Efficient automated detection of mitotic cells from breast histological images using deep convolution neutral network with wavelet decomposed patches.

In medical practice, the mitotic cell count from histological images acts as a proliferative marker for cancer diagnosis. Therefore, an accurate method for detecting mitotic cells in histological images is essential for cancer screening. Manual evaluation of clinically relevant image features that might reflect mitotic cells in histological images is time-consuming and error prone, due to the heterogeneous physical characteristics of mitotic cells. Computer-assisted automated detection of mitotic cells could overcome these limitations of manual analysis and act as a useful tool for pathologists to make cancer diagnoses efficiently and accurately. Here, we propose a new approach for mitotic cell detection in breast histological images that uses a deep convolution neural network (CNN) with wavelet decomposed image patches. In this approach, raw image patches of 81 × 81 pixels are decomposed to patches of 21 × 21 pixels using Haar wavelet and subsequently used in developing a deep CNN model for automated detection of mitotic cells. The decomposition step reduces convolution time for mitotic cell detection relative to the use of raw image patches in conventional CNN models. The proposed deep network was tested using the MITOS (ICPR2012) and MITOS-ATYPIA-14 breast cancer histological datasets and shown to outperform existing algorithms for mitotic cell detection. Overall, our method improves the performance and reduces the computational burden of conventional deep CNN approaches for mitotic cell detection.

Automatic identification of clinically relevant regions from oral tissue histological images for oral squamous cell carcinoma diagnosis.

Identification of various constituent layers such as epithelial, subepithelial, and keratin of oral mucosa and characterization of keratin pearls within keratin region as well, are the important and mandatory tasks for clinicians during the diagnosis of different stages in oral cancer (such as precancerous and cancerous). The architectural variations of epithelial layers and the presence of keratin pearls, which can be observed in microscopic images, are the key visual features in oral cancer diagnosis. The computer aided tool doing the same identification task would certainly provide crucial aid to clinicians for evaluation of histological images during diagnosis. In this paper, a two-stage approach is proposed for computing oral histology images, where 12-layered (7 × 7×3 channel patches) deep convolution neural network (CNN) are used for segmentation of constituent layers in the first stage and in the second stage the keratin pearls are detected from the segmented keratin regions using texture-based feature (Gabor filter) trained random forests. The performance of the proposed computing algorithm is tested in our developed oral cancer microscopic image database. The proposed texture-based random forest classifier has achieved 96.88% detection accuracy for detection of keratin pearls.

Automated identification of normoblast cell from human peripheral blood smear images.

In this paper, we have presented a new computer-aided technique for automatic detection of nucleated red blood cells (NRBCs) or normoblast cell from peripheral blood smear image. The proposed methodology initiates with the localization of the nucleated cells by adopting multilevel thresholding approach in smear images. A novel colour space transformation technique has been introduced to differentiate nucleated blood cells [white blood cells (WBCs) and NRBC] from red blood cells (RBCs) by enhancing the contrast between them. Subsequently, special fuzzy c-means (SFCM) clustering algorithm is applied on enhanced image to segment out the nucleated cell. Finally, nucleated RBC and WBC are discriminated by the random forest tree classifier based on first-order statistical-based features. Experimentally, we observed that the proposed technique achieved 99.42% accuracy in automatic detection of NRBC from blood smear images. Further, the technique could be used to assist the clinicians to diagnose a different anaemic condition.

Automated identification of keratinization and keratin pearl area from in situ oral histological images.

Oral squamous cell carcinoma (OSCC) has contributed 90% of oral cancer worldwide. In situ histological evaluation of tissue sections is the gold standard for oral cancer detection. Formation of keratinization and keratin pearl is one of the most important histological features for OSCC grading. This paper aims at developing a computer assisted quantitative microscopic methodology for automated identification of keratinization and keratin pearl area from in situ oral histological images. The proposed methodology includes colour space transform in YDbDr channel, enhancement of keratinized area in most significant bit (MSB) plane of Db component, segmentation of keratinized area using Chan-Vese model. The proposed methodology achieves 95.08% segmentation accuracy in comparison with (manually) experts-based ground truths. In addition, a grading index describing keratinization area is explored for grading OSCC cases (poorly, moderately and well differentiated).

Automated tissue classification framework for reproducible chronic wound assessment.

The aim of this paper was to develop a computer assisted tissue classification (granulation, necrotic, and slough) scheme for chronic wound (CW) evaluation using medical image processing and statistical machine learning techniques. The red-green-blue (RGB) wound images grabbed by normal digital camera were first transformed into HSI (hue, saturation, and intensity) color space and subsequently the "S" component of HSI color channels was selected as it provided higher contrast. Wound areas from 6 different types of CW were segmented from whole images using fuzzy divergence based thresholding by minimizing edge ambiguity. A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques. Finally, statistical learning algorithms, namely, Bayesian classification and support vector machine (SVM), were trained and tested for wound tissue classification in different CW images. The performance of the wound area segmentation protocol was further validated by ground truth images labeled by clinical experts. It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively. The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793).

Structural and textural classification of erythrocytes in anaemic cases: a scanning electron microscopic study.

The objective of this study is to address quantitative microscopic approach for automated screening of erythrocytes in anaemic cases using scanning electron microscopic (SEM) images of unstained blood cells. Erythrocytes were separated from blood samples and processed for SEM imaging. Thereafter, erythrocytes were segmented using marker controlled watershed transformation technique. Total 47 structural and textural features of erythrocytes were extracted using various mathematical measures for six types of anaemic cases as compared to the control group. These features were statistically evaluated at 1% level of significance and subsequently ranked using Fisher's F-statistic describing the group discriminating potentiality. Amongst all extracted features, twenty nine features were found to be statistically significant (p<0.001). Finally, Bayesian classifier was applied to classify six types of anaemia based on top seventeen ranked features those of which are of course statistically significant. The present study yielded a predictive accuracy of 88.99%.

Machine learning approach for automated screening of malaria parasite using light microscopic images.

The aim of this paper is to address the development of computer assisted malaria parasite characterization and classification using machine learning approach based on light microscopic images of peripheral blood smears. In doing this, microscopic image acquisition from stained slides, illumination correction and noise reduction, erythrocyte segmentation, feature extraction, feature selection and finally classification of different stages of malaria (Plasmodium vivax and Plasmodium falciparum) have been investigated. The erythrocytes are segmented using marker controlled watershed transformation and subsequently total ninety six features describing shape-size and texture of erythrocytes are extracted in respect to the parasitemia infected versus non-infected cells. Ninety four features are found to be statistically significant in discriminating six classes. Here a feature selection-cum-classification scheme has been devised by combining F-statistic, statistical learning techniques i.e., Bayesian learning and support vector machine (SVM) in order to provide the higher classification accuracy using best set of discriminating features. Results show that Bayesian approach provides the highest accuracy i.e., 84% for malaria classification by selecting 19 most significant features while SVM provides highest accuracy i.e., 83.5% with 9 most significant features. Finally, the performance of these two classifiers under feature selection framework has been compared toward malaria parasite classification.