The development of an automatic telemedicine system for computer-aided screening and grading of diabetic retinopathy depends on reliable detection of retinal lesions in fundus images. In this paper, a novel method for automatic detection of both microaneurysms and hemorrhages in color fundus images is described and validated. The main contribution is a new set of shape features, called Dynamic Shape Features, that do not require precise segmentation of the regions to be classified. These features represent the evolution of the shape during image flooding and allow to discriminate between lesions and vessel segments. The method is validated per-lesion and per-image using six databases, four of which are publicly available. It proves to be robust with respect to variability in image resolution, quality and acquisition system. On the Retinopathy Online Challenge's database, the method achieves a FROC score of 0.420 which ranks it fourth. On the Messidor database, when detecting images with diabetic retinopathy, the proposed method achieves an area under the ROC curve of 0.899, comparable to the score of human experts, and it outperforms state-of-the-art approaches.

Study design: Reliability study. Objectives:To assess between-acquisition reliability of new multi-levels trunk cross-sections measurements, in order to define what is a real change when comparing two trunk surface acquisitions of a same patient, before and after surgery or throughout the clinical monitoring.Summary of background data: Several cross-sectional surface measurements have been proposed in the literature for non-invasive assessment of trunk deformity in patients with adolescent idiopathic scoliosis (AIS). However, only the maximum values along the trunk are evaluated and used for monitoring progression and assessing treatment outcome. Methods:Back surface rotation (BSR), trunk rotation (TR) and coronal and sagittal trunk deviation are computed on 300 cross-sections of the trunk. Each set of 300 measures is represented as a single functional data using a set of basis functions. To evaluate betweenacquisition variability at all trunk levels, a test-retest reliability study is conducted on 35 AIS patients. A functional correlation analysis is also carried out to evaluate any redundancy between the measurements.Results: Each set of 300 measures was successfully described using only 10 basis functions.The test-retest reliability of the functional measurements is good to very good all over the trunk, except above the shoulders levels. The typical errors of measurement are between 1.20 and 2.2 for the rotational measures and between 2 to 6 mm for deviation measures. There is a very strong correlation between BSR and TR all over the trunk, a moderate correlation between coronal trunk deviation and both BSR and TR and no correlation between sagittal trunk deviation and any other measurement. Conclusions:This novel representation of trunk surface measurements allows for a global assessment of trunk surface deformity. Multilevel trunk measurements provide a broader perspective of the trunk deformity and allow a reliable multi-level monitoring during clinical follow-up of patients with AIS and a reliable assessment of the esthetic outcome after surgery. KEY WORDS:Scoliosis, multi-level trunk surface measurement, functional data analysis, reliability, correlation. KEY POINTS:1) Trunk cross-sections measurements are reliable all along the trunk, except at the shoulders level.2) The maximum value of a measurement along the trunk overlooks the extent of the hump above and below the apex of the curve. MINI ABSTRACT / PRÉCIS:This study assesses the reliability of multi-levels trunk cross-sections measurements and defines the difference needed between trunk surface acquisitions to detect a real progression and/or surgical correction of trunk surface deformity at all trunk levels.

Abstract-Among the external manifestations of scoliosis, the rib hump, which is associated to the ribs' deformities and rotations, constitutes for patients the most disturbing aspect of the scoliotic deformity. A personalized 3D model of the rib cage is important for a better evaluation of the deformity and thus, better treatment planning. A novel method for the 3D reconstruction of the rib cage, based only on two standard radiographs, is proposed in this article. For each rib, two points are extrapolated from the reconstructed spine, and three points are reconstructed by stereo radiography. The reconstruction is then refined using a surface approximation. The method was evaluated using clinical data of 13 patients with scoliosis. A comparison was conducted between the reconstructions obtained with the proposed method and those obtained using a previous reconstruction method based on two frontal radiographs. A first comparison criterion was the distances between the reconstructed ribs and the surface topography of the trunk, considered as the reference modality. The correlation between ribs axial rotation and back surface rotation was also evaluated. The proposed method successfully reconstructed the ribs of the 6 th to 12 th thoracic levels. The evaluation results showed that the three dimensional configuration of the new rib reconstructions is more consistent with the surface topography and provides more accurate measurements of ribs axial rotation.

Age-related macular degeneration (AMD) is a disease which causes visual deficiency and irreversible blindness to the elderly. In this paper, an automatic classification method for AMD is proposed to perform robust and reproducible assessments in a telemedicine context. First, a study was carried out to highlight the most relevant features for AMD characterization based on texture, color, and visual context in fundus images. A support vector machine and a random forest were used to classify images according to the different AMD stages following the AREDS protocol and to evaluate the features' relevance. Experiments were conducted on a database of 279 fundus images coming from a telemedicine platform. The results demonstrate that local binary patterns in multiresolution are the most relevant for AMD classification, regardless of the classifier used. Depending on the classification task, our method achieves promising performances with areas under the ROC curve between 0.739 and 0.874 for screening and between 0.469 and 0.685 for grading. Moreover, the proposed automatic AMD classification system is robust with respect to image quality.