The analysis of medical images has been woven into the fabric of the pattern analysis and machine intelligence (PAMI) community since the earliest days of these Transactions. Initially, the efforts in this area were seen as applying pattern analysis and computer vision techniques to another interesting dataset. However, over the last two to three decades, the unique nature of the problems presented within this area of study have led to the development of a new discipline in its own right. Examples of these include: the types of image information that are acquired, the fully three-dimensional image data, the nonrigid nature of object motion and deformation, and the statistical variation of both the underlying normal and abnormal ground truth. In this paper, we look at progress in the field over the last 20 years and suggest some of the challenges that remain for the years to come.

https://hal.inria.fr/inria-00615100/document

Medical image analysis: progress over two decades and the challenges ahead

https://bio3d.colorado.edu/SerialEM/serialEMJSB.pdf

Automated electron microscope tomography using robust prediction of specimen movements.

中枢神経系疾患の治療は正常細胞（ニューロン）の機能維持を目的とするが，脳血管障害のように機能障害の原因が細胞の死滅に基づくことは多い．一方，脳腫瘍の治療においては薬物療法や放射線療法といった腫瘍細胞の死滅を目標とするものが大きな位置を占める．いずれの場合にも，細胞死の機序を理解することは各種病態や治療法の理解のうえで重要である．現在のところ最も研究の進んでいる細胞死の型はアポトーシスである．そのなかで重要な位置を占めるミトコンドリアにおける反応および抗アポトーシス因子について概要を紹介する．

Neuroscience 細胞死：最近の知見

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

http://www.cvs.rochester.edu/knill_lab/papers/35_TINS_2004.pdf

The Bayesian brain: the role of uncertainty in neural coding and computation

Observer Models as a Surrogate to Perception Experiments

Recent work applied model observers to predict the effect of JPEG and wavelet image compression on human visual detection of simulated lesions embedded in real structured backgrounds (x-ray coronary angiograms). We extend the use of model observers to perform parameter optimization of image compression in order to maximize visual detection performance at a given compression ratio. A simulated annealing algorithm was used to find the optimal quantization matrix. In each iteration, the 64 quantization parameters of the JPEG algorithm were randomly perturbed (while preserving a fixed compression ratio). Each set of quantization parameters setting was used to compress 400 test images. Model observer performance (Pc) was then obtained for the images that had undergone compression. The simulated annealing algorithm converged (as determined by the 'annealing schedule') to an 'optimal' quantization matrix. A follow-up human psychophysical study with two naive observers was conducted to compare optimal quantization matrix with respect to the default JPEG quantization matrix. For both human observers visual detection performance improved significantly from the default to the optimized quantization matrix condition. Our results suggest that model observers can be successfully used for task-based performance optimization of image compression algorithms.© (2000) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Model observer based optimization of JPEG image compression

Schatzkin et al. and other authors demonstrated that the ratios of some conditional statistics such as the true positive fraction are equal to the ratios of unconditional statistics, such as disease detection rates, and therefore we can calculate these ratios between two screening tests on the same population even if negative test patients are not followed with a reference procedure and the true and false negative rates are unknown. We demonstrate that this same property applies to an expected utility metric. We also demonstrate that while simple estimates of relative specificities and relative areas under ROC curves (AUC) do depend on the unknown negative rates, we can write these ratios in terms of disease prevalence, and the dependence of these ratios on a posited prevalence is often weak particularly if that prevalence is small or the performance of the two screening tests is similar. Therefore we can estimate relative specificity or AUC with little loss of accuracy, if we use an approximate value of disease prevalence.

/pdf/using-relative-statistics-and-approximate-disease-prevalence-2iia98x3m2.pdf

Using Relative Statistics and Approximate Disease Prevalence to Compare Screening Tests

Most metrics of medical image quality typically treat all variability components of the background as a Gaussian noise process. This includes task based model observers (non-prewhitening matched filter without and with an eye filter, NPW and NPWE; Hotelling and Channelized Hotelling) as well as Fourier metrics of medical image quality based on the noise power spectra. However, many investigators have observed that unlike many of the models/metrics, physicians often can discount signal-looking structures that are part of the normal anatomic background. This process has been referred to as reading around the background or noise. The purpose of this paper is to develop an experimental framework to systematically study the ability of human observers to read around learned backgrounds and compare their ability to that of an optimal ideal observer which has knowledge of the background. We measured human localization performance of one of twelve targets in the presence of a fixed background consisting of randomly placed Gaussians with random contrasts and sizes, and white noise. Performance was compared to a condition in which the test images contained only white noise but with higher contrast. Human performance was compared to standard model observers that treat the background as a Gaussian noise process (NPW, NPWE and Hotelling), a Fourier-based prewhitening matched filter, and an ideal observer. The Hotelling, NPW, NPWE models as well as the Fourier-based prewhitening matched filter predicted higher performance for the white noise test images than the background plus white noise. In contrast, ideal and human performance was higher for the background plus white noise condition. Furthermore, human performance exceeded that of the NPW, NPWE and Hotelling models and reached an efficiency of 19% relative to the ideal observer. Our results demonstrate that for some types of images human signal localization performance is consistent with use of knowledge about the high order moments of the backgrounds to discount signal-looking structures that belong to the background. In such scenarios model observers and metrics that either ignore the background or treat the background as a Gaussian process (Hotelling, Channelized Hotelling, Task-based SNR) under predict human performance.

The efficiency of reading around learned backgrounds

Task-based image quality procedures in CT that substitute a human observer with a model observer usually use single-slice images with uniform backgrounds from homogeneous phantoms. However, anatomical structures and inhomogeneities in organs generate noise that can affect the detection performance of human observers. The purpose of this work was to assess the impact of background type, uniform or liver, and the viewing modality, single- or multislice, on the detection performance of human and model observers. We collected abdominal CT scans from patients and homogeneous phantom scans in which we digitally inserted low-contrast signals that mimicked a liver lesion. We ran a rating experiment with the two background conditions with three signal sizes and three human observers presenting images in two reading modalities: single- and multislice. In addition, channelized Hotelling observers (CHO) for single- and multislice detection were implemented and evaluated according to their degree of correlation with the human observer performance. For human observers, there was a small but significant improvement in performance with multislice compared to the single-slice viewing mode. Our data did not reveal a significant difference between uniform and anatomical backgrounds. Model observers demonstrated a good correlation with human observers for both viewing modalities. Human observers have very similar performances in both multi- and single-slice viewing mode. It is therefore preferable to use single-slice CHO as this model is computationally more tractable than multislice CHO. However, using images from a homogeneous phantom can result in overestimating image quality as CHO performance tends to be higher in uniform than anatomical backgrounds, while human observers have similar detection performances.

/pdf/channelized-hotelling-observer-correlation-with-human-2yl5lr2fzo.pdf

Craig K. Abbey

Papers

Observer Models as a Surrogate to Perception Experiments

Model observer based optimization of JPEG image compression

Using Relative Statistics and Approximate Disease Prevalence to Compare Screening Tests

The efficiency of reading around learned backgrounds

Channelized Hotelling observer correlation with human observers for low-contrast detection in liver CT images.