's to separate benign from (pre-)malignant lesions, using four normalization techniques. To assess the potential for detecting invisible tissue alterations, we compare PC scores of healthy mucosa and surroundings/contralateral positions of lesions. The spectra show large variations in shape and intensity within each lesion group. Intensities and PC score distributions demonstrate large overlap between benign and (pre-)malignant lesions. The receiver-operator characteristic areas under the curve (ROC-AUCs) for distinguishing cancerous from healthy tissue are excellent (0.90 to 0.97). However, the ROC-AUCs are too low for classification of benign versus (pre-)malignant mucosa for all methods (0.50 to 0.70). Some statistically significant differences between surrounding/contralateral tissues of benign and healthy tissue and of (pre-)malignant lesions are observed. We can successfully separate healthy mucosa from cancers (ROC-AUC>0.9). However, autofluorescence spectroscopy is not able to distinguish benign from visible (pre-)malignant lesions using our methods (ROC-AUC<0.65). The observed significant differences between healthy tissue and surroundings/contralateral positions of lesions might be useful for invisible tissue alteration detection.     

Characterization of mammographic masses based on level set segmentation with new image features and patient information

Computer-aided diagnosis (CAD) for characterization of mammographic masses as malignant or benign has the potential to assist radiologists in reducing the biopsy rate without increasing false negatives. The purpose of this study was to develop an automated method for mammographic mass segmentation and explore new image based features in combination with patient information in order to improve the performance of mass characterization. The authors' previous CAD system, which used the active contour segmentation, and morphological, textural, and spiculation features, has achieved promising results in mass characterization. The new CAD system is based on the level set method and includes two new types of image features related to the presence of microcalcifications with the mass and abruptness of the mass margin, and patient age. A linear discriminant analysis (LDA) classifier with stepwise feature selection was used to merge the extracted features into a classification score. The classification accuracy was evaluated using the area under the receiver operating characteristic curve. The authors' primary data set consisted of 427 biopsy-proven masses (200 malignant and 227 benign) in 909 regions of interest (ROIs) (451 malignant and 458 benign) from multiple mammographic views. Leave-one-case-out resampling was used for training and testing. The new CAD system based on the level set segmentation and the new mammographic feature space achieved a view-based Az value of 0.83 +/- 0.01. The improvement compared to the previous CAD system was statistically significant (p = 0.02). When patient age was included in the new CAD system, view-based and case-based Az values were 0.85 +/- 0.01 and 0.87 +/- 0.02, respectively. The study also demonstrated the consistency of the newly developed CAD system by evaluating the statistics of the weights of the LDA classifiers in leave-one-case-out classification. Finally, an independent test on the publicly available digital database for screening mammography with 132 benign and 197 malignant ROIs containing masses achieved a view-based Az value of 0.84 +/- 0.02.     

Stereological estimation of nucleolar organizer regions in prostatic tissue with an optical disector.

Silver-stained nucleolar organizer regions (AgNORs) were studied in 10 hyperplastic, 10 inflamed, nine prostatic intraepithelial neoplastic (PIN) and 20 malignant prostatic lesions. Optical disector measurement on 15 micron sections showed that upper frequency limits for 1.5 microns and 2.0 microns AgNOR particles were 10% and 2% in benign lesions and 18% and 9% in PIN. Using these cut-off values for diagnosis we found a low sensitivity and high specificity in distinguishing benign lesions from PIN and PIN from carcinoma. A high sensitivity and high specificity were obtained in separating benign lesions from carcinoma. AgNOR typing on routine "two-dimensional" sections showed that upper frequency limits for types B2, B3 and C2 were 25%, 3% and 0% in benign lesions and 38%, 23% and 11% in PIN. Using these cut-off values for diagnosis we found lower sensitivity and specificity values among all the differential diagnostic categories. We conclude that although both methods may contribute to the differential diagnosis between benign and malignant prostatic lesions, stereological estimation was a technically simple method, ensuring unbiased sampling and resulting in higher sensitivity and specificity. It may thus prove helpful in the differentiation of borderline cases in routine diagnostic pathology.     

