For a unified analysis of medical images from different modalities, data harmonization using image-to-image (I2I) translation is desired. We study this problem employing an optical coherence tomography (OCT) data set of Spectralis-OCT and Home-OCT images. I2I translation is challenging because the images are unpaired, and a bijective mapping does not exist due to the information discrepancy between both domains. This problem has been addressed by the Contrastive Learning for Unpaired I2I Translation (CUT) approach, but it reduces semantic consistency. To restore the semantic consistency, we support the style decoder using an additional segmentation decoder. Our approach increases the similarity between the style-translated images and the target distribution. Importantly, we improve the segmentation of biomarkers in Home-OCT images in an unsupervised domain adaptation scenario. Our data harmonization approach provides potential for the monitoring of diseases, e.g., age related macular disease, using different OCT devices.
Generative adversarial networks (GANs) are currently rarely applied on 3D medical images of large size, due to their immense computational demand. The present work proposes a multi-scale patch-based GAN approach for establishing unpaired domain translation by generating 3D medical image volumes of high resolution in a memory-efficient way. The key idea to enable memory-efficient image generation is to first generate a low-resolution version of the image followed by the generation of patches of constant sizes but successively growing resolutions. To avoid patch artifacts and incorporate global information, the patch generation is conditioned on patches from previous resolution scales. Those multi-scale GANs are trained to generate realistically looking images from image sketches in order to perform an unpaired domain translation. This allows to preserve the topology of the test data and generate the appearance of the training domain data. The evaluation of the domain translation scenarios is performed on brain MRIs of size 155x240x240 and thorax CTs of size up to 512x512x512. Compared to common patch-based approaches, the multi-resolution scheme enables better image quality and prