Abstract: Confident use of medial surfaces in medical decision support systems requires evaluating their quality for detecting pathological deformations and describing anatomical volumes. Validation in the medical imaging field is a challenging task mainly due to the difficulties for getting consensual ground truth. In this paper we propose a validation benchmark for assessing medial surfaces in the context of medical applications. Our benchmark includes a home-made database of synthetic medial surfaces and volumes and specific scores for evaluating surface accuracy, its stability against volume deformations and its capabilities for accurate reconstruction of anatomical volumes.

Abstract: Evaluation of the performance and limitations of medical imaging algorithms is essential to estimate their impact in social, economic or clinical aspects. However, validation of medical imaging techniques is a challenging task due to the variety of imaging and clinical problems involved, as well as, the difficulties for systematically extracting a reliable solely ground truth. Although specific validation protocols are reported in any medical imaging paper, there are still two major concerns: definition of standardized methodologies transversal to all problems and generalization of conclusions to the whole clinical data set.
We claim that both issues would be fully solved if we had a statistical model relating ground truth and the output of computational imaging techniques. Such a statistical model could conclude to what extent the algorithm behaves like the ground truth from the analysis of a sampling of the validation data set. We present a statistical inference framework reporting the agreement and describing the relationship of two quantities. We show its transversality by applying it to validation of two different tasks: contour segmentation and landmark correspondence.

Abstract: State of the art machine learning methods need huge amounts of data with unambiguous annotations for their training. In the context of medical imaging this is, in general, a very difficult task due to limited access to clinical data, the time required for manual annotations and variability across experts. Simulated data could serve for data augmentation provided that its appearance was comparable to the actual appearance of intra-operative acquisitions. Generative Adversarial Networks (GANs) are a powerful tool for artistic style transfer, but lack a criteria for selecting epochs ensuring also preservation of intra-operative content.
We propose a multi-objective optimization strategy for a selection of cycleGAN epochs ensuring a mapping between virtual images and the intra-operative domain preserving anatomical content. Our approach has been applied to simulate intra-operative bronchoscopic videos and chest CT scans from virtual sketches generated using simple graphical primitives.

Abstract: Plaque analysis in IVUS planes needs accurate intima and adventitia models. Large variety in adventitia descriptors difficulties its detection and motivates using a classification strategy for selecting points on the structure. Whatever the set of descriptors used, the selection stage suffers from fake responses due to noise and uncompleted true curves. In order to smooth background noise while strengthening responses, we apply a restricted anisotropic filter that homogenizes grey levels along the image significant structures. Candidate points are extracted by means of a simple semi supervised adaptive classification of the filtered image response to edge and calcium detectors. The final model is obtained by interpolating the former line segments with an anisotropic contour closing technique based on functional extension principles.

Abstract: Assessing Optical Flow (OF) quality is essential for its further use in reliable decision support systems. The absence of ground truth in such situations leads to the computation of OF Confidence Measures (CM) obtained from either input or output data. A fair comparison across the capabilities of the different CM for bounding OF error is required in order to choose the best OF-CM pair for discarding points where OF computation is not reliable. This paper presents a statistical probabilistic framework for assessing the quality of a given CM. Our quality measure is given in terms of the percentage of pixels whose OF error bound can not be determined by CM values. We also provide statistical tools for the computation of CM values that ensures a given accuracy of the flow field.