My approach to the diagnosis of mesothelial lesions

Mesothelial lesions pose considerable diagnostic challenges not only because benign tumours, reactive proliferations and malignant mesothelioma can mimic one another, but also because the morphological patterns displayed by malignant mesothelioma can simulate a variety of epithelial and non-epithelial malignancies. Immunohistochemical markers can aid in distinguishing epithelioid malignant mesothelioma from metastatic adenocarcinoma, but because no single marker reliably separates all cases, a panel of stains is recommended. Immunohistochemical studies are of more limited value in sarcomatoid malignant mesothelioma, and other features often play an essential role. The separation of reactive mesothelial proliferations from malignant mesothelioma on small biopsy can be quite difficult, as distinguishing features, such as stromal invasion, often cannot be adequately assessed. In adequately sampled lesions, however, the distinction between malignant mesothelioma, benign mesothelial proliferations and other tumours can be achieved in most cases by using a carefully integrated approach that incorporates clinical and radiographic data, immunohistochemical studies and, in selected cases, histochemical and ultrastructural techniques.     

Non-melanocytic mimics of melanoma: part I: intraepidermal mimics

Melanoma comprises a wide range of cytological and architectural features histopathologically and hence can mimic many benign and malignant lesions of epithelial, mesenchymal and hematopoietic cell lines of differentiation. Therefore, analysis and close clinical, histological, histochemical and immunohistochemical correlation is vital in distinguishing challenging melanoma cases from their mimics. In this review, the different features of the benign, pre-malignant and malignant intraepidermal non-melanocytic tumours and tumour-like lesions that can closely mimic intraepidermal melanoma (melanoma in situ) are emphasised.     

Comparing Performance of the CADstream and the DynaCAD Breast MRI CAD Systems

Computer-aided diagnosis (CAD) systems are software programs that use algorithms to find patterns associated with breast cancer on breast magnetic resonance imaging (MRI). The most commonly used CAD systems in the USA are CADstream (CS) (Merge Healthcare Inc., Chicago, IL) and DynaCAD for Breast (DC) (Invivo, Gainesville, FL). Our primary objective in this study was to compare the CS and DC breast MRI CAD systems for diagnostic accuracy and postprocessed image quality. Our secondary objective was to compare the evaluation times of radiologists using each system. Three radiologists evaluated 30 biopsy-proven malignant lesions and 29 benign lesions on CS and DC and rated the lesions’ malignancy status using the Breast Imaging Reporting and Data System. Image quality was ranked on a 0–5 scale, and mean reading times were also recorded. CS detected 70 % of the malignant and 32 % of the benign lesions while DC detected 81 % of the malignant lesions and 34 % of the benign lesions. Analysis of the area under the receiver operating characteristic curve revealed that the difference in diagnostic performance was not statistically significant. On image quality scores, CS had significantly higher volume rendering (VR) (p < 0.0001) and motion correction (MC) scores (p < 0.0001). There were no statistically significant differences in the remaining image quality scores. Differences in evaluation times between DC and CS were also not statistically significant. We conclude that both CS and DC perform similarly in aiding detection of breast cancer on MRI. MRI CAD selection will likely be based on other factors, such as user interface and image quality preferences, including MC and VR.     

A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography

Mass segmentation plays a crucial role in computer-aided diagnosis (CAD) systems for classification of suspicious regions as normal, benign, or malignant. In this article we present a robust and automated segmentation technique--based on dynamic programming--to segment mass lesions from surrounding tissue. In addition, we propose an efficient algorithm to guarantee resulting contours to be closed. The segmentation method based on dynamic programming was quantitatively compared with two other automated segmentation methods (region growing and the discrete contour model) on a dataset of 1210 masses. For each mass an overlap criterion was calculated to determine the similarity with manual segmentation. The mean overlap percentage for dynamic programming was 0.69, for the other two methods 0.60 and 0.59, respectively. The difference in overlap percentage was statistically significant. To study the influence of the segmentation method on the performance of a CAD system two additional experiments were carried out. The first experiment studied the detection performance of the CAD system for the different segmentation methods. Free-response receiver operating characteristics analysis showed that the detection performance was nearly identical for the three segmentation methods. In the second experiment the ability of the classifier to discriminate between malignant and benign lesions was studied. For region based evaluation the area Az under the receiver operating characteristics curve was 0.74 for dynamic programming, 0.72 for the discrete contour model, and 0.67 for region growing. The difference in Az values obtained by the dynamic programming method and region growing was statistically significant. The differences between other methods were not significant.     

超声引导下经皮肺自动穿刺活检的临床应用

目的通过超声引导下经皮肺自动穿刺活检对肺及胸膜肿块作出病理诊断,为早期诊断肺及胸膜肿块提供可靠依据方法对３０例经Ｘ线及ＣＴ诊断为肺部外周型肿块或怀疑结核或炎症但临床高度怀疑癌变或胸膜病变,需进一步明确诊断者,在超块引导下经皮用自动穿刺活检针进行穿刺活检及病理检查．结果全部获得病理学诊断．其中良性病变１１例（占３６７％）,恶性病变１９例（占６３．３％）结论对于胸膜病变及贴近胸壁的肺占位病变,经皮肺自动穿刺活检是一种良好方法．     

Expression of HBME-1 and CD56 in follicular variant of papillary carcinoma in children: An immunohistochemical study and their diagnostic utility

Papillary thyroid carcinoma (PTC) is the most common differentiated thyroid cancer in children; and the follicular variant is the second most common variant after the classic subtype. The histological appearance of follicular variant of papillary thyroid cancer (FVPTC), can be mimicked by benign follicular nodules. Pediatric pathologists encountering such lesions with FVPTC-like appearance may err on diagnosing the benign lesions as malignant. In adult patients, several immunohistochemical markers have emerged recently as a useful adjunct to distinguish differentiated thyroid carcinomas from benign follicular lesions. We undertook an inter-institutional retrospective study to establish the diagnostic utility of immunohistochemical staining for HBME-1, Galectin-3 and CD56 in differentiating FVPTC from its benign mimics, follicular adenoma and adenomatoid nodules, in children. Our specific aim of the project was to define the sensitivity and specificity of the three antibodies in FVPTC. Based on institutional diagnoses, a total of 66 cases were obtained: 32 FVPTC and 34 benign follicular nodules that comprised of 23 follicular adenoma and 11 adenomatoid nodules. Five investigators, who were blinded to the original diagnoses, independently reviewed the slides following pre-determined criteria and semi-quantitatively scoring the immunohistochemical staining. The immunohistochemical staining revealed that a combination of positive HBME-1 and negative CD56 result gave 100% specificity and positive predictive value in distinguishing FVPTC from benign follicular nodules. However, the antibody combination suffered from a lower sensitivity (50%). We used a cutoff of 25% positivity of tumor cells in determining positivity of tumor cells to an antibody. In conclusion, our study found a very high specificity and strong positive predictive value for the combination of HBME-1 and CD56 immunohistochemical stains in distinguishing FVPTC from benign follicular lesions.     

Expression of a lymphatic endothelial cell marker in benign and malignant vascular tumors

Tumors of endothelial cell origin are relatively common. Soft tissue tumors and numerous subtypes of benign and malignant vascular tumors have been described; the histogenesis of many of these tumors is uncertain, and distinguishing between benign and malignant vascular tumors, some of which express lymphatic endothelial cell markers, can be problematic. In the present study, immunophenotypic expression of a novel hyaluronan receptor (LYVE-1), which is expressed by endothelial cells of normal lymphatic vessels but not blood vessels, was determined in benign and malignant vascular tumors. It was found that, except in lymphangiomas, intramuscular hemangiomas, and Masson's hemangiomas, endothelial cells in benign blood vessel tumors (including capillary and cavernous hemangiomas, glomus tumors, pyogenic granulomas, and epithelioid hemangiomas) were negative for LYVE-1, and that all angiosarcomas and Kaposi's sarcomas were positive for LYVE-1. Expression of LYVE-1 and other lymphatic endothelial cell markers in relatively few vascular neoplasms has implications for the histogenesis of these lesions, and may prove useful in distinguishing angiosarcoma and Kaposi's sarcoma from most common benign vascular tumors.     

Tetranectin expression in human colonic neoplasia

Pigmented lesions of palmar and plantar skin may cause diagnostic problems, partly because they are infrequently excised and also because some features of benign lesions in these sites may raise the suspicion of melanoma if considered alone. We have examined a series of benign melanocytic lesions and compared them with melanomas from these sites. The presence of severe melanocytic atypia was the most valuable feature in distinguishing between naevi and melanomas. Pagetoid infiltration of the epidermis by single atypical cells, or small groups of cells with abundant pale cytoplasm was seen only in melanomas, while transepidermal elimination of well-circumscribed nests was present only in benign lesions. A lymphocytic infiltrate was present in the dermis in 13 of 14 malignant lesions, but only two of the 26 naevi showed a sparse infiltrate: we suggest that the presence of a lymphocytic infiltrate should prompt a careful search for other features of malignancy. Other features examined, including elongation of rete ridges, pattern of melanocyte distribution at the dermo-epidermal junction, dermal sclerosis, and pigment in the stratum corneum or in the dermis, were seen in both naevi and melanomas and were not found to be useful in distinguishing benign from malignant lesions.     

Keratin immunoreactivity in fine-needle aspiration of the prostate: an aid in the differentiation of benign epithelium from well-differentiated adenocarcinoma

The efficacy of utilizing immunocytochemical staining of prostatic basal cells in separating benign from malignant prostatic epithelium was tested by staining fine-needle aspiration smears of prostatic lesions with the monoclonal antibody EAB-903. This antibody has been shown to stain keratin subtypes present in the prostate only in basal cells. The study utilized 12 benign, nine malignant, and four suspicious-for-carcinoma cases. Ten of 12 benign cases showed an intermingled pattern of staining, which was not found in the malignant cases. Our findings indicate that this distinctive pattern of staining may assist in distinguishing benign epithelium from well-differentiated prostatic adenocarcinoma.     

Can mucinous lesions of the breast be reliably diagnosed by core needle biopsy?

Lesions of the breast containing extravasated mucin span a continuum from benign mucoceles to invasive mucinous (colloid) carcinoma. It is well known that distinguishing benign from malignant mucinous lesions is difficult infine-needle aspiration material. Whether these lesions also are difficult to distinguish in core needle biopsy material is not known. To address this, I reviewed the results of 4,297 breast core needle biopsies. Mucinous lesions were identified in 22 cases (0.51%), and excisional biopsy material was available for 15 of these. At excision, 0 of 8 benign mucinous lesions showed carcinoma, while 7 of 7 mucinous lesions associated with carcinoma at the time of core needle biopsy showed carcinoma at excision. The vast majority of mucinous lesions of the breast can be diagnosed accurately by core needle biopsy. Whether all such lesions require excision is not known at this time.     

Nucleolar organizer regions distribution in fine needle aspiration cytological smears from breast lesions

Fine needle aspiration (FNA) cytology is now an integral part of the pre-operative investigation of breast lesions and the therapeutic protocol is today often planned on the basis of cytodiagnosis. However, from time to time the cytological picture may be equivocal or inconclusive. In recent years, nucleolar organizer region (NOR) scores have been explored for potential value in the diagnosis of malignancy as the scores in malignant nuclei are seen to be higher than in benign or reactive nuclei. With a view to applying NOR scoring in the evaluation of cytologically equivocal cases, we adopted the argyrophil technique for staining NOR s (AgNOR) in FNA cytological smears of 56 breast lesions, comprising 31 benign and 25 malignant lesions. Histological correlation was possible in 26 of these cases (17 malignant and 9 benign) and AgNOR scoring was done on paraffin sections of these as well. There was a significant difference between mean AgNOR scores in benign and malignant lesions in the cytological smears (P < 0.001). The AgNOR scores ranged from 2.5 to 5.0 per cell in benign lesions and 5.8 to 17.2 per cell in malignant lesions. None of the cases fell into the gray zone of overlap. One malignant lesion that was cytologically equivocal showed a mean AgNOR score of 6.08. The AgNOR scores on histological sections also showed a statistically significant difference (P < 0.001) between benign and malignant lesions with mean scores ranging from 1.34 to 2.58 dots per cell in benign lesions and scores of 2.42 to 5.28 dots per cell in malignant lesions. However, the scores overlapped in four cases and therefore it was considered unsuitable for routine diagnostic work. From this preliminary study, we conclude that an FNA AgNOR score of 5.0 and less strongly favours a benign lesion whereas a score above 5.0 would be in favour of a malignant lesion. A larger study would be needed to verify our impression that AgNOR scoring can be useful in cytologically equivocal cases.