Typical medical image annotation systems use manual annotation or complex proprietary software such as computerassisted-diagnosis. A more objective approach is required to achieve generalised Content Based Image Retrieval (CBIR) functionality. The Automated Medical Image Collection Annotation (AMICA) toolkit described here addresses this need. A range of content analysis functions are provided to tag images and image regions. The user uploads a DICOM file to an online portal and the software finds and displays images that have similar characteristics. AMICA has been developed to run in the Microsoft cloud environment using the Windows Azure platform, to cater for the storage requirements of typical large medical

Many widely used digital medical image collections have been established but these are generally used as raw data sources without related image analysis toolsets. Providing associated functionality to allow specific types of operations to be performed on these images has proved beneficial in some cases (e. g. brain image registration and atlases). However, toolset development to provide generic image analysis functions on medical images has tended to be ad hoc, with Open Source options proliferating (e. g. ITK). Our Automated Medical Image Collection Annotation (AMICA) system is both an image repository, to which the research community can contribute image datasets, and a search/retrieval system that uses automated image annotation. AMICA was designed for the Windows Azure platform to leverage the flexibility and scalability of the cloud. It is intended that AMICA will expand beyond its initial pilot implementation (for brain CT, MR images) to accommodate a wide range of modalities and anatomical regions. This initiative aims to contribute to advances in clinical research by permitting a broader use and reuse of medical image data than is currently attainable. For example, cohort studies for cases with particular physiology or phenotypes will be able to source and include enough cases to provide high statistical power, allowing more individualised risk factors to be assessed and thus allowing screening and staging processes to be optimised. Also, education, training and credentialing of clinicians in image interpretation, will be more effective because it will be possible to select instances of images with specific visual aspects, or correspond to types of cases where reading performance improvement is desirable.

Monitoring the natural environment is increasingly important as habit degradation and climate change reduce the world's biodiversity. We have developed software tools and applications to assist ecologists with the collection and analysis of acoustic data at large spatial and temporal scales. One of our key objectives is automated animal call recognition, and our approach has three novel attributes. First, we work with raw environmental audio, contaminated by noise and artefacts and containing calls that vary greatly in volume depending on the animal's proximity to the microphone. Second, initial experimentation suggested that no single recognizer could deal with the enormous variety of calls. Therefore, we developed a toolbox of generic recognizers to extract invariant features for each call type. Third, many species are cryptic and offer little data with which to train a recognizer. Many popular machine learning methods require large volumes of training and validation data and considerable time and expertise to prepare. Consequently we adopt bootstrap techniques that can be initiated with little data and refined subsequently. In this paper, we describe our recognition tools and present results for real ecological problems.

Monitoring environmental health is becoming increasingly important as human activity and climate change place greater pressure on global biodiversity. Acoustic sensors provide the ability to collect data passively, objectively and continuously across large areas for extended periods. While these factors make acoustic sensors attractive as autonomous data collectors, there are significant issues associated with large-scale data manipulation and analysis. We present our current research into techniques for analysing large volumes of acoustic data efficiently. We provide an overview of a novel online acoustic environmental workbench and discuss a number of approaches to scaling analysis of acoustic data; online collaboration, manual, automatic and human-in-the loop analysis.

Monitoring and assessing environmental health is becoming increasingly important as human activity and climate change place greater pressure on global biodiversity. Acoustic sensors provide the ability to collect data passively, objectively and continuously across large areas for extended periods of time. While these factors make acoustic sensors attractive as autonomous data collectors, there are significant issues associated with large-scale data manipulation and analysis. We present our current research into techniques for analysing large volumes of acoustic data effectively and efficiently. We provide an overview of a novel online acoustic environmental workbench and discuss a number of approaches to scaling analysis of acoustic data, collaboration, manual, automatic and human-in-the loop analysis.

This technical report is concerned with one aspect of environmental monitoring—the detection and analysis of acoustic events in sound recordings of the environment. Sound recordings offer ecologists the potential advantages of cheaper and increased sampling. An acoustic event detection algorithm is introduced that outputs a compact rectangular marquee description of each event. It can disentangle superimposed events, which are a common occurrence during morning and evening choruses. Next, three uses to which acoustic event detection can be put are illustrated. These tasks have been selected because they illustrate quite different modes of analysis: (1) the detection of diffuse events caused by wind and rain, which are a frequent contaminant of recordings of the terrestrial environment; (2) the detection of bird calls using the spatial distribution of their component events; and (3) the preparation of acoustic maps for whole ecosystem analysis. This last task utilises the temporal distribution of events over a daily, monthly or yearly cycle.

