Skin lesions are a severe disease globally. Early detection of melanoma in dermoscopy images significantly increases the survival rate. However, the accurate recognition of melanoma is extremely challenging due to the following reasons: low contrast between lesions and skin, visual similarity between melanoma and non-melanoma lesions, etc. Hence, reliable automatic detection of skin tumors is very useful to increase the accuracy and efficiency of pathologists. In this paper, we proposed two deep learning methods to address three main tasks emerging in the area of skin lesion image processing, i.e., lesion segmentation (task 1), lesion dermoscopic feature extraction (task 2) and lesion classification (task 3). A deep learning framework consisting of two fully convolutional residual networks (FCRN) is proposed to simultaneously produce the segmentation result and the coarse classification result. A lesion index calculation unit (LICU) is developed to refine the coarse classification results by calculating the distance heat-map. A straight-forward CNN is proposed for the dermoscopic feature extraction task. The proposed deep learning frameworks were evaluated on the ISIC 2017 dataset. Experimental results show the promising accuracies of our frameworks, i.e., 0.753 for task 1, 0.848 for task 2 and 0.912 for task 3 were achieved.

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent deep learning works such as style transfer, we employ a pre-trained deep convolutional neural network (CNN) and use its hidden features to define a feature perceptual loss for VAE training. Evaluated on the CelebA face dataset, we show that our model produces better results than other methods in the literature. We also show that our method can produce latent vectors that can capture the semantic information of face expressions and can be used to achieve state-of-the-art performance in facial attribute prediction.

A cyclic peptide specific for type I collagen is derivatized with three {Gd(dtpa)} moieties to create a molecular MRI contrast agent for fibrosis imaging. In a mouse model of myocardial infarction (heart attack), collagen levels are elevated in the infarct zone. MRI after injection of the contrast agent selectively enhances and delineates the infarct zone (see preinjection and postinjection images); dtpa=diethylenetriaminepentaacetate.

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline [1]. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net [2], FCN [3], and Mask- RCNN [4] were popularly used, typically based on ResNet [5] or VGG [6] base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

BackgroundCancer associated cachexia affects the majority of cancer patients during the course of the disease and thought to be directly responsible for about a quarter of all cancer deaths. Current evidence suggests that a pro‐inflammatory state may be associated with this syndrome although the molecular mechanisms responsible for the development of cachexia are poorly understood. The purpose of this work was the identification of key drivers of cancer cachexia that could provide a potential point of intervention for the treatment and/or prevention of this syndrome.MethodsGenetically engineered and xenograft tumour models were used to dissect the molecular mechanisms driving cancer cachexia. Cytokine profiling from the plasma of cachectic and non‐cachectic cancer patients and mouse models was utilized to correlate circulating cytokine levels with the cachexia phenotype.ResultsUtilizing engineered tumour models we identified MAP3K11/GDF15 pathway activation as a potent inducer of cancer cachexia. Increased expression and high circulating levels of GDF15 acted as a key mediator of this process. In animal models, tumour‐produced GDF15 was sufficient to trigger the cachexia phenotype. Elevated GDF15 circulating levels correlated with the onset and progression of cachexia in animal models and in patients with cancer. Inhibition of GDF15 biological activity with a specific antibody reversed body weight loss and restored muscle and fat tissue mass in several cachectic animal models regardless of their complex secreted cytokine profile.ConclusionsThe combination of correlative observations, gain of function, and loss of function experiments validated GDF15 as a key driver of cancer cachexia and as a potential therapeutic target for the treatment and/or prevention of this syndrome.