This paper tries to give a gentle introduction to deep learning in medical image processing, proceeding from theoretical foundations to applications. We first discuss general reasons for the popularity of deep learning, including several major breakthroughs in computer science. Next, we start reviewing the fundamental basics of the perceptron and neural networks, along with some fundamental theory that is often omitted. Doing so allows us to understand the reasons for the rise of deep learning in many application domains. Obviously medical image processing is one of these areas which has been largely affected by this rapid progress, in particular in image detection and recognition, image segmentation, image registration, and computer-aided diagnosis. There are also recent trends in physical simulation, modeling, and reconstruction that have led to astonishing results. Yet, some of these approaches neglect prior knowledge and hence bear the risk of producing implausible results. These apparent weaknesses highlight current limitations of deep ()learning. However, we also briefly discuss promising approaches that might be able to resolve these problems in the future.

Significance: X-ray computed tomography (CT) is one of the most commonly used diagnostic three-dimensional imaging modalities today. Conventionally, this noninvasive technique generates contrast by measuring the X-ray attenuation properties of different tissues. Considering the wave nature of X-rays, complementary contrast can be achieved by further measuring their small-angle scattering (dark-field) properties. This provides additional valuable diagnostic information on otherwise unresolved tissue microstructure. In our work, we have translated this wave-optical mechanism from the optical bench to a human-sized prototype CT system. This involved the integration of an interferometer into a clinical CT gantry and overcoming several associated challenges regarding vibrations, continuous gantry rotation, and large field of view. This development puts complementary X-ray contrast within reach for real-word medical applications.

To investigate the chest radiograph classification performance of vision transformers (ViTs) and interpretability of attention-based saliency maps, using the example of pneumothorax classification. In this retrospective study, ViTs were fine-tuned for lung disease classification using four public datasets: CheXpert, Chest X-Ray 14, MIMIC CXR, and VinBigData. Saliency maps were generated using transformer multimodal explainability and gradient-weighted class activation mapping (GradCAM). Classification performance was evaluated on the Chest X-Ray 14, VinBigData, and Society for Imaging Informatics in Medicine–American College of Radiology (SIIM-ACR) Pneumothorax Segmentation datasets using the area under the receiver operating characteristic curve (AUC) analysis and compared with convolutional neural networks (CNNs). The explainability methods were evaluated with positive and negative perturbation, sensitivity-n, effective heat ratio, intra-architecture repeatability, and interarchitecture reproducibility. In the user study, three radiologists classified 160 chest radiographs with and without saliency maps for pneumothorax and rated their usefulness. ViTs had comparable chest radiograph classification AUCs compared with state-of-the-art CNNs: 0.95 (95% CI: 0.94, 0.95) versus 0.83 (95%, CI 0.83, 0.84) on Chest X-Ray 14, 0.84 (95% CI: 0.77, 0.91) versus 0.83 (95% CI: 0.76, 0.90) on VinBigData, and 0.85 (95% CI: 0.85, 0.86) versus 0.87 (95% CI: 0.87, 0.88) on SIIM-ACR. Both saliency map methods unveiled a strong bias toward pneumothorax tubes in the models. Radiologists found 47% of the attention-based and 39% of the GradCAM saliency maps useful. The attention-based methods outperformed GradCAM on all metrics. ViTs performed similarly to CNNs in chest radiograph classification, and their attention-based saliency maps were more useful to radiologists and outperformed GradCAM. Keywords: Conventional Radiography, Thorax, Diagnosis, Supervised Learning, Convolutional Neural Network (CNN) Online supplemental material is available for this article. © RSNA, 2023

The sampling patterns of the light field microscope (LFM) are highly depth-dependent, which implies non-uniform recoverable lateral resolution across depth. Moreover, reconstructions using state-of-the-art approaches suffer from strong artifacts at axial ranges, where the LFM samples the light field at a coarse rate. In this work, we analyze the sampling patterns of the LFM, and introduce a flexible light field point spread function model (LFPSF) to cope with arbitrary LFM designs. We then propose a novel aliasing-aware deconvolution scheme to address the sampling artifacts. We demonstrate the high potential of the proposed method on real experimental data.

Deep learning based solutions are being succesfully implemented for a wide variety of applications. Most notably, clinical use-cases have gained an increased interest and have been the main driver behind some of the cutting-edge data-driven algorithms proposed in the last years. For applications like sparse-view tomographic reconstructions, where the amount of measurement data is small in order to keep acquisition time short and radiation dose low, reduction of the streaking artifacts has prompted the development of data-driven denoising algorithms with the main goal of obtaining diagnostically viable images with only a subset of a full-scan data. We propose WNet, a data-driven dual-domain denoising model which contains a trainable reconstruction layer for sparse-view artifact denoising. Two encoder-decoder networks perform denoising in both sinogram- and reconstruction-domain simultaneously, while a third layer implementing the Filtered Backprojection algorithm is sandwiched between the first two and takes care of the reconstruction operation. We investigate the performance of the network on sparse-view chest CT scans, and we highlight the added benefit of having a trainable reconstruction layer over the more conventional fixed ones. We train and test our network on two clinically relevant datasets and we compare the obtained results with three different types of sparse-view CT denoising and reconstruction algorithms.