Climate change and human activity are subjecting the environment to unprecedented rates of change. Monitoring these changes is an immense task that demands new levels of automated monitoring and analysis. We propose the use of acoustics as a proxy for the time consuming auditing of fauna, especially for determining the presence/absence of species. Acoustic monitoring is deceptively simple; seemingly all that is required is a sound recorder. However there are many major challenges if acoustics are to be used for large scale monitoring of ecosystems. Key issues are scalability and automation. This paper discusses our approach to this important research problem. Our work is being undertaken in collaboration with ecologists interested both in identifying particular species and in general ecosystem health.

The requirement to monitor the rapid pace of environmental change due to global warming and to human development is producing large volumes of data but placing much stress on the capacity of ecologists to store, analyse and visualise that data. To date, much of the data has been provided by low level sensors monitoring soil moisture, dissolved nutrients, light intensity, gas composition and the like. However, a significant part of an ecologist’s work is to obtain information about species diversity, distributions and relationships. This task typically requires the physical presence of an ecologist in the field, listening and watching for species of interest. It is an extremely difficult task to automate because of the higher order difficulties in bandwidth, data management and intelligent analysis if one wishes to emulate the highly trained eyes and ears of an ecologist. This paper is concerned with just one part of the bigger challenge of environmental monitoring – the acquisition and analysis of acoustic recordings of the environment. Our intention is to provide helpful tools to ecologists – tools that apply information technologies and computational technologies to all aspects of the acoustic environment. The on-line system which we are building in conjunction with ecologists offers an integrated approach to recording, data management and analysis. The ecologists we work with have different requirements and therefore we have adopted the toolbox approach, that is, we offer a number of different web services that can be concatenated according to need. In particular, one group of ecologists is concerned with identifying the presence or absence of species and their distributions in time and space. Another group, motivated by legislative requirements for measuring habitat condition, are interested in summary indices of environmental health. In both case, the key issues are scalability and automation.

Hiding watermark information in medical image data files is one method of enhancing security and protecting patient privacy. However the research area of medical image watermarking has not been particularly active, partly due to concerns that any distortion could affect the diagnostic value of the medical image. These concerns can be addressed by ensuring that any image changes are kept below visual perception thresholds. In this paper the effects of image watermarking and common image manipulations are measured using the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Measure (SSIM) and Steerable Visual Difference Predictor (SVDP) numerical metrics. Two methods of block based watermarking are compared: the Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT). To ensure a fair comparison a 128-pixel block size is used which allows an identical amount of information to be embedded for each method (3072 bits multiplied by embedding strength). The results suggest that although the two methods are similar, the DCT method is preferable if localization of changes is required. If localization is not required the DWT method is supported.

Increasing transmission of medical images across multiple user systems raises concerns for image security. Hiding watermark information in medical image data files is one solution for enhancing security and privacy protection of data. Medical image watermarking however is not a widely studied area, due partially to speculations on loss in viewer performance caused by degradation of image information. Such concerns are addressed if the amount of information lost due to watermarking can be kept at minimal levels and below visual perception thresholds. This paper describes experiments where three alternative visual quality metrics were used to assess the degradation caused by watermarking medical images. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) medical images were watermarked using different methods: Block based Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) with various embedding strengths. The visual degradation of each watermarking parameter setting was assessed using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Measure (SSIM) and Steerable Visual Difference Predictor (SVDP) numerical metrics. The suitability of each of the three numerical metrics for medical image watermarking visual quality assessment is noted. In addition, subjective test results from human observers are used to suggest visual degradation thresholds.

Computer vision tasks such as registration, modeling and object recognition, are becoming increasingly useful in industry. Each of these applications employs correspondence algorithms to compute accurate mappings between partially overlapping surfaces. In industry, it is essential to select an appropriate correspondence algorithm for a given surface matching task. A correspondence framework has recently been proposed to assist in the selection and creation of correspondence algorithms for these tasks. This paper demonstrates how to use the correspondence framework to create a new surface matching algorithm, which uses stages of an existing model matching algorithm. The efficiency with which the new algorithm is created using the correspondence frame work is emphasized. In addition, results show that the new algorithm is both robust and efficient.

