The continuous development and extensive use of computed tomography (CT) in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifacts, which can adversely affect the radiologists' judgment and confidence. Hence, advanced image reconstruction from low-dose CT data is needed to improve the diagnostic performance, which is a challenging problem due to its ill-posed nature. Over the past years, various low-dose CT methods have produced impressive results. However, most of the algorithms developed for this application, including the recently popularized deep learning techniques, aim for minimizing the mean-squared error (MSE) between a denoised CT image and the ground truth under generic penalties. Although the peak signal-to-noise ratio is improved, MSE- or weighted-MSE-based methods can compromise the visibility of important structural details after aggressive denoising. This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is a key concept of the optimal transport theory and promises to improve the performance of GAN. The perceptual loss suppresses noise by comparing the perceptual features of a denoised output against those of the ground truth in an established feature space, while the GAN focuses more on migrating the data noise distribution from strong to weak statistically. Therefore, our proposed method transfers our knowledge of visual perception to the image denoising task and is capable of not only reducing the image noise level but also trying to keep the critical information at the same time. Promising results have been obtained in our experiments with clinical CT images.

Hyperspectral unmixing is one of the most important techniques in analyzing hyperspectral images, which decomposes a mixed pixel into a collection of constituent materials weighted by their proportions. Recently, many sparse nonnegative matrix factorization (NMF) algorithms have achieved advanced performance for hyperspectral unmixing because they overcome the difficulty of absence of pure pixels and sufficiently utilize the sparse characteristic of the data. However, most existing sparse NMF algorithms for hyperspectral unmixing only consider the Euclidean structure of the hyperspectral data space. In fact, hyperspectral data are more likely to lie on a low-dimensional submanifold embedded in the high-dimensional ambient space. Thus, it is necessary to consider the intrinsic manifold structure for hyperspectral unmixing. In order to exploit the latent manifold structure of the data during the decomposition, manifold regularization is incorporated into sparsity-constrained NMF for unmixing in this paper. Since the additional manifold regularization term can keep the close link between the original image and the material abundance maps, the proposed approach leads to a more desired unmixing performance. The experimental results on synthetic and real hyperspectral data both illustrate the superiority of the proposed method compared with other state-of-the-art approaches.

A novel platform was developed that fuses pre-biopsy magnetic resonance imaging with real-time transrectal ultrasound imaging to identify and biopsy lesions suspicious for prostate cancer. The cancer detection rates for the first 101 patients are reported. This prospective, single institution study was approved by the institutional review board. Patients underwent 3.0 T multiparametric magnetic resonance imaging with endorectal coil, which included T2-weighted, spectroscopic, dynamic contrast enhanced and diffusion weighted magnetic resonance imaging sequences. Lesions suspicious for cancer were graded according to the number of sequences suspicious for cancer as low (2 or less), moderate (3) and high (4) suspicion. Patients underwent standard 12-core transrectal ultrasound biopsy and magnetic resonance imaging/ultrasound fusion guided biopsy with electromagnetic tracking of magnetic resonance imaging lesions. Chi-square and within cluster resampling analyses were used to correlate suspicion on magnetic resonance imaging and the incidence of cancer detected on biopsy. Mean patient age was 63 years old. Median prostate specific antigen at biopsy was 5.8 ng/ml and 90.1% of patients had a negative digital rectal examination. Of patients with low, moderate and high suspicion on magnetic resonance imaging 27.9%, 66.7% and 89.5% were diagnosed with cancer, respectively (p <0.0001). Magnetic resonance imaging/ultrasound fusion guided biopsy detected more cancer per core than standard 12-core transrectal ultrasound biopsy for all levels of suspicion on magnetic resonance imaging. Prostate cancer localized on magnetic resonance imaging may be targeted using this novel magnetic resonance imaging/ultrasound fusion guided biopsy platform. Further research is needed to determine the role of this platform in cancer detection, active surveillance and focal therapy, and to determine which patients may benefit.

Shortage of fully annotated datasets has been a limiting factor in developing deep learning based image segmentation algorithms and the problem becomes more pronounced in multi-organ segmentation. In this paper, we propose a unified training strategy that enables a novel multi-scale deep neural network to be trained on multiple partially labeled datasets for multi-organ segmentation. In addition, a new network architecture for multi-scale feature abstraction is proposed to integrate pyramid input and feature analysis into a U-shape pyramid structure. To bridge the semantic gap caused by directly merging features from different scales, an equal convolutional depth mechanism is introduced. Furthermore, we employ a deep supervision mechanism to refine the outputs in different scales. To fully leverage the segmentation features from all the scales, we design an adaptive weighting layer to fuse the outputs in an automatic fashion. All these mechanisms together are integrated into a Pyramid Input Pyramid Output Feature Abstraction Network (PIPO-FAN). Our proposed method was evaluated on four publicly available datasets, including BTCV, LiTS, KiTS and Spleen, where very promising performance has been achieved. The source code of this work is publicly shared at https://github.com/DIAL-RPI/PIPO-FAN to facilitate others to reproduce the work and build their own models using the introduced mechanisms.