This paper proposes an automatic method for classifying Aortic valvular stenosis (AS) using ECG (Electrocardiogram) images by the deep learning whose training ECG images are annotated by the diagnoses given by the medical doctor who observes the echocardiograms. Besides, it explores the relationship between the trained deep learning network and its determinations, using the Grad-CAM.In this study, one-beat ECG images for 12-leads and 4-leads are generated from ECG’s and train CNN’s (Convolutional neural network). By applying the Grad-CAM to the trained CNN’s, feature areas are detected in the early time range of the one-beat ECG image. Also, by limiting the time range of the ECG image to that of the feature area, the CNN for the 4-lead achieves the best classification performance, which is close to expert medical doctors’ diagnoses.Clinical Relevance-This paper achieves as high AS classification performance as medical doctors’ diagnoses based on echocardiograms by proposing an automatic method for detecting AS only using ECG.Nowadays, cancer has become a major threat to people’s lives and health. Convolutional neural network (CNN) has been used for cancer early identification, which cannot achieve the desired results in some cases, such as images with affine transformation. Due to robustness to rotation and affine transformation, capsule network can effectively solve this problem of CNN and achieve the expected performance with less training data, which are very important for medical image analysis. In this paper, an enhanced capsule network is proposed for medical image classification. For the proposed capsule network, the feature decomposition module and multi-scale feature extraction module are introduced into the basic capsule network. The feature decomposition module is presented to extract richer features, which reduces the amount of calculation and speeds up the network convergence. The multi-scale feature extraction module is used to extract important information in the low-level capsules, which guarantees the extracted features to be transmitted to the high-level capsules. The proposed capsule network was applied on PatchCamelyon (PCam) dataset. Experimental results show that it can obtain good performance for medical image classification task, which provides good inspiration for other image classification tasks.This paper proposes a new method for automatic detection of glaucoma from stereo pair of fundus images. The basis for detecting glaucoma is using the optic cup-to-disc area ratio, where the surface area of the optic cup is segmented from the disparity map estimated from the stereo fundus image pair. More specifically, we first estimate the disparity map from the stereo image pair. Then, the optic disc is segmented from one of the stereo image. Based upon the location of the optic disc, we perform an active contour segmentation on the disparity map to segment the optic cup. Thereafter, we can compute the optic cup-to-disc area ratio by dividing the area (i.e. the total number of pixels) of the segmented optic cup region to that of the segmented optic disc region. Our experimental results using the available test dataset shows the efficacy of our proposed approach.Semi-automatic measurements are performed on 18FDG PET-CT images to monitor the evolution of metastatic sites in the clinical follow-up of metastatic breast cancer patients. Apart from being time-consuming and prone to subjective approximation, semi-automatic tools cannot make the difference between cancerous regions and active organs, presenting a high 18FDG uptake.In this work, we combine a deep learning-based approach with a superpixel segmentation method to segment the main active organs (brain, heart, bladder) from full-body PET images. In particular, we integrate a superpixel SLIC algorithm at different levels of a convolutional network. Results are compared with a deep learning segmentation network alone. Zileuton nmr The methods are cross-validated on full-body PET images of 36 patients and tested on the acquisitions of 24 patients from a different study center, in the context of the ongoing EPICUREseinmeta study. The similarity between the manually defined organ masks and the results is evaluated with the Dice score. Moreover, the amount of false positives is evaluated through the positive predictive value (PPV).According to the computed Dice scores, all approaches allow to accurately segment the target organs. However, the networks integrating superpixels are better suited to transfer knowledge across datasets acquired on multiple sites (domain adaptation) and are less likely to segment structures outside of the target organs, according to the PPV.Hence, combining deep learning with superpixels allows to segment organs presenting a high 18FDG uptake on PET images without selecting cancerous lesion, and thus improves the precision of the semi-automatic tools monitoring the evolution of breast cancer metastasis.Clinical relevance- We demonstrate the utility of combining deep learning and superpixel segmentation methods to accurately find the contours of active organs from metastatic breast cancer images, to different dataset distributions.18FDG PET/CT imaging is commonly used in diagnosis and follow-up of metastatic breast cancer, but its quantitative analysis is complicated by the number and location heterogeneity of metastatic lesions. Considering that bones are the most common location among metastatic sites, this work aims to compare different approaches to segment the bones and bone metastatic lesions in breast cancer.Two deep learning methods based on U-Net were developed and trained to segment either both bones and bone lesions or bone lesions alone on PET/CT images. These methods were cross-validated on 24 patients from the prospective EPICUREseinmeta metastatic breast cancer study and were evaluated using recall and precision to measure lesion detection, as well as the Dice score to assess bones and bone lesions segmentation accuracy.Results show that taking into account bone information in the training process allows to improve the precision of the lesions detection as well as the Dice score of the segmented lesions. Moreover, using the obtained bone and bone lesion masks, we were able to compute a PET bone index (PBI) inspired by the recognized Bone Scan Index (BSI).