Increasingly widespread communication of medical images across multiple user systems raises concerns for image security, for which digital image watermarking offers one solution. While digital image watermarking methods have been widely studied, much less attention has been paid to their application in medical imaging situations, due partially to speculations on loss in viewer performance due to degradation of image information. Such concerns are addressed if the amount of information lost due to watermarking can be kept at minimal levels and certainly well below visual perception thresholds. This paper describes a method for applying watermarks to medical images on a locally varying basis, so as to ensure that the visual impact of changes in pixel values is minimal. The method uses an adaptive approach based on 8x8 blocks of pixels, and takes into account the imaging modality and local image contents according to common perceptual information models, when determining the amount of watermark payload information to be encoded. It is assumed that 'light' watermarking is desirable, and some typical examples of watermarks that might be used (e.g. patient identifiers and examination details) are provided to substantiate this position. Experimental results for typical CT and NM images are presented, and the performance of the method across a range of different choices of parameters is analysed. This would be useful in situations where images are manipulated on and transferred between many different independent image storage systems (including PACS), which would not allow the integrity of the image data to be assured.

Transfer of digital medical images between multiple parties requires the assurance of image identity and integrity, which can be achieved through image watermarking. This raises concerns for loss in viewer performance due to degradation of image quality. Here we describe an approach to ensure that impact on the image quality is well below the threshold of visual perceptibility. The principles on which this approach rests are the choice of a suitably light payload, and the use of different watermarking methods and parameters for different medical image types. We provide examples of this approach applied to MR, CT and CR images.

Medical image watermarking has been proposed as an appropriate method for enhancing data security, content verification and numerical image fidelity. Due to the sensitive nature of the data, medical image watermarking requires that any additional information that is stored within an image must not affect the perceptual integrity of the image. In typical approaches, additional information is generally hidden in the entire image, or in the background regions of an image (so as not to affect the medical data). This paper presents a novel model whereby medical image regions are watermarked differently so that perceptual degradation due to watermarking is limited. The model partitions images into regions and characterises each region according to some feature(s). Each region is then watermarked with a particular watermark method and payload capacity such that perceptual degradation is limited. This paper presents the model in conceptual form and then uses one instance of it to demonstrate how it would be used in practise. Results on MR and CT images demonstrate that less visually sensitive areas on images can be watermarked using more robust techniques and more sensitive areas can be watermarked using lighter or no embedding.

Beyond the inherent technical challenges, current research into the three dimensional surface correspondence problem is hampered by a lack of uniform terminology, an abundance of application specific algorithms, and the absence of a consistent model for comparing existing approaches and developing new ones. This paper addresses these challenges by presenting a framework for analysing, comparing, developing, and implementing surface correspondence algorithms. The framework uses five distinct stages to establish correspondence between surfaces. It is general, encompassing a wide variety of existing techniques, and flexible, facilitating the synthesis of new correspondence algorithms. This paper presents a review of existing surface correspondence algorithms, and shows how they fit into the correspondence framework. It also shows how the framework can be used to analyse and compare existing algorithms and develop new algorithms using the framework's modular structure. Six algorithms, four existing and two new, are implemented using the framework. Each implemented algorithm is used to match a number of surface pairs. Results demonstrate that the correspondence framework implementations are faithful implementations of existing algorithms, and that powerful new surface correspondence algorithms can be created.

Digital watermarking has been proposed to increase medical image security, confidentiality and integrity. Med ical image watermarking is a special subcategory of image watermarking in the sense that the images have special requirements. Particularly, watermarked medical images should not differ perceptually from their original counter parts, because the clinical reading of the images (e.g. for diagnosis) must not be affected. This paper presents a preliminary study on the degradation of medical images when embedded with different watermarks, using a variety of popular systems. Image quality is measured with a number of widely used metrics, which have been applied elsewhere in image processing. The general conclusion that arises from the results is that typical watermark embedding can cause numerical and perceptual errors in an image. The greater the robustness of a watermark, the greater the errors are likely to be. Consequently medical image watermarking remains an open area for research, and it appears that a selection of different watermarks for different medical imag e types is the most appropriate solution to the generic problem.

A wide variety of applications including object recognition and terrain mapping, rely upon automatic three dimensional surface modelling. The automatic correspondence stage of the modelling process has proven challenging. Intrinsic correspondence methods determine matching segments of partially overlapping 3D surfaces, by using properties intrinsic to the surfaces. These methods do not require initial relative orientations to begin the matching procedures. Hence, intrinsic methods are well-suited for automatic matching. This paper introduces a novel intrinsic automatic correspondence algorithm. Local feature support regions are described using distance and angular metrics, which are used to construct cumulative distribution function signatures. Local correspondences are hypothesised by comparing the signatures of two surfaces. A geometric consistency test is then applied to select the best local correspondences. Finally, registrations are computed from the remaining correspondences and the best alignment is selected. Results demonstrating the algorithm’s accuracy in selecting correspondences for mutual partially overlapping surfaces, are presented. The algorithm’s parameters prove robust, with only the local region size being surface dependent.