Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

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.

/pdf/computer-aided-tumor-detection-in-endoscopic-video-using-4n5nqty54s.pdf

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

Video capsule endoscopy (VCE) has revolutionized the diagnostic work-up in the field of small bowel diseases. Furthermore, VCE has the potential to become the leading screening technique for the entire gastrointestinal tract. Computational methods that can be implemented in software can enhance the diagnostic yield of VCE both in terms of efficiency and diagnostic accuracy. Since the appearance of the first capsule endoscope in clinical practice in 2001, information technology (IT) research groups have proposed a variety of such methods, including algorithms for detecting haemorrhage and lesions, reducing the reviewing time, localizing the capsule or lesion, assessing intestinal motility, enhancing the video quality and managing the data. Even though research is prolific (as measured by publication activity), the progress made during the past 5 years can only be considered as marginal with respect to clinically significant outcomes. One thing is clear-parallel pathways of medical and IT scientists exist, each publishing in their own area, but where do these research pathways meet? Could the proposed IT plans have any clinical effect and do clinicians really understand the limitations of VCE software? In this Review, we present an in-depth critical analysis that aims to inspire and align the agendas of the two scientific groups.

Software for enhanced video capsule endoscopy: challenges for essential progress

Medical decision making can be regarded as a process, combining both analytical cognition and intuition. It involves reasoning within complex causal models of multiple concepts, usually described by uncertain, imprecise, and/or incomplete information. Aiming to model medical decision making, we propose a novel approach based on cognitive maps and intuitionistic fuzzy logic. The new model, called intuitionistic fuzzy cognitive map (iFCM), extends the existing fuzzy cognitive map (FCM) by considering the expert's hesitancy in the determination of the causal relations between the concepts of a domain. Furthermore, a modification in the formulation of the new model makes it even less sensitive than the original model to missing input data. To validate its effectiveness, an iFCM with 34 concepts representing fuzzy, linguistically expressed patient-specific data, symptoms, and multimodal measurements was constructed for pneumonia severity assessment. The results obtained reveal its comparative advantage over the respective FCM model by providing decisions that match better with the ones made by the experts. The generality of the proposed approach suggests its suitability for a variety of medical decision-making tasks.

Intuitionistic Fuzzy Cognitive Maps for Medical Decision Making

B-scan ultrasound provides a non-invasive low-cost imaging solution to primary care diagnostics. The inherent speckle noise in the images produced by this technique introduces uncertainty in the representation of their textural characteristics. To cope with the uncertainty, we propose a novel fuzzy feature extraction method to encode local texture. The proposed method extends the Local Binary Pattern (LBP) approach by incorporating fuzzy logic in the representation of local patterns of texture in ultrasound images. Fuzzification allows a Fuzzy Local Binary Pattern (FLBP) to contribute to more than a single bin in the distribution of the LBP values used as a feature vector. The proposed FLBP approach was experimentally evaluated for supervised classification of nodular and normal samples from thyroid ultrasound images. The results validate its effectiveness over LBP and other common feature extraction methods.

/pdf/fuzzy-local-binary-patterns-for-ultrasound-texture-21cwrhxkfo.pdf

Fuzzy Local Binary Patterns for Ultrasound Texture Characterization

This paper proposes a novel methodology for automatic detection and localization of gastrointestinal (GI) anomalies in endoscopic video frame sequences. Training is performed with weakly annotated images, using only image-level, semantic labels instead of detailed, and pixel-level annotations. This makes it a cost-effective approach for the analysis of large videoendoscopy repositories. Other advantages of the proposed methodology include its capability to suggest possible locations of GI anomalies within the video frames, and its generality, in the sense that abnormal frame detection is based on automatically derived image features. It is implemented in three phases: 1) it classifies the video frames into abnormal or normal using a weakly supervised convolutional neural network (WCNN) architecture; 2) detects salient points from deeper WCNN layers, using a deep saliency detection algorithm; and 3) localizes GI anomalies using an iterative cluster unification (ICU) algorithm. ICU is based on a pointwise cross-feature-map (PCFM) descriptor extracted locally from the detected salient points using information derived from the WCNN. Results, from extensive experimentation using publicly available collections of gastrointestinal endoscopy video frames, are presented. The data sets used include a variety of GI anomalies. Both anomaly detection and localization performance achieved, in terms of the area under receiver operating characteristic (AUC), were >80%. The highest AUC for anomaly detection was obtained on conventional gastroscopy images, reaching 96%, and the highest AUC for anomaly localization was obtained on wireless capsule endoscopy images, reaching 88%.

Dimitris K. Iakovidis

Papers

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

Software for enhanced video capsule endoscopy: challenges for essential progress

Intuitionistic Fuzzy Cognitive Maps for Medical Decision Making

Fuzzy Local Binary Patterns for Ultrasound Texture Characterization

Detecting and Locating Gastrointestinal Anomalies Using Deep Learning and Iterative Cluster Unification