Malignant mesothelioma of the pleura: interobserver variability

State-of-the-Art of Breast Cancer Diagnosis in Medical Images via Convolutional Neural Networks (CNNs)

Early detection of breast cancer is crucial for a better prognosis. Various studies have been conducted where tumor lesions are detected and localized on images. This is a narrative review where the studies reviewed are related to five different image modalities: histopathological, mammogram, magnetic resonance imaging (MRI), ultrasound, and computed tomography (CT) images, making it different from other review studies where fewer image modalities are reviewed. The goal is to have the necessary information, such as pre-processing techniques and CNN-based diagnosis techniques for the five modalities, readily available in one place for future studies. Each modality has pros and cons, such as mammograms might give a high false positive rate for radiographically dense breasts, while ultrasounds with low soft tissue contrast result in early-stage false detection, and MRI provides a three-dimensional volumetric image, but it is expensive and cannot be used as a routine test. Various studies were manually reviewed using particular inclusion and exclusion criteria; as a result, 91 recent studies that classify and detect tumor lesions on breast cancer images from 2017 to 2022 related to the five image modalities were included. For histopathological images, the maximum accuracy achieved was around 99 % , and the maximum sensitivity achieved was 97.29 % by using DenseNet, ResNet34, and ResNet50 architecture. For mammogram images, the maximum accuracy achieved was 96.52 % using a customized CNN architecture. For MRI, the maximum accuracy achieved was 98.33 % using customized CNN architecture. For ultrasound, the maximum accuracy achieved was around 99 % by using DarkNet-53, ResNet-50, G-CNN, and VGG. For CT, the maximum sensitivity achieved was 96 % by using Xception architecture. Histopathological and ultrasound images achieved higher accuracy of around 99 % by using ResNet34, ResNet50, DarkNet-53, G-CNN, and VGG compared to other modalities for either of the following reasons: use of pre-trained architectures with pre-processing techniques, use of modified architectures with pre-processing techniques, use of two-stage CNN, and higher number of studies available for Artificial Intelligence (AI)/machine learning (ML) researchers to reference. One of the gaps we found is that only a single image modality is used for CNN-based diagnosis; in the future, a multiple image modality approach can be used to design a CNN architecture with higher accuracy.

Organoids revealed: morphological analysis of the profound next generation in-vitro model with artificial intelligence

In modern terminology, "organoids" refer to cells that grow in a specific three-dimensional (3D) environment in vitro, sharing similar structures with their source organs or tissues. Observing the morphology or growth characteristics of organoids through a microscope is a commonly used method of organoid analysis. However, it is difficult, time-consuming, and inaccurate to screen and analyze organoids only manually, a problem which cannot be easily solved with traditional technology. Artificial intelligence (AI) technology has proven to be effective in many biological and medical research fields, especially in the analysis of single-cell or hematoxylin/eosin stained tissue slices. When used to analyze organoids, AI should also provide more efficient, quantitative, accurate, and fast solutions. In this review, we will first briefly outline the application areas of organoids and then discuss the shortcomings of traditional organoid measurement and analysis methods. Secondly, we will summarize the development from machine learning to deep learning and the advantages of the latter, and then describe how to utilize a convolutional neural network to solve the challenges in organoid observation and analysis. Finally, we will discuss the limitations of current AI used in organoid research, as well as opportunities and future research directions.

Graphic abstract

The Italian Experience in the Development of Mesothelioma Registries: A Pathway for Other Countries to Address the Negative Legacy of Asbestos

Asbestos (all forms, including chrysotile, crocidolite, amosite, tremolite, actinolite, and anthophyllite) is carcinogenic to humans and causally associated with mesothelioma and cancer of the lung, larynx, and ovary. It is one of the carcinogens most diffuse in the world, in workplaces, but also in the environment and is responsible for a very high global cancer burden. A large number of countries, mostly with high-income economies, has banned the use of asbestos which, however, is still widespread in low- and middle-income countries. It remains, thus, one of the most common occupational and environmental carcinogens worldwide. Italy issued an asbestos ban in 1992, following the dramatic observation of a large increase in mortality from mesothelioma and other asbestos-related diseases in exposed workers and also in subjects with non-occupational exposure. A mesothelioma registry was also organized and still monitors the occurrence of mesothelioma cases, conducting a case-by-case evaluation of asbestos exposure. In this report, we describe two Italian communities, Casale Monferrato and Broni, that faced an epidemic of mesothelioma resulting from the production of asbestos cement and the diffuse environmental exposure; we present the activity and results of the Italian mesothelioma registry (ReNaM), describe the risk-communication activities at the local and national level with a focus on international cooperation and also describe the interaction between mesothelioma registration and medical services specialized in mesothelioma diagnosis and treatment in an area at high risk of mesothelioma. Finally, we assess the potential application of the solutions and methods already developed in Italy in a city in Colombia with high mesothelioma incidence associated with the production of asbestos-cement materials and the presence of diffuse environmental asbestos pollution.

Spatially Constrained Context-Aware Hierarchical Deep Correlation Filters for Nucleus Detection in Histology Images

Nucleus detection in histology images is a fundamental step for cellular-level analysis in computational pathology. In clinical practice, quantitative nuclear morphology can be used for diagnostic decision making, prognostic stratification, and treatment outcome prediction. Nucleus detection is a challenging task because of large variations in the shape of different types of nucleus such as nuclear clutter, heterogeneous chromatin distribution, and irregular and fuzzy boundaries. To address these challenges, we aim to accurately detect nuclei using spatially constrained context-aware correlation filters using hierarchical deep features extracted from multiple layers of a pre-trained network. During training, we extract contextual patches around each nucleus which are used as negative examples while the actual nucleus patch is used as a positive example. In order to spatially constrain the correlation filters, we propose to construct a spatial structural graph across different nucleus components encoding pairwise similarities. The correlation filters are constrained to act as eigenvectors of the Laplacian of the spatial graphs enforcing these to capture the nucleus structure. A novel objective function is proposed by embedding graph-based structural information as well as the contextual information within the discriminative correlation filter framework. The learned filters are constrained to be orthogonal to both the contextual patches and the spatial graph-Laplacian basis to improve the localization and discriminative performance. The proposed objective function trains a hierarchy of correlation filters on different deep feature layers to capture the heterogeneity in nuclear shape and texture. The proposed algorithm is evaluated on three publicly available datasets and compared with 15 current state-of-the-art methods demonstrating competitive performance in terms of accuracy, speed, and generalization.

