Fig 1 - uploaded by Prakash Hiremath
Content may be subject to copyright.
Source publication
In this paper, we present a novel method based on active contours for segmentation and fuzzy rule based classification of microscopic images of esophagus tissues obtained from the abnormal regions of human esophagus detected through endoscopy. This method is used for classification of Squamous Cell Carcinoma (SCC) of esophagus, namely, well differe...
Citations
... Nevertheless, to the best of our knowledge, there is no dynamic model for the development of ESD and ESCC based on their diagnosis system (Vienna). However, some studies have been done to grade ESCC tumors and ESD by using image processing techniques [6][7][8]. ...
... Prior studies on ESCC strived at two objectives: (1) finding high-risk populations and exploring the effective risk factors on the prevalence of ESCC [33,34] and (2) developing computational pathology and cytology to improve the methods of diagnosis (e.g., image processing techniques) [6,7]. In the former (1), mostly, there is a statistical approach, and risk models are defined [33,34]. ...
... Since biological evidence consists of a series of possible not often probable events, and the a priori probabilities and the state conditional densities of different diagnosis classes are not known [35], statistics may not have reasonable applicability. In the latter (2), it is tried to find robust features from the pathological images or develop classifiers [6,7]. In these studies, the defined classifiers have global formulations, whereas our model was designed based on some assumptions of the real system. ...
Esophageal squamous cell carcinoma is the most predominant malignancy of the esophagus. Its histological precursors (dysplasia) emerge in the esophageal epithelium that their progression into the underlying layers leads to cancer. The epithelium is the origin of many solid cancers and, accordingly, the focus of numerous computational models. In this work, we proposed a framework to establish a two-dimensional, globally coupled map to model the epithelium dynamics. The model aims at diagnosing the early stage of dysplasia based on microscopic images of endoscopic biopsies. We used the logistic map as a black-box model for the epithelial cells. By relating between the structure and dynamic of the epithelium, we defined the coupling function and proposed a case-dependent model in which the parameters were adjusted based on fractal geometry of each pathological image. Thus, by assigning different attractors to the cells’ behavior, the lattice dynamic was investigated by the Lyapunov exponent. The decreasing pattern of Lyapunov exponent variations across the epithelium thickness had reasonable performance in diagnosing the normal specimens from the low-grade dysplasia ones. The results showed that there could be a direct relationship between the structural complexity of this system and its uncertainty of dynamics.
The modeling process of the esophageal epithelium to classify the experimental data at normal and LGD stages.
... A computer-assisted quantitative microscopic methodology was developed for automated identification of keratinization and keratin pearl area from in situ oral histological images (Das et al., 2015). In another study on endoscopic images of the oesophagus, active contourbased segmentation and fuzzy rule-based classification were proposed (Hiremath and Iranna, 2011). A computer-aided risk evaluation module for oropharyngeal SCC was developed by Lewis et al. (2014). ...
... 95.08 % segmentation accuracy was achieved by proposed methodology (Das et al., 2015). 100 % classification accuracy was obtained using color and some textural features in detecting squamous cell carcinoma of oesophagus (Hiremath and Iranna, 2011). In another study by et al., textural feature of OSCC and normal cells were studied, where they achieve 100 % classification accuracy (Rahman et al., 2017). ...
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.
... These systems are developed by the implementation of different image processing techniques to improve and expedite the process of diagnosis [20]. To the best of our knowledge, diagnostic image processing approaches to the endoscopic biopsies of ESD and ESCC are rare and only focus on the grading of ESCC [21][22][23]. However, Barrett esophagus, the EAC premalignant precursor, has been the topic of a larger number of investigations comparatively (e.g. ...
... Despite the cancerous cells images that have considerable differences in shape, texture, and contrast with normal cells [21], the differences between early ESD and normal cells are slight. In [23], to classify ESCC and non-neoplasia tissues, based on images of the surface epithelium, both normal and LGD specimens were determined in the same group. ...
... However, as mentioned in Section 1, as far as we know, this paper is a novel study on the classification of endoscopic biopsies of ESD lesions. The other studies on this topic are rare and limited to the grading of ESCC [21][22][23]. In ESCC, the neoplastic transformation involves the full thickness of epithelium and the grading index is a measure expressing the level of differentiability of malignant cells. ...
Esophageal squamous cell carcinoma (ESCC) is the most prevalent malignancy of the esophagus with a very poor prognosis. Nevertheless, squamous cell dysplasia (ESD) has been identified as the only histo-logical precursors of ESCC. Since, tissue alterations are slight in the early stage of ESD, human diagnosis is subjective. Hence, this work presents a first computer-aided system to differentiate low-grade dys-plasia (LGD) from normal esophageal mucosa according to Vienna grading system, which is the most widespread method for histological grading of esophagus tissues. We captured microscopic images of a well-oriented region of Normal and LGD biopsies to characterize the architectural and cytological properties of specimens based on the computational analysis. We produced two sets of enhanced images. Then, by considering the fractal concept, we defined a new scale-dependent function in the generalized fractal dimension formulation to include the special information of both preprocessed images together. Then, for each image, a pattern was computed from variations of tissue fractal geometry across the pathway of dysplasia development. We proposed features extracted from these patterns to classify deviations of tissue characteristics from the normal stage. This method successfully differentiated the two diagnosis classes with statistical significance and high performance (accuracy = 97.78% ± 0.05, p < 0.0001). To approve the self-similar property of the esophagus tissue and evaluate the robustness of this technique, it was conducted at two image magnifications and repeated for different biopsy sizes. Our results confirm that this tissue is a multifractal object and fractal analysis effectively extends the conventional light microscopy method allowing for an early detection of ESD. Thus, computer-aided detection can support pathologists' diagnosis and result in a consistent decision. On the other hand, generally, the proposed method can be used to estimate the fractal dimension of other images.
... Also, colour and some textural features have been used to detect squamous cell carcinoma of oesophagus (Hiremath et al., 2007). For classification of squamous cell carcinoma of oesophagus, Hiremath & Iranna (2011) have also used fuzzy-rulebased approaches. A computer aided risk evaluation module for oropharyngeal SCC has been developed by Lewis et al. (2014). ...
Despite being an area of cancer with highest worldwide incidence, oral cancer yet remains to be widely researched. Studies on computer-aided analysis of pathological slides of oral cancer contribute a lot to the diagnosis and treatment of the disease. Some researches in this direction have been carried out on oral submucous fibrosis. In this work an approach for analysing abnormality based on textural features present in squamous cell carcinoma histological slides have been considered. Histogram and grey-level co-occurrence matrix approaches for extraction of textural features from biopsy images with normal and malignant cells are used here. Further, we have used linear support vector machine classifier for automated diagnosis of the oral cancer, which gives 100% accuracy.
... One possibility would be to use the active contours method in order to evolve a curve representing the boundaries from the ROI [31]. Recently, this method has been explored in order to segment histology images [32][33][34]. One potential drawback when using active contours is that some implementations require the user to manually specify an initial boundary. ...
The use of digital imaging and algorithm-assisted identification of regions of interest is revolutionizing the practice of anatomic pathology. Currently automated methods for extracting the tumour regions in basal cell carcinomas are lacking. In this manuscript a colour-deconvolution based tumour extraction algorithm is presented.
Haematoxylin and eosin stained basal cell carcinoma histology slides were digitized and analyzed using the open source image analysis program ImageJ. The pixels belonging to tumours were identified by the algorithm, and the performance of the algorithm was evaluated by comparing the pixels identified as malignant with a manually determined dataset.The algorithm achieved superior results with the nodular tumour subtype. Pre-processing using colour deconvolution resulted in a slight decrease in sensitivity, but a significant increase in specificity. The overall sensitivity and specificity of the algorithm was 91.0% and 86.4% respectively, resulting in a positive predictive value of 63.3% and a negative predictive value of 94.2%
The proposed image analysis algorithm demonstrates the feasibility of automatically extracting tumour regions from digitized basal cell carcinoma histology slides. The proposed algorithm may be adaptable to other stain combinations and tumour types.
Background:
Oral squamous cell carcinoma (OSCC) is the most prevalent form of oral cancer. Very few researches have been carried out for the automatic diagnosis of OSCC using artificial intelligence techniques. Though biopsy is the ultimate test for cancer diagnosis, analyzing a biopsy report is a very much challenging task. To develop computer-assisted software that will diagnose cancerous cells automatically is very important and also a major need of the hour.
Aim:
To identify OSCC based on morphological and textural features of hand-cropped cell nuclei by traditional machine learning methods.
Methods:
In this study, a structure for semi-automated detection and classification of oral cancer from microscopic biopsy images of OSCC, using clinically significant and biologically interpretable morphological and textural features, are examined and proposed. Forty biopsy slides were used for the study from which a total of 452 hand-cropped cell nuclei has been considered for morphological and textural feature extraction and further analysis. After making a comparative analysis of commonly used methods in the segmentation technique, a combined technique is proposed. Our proposed methodology achieves the best segmentation of the nuclei. Henceforth the features extracted were fed into five classifiers, support vector machine, logistic regression, linear discriminant, k-nearest neighbors and decision tree classifier. Classifiers were also analyzed by training time. Another contribution of the study is a large indigenous cell level dataset of OSCC biopsy images.
Results:
We achieved 99.78% accuracy applying decision tree classifier in classifying OSCC using morphological and textural features.
Conclusion:
It is found that both morphological and textural features play a very important role in OSCC diagnosis. It is hoped that this type of framework will help the clinicians/pathologists in OSCC diagnosis.
Background/Objectives: The primary objective of this paper is to classify the clinical dataset of cervical cancer to identify the stage of cancer which helps in proper treatment of patient suffering from cancer. Methods/Statistical Analysis: This research work basically moves toward the detection of cervical cancer using Pap smear images. Analysis of Pap smear of cervical region is an efficient technique to study any abnormality in cervical cells. The proposed system firstly segment the pap image using Edge Detection to separate the cell nuclei from cytoplasm and background and then extract various features of cervical pap images like area, perimeter, elongation and then these features are normalized using min-max method. After normalization KNN method is used to classify cancer according to its abnormality. Findings: The classification accuracy with 84.3% of maximum performance with no validation and classification accuracy with 82.9% of maximum performance with 5 Fold cross validation is achieved.
Microscopic image analysis plays foremost role in understanding of biological processes, diseases diagnosis and cells/ tissues identification. Image analysis sequence starts with the acquisition, proceeds to restoration and segmentation to conclude with analysis. Microscopic images classification is one of the challenging tasks that have a leading role in the medical domain. In this chapter, an overview on the different techniques used for microscopic images classification is presented guiding the reader through the advanced knowledge of major quantitative image classification approaches. An applied example is conducted on classifying different Albino rats’ samples captured using light microscope for three different organs, namely hippocampus, renal and pancreas. The dataset consists of 60 images from each images set. The Bag-of-Features (BoF) technique is employed for features extraction and selection. The BoF selected features are used as input to the multiclass linear support vector machine classifier. The proposed classifier achieved 94% average classification accuracy for the three classes. Additionally, for binary classification the achieved average accuracy is 100% for the classification of the hippocampus and pancreas and 92% to classify the hippocampus and the renal sets.
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).
Copyright © 2015 Elsevier Ltd. All rights reserved.
