Stavros A. Karkanis

Computer-aided tumor detection in endoscopic video using color wavelet features

We present an approach to the detection of tumors in colonoscopic video. It is based on a new color feature extraction scheme to represent the different regions in the frame sequence. This scheme is built on the wavelet decomposition. The features named as color wavelet covariance (CWC) are based on the covariances of second-order textural measures and an optimum subset of them is proposed after the application of a selection algorithm. The proposed approach is supported by a linear discriminant analysis (LDA) procedure for the characterization of the image regions along the video frames. The whole methodology has been applied on real data sets of color colonoscopic videos. The performance in the detection of abnormal colonic regions corresponding to adenomatous polyps has been estimated high, reaching 97% specificity and 90% sensitivity.

CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames

In this paper, we present CoLD (colorectal lesions detector) an innovative detection system to support colorectal cancer diagnosis and detection of pre-cancerous polyps, by processing endoscopy images or video frame sequences acquired during colonoscopy. It utilizes second-order statistical features that are calculated on the wavelet transformation of each image to discriminate amongst regions of normal or abnormal tissue. An artificial neural network performs the classification of the features. CoLD integrates the feature extraction and classification algorithms under a graphical user interface, which allows both novice and expert users to utilize effectively all systems functions. It has been developed in close cooperation with gastroenterology specialists and has been tested on various colonoscopy videos. The detection accuracy of the proposed system has been estimated to be more than 95%. As it has been resulted, it can be used as a supplementary diagnostic tool for colorectal lesions.

Variable Background Active Contour Model for Computer-Aided Delineation of Nodules in Thyroid Ultrasound Images

This paper presents a computer-aided approach for nodule delineation in thyroid ultrasound (US) images. The developed algorithm is based on a novel active contour model, named variable background active contour (VBAC), and incorporates the advantages of the level set region-based active contour without edges (ACWE) model, offering noise robustness and the ability to delineate multiple nodules. Unlike the classic active contour models that are sensitive in the presence of intensity inhomogeneities, the proposed VBAC model considers information of variable background regions. VBAC has been evaluated on synthetic images, as well as on real thyroid US images. From the quantification of the results, two major impacts have been derived: 1) higher average accuracy in the delineation of hypoechoic thyroid nodules, which exceeds 91%; and 2) faster convergence when compared with the ACWE model.

Detection of lesions in endoscopic video using textural descriptors on wavelet domain supported by artificial neural network architectures

Video processing for classification applications in medical imaging is an area with great importance. In this paper a framework for classification of suspicious lesions using the video produced during an endoscopic session is presented. The proposed approach is based on a feature extraction scheme that uses second order statistical information of the wavelet transformation. These features are used as input to a multilayer feedforward neural network (MFNN) architecture, which has been trained using features of normal and tumor regions. The system uses a limited number of frames with a rather small population of training vectors. The classification results are promising, since the system has been proven to be capable to classify and locate regions, that correspond to lesions with a success of 94 up to 99%, in a sequence of the video-frames. The proposed methodology can be used as a valuable diagnostic tool that may assist physicians to identify possible tumor regions or malignant formations.

Image recognition and neuronal networks: Intelligent systems for the improvement of imaging information

Summary Intelligent computerised systems can provide useful assistance to the physician in the rapid identification of tissue abnormalities and accurate diagnosis in real-time. This paper reviews basic issues in medical imaging and neural network-based systems for medical image interpretation. In the framework of intelligent systems, a simple scheme that has been implemented is presented as an example of the use of intelligent systems to discriminate between normal and cancerous regions in colonoscopic images. Preliminary results indicate that this scheme is capable of high accuracy detection of abnormalities within the image. It can also be successfully applied to different types of images, to detect abnormalities that belong to different cancer types.

Tumor recognition in endoscopic video images using artificial neural network architectures

The paper focuses on a scheme for automated tumor recognition using images acquired during endoscopic sessions. The proposed recognition system is based on multilayer feed forward neural networks (MFNNs) and uses texture information encoded with corresponding statistical measures that are fed as input to the MFNN. Experiments were performed for recognition of different types of tumors in various images and also a number of sequentially acquired frames. The recognition of a polypoid tumor of the colon in the original image, which were used for training was very high. The trained network was also able to satisfactorily recognize the tumor in a sequence of video frames. The results of the proposed approach were very promising and it seems that it can be efficiently applied for tumor recognition.

Supervised and unsupervised neural network methods applied to textile quality control based on improved wavelet feature extraction techniques

This paper aims at investigating novel solutions to the problem of textile defect detection from images, that can find applications in building robust quality control vision based systems in textile production. The proposed solutions focus on detecting defects from the textural properties of their corresponding wavelet transformed images. More specifically a novel methodology is investigated for discriminating defects in textile images by applying supervised and unsupervised neural classification techniques, employing multilayer perceptrons (MLP)-trained with the on-line backpropagation algorithm and Kohonens Self-Organizing Feature Maps (SOFM) respectively. These parallel techniques are applied to innovative wavelet based feature vectors. These vectors are extracted from the wavelet transformed original images using the cooccurrence matrices framework and SVD analysis. The results of the proposed methodology are illustrated in defective textile images where the defective areas are recognized with about ...

Image compression using the wavelet transform on textural regions of interest

This paper suggests a new image compression scheme, using the discrete wavelet transformation (DWT), which is based on attempting to preserve the texturally important image characteristics. The main point of the proposed methodology lies on that, the image is divided into regions of textural significance employing textural descriptors as criteria and fuzzy clustering methodologies. These textural descriptors include cooccurrence matrices based measures and coherence analysis derived features. While rival image compression methodologies utilizing the DWT apply it to the whole original image, the herein presented novel approach involves a more sophisticated scheme in the application of the DWT. More specifically, the DWT is applied separately to each region in which the original image is partitioned and, depending on how it has been texturally clustered, its relative number of the wavelet coefficients to keep is then determined. Therefore, different compression ratios are applied to the above specified image regions. The reconstruction process of the original image involves the linear combination of its corresponding reconstructed regions. An experimental study is conducted to qualitatively assessing the proposed compression approach. Moreover, this experimental study aims at comparing different textural measures in terms of their results concerning the quality of the reconstructed image.

Evaluation of textural feature extraction schemes for neural network-based interpretation of regions in medical images

A few approaches have been presented in the literature towards the discrimination of texture in medical images. Medical experts proposed that the more valuable information for discriminating among normal and suspicious cancer regions in endoscopic images is the texture of the examined tissue. Texture can be encoded by a number of mathematical descriptors. Three well-known textural descriptors, as well as a new wavelet-based one are used in this paper for an accurate study and evaluation of the methodologies encountered. Experiments conducted include tests with various images from the Brodatz album, as well as interpretation of tissue regions in endoscopic image. In all cases the recognition task is supported by multilayer perceptron type neural network architectures.

A variable background active contour model for automatic detection of thyroid nodules in ultrasound images

A novel active contour model named variable background active contour model is proposed and applied for the detection of thyroid nodules in ultrasound images. The new model offers edge independency, no need for smoothing, ability for topological changes and it is more accurate when compared to the active contour without edges model. Improved accuracy is achieved by introducing as background a limited image subset which appropriately changes shape to reduce the effects of background inhomogeneity. We validated the proposed model on ultrasound images acquired from 24 patients and the results demonstrate an improvement in accuracy when compared to the active contour without edges model.