Deep learning in digital pathology image analysis: a survey

Deep learning (DL) has achieved state-of-the-art performance in many digital pathology analysis tasks. Traditional methods usually require hand-crafted domain-specific features, and DL methods can learn representations without manually designed features. In terms of feature extraction, DL approaches are less labor intensive compared with conventional machine learning methods. In this paper, we comprehensively summarize recent DL-based image analysis studies in histopathology, including different tasks (e.g., classification, semantic segmentation, detection, and instance segmentation) and various applications (e.g., stain normalization, cell/gland/region structure analysis). DL methods can provide consistent and accurate outcomes. DL is a promising tool to assist pathologists in clinical diagnosis.

Computational recognition of lncRNA signature of tumor-infiltrating B lymphocytes with potential implications in prognosis and immunotherapy of bladder cancer

Long noncoding RNAs (lncRNAs) have been associated with cancer immunity regulation and the tumor microenvironment (TME). However, functions of lncRNAs of tumor-infiltrating B lymphocytes (TIL-Bs) and their clinical significance have not yet been fully elucidated. In the present study, a machine learning-based computational framework is presented for the identification of lncRNA signature of TIL-Bs (named 'TILBlncSig') through integrative analysis of immune, lncRNA and clinical profiles. The TILBlncSig comprising eight lncRNAs (TNRC6C-AS1, WASIR2, GUSBP11, OGFRP1, AC090515.2, PART1, MAFG-DT and LINC01184) was identified from the list of 141 B-cell-specific lncRNAs. The TILBlncSig was capable of distinguishing worse compared with improved survival outcomes across different independent patient datasets and was also independent of other clinical covariates. Functional characterization of TILBlncSig revealed it to be an indicator of infiltration of mononuclear immune cells (i.e. natural killer cells, B-cells and mast cells), and it was associated with hallmarks of cancer, as well as immunosuppressive phenotype. Furthermore, the TILBlncSig revealed predictive value for the survival outcome and immunotherapy response of patients with anti-programmed death-1 (PD-1) therapy and added significant predictive power to current immune checkpoint gene markers. The present study has highlighted the value of the TILBlncSig as an indicator of immune cell infiltration in the TME from a noncoding RNA perspective and strengthened the potential application of lncRNAs as predictive biomarkers of immunotherapy response, which warrants further investigation.

Histopathological imaging database for oral cancer analysis

The repository is composed of 1224 images divided into two sets of images with two different resolutions. First set consists of 89 histopathological images with the normal epithelium of the oral cavity and 439 images of Oral Squamous Cell Carcinoma (OSCC) in 100x magnification. The second set consists of 201 images with the normal epithelium of the oral cavity and 495 histopathological images of OSCC in 400x magnification. The images were captured using a Leica ICC50 HD microscope from Hematoxyline and Eosin (H&E) stained tissue slides collected, prepared and catalogued by medical experts from 230 patients. A subset of 269 images from the second data set was used to detect OSCC based on textural features [1]. Histopathology plays a very important role in diagnosing a disease. It is the investigation of biological tissues to detect the presence of diseased cells in microscopic detail. It usually involves a biopsy. Till date biopsy is the gold-standard test to diagnose cancer. The biopsy slides are examined based on various cytological criteria under a microscope. Therefore, there is a high possibility of not retaining uniformity and ensuring reproducibility in outcomes [2, 3]. Computational diagnostic tools, on the other hand, facilitate objective judgments by making the use of the quantitative measure. This dataset can be utilized in establishing automated diagnostic tool using Artificial Intelligence approaches.

Automated oral squamous cell carcinoma identification using shape, texture and color features of whole image strips

Despite profound knowledge of the incidence of oral cancers and a large body of research beyond it, it continues to beat diagnosis and treatment management. Post physical observation by clinicians, a biopsy is a gold standard for accurate detection of any abnormalities. Towards the application of artificial intelligence as an aid to diagnosis, automated cell nuclei segmentation is the most essential step for the recognition of the cancer cells. In this study, we have extracted the shape, texture and color features from the histopathological images collected indigenously from regional hospitals. A dataset of 42 whole slide slices was used to automatically segment and generate a cell level dataset of 720 nuclei. Next, different classifiers were applied for classification purposes. 99.4 % accuracy using Decision Tree Classifier, 100 % accuracy using both SVM and Logistic regression and 100 % accuracy using SVM, Logistic regression and Linear Discriminant were acquired for shape, textural and color features respectively. The in-depth analysis showed SVM and Linear Discriminant classifier gave the best result for texture and color features respectively. The achieved result can be effectively converted to software as an assistant diagnostic tool.

Deep learning techniques for detecting preneoplastic and neoplastic lesions in human colorectal histological images

Trained pathologists base colorectal cancer identification on the visual interpretation of microscope images. However, image labeling is not always straightforward and this repetitive task is prone to mistakes due to human distraction. Significant efforts are underway to develop informative tools to assist pathologists and decrease the burden and frequency of errors. The present study proposes a deep learning approach to recognize four different stages of cancerous tissue development, including normal mucosa, early preneoplastic lesion, adenoma and cancer. A dataset of human colon tissue images collected and labeled over a 10-year period by a team of pathologists was partitioned into three sets. These were used to train, validate and test the neural network, comprising several convolutional and a few linear layers. The approach used in the present study is 'direct'; it labels raw images and bypasses the segmentation step. An overall accuracy of >95% was achieved, with the majority of mislabeling referring to a near category. Tests on an external dataset with a different resolution yielded accuracies >80%. The present study demonstrated that the neural network, when properly trained, can provide fast, accurate and reproducible labeling for colon cancer images, with the potential to significantly improve the quality and speed of medical diagnoses.

Assessing the Impact of Color Normalization in Convolutional Neural Network-Based Nuclei Segmentation Frameworks

Image analysis tools for cancer, such as automatic nuclei segmentation, are impacted by the inherent variation contained in pathology image data. Convolutional neural networks (CNN), demonstrate success in generalizing to variable data, illustrating great potential as a solution to the problem of data variability. In some CNN-based segmentation works for digital pathology, authors apply color normalization (CN) to reduce color variability of data as a preprocessing step prior to prediction, while others do not. Both approaches achieve reasonable performance and yet, the reasoning for utilizing this step has not been justified. It is therefore important to evaluate the necessity and impact of CN for deep learning frameworks, and its effect on downstream processes. In this paper, we evaluate the effect of popular CN methods on CNN-based nuclei segmentation frameworks.

A Novel Digital Score for Abundance of Tumour Infiltrating Lymphocytes Predicts Disease Free Survival in Oral Squamous Cell Carcinoma

Oral squamous cell carcinoma (OSCC) is the most common type of head and neck (H&N) cancers with an increasing worldwide incidence and a worsening prognosis. The abundance of tumour infiltrating lymphocytes (TILs) has been shown to be a key prognostic indicator in a range of cancers with emerging evidence of its role in OSCC progression and treatment response. However, the current methods of TIL analysis are subjective and open to variability in interpretation. An automated method for quantification of TIL abundance has the potential to facilitate better stratification and prognostication of oral cancer patients. We propose a novel method for objective quantification of TIL abundance in OSCC histology images. The proposed TIL abundance (TILAb) score is calculated by first segmenting the whole slide images (WSIs) into underlying tissue types (tumour, lymphocytes, etc.) and then quantifying the co-localization of lymphocytes and tumour areas in a novel fashion. We investigate the prognostic significance of TILAb score on digitized WSIs of Hematoxylin and Eosin (H&E) stained slides of OSCC patients. Our deep learning based tissue segmentation achieves high accuracy of 96.31%, which paves the way for reliable downstream analysis. We show that the TILAb score is a strong prognostic indicator (p = 0.0006) of disease free survival (DFS) on our OSCC test cohort. The automated TILAb score has a significantly higher prognostic value than the manual TIL score (p = 0.0024). In summary, the proposed TILAb score is a digital biomarker which is based on more accurate classification of tumour and lymphocytic regions, is motivated by the biological definition of TILs as tumour infiltrating lymphocytes, with the added advantages of objective and reproducible quantification.

Deep learning nuclei detection: A simple approach can deliver state-of-the-art results

BACKGROUND

Deep convolutional neural networks have become a widespread tool for the detection of nuclei in histopathology images. Many implementations share a basic approach that includes generation of an intermediate map indicating the presence of a nucleus center, which we refer to as PMap. Nevertheless, these implementations often still differ in several parameters, resulting in different detection qualities.

METHODS

We identified several essential parameters and configured the basic PMap approach using combinations of them. We thoroughly evaluated and compared various configurations on multiple datasets with respect to detection quality, efficiency and training effort.

RESULTS

Post-processing of the PMap was found to have the largest impact on detection quality. Also, two different network architectures were identified that improve either detection quality or runtime performance. The best-performing configuration yields f1-measures of 0.816 on H&E stained images of colorectal adenocarcinomas and 0.819 on Ki-67 stained images of breast tumor tissue. On average, it was fully trained in less than 15,000 iterations and processed 4.15 megapixels per second at prediction time.

CONCLUSIONS

The basic PMap approach is greatly affected by certain parameters. Our evaluation provides guidance on their impact and best settings. When configured properly, this simple and efficient approach can yield equal detection quality as more complex and time-consuming state-of-the-art approaches.

Fractional Wavelet Scattering Network and Applications

OBJECTIVE

This study introduces a fractional wavelet scattering network (FrScatNet), which is a generalized translation invariant version of the classical wavelet scattering network.

METHODS

In our approach, the FrScatNet is constructed based on the fractional wavelet transform (FRWT). The fractional scattering coefficients are iteratively computed using FRWTs and modulus operators. The feature vectors constructed by fractional scattering coefficients are usually used for signal classification. In this paper, an application example of the FrScatNet is provided in order to assess its performance on pathological images. First, the FrScatNet extracts feature vectors from patches of the original histological images under different orders. Then we classify those patches into target (benign or malignant) and background groups. And the FrScatNet property is analyzed by comparing error rates computed from different fractional orders, respectively. Based on the above pathological image classification, a gland segmentation algorithm is proposed by combining the boundary information and the gland location.

RESULTS

The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is improved in fractional scattering domain. We also compare the FrScatNet-based gland segmentation method with those proposed in the 2015 MICCAI Gland Segmentation Challenge and our method achieves comparable results.

CONCLUSION

The FrScatNet is shown to achieve accurate and robust results. More stable and discriminative fractional scattering coefficients are obtained by the FrScatNet in this paper.

SIGNIFICANCE

The added fractional order parameter is able to analyze the image in the fractional scattering domain.

Survival after Pleural Malignant Mesothelioma a Population-based Study in Italy

Aims and Background

The study analyzed survival after malignant mesothelioma in the population-based Registry of Malignant Mesothelioma of Piedmont (NW Italy, 4.5 million total population). It focused on possible differences related to period of diagnosis a proxy of changes in diagnostic or therapeutic procedures.

Methods

Cases were actively searched in pathology units and files of hospital admissions and discharges. In 1990-1998, 693 incident cases were diagnosed in residents in the region: 590 of them had a histologic diagnosis of pleural mesothelioma in life and were included in the study. Vital status was ascertained at the municipality of residence as of January 1, 2000.

Results

Fifty-eight cases were alive (9.8%) and 20 were lost (3.6%) at the end of the follow-up. Median survival was 0.71 years (95% Cl, 0.64-0.78). Cumulative survival was 35.9% at 1 year (95% Cl, 32.0-39.8) and 14.2% at 2 years (95% Cl, 11.2-17.1). Survival was associated to age (longer survival for younger subjects at diagnosis; P <0.0001) and to histology (longer survival for epithelial mesothelioma, shorter for fibrous and intermediate for mixed or unspecified types; P <0.0001). There was no difference in survival for period of diagnosis. The results were confirmed in multivariate analyses. Analyses according to type of hospital (with vs without thoracic surgery) did not show any statistically significant difference.

Discussion

The study on survival after malignant mesothelioma is the second largest of the three population-based studies in the world, which showed results similar to ours. Survival measured in published clinical series ranged between 18.4% and 57.6% at 1 year for pleural and 24.1% and 33.8% for peritoneal mesothelioma. The most striking effect of the present study was the absence of improvement in survival with period of diagnosis. Either there was no change in treatment efficacy or the effect was limited to small subgroups and could not be noticed when the analysis included larger categories.

Reproducibility of Malignant Pleural Mesothelioma Histopathologic Subtyping

CONTEXT

- Malignant pleural mesothelioma (MPM) is a rare tumor with poor prognosis. Several studies have analyzed potential prognostic markers, but histologic type remains the single most important prognostic factor. Histologic subtypes of epithelioid MPM seem to have prognostic and therapeutic implications. Interobserver agreement in histologic pattern classification should be high.

OBJECTIVE

- To assess interobserver and intraobserver reproducibility in histologic differentiation between the main types of MPMs, and in further subtyping of epithelioid-type mesothelioma.

DESIGN

- One representative hematoxylin-eosin-stained slide was selected from the archive for each of 200 patients with MPM. They were reviewed independently by 3 pathologists and classified according to the current World Health Organization classification of pleural tumors. After the first round of evaluations, a consensus meeting was organized where problems were addressed and representative images for each histologic category were selected. Two months later, cases were reevaluated by all 3 pathologists.

RESULTS

- After the first round, overall interobserver agreement for histologic subtyping of mesothelioma was fair (κ, 0.36). The agreement was increased to substantial (κ, 0.63) in the second round. Improvement was found in interobserver agreement for all types of MPM and for most epithelioid subtypes.

CONCLUSIONS

- Moderate to substantial agreement in histologic typing and subtyping of MPM can be achieved. However, training with additional clarification of diagnostic criteria, their strict application, and help from consensus-based illustrative images is needed.

Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization

Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.

Stain Specific Standardization of Whole-Slide Histopathological Images

Variations in the color and intensity of hematoxylin and eosin (H&E) stained histological slides can potentially hamper the effectiveness of quantitative image analysis. This paper presents a fully automated algorithm for standardization of whole-slide histopathological images to reduce the effect of these variations. The proposed algorithm, called whole-slide image color standardizer (WSICS), utilizes color and spatial information to classify the image pixels into different stain components. The chromatic and density distributions for each of the stain components in the hue-saturation-density color model are aligned to match the corresponding distributions from a template whole-slide image (WSI). The performance of the WSICS algorithm was evaluated on two datasets. The first originated from 125 H&E stained WSIs of lymph nodes, sampled from 3 patients, and stained in 5 different laboratories on different days of the week. The second comprised 30 H&E stained WSIs of rat liver sections. The result of qualitative and quantitative evaluations using the first dataset demonstrate that the WSICS algorithm outperforms competing methods in terms of achieving color constancy. The WSICS algorithm consistently yields the smallest standard deviation and coefficient of variation of the normalized median intensity measure. Using the second dataset, we evaluated the impact of our algorithm on the performance of an already published necrosis quantification system. The performance of this system was significantly improved by utilizing the WSICS algorithm. The results of the empirical evaluations collectively demonstrate the potential contribution of the proposed standardization algorithm to improved diagnostic accuracy and consistency in computer-aided diagnosis for histopathology data.

Novel structural descriptors for automated colon cancer detection and grading

The histopathological examination of tissue specimens is necessary for the diagnosis and grading of colon cancer. However, the process is subjective and leads to significant inter/intra observer variation in diagnosis as it mainly relies on the visual assessment of histopathologists. Therefore, a reliable computer-aided technique, which can automatically classify normal and malignant colon samples, and determine grades of malignant samples, is required. In this paper, we propose a novel colon cancer diagnostic (CCD) system, which initially classifies colon biopsy images into normal and malignant classes, and then automatically determines the grades of colon cancer for malignant images. To this end, various novel structural descriptors, which mathematically model and quantify the variation among the structure of normal colon tissues and malignant tissues of various cancer grades, have been employed. Radial basis function (RBF) kernel of support vector machines (SVM) has been employed as classifier in order to classify/grade colon samples based on these descriptors. The proposed system has been tested on 92 malignant and 82 normal colon biopsy images. The classification performance has been measured in terms of various performance measures, and quite promising performance has been observed. Compared with previous techniques, the proposed system has demonstrated better cancer detection (classification accuracy=95.40%) and grading (classification accuracy=93.47%) capability. Therefore, the proposed CCD system can provide a reliable second opinion to the histopathologists.

Automated colon cancer detection using hybrid of novel geometric features and some traditional features

Automatic classification of colon into normal and malignant classes is complex due to numerous factors including similar colors in different biological constituents of histopathological imagery. Therefore, such techniques, which exploit the textural and geometric properties of constituents of colon tissues, are desired. In this paper, a novel feature extraction strategy that mathematically models the geometric characteristics of constituents of colon tissues is proposed. In this study, we also show that the hybrid feature space encompassing diverse knowledge about the tissues׳ characteristics is quite promising for classification of colon biopsy images. This paper thus presents a hybrid feature space based colon classification (HFS-CC) technique, which utilizes hybrid features for differentiating normal and malignant colon samples. The hybrid feature space is formed to provide the classifier different types of discriminative features such as features having rich information about geometric structure and image texture. Along with the proposed geometric features, a few conventional features such as morphological, texture, scale invariant feature transform (SIFT), and elliptic Fourier descriptors (EFDs) are also used to develop a hybrid feature set. The SIFT features are reduced using minimum redundancy and maximum relevancy (mRMR). Various kernels of support vector machines (SVM) are employed as classifiers, and their performance is analyzed on 174 colon biopsy images. The proposed geometric features have achieved an accuracy of 92.62%, thereby showing their effectiveness. Moreover, the proposed HFS-CC technique achieves 98.07% testing and 99.18% training accuracy. The better performance of HFS-CC is largely due to the discerning ability of the proposed geometric features and the developed hybrid feature space.

GECC: Gene Expression Based Ensemble Classification of Colon Samples

Gene expression deviates from its normal composition in case a patient has cancer. This variation can be used as an effective tool to find cancer. In this study, we propose a novel gene expressions based colon classification scheme (GECC) that exploits the variations in gene expressions for classifying colon gene samples into normal and malignant classes. Novelty of GECC is in two complementary ways. First, to cater overwhelmingly larger size of gene based data sets, various feature extraction strategies, like, chi-square, F-Score, principal component analysis (PCA) and minimum redundancy and maximum relevancy (mRMR) have been employed, which select discriminative genes amongst a set of genes. Second, a majority voting based ensemble of support vector machine (SVM) has been proposed to classify the given gene based samples. Previously, individual SVM models have been used for colon classification, however, their performance is limited. In this research study, we propose an SVM-ensemble based new approach for gene based classification of colon, wherein the individual SVM models are constructed through the learning of different SVM kernels, like, linear, polynomial, radial basis function (RBF), and sigmoid. The predicted results of individual models are combined through majority voting. In this way, the combined decision space becomes more discriminative. The proposed technique has been tested on four colon, and several other binary-class gene expression data sets, and improved performance has been achieved compared to previously reported gene based colon cancer detection techniques. The computational time required for the training and testing of 208 × 5,851 data set has been 591.01 and 0.019 s, respectively.

Ensemble classification of colon biopsy images based on information rich hybrid features

In recent years, classification of colon biopsy images has become an active research area. Traditionally, colon cancer is diagnosed using microscopic analysis. However, the process is subjective and leads to considerable inter/intra observer variation. Therefore, reliable computer-aided colon cancer detection techniques are in high demand. In this paper, we propose a colon biopsy image classification system, called CBIC, which benefits from discriminatory capabilities of information rich hybrid feature spaces, and performance enhancement based on ensemble classification methodology. Normal and malignant colon biopsy images differ with each other in terms of the color distribution of different biological constituents. The colors of different constituents are sharp in normal images, whereas the colors diffuse with each other in malignant images. In order to exploit this variation, two feature types, namely color components based statistical moments (CCSM) and Haralick features have been proposed, which are color components based variants of their traditional counterparts. Moreover, in normal colon biopsy images, epithelial cells possess sharp and well-defined edges. Histogram of oriented gradients (HOG) based features have been employed to exploit this information. Different combinations of hybrid features have been constructed from HOG, CCSM, and Haralick features. The minimum Redundancy Maximum Relevance (mRMR) feature selection method has been employed to select meaningful features from individual and hybrid feature sets. Finally, an ensemble classifier based on majority voting has been proposed, which classifies colon biopsy images using the selected features. Linear, RBF, and sigmoid SVM have been employed as base classifiers. The proposed system has been tested on 174 colon biopsy images, and improved performance (=98.85%) has been observed compared to previously reported studies. Additionally, the use of mRMR method has been justified by comparing the performance of CBIC on original and reduced feature sets.

New morphological features for grading pancreatic ductal adenocarcinomas

Pathological diagnosis is influenced by subjective factors such as the individual experience and knowledge of doctors. Therefore, it may be interpreted in different ways for the same symptoms. The appearance of digital pathology has created good foundation for objective diagnoses based on quantitative feature analysis. Recently, numerous studies are being done to develop automated diagnosis based on the digital pathology. But there are as of yet no general automated methods for pathological diagnosis due to its specific nature. Therefore, specific methods according to a type of disease and a lesion could be designed. This study proposes quantitative features that are designed to diagnose pancreatic ductal adenocarcinomas. In the diagnosis of pancreatic ductal adenocarcinomas, the region of interest is a duct that consists of lumen and epithelium. Therefore, we first segment the lumen and epithelial nuclei from a tissue image. Then, we extract the specific features to diagnose the pancreatic ductal adenocarcinoma from the segmented objects. The experiment evaluated the classification performance of the SVM learned by the proposed features. The results showed an accuracy of 94.38% in the experiment distinguishing between pancreatic ductal adenocarcinomas and normal tissue and a classification accuracy of 77.03% distinguishing between the stages of pancreatic ductal adenocarcinomas.

A recent survey on colon cancer detection techniques

Colon cancer causes deaths of about half a million people every year. Common method of its detection is histopathological tissue analysis, which, though leads to vital diagnosis, is significantly correlated to the tiredness, experience, and workload of the pathologist. Researchers have been working since decades to get rid of manual inspection, and to develop trustworthy systems for detecting colon cancer. Several techniques, based on spectral/spatial analysis of colon biopsy images, and serum and gene analysis of colon samples, have been proposed in this regard. Due to rapid evolution of colon cancer detection techniques, a latest review of recent research in this field is highly desirable. The aim of this paper is to discuss various colon cancer detection techniques. In this survey, we categorize the techniques on the basis of the adopted methodology and underlying data set, and provide detailed description of techniques in each category. Additionally, this study provides an extensive comparison of various colon cancer detection categories, and of multiple techniques within each category. Further, most of the techniques have been evaluated on similar data set to provide a fair performance comparison. Analysis reveals that neither of the techniques is perfect; however, research community is progressively inching toward the finest possible solution.

Efficient nucleus detector in histopathology images

In traditional cancer diagnosis, (histo)pathological images of biopsy samples are visually analysed by pathologists. However, this judgment is subjective and leads to variability among pathologists. Digital scanners may enable automated objective assessment, improved quality and reduced throughput time. Nucleus detection is seen as the corner stone for a range of applications in automated assessment of (histo)pathological images. In this paper, we propose an efficient nucleus detector designed with machine learning. We applied colour deconvolution to reconstruct each applied stain. Next, we constructed a large feature set and modified AdaBoost to create two detectors, focused on different characteristics in appearance of nuclei. The proposed modification of AdaBoost enables inclusion of the computational cost of each feature during selection, thus improving the computational efficiency of the resulting detectors. The outputs of the two detectors are merged by a globally optimal active contour algorithm to refine the border of the detected nuclei. With a detection rate of 95% (on average 58 incorrectly found objects per field-of-view) based on 51 field-of-view images of Her2 immunohistochemistry stained breast tissue and a complete analysis in 1 s per field-of-view, our nucleus detector shows good performance and could enable a range of applications in automated assessment of (histo)pathological images.

Automatic differential diagnosis of pancreatic serous and mucinous cystadenomas based on morphological features

Generally, pathological diagnosis using an electron microscope is time-consuming and likely to result in a subjective judgment, because pathologists perform manual screening of tissue slides at high magnifications. Recently, the advent of digital pathology technology has provided the basis for convenient screening and quantitative analysis by digitizing tissue slides through a computer system. However, a screening process with high magnification still takes quite a long time. To solve these problems, recently the use of computer-aided design techniques for performing pathologic diagnosis has been increasing in digital pathology. For pathological diagnosis, we need different diagnostic methods for different regions with different characteristics. Therefore, in order to effectively diagnose different lesions and types of diseases, a quantitative method for extracting specific features is required in computerized pathologic diagnosis. This study is about an automated differential diagnosis system to differentiate between benign serous cystadenoma and possibly-malignant mucinous cystadenoma. In order to diagnose cystic tumors, the first step is identifying a cystic region and inspecting its epithelial cells. First, we identify the lumen boundary of a cyst using the Direction Cumulative Map considering 8-ways. Then, the Epithelial Nuclei Identification algorithm is used to discern epithelial nuclei. After that, three morphological features for the differential diagnosis of mucinous and serous cystadenomas are extracted. To demonstrate the superiority of the proposed features, the experiments compared performance of the classifiers learned by using the proposed morphological features and the classical morphological features based on nuclei. The classifiers in the simulations are as follows; Bayesian Classifier, k-Nearest Neighbors, Support Vector Machine, and Artificial Neural Network. The results show that all classifiers using the proposed features have the best classification performance.

A resampling-based Markovian model for automated colon cancer diagnosis

In recent years, there has been a great effort in the research of implementing automated diagnostic systems for tissue images. One major challenge in this implementation is to design systems that are robust to image variations. In order to meet this challenge, it is important to learn the systems on a large number of labeled images from a different range of variation. However, acquiring labeled images is quite difficult in this domain, and hence, the labeled training data are typically very limited. Although the issue of having limited labeled data is acknowledged by many researchers, it has rarely been considered in the system design. This paper successfully addresses this issue, introducing a new resampling framework to simulate variations in tissue images. This framework generates multiple sequences from an image for its representation and models them using a Markov process. Working with colon tissue images, our experiments show that this framework increases the generalization capacity of a learner by increasing the size and variation of the training data and improves the classification performance of a given image by combining the decisions obtained on its sequences.

Intraperitoneal free cancer cells in non-gynaecological adenocarcinomas: a reproducibility study

OBJECTIVE

In recent years, therapeutic approaches including cytoreductive surgery followed by intraperitoneal chemotherapy have proven effective in peritoneal carcinomatosis of colorectal origin. If cytology is to be used to include patients in aggressive treatment regimens, it is necessary to evaluate its performance, particularly in terms of specificity. The aim of this study was to assess interobserver agreement for the detection of intraperitoneal free cancer cells (IFCCs) in patients with non-gynaecological adenocarcinomas.

METHODS

Over a 5-year period, 1223 patients were recruited in 19 French surgery departments. Peritoneal samples were examined in 14 dispersed pathology laboratories. Giemsa-stained slides were sent to a control reader blind to the previous diagnosis. Discordant cases, concordant positive results and a random selection of negative concordant cases were reviewed by a panel of seven cytopathologists. The 'final diagnosis' was that of the consensus meetings but took into account locally-processed slides.

RESULTS

Gathering dubious cases with negative results, a 95.6% concordance was achieved between local readers and the control reader. IFCCs were ascertained by the panel in 85 cases (7.0%). Eight of 873 colorectal cancers cases viewed locally were falsely positive (0.9%). Radiotherapy and neoadjuvant therapy had no impact on the false-positive rate as assessed by final validation by the panel (P > 0.05). Samples initially considered as dubious were reclassified as negative by the panel in 24 of 25 cases (96.0%).

CONCLUSIONS

The panel consensus allowed reclassification of most dubious/equivocal peritoneal cytology cases, whereas clearcut distinction between benign and malignant cases was correctly achieved in almost all cases.

Identification of components of fibroadenoma in cytology preparations using texture analysis: a morphometric study

OBJECTIVES

To evaluate the utility of image analysis using textural parameters obtained from a co-occurrence matrix in differentiating the three components of fibroadenoma of the breast, in fine needle aspirate smears.

METHODS

Sixty cases of histologically proven fibroadenoma were included in this study. Of these, 40 cases were used as a training set and 20 cases were taken as a test set for the discriminant analysis. Digital images were acquired from cytological preparations of all the cases and three components of fibroadenoma (namely, monolayered cell clusters, stromal fragments and background with bare nuclei) were selected for image analysis. A co-occurrence matrix was generated and a texture parameter vector (sum mean, energy, entropy, contrast, cluster tendency and homogeneity) was calculated for each pixel. The percentage of pixels correctly classified to a component of fibroadenoma on discriminant analysis was noted.

RESULTS

The textural parameters, when considered in isolation, showed considerable overlap in their values of the three cytological components of fibroadenoma. However, the stepwise discriminant analysis revealed that all six textural parameters contributed significantly to the discriminant functions. Discriminant analysis using all the six parameters showed that the numbers of pixels correctly classified in training and tests sets were 96.7% and 93.0%, respectively.

CONCLUSION

Textural analysis using a co-occurrence matrix appears to be useful in differentiating the three cytological components of fibroadenoma. These results could further be utilized in developing algorithms for image segmentation and automated diagnosis, but need to be confirmed in further studies.

Graph run-length matrices for histopathological image segmentation

The histopathological examination of tissue specimens is essential for cancer diagnosis and grading. However, this examination is subject to a considerable amount of observer variability as it mainly relies on visual interpretation of pathologists. To alleviate this problem, it is very important to develop computational quantitative tools, for which image segmentation constitutes the core step. In this paper, we introduce an effective and robust algorithm for the segmentation of histopathological tissue images. This algorithm incorporates the background knowledge of the tissue organization into segmentation. For this purpose, it quantifies spatial relations of cytological tissue components by constructing a graph and uses this graph to define new texture features for image segmentation. This new texture definition makes use of the idea of gray-level run-length matrices. However, it considers the runs of cytological components on a graph to form a matrix, instead of considering the runs of pixel intensities. Working with colon tissue images, our experiments demonstrate that the texture features extracted from "graph run-length matrices" lead to high segmentation accuracies, also providing a reasonable number of segmented regions. Compared with four other segmentation algorithms, the results show that the proposed algorithm is more effective in histopathological image segmentation.

Analysis of breast cancer by small angle X-ray scattering (SAXS)

Small angle X-ray scattering (SAXS) images of normal breast tissue and benign and malignant breast tumour tissues, fixed in formalin, were measured at the momentum transfer range of 0.063 nm(-1) < or = q (= 4pisin(theta/2)/lambda) < or = 2.720 nm(-1). Four intrinsic parameters were extracted from the scattering profiles (1D SAXS image reduced) and, from the combination of these parameters, another three parameters were also created. All parameters, intrinsic and derived, were subject to discriminant analysis, and it was verified that parameters such as the area of diffuse scatter at the momentum transfer range 0.50 < or = q < or = 0.56 nm(-1), the ratio between areas of fifth-order axial and third-order lateral peaks and third-order axial spacing provide the most significant information for diagnosis (p < 0.001). Thus, in this work it was verified that by combining these three parameters it was possible to classify human breast tissues as normal, benign lesion or malignant lesion with a sensitivity of 83% and a specificity of 100%.

Problems in mesothelioma diagnosis

Many centres are now seeing increasing numbers of patients with malignant mesothelioma. This presents pathologists involved in making the diagnosis with a number of problems, which can be divided into those encountered in making the distinction between mesothelioma and benign changes and those experienced in separating mesotheliomas from other types of epithelial and connective tissue tumours. Immunohistochemistry plays a major role in helping to make the diagnosis, but it should be interpreted with due regard to the clinical setting and radiological features, and with a knowledge of the wide morphological variations seen in mesothelioma. This review identifies some of these problems and addresses the uses and limitations of immunohistochemistry in different situations. It includes a discussion of some of the less common variants of mesothelioma and other pleural-based tumours that enter into the differential diagnosis.

Breast cancer diagnosis using level-set statistics and support vector machines

Breast cancer diagnosis based on microscopic biopsy images and machine learning has demonstrated great promise in the past two decades. Various feature selection (or extraction) and classification algorithms have been attempted with success. However, some feature selection processes are complex and the number of features used can be quite large. We propose a new feature selection method based on level-set statistics. This procedure is simple and, when used with support vector machines (SVM), only a small number of features is needed to achieve satisfactory accuracy that is comparable to those using more sophisticated features. Therefore, the classification can be completed in much shorter time. We use multi-class support vector machines as the classification tool. Numerical results are reported to support the viability of this new procedure.

How "objective" are psychiatric diagnoses?: (guess again)

Critics of psychiatry often argue that psychiatric diagnosis lacks "objectivity," particularly when compared with diagnosis in other medical specialties. However, when one examines interrater reliability-an important component of objectivity-the kappa values for several major psychiatric disorders are generally on a par with those in other medical specialties. Nonetheless, in psychiatry as in all of general medicine, there is an irreducible element of the subjective. That is part of the "art" of medical and psychiatric practice.

Accuracy and reproducibility of pleural effusion cytology

The increasing number of Malignant Mesothelioma (MM) cases that arrive for expert examinations to court for compensation reasons in subjects exposed to asbestos, in many instances rely exclusively on cytological smears of pleural effusion. We evaluated the accuracy and reproducibility of cytological pleural effusions, based on morphological criteria alone. Nine pathologists and eight residents from seven institutions in north-east Italy blindly examined 45 smears of MM (17), metastases (14) and benign effusions (14), in two rounds. Diagnoses had been confirmed by immunohistochemical and clinical follow-up, and eventually at autopsy. Diagnostic accuracy, interobserver and intraobserver agreement in the distinction of benign vs malignant cases, and in the differentiation of primary from metastatic malignancies, were evaluated. The distinction of benign from malignant smears resulted rather satisfactory (k=0.514), but markedly decreased in differentiation of MM from metastases (overall agreement: k=0.343), as well as when readings from residents were analyzed (k=0.132). Cytology is a useful and reliable tool in the identification of malignancies, but when the distinction of primary from metastatic tumors is addressed morphological criteria alone are not sufficient for a definite diagnosis of MM and the use of cell blocks, immunohistochemistry (IHC) and molecular ancillary techniques are recommended.

Mathematical modeling of the malignancy of cancer using graph evolution

We report a novel computational method based on graph evolution process to model the malignancy of brain cancer called glioma. In this work, we analyze the phases that a graph passes through during its evolution and demonstrate strong relation between the malignancy of cancer and the phase of its graph. From the photomicrographs of tissues, which are diagnosed as normal, low-grade cancerous and high-grade cancerous, we construct cell-graphs based on the locations of cells; we probabilistically generate an edge between every pair of cells depending on the Euclidean distance between them. For a cell-graph, we extract connectivity information including the properties of its connected components in order to analyze the phase of the cell-graph. Working with brain tissue samples surgically removed from 12 patients, we demonstrate that cell-graphs generated for different tissue types evolve differently and that they exhibit different phase properties, which distinguish a tissue type from another.

Sensitivity and specificity of immunohistochemical markers used in the diagnosis of epithelioid mesothelioma: a detailed systematic analysis using published data

AIMS

Immunohistochemistry is frequently employed to aid the distinction between mesothelioma and pulmonary adenocarcinoma metastatic to the pleura, but there is uncertainty as to which antibodies are most useful. We analysed published data in order to establish sensitivity and specificity of antibodies used to distinguish between these tumours with a view to defining the most appropriate immunohistochemical panel to use when faced with this diagnostic problem.

METHODS AND RESULTS

A systematic analysis of the results of 88 published papers comparing immunohistochemical staining of a panel of antibodies in mesothelioma with epithelioid areas, and pulmonary adenocarcinoma metastatic to the pleura. Results for a total of 15 antibodies were analysed and expressed in terms of sensitivity and specificity. The most sensitive antibodies for identifying pulmonary adenocarcinoma were MOC-31 and BG8 (both 93%), whilst the most specific were monoclonal CEA (97%) and TTF-1 (100%). The most sensitive antibodies to identify epithelioid mesothelioma were CK5/6 (83%) and HBME-1 (85%). The most specific antibodies were CK5/6 (85%) and WT1 (96%).

CONCLUSIONS

No single antibody is able to differentiate reliably between these two tumours. The use of a small panel of antibodies with a high combined sensitivity and specificity is recommended.

Increased risk of malignant mesothelioma of the pleura after residential or domestic exposure to asbestos: a case-control study in Casale Monferrato, Italy

The association of malignant mesothelioma (MM) and nonoccupational asbestos exposure is currently debated. Our study investigates environmental and domestic asbestos exposure in the city where the largest Italian asbestos cement (AC) factory was located. This population-based case-control study included pleural MM (histologically diagnosed) incidents in the area in 1987-1993, matched by age and sex to two controls (four if younger than 60). Diagnoses were confirmed by a panel of five pathologists. We interviewed 102 cases and 273 controls in 1993-1995, out of 116 and 330 eligible subjects. Information was checked and completed on the basis of factory and Town Office files. We adjusted analyses for occupational exposure in the AC industry. In the town there were no other relevant industrial sources of asbestos exposure. Twenty-three cases and 20 controls lived with an AC worker [odds ratio (OR) = 4.5; 95% confidence interval (CI), 1.8-11.1)]. The risk was higher for the offspring of AC workers (OR = 7.4; 95% CI, 1.9-28.1). Subjects attending grammar school in Casale also showed an increased risk (OR = 3.3; 95% CI, 1.4-7.7). Living in Casale was associated with a very high risk (after selecting out AC workers: OR = 20.6; 95% CI, 6.2-68.6), with spatial trend with increasing distance from the AC factory. The present work confirms the association of environmental asbestos exposure and pleural MM, controlling for other sources of asbestos exposure, and suggests that environmental exposure caused a greater risk than domestic exposure.

Value of morphometry, texture analysis, densitometry, and histometry in the differential diagnosis and prognosis of malignant mesothelioma

Malignant mesothelioma is a tumour with increasing incidence due to widespread use of its causative agent, asbestos, in the past decades. The poor survival necessitates a correct differentiation from other lesions at the same site, such as hyperplastic mesothelium and carcinomas metastatic to pleura or peritoneum. Since genetic and immunohistochemical markers are not absolutely differentiating, the diagnosis is based on the histology complemented with (immuno)histochemistry. However, as the tumour presents itself in numerous heterogeneous histological forms, visual evaluation is extremely difficult. In order to evaluate the prognostic and diagnostic performance of syntactic structure analysis (SSA), chromatin texture analysis, densitometry, and morphometry, an automated KNN-classification system has been used to compare Feulgen-stained tissue sections of hyperplastic mesothelium, malignant mesothelioma, and pulmonary adenocarcinoma. In addition, we also studied most discriminative aspects in the differentiation, typing, and prediction of survival. The results indicate that for the diagnosis of malignant mesothelioma, chromatin texture parameters outperform SSA, densitometry, and morphometry (recognition score=96.8 per cent). Most discriminative parameters highlight spatial patterns of the chromatin distribution that are hard to appraise visually and directly show the benefits of a quantitative approach. Typing of the tumour is best described by SSA parameters, relating to the spatial arrangement of the cells in the tissue (recognition score=94.9 per cent). In survival time classifications, chromatin texture yields the highest recognition score (82.9 per cent), although accurate estimations are unreliable due to a large degree of misclassification.

Utility of surfactant protein B precursor and thyroid transcription factor 1 in differentiating adenocarcinoma of the lung from malignant mesothelioma

Differentiation of malignant mesothelioma from adenocarcinoma, particularly from a lung primary, remains a difficult diagnostic problem. Surfactant protein B precursor (pro-SP-B) and thyroid transcription factor 1 (ITF-1) are expressed selectively in the normal respiratory epithelium and in adenocarcinomas of the lung. In this study, we evaluated the utility of pro-SP-B and ITF-1 in distinguishing pulmonary adenocarcinomas and malignant mesotheliomas. Immunoreactivity for pro-SP-B and TTF-1 was examined in paraffin sections of 370 primary lung carcinomas (208 adenocarcinomas, 101 squamous cell carcinomas, and 61 large cell carcinomas) and 95 malignant mesotheliomas, using a pro-SP-B antiserum and a monoclonal TTF-1 antibody with a biotin-streptavidin detection system. Immunostaining for pro-SP-B was detected in 57% of adenocarcinomas, and 20% of large cell carcinomas. Immunoreactivity for TTF-1 was shown in 76% of adenocarcinomas and 26% of large cell carcinomas. Malignant mesotheliomas and squamous cell carcinomas did not stain with either antibody. The expression of pro-SP-B and TTF-1 in adenocarcinomas of the lung but not in malignant mesotheliomas shows that pro-SP-B and TTF-1 staining is useful in differentiating these neoplasms.

Malignant mesothelioma of the pleura. The reproducibility of the immunohistological diagnosis

The reproducibility of the histopathological diagnosis of pleural malignant mesothelioma (MM), after supplementing routine H&E stain by immunohistochemistry (IH) in 77 cases of original diagnoses of MM, was assessed by examining interobserver variation between five pathologists. A battery of commercial antibodies (cytokeratins, vimentin, HMFG-2, anti Leu-M1 [CD15], BerEP4, B72.3 [TAG-72], carcinoembyonic antigen), considered to be useful in enhancing diagnostic accuracy, was used. The number of definitively classified tumors (accepted MM plus rejected MM) increased from 57 on H&E stain to 60 after IH, with 59 (76.6%) cases being accepted as true MM. Based on IH, the chance-adjusted interobserver agreement was poor (kappa w = 0.29) and lower than that observed on previous H&E alone. The intraobserver agreement for four of the five pathologists was rather good (kappa w = 0.54-0.56). The inter- and intraobserver concordance was higher in accepting than excluding the cases as MM. A larger number of cases were classified by all reviewers as mixed or sarcomatous variants after IH. In the interpretation of each immunostain, kappa values ranged from 0.19 for B72.3 to 0.62 for HMFG-2, which were respectively the least and the most consistently interpreted immunostains. The information additionally contributed by IH did not seem to change the pathologists' diagnoses very much in comparison with those made by routine H&E stain. Until highly specific and sensitive probes for the positive identification of MM become available, a careful scrutiny of routinely stained preparations still remains the most rewarding component of the diagnostic pathway.

Newly marketed tissue markers for malignant mesothelioma: immunoreactivity of rabbit AMAD-2 antiserum compared with monoclonal antibody HBME-1 and a review of the literature on so-called antimesothelioma antibodies

A complementary DNA (cDNA) library was constructed from a human malignant mesothelioma (MM) cell line and a cDNA fragment encoding for a cytoplasmic mesothelial protein recognized by the polyclonal antibody AMAD-1 was then cloned and expressed in Escherichia coli. The purified recombinant protein was used to raise a novel antibody, named AMAD-2, in rabbits. This antibody reacted with normal mesothelium and most MM (15 of 17) on paraffin sections and featured a cytoplasmic labeling. Conversely, AMAD-2 immunostaining of normal and tumor tissues from body sites other than serosal membranes was limited with respect to the proportion of positive specimens and usually less conspicuous than in MM. AMAD-2 immunoreactivity was subsequently compared with staining for HBME-1, another newly marketed antimesothelial monoclonal antibody, concerning the ability to distinguish pleural MM from metastatic pleural tumors of epithelial type. A granular cytoplasmic immunoreactivity for AMAD-2 was present in 50% or more of tumor cells in all 84 MM, regardless of histological type, but also in 3 (7%) of 42 pleural metastases, albeit only focally. HBME-1 was shown in 63 of 66 epithelial MM and in the epithelial component of all 8 mixed MM, with a prevailingly membranous pattern, usually homogeneous and strong, whereas none of the 10 sarcomatous MM was positive. HBME-1 was also expressed in 6 (14%) of 42 pleural metastases in a cytoplasmic or membranous pattern. Compared with HBME-1, AMAD-2 showed a higher degree of specificity and sensitivity for MM. AMAD-2 still proved to be superior to HBME-1, also when sarcomatoid MM were excluded from the assessment. This finding supports the view that AMAD-2 is an antibody highly, although not entirely, specific for the mesothelial lineage, whereas HBME-1 is probably a cell marker more closely related to the epithelial differentiation of MM. Therefore, AMAD-2 is preferable as a positive tissue marker to be incorporated in the optimal immunohistochemical panel for the diagnosis of MM.