RESUMEN
This paper presents a novel architecture for simultaneous estimation of highly accurate optical flows and rigid scene transformations for difficult scenarios where the brightness assumption is violated by strong shading changes. In the case of rotating objects or moving light sources, such as those encountered for driving cars in the dark, the scene appearance often changes significantly from one view to the next. Unfortunately, standard methods for calculating optical flows or poses are based on the expectation that the appearance of features in the scene remains constant between views. These methods may fail frequently in the investigated cases. The presented method fuses texture and geometry information by combining image, vertex and normal data to compute an illumination-invariant optical flow. By using a coarse-to-fine strategy, globally anchored optical flows are learned, reducing the impact of erroneous shading-based pseudo-correspondences. Based on the learned optical flows, a second architecture is proposed that predicts robust rigid transformations from the warped vertex and normal maps. Particular attention is paid to situations with strong rotations, which often cause such shading changes. Therefore, a 3-step procedure is proposed that profitably exploits correlations between the normals and vertices. The method has been evaluated on a newly created dataset containing both synthetic and real data with strong rotations and shading effects. These data represent the typical use case in 3D reconstruction, where the object often rotates in large steps between the partial reconstructions. Additionally, we apply the method to the well-known Kitti Odometry dataset. Even if, due to fulfillment of the brightness assumption, this is not the typical use case of the method, the applicability to standard situations and the relation to other methods is therefore established.
RESUMEN
We have developed a sensor for monitoring the hemoglobin (Hb) concentration in the effluent of a continuous bladder irrigation. The Hb concentration measurement is based on light absorption within a fixed measuring distance. The light frequency used is selected so that both arterial and venous Hb are equally detected. The sensor allows the measurement of the Hb concentration up to a maximum value of 3.2 g/dL (equivalent to ≈20% blood concentration). Since bubble formation in the outflow tract cannot be avoided with current irrigation systems, a neural network is implemented that can robustly detect air bubbles within the measurement section. The network considers both optical and temporal features and is able to effectively safeguard the measurement process. The sensor supports the use of different irrigants (salt and electrolyte-free solutions) as well as measurement through glass shielding. The sensor can be used in a non-invasive way with current irrigation systems. The sensor is positively tested in a clinical study.
Asunto(s)
Inteligencia Artificial , Hemoglobinas , Redes Neurales de la Computación , Vejiga UrinariaRESUMEN
We developed a new mobile ultrasound device for long-term and automated bladder monitoring without user interaction consisting of 32 transmit and receive electronics as well as a 32-element phased array 3 MHz transducer. The device architecture is based on data digitization and rapid transfer to a consumer electronics device (e.g., a tablet) for signal reconstruction (e.g., by means of plane wave compounding algorithms) and further image processing. All reconstruction algorithms are implemented in the GPU, allowing real-time reconstruction and imaging. The system and the beamforming algorithms were evaluated with respect to the imaging performance on standard sonographical phantoms (CIRS multipurpose ultrasound phantom) by analyzing the resolution, the SNR and the CNR. Furthermore, ML-based segmentation algorithms were developed and assessed with respect to their ability to reliably segment human bladders with different filling levels. A corresponding CNN was trained with 253 B-mode data sets and 20 B-mode images were evaluated. The quantitative and qualitative results of the bladder segmentation are presented and compared to the ground truth obtained by manual segmentation.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Vejiga Urinaria , Humanos , Aprendizaje Automático , Fantasmas de Imagen , Ultrasonografía , Vejiga Urinaria/diagnóstico por imagenRESUMEN
PURPOSE: The purpose of the study was to provide a comprehensive review of recent machine learning (ML) and deep learning (DL) applications in urological practice. Numerous studies have reported their use in the medical care of various urological disorders; however, no critical analysis has been made to date. METHODS: A detailed search of original articles was performed using the PubMed MEDLINE database to identify recent English literature relevant to ML and DL applications in the fields of urolithiasis, renal cell carcinoma (RCC), bladder cancer (BCa), and prostate cancer (PCa). RESULTS: In total, 43 articles were included addressing these four subfields. The most common ML and DL application in urolithiasis is in the prediction of endourologic surgical outcomes. The main area of research involving ML and DL in RCC concerns the differentiation between benign and malignant small renal masses, Fuhrman nuclear grade prediction, and gene expression-based molecular signatures. BCa studies employ radiomics and texture feature analysis for the distinction between low- and high-grade tumors, address accurate image-based cytology, and use algorithms to predict treatment response, tumor recurrence, and patient survival. PCa studies aim at developing algorithms for Gleason score prediction, MRI computer-aided diagnosis, and surgical outcomes and biochemical recurrence prediction. Studies consistently found the superiority of these methods over traditional statistical methods. CONCLUSIONS: The continuous incorporation of clinical data, further ML and DL algorithm retraining, and generalizability of models will augment the prediction accuracy and enhance individualized medicine.
