The BIOSCAN project, led by the International Barcode of Life Consortium, seeks to study changes in biodiversity on a global scale. One component of the project is focused on studying the species interaction and dynamics of all insects. In addition to genetically barcoding insects, over 1.5 million images per year will be collected, each needing taxonomic classification. With the immense volume of incoming images, relying solely on expert taxonomists to label the images would be impossible; however, artificial intelligence and computer vision technology may offer a viable high-throughput solution. Additional tasks including manually weighing individual insects to determine biomass, remain tedious and costly. Here again, computer vision may offer an efficient and compelling alternative. While the use of computer vision methods is appealing for addressing these problems, significant challenges resulting from biological factors present themselves. These challenges are formulated in the context of machine learning in this paper.
Egocentric 3D human pose estimation (HPE) from images is challenging due to severe self-occlusions and strong distortion introduced by the fish-eye view from the head mounted camera. Although existing works use intermediate heatmap-based representations to counter distortion with some success, addressing self-occlusion remains an open problem. In this work, we leverage information from past frames to guide our self-attention-based 3D HPE estimation procedure -- Ego-STAN. Specifically, we build a spatio-temporal Transformer model that attends to semantically rich convolutional neural network-based feature maps. We also propose feature map tokens: a new set of learnable parameters to attend to these feature maps. Finally, we demonstrate Ego-STAN's superior performance on the xR-EgoPose dataset where it achieves a 30.6% improvement on the overall mean per-joint position error, while leading to a 22% drop in parameters compared to the state-of-the-art.
Histopathological visualizations are a pillar of modern medicine and biological research. Surgical oncology relies exclusively on post-operative histology to determine definitive surgical success and guide adjuvant treatments. The current histology workflow is based on bright-field microscopic assessment of histochemical stained tissues and has some major limitations. For example, the preparation of stained specimens for brightfield assessment requires lengthy sample processing, delaying interventions for days or even weeks. Hence, there is a pressing need for improved histopathology methods. In this paper, we present a deep-learning-based approach for virtual label-free histochemical staining of total-absorption photoacoustic remote sensing (TA-PARS) images of unstained tissue. TA-PARS provides an array of directly measured label-free contrasts such as scattering and total absorption (radiative and non-radiative), ideal for developing H&E colorizations without the need to infer arbitrary tissue structures. We use a Pix2Pix generative adversarial network (GAN) to develop visualizations analogous to H&E staining from label-free TA-PARS images. Thin sections of human skin tissue were first virtually stained with the TA-PARS, then were chemically stained with H&E producing a one-to-one comparison between the virtual and chemical staining. The one-to-one matched virtually- and chemically- stained images exhibit high concordance validating the digital colorization of the TA-PARS images against the gold standard H&E. TA-PARS images were reviewed by four dermatologic pathologists who confirmed they are of diagnostic quality, and that resolution, contrast, and color permitted interpretation as if they were H&E. The presented approach paves the way for the development of TA-PARS slide-free histology, which promises to dramatically reduce the time from specimen resection to histological imaging.
Many measurement modalities which perform imaging by probing an object pixel-by-pixel, such as via Photoacoustic Microscopy, produce a multi-dimensional feature (typically a time-domain signal) at each pixel. In principle, the many degrees of freedom in the time-domain signal would admit the possibility of significant multi-modal information being implicitly present, much more than a single scalar "brightness", regarding the underlying targets being observed. However, the measured signal is neither a weighted-sum of basis functions (such as principal components) nor one of a set of prototypes (K-means), which has motivated the novel clustering method proposed here, capable of learning centroids (signal shapes) that are related to the underlying, albeit unknown, target characteristics in a scalable and noise-robust manner.
In this paper we investigate a variety of deep learning strategies for solving inverse problems. We classify existing deep learning solutions for inverse problems into three categories of Direct Mapping, Data Consistency Optimizer, and Deep Regularizer. We choose a sample of each inverse problem type, so as to compare the robustness of the three categories, and report a statistical analysis of their differences. We perform extensive experiments on the classic problem of linear regression and three well-known inverse problems in computer vision, namely image denoising, 3D human face inverse rendering, and object tracking, selected as representative prototypes for each class of inverse problems. The overall results and the statistical analyses show that the solution categories have a robustness behaviour dependent on the type of inverse problem domain, and specifically dependent on whether or not the problem includes measurement outliers. Based on our experimental results, we conclude by proposing the most robust solution category for each inverse problem class.
We have developed a multimodal photoacoustic remote sensing (PARS) microscope combined with swept source optical coherence tomography for in vivo, non-contact retinal imaging. Building on the proven strength of multiwavelength PARS imaging, the system is applied for estimating retinal oxygen saturation in the rat retina. The capability of the technology is demonstrated by imaging both microanatomy and the microvasculature of the retina in vivo. To our knowledge this is the first time a non-contact photoacoustic imaging technique is employed for in vivo oxygen saturation measurement in the retina.
In recent years a vast amount of visual content has been generated and shared from various fields, such as social media platforms, medical images, and robotics. This abundance of content creation and sharing has introduced new challenges. In particular, searching databases for similar content, i.e.content based image retrieval (CBIR), is a long-established research area, and more efficient and accurate methods are needed for real time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of intelligent search. In this survey we organize and review recent CBIR works that are developed based on deep learning algorithms and techniques, including insights and techniques from recent papers. We identify and present the commonly-used benchmarks and evaluation methods used in the field. We collect common challenges and propose promising future directions. More specifically, we focus on image retrieval with deep learning and organize the state of the art methods according to the types of deep network structure, deep features, feature enhancement methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, aiming to promote a global view of the field of instance-based CBIR.