Asunto(s)
Carcinoma de Células Renales , Aprendizaje Profundo/tendencias , Neoplasias Renales , Aprendizaje Automático/tendencias , Neoplasias de la Próstata , Neoplasias de la Vejiga Urinaria , Urolitiasis , Urología/educación , Carcinoma de Células Renales/diagnóstico , Carcinoma de Células Renales/terapia , Predicción , Humanos , Neoplasias Renales/diagnóstico , Neoplasias Renales/terapia , Masculino , Neoplasias de la Próstata/diagnóstico , Neoplasias de la Próstata/terapia , Neoplasias de la Vejiga Urinaria/diagnóstico , Neoplasias de la Vejiga Urinaria/terapia , Urolitiasis/diagnóstico , Urolitiasis/terapiaRESUMEN
The estimation of human hand pose has become the basis for many vital applications where the user depends mainly on the hand pose as a system input. Virtual reality (VR) headset, shadow dexterous hand and in-air signature verification are a few examples of applications that require to track the hand movements in real-time. The state-of-the-art 3D hand pose estimation methods are based on the Convolutional Neural Network (CNN). These methods are implemented on Graphics Processing Units (GPUs) mainly due to their extensive computational requirements. However, GPUs are not suitable for the practical application scenarios, where the low power consumption is crucial. Furthermore, the difficulty of embedding a bulky GPU into a small device prevents the portability of such applications on mobile devices. The goal of this work is to provide an energy efficient solution for an existing depth camera based hand pose estimation algorithm. First, we compress the deep neural network model by applying the dynamic quantization techniques on different layers to achieve maximum compression without compromising accuracy. Afterwards, we design a custom hardware architecture. For our device we selected the FPGA as a target platform because FPGAs provide high energy efficiency and can be integrated in portable devices. Our solution implemented on Xilinx UltraScale+ MPSoC FPGA is 4.2× faster and 577.3× more energy efficient than the original implementation of the hand pose estimation algorithm on NVIDIA GeForce GTX 1070.
Asunto(s)
Algoritmos , Mano , Redes Neurales de la Computación , Humanos , Movimiento , Fenómenos FísicosRESUMEN
BACKGROUND: Mixed reality (MR), the computer-supported augmentation of a real environment with virtual elements, becomes ever more relevant in the medical domain, especially in urology, ranging from education and training over surgeries. We aimed to review existing MR technologies and their applications in urology. METHODS: A non-systematic review of current literature was performed using the PubMed-Medline database using the medical subject headings (MeSH) term "mixed reality", combined with one of the following terms: "virtual reality", "augmented reality", ''urology'' and "augmented virtuality". The relevant studies were utilized. RESULTS: MR applications such as MR guided systems, immersive VR headsets, AR models, MR-simulated ureteroscopy and smart glasses have enormous potential in education, training and surgical interventions of urology. Medical students, urology residents and inexperienced urologists can gain experience thanks to MR technologies. MR applications are also used in patient education before interventions. CONCLUSIONS: For surgical support, the achievable accuracy is often not sufficient. The main challenges are the non-rigid nature of the genitourinary organs, intraoperative data acquisition, online and multimodal registration and calibration of devices. However, the progress made in recent years is tremendous in all respects and the gap is constantly shrinking.
RESUMEN
We present a novel GPU-based algorithm for high-quality rendering of bivariate spline surfaces. An essential difference to the known methods for rendering graph surfaces is that we use quartic smooth splines on triangulations rather than triangular meshes. Our rendering approach is direct in the sense that since we do not use an intermediate tessellation but rather compute ray-surface intersections (by solving quartic equations numerically) as well as surface normals (by using Bernstein-Bézier techniques) for Phong illumination on the GPU. Inaccurate shading and artifacts appearing for triangular tesselated surfaces are completely avoided. Level of detail is automatic since all computations are done on a per fragment basis. We compare three different (quasi-) interpolating schemes for uniformly sampled gridded data, which differ in the smoothness and the approximation properties of the splines. The results show that our hardware based renderer leads to visualizations (including texturing, multiple light sources, environment mapping, etc.) of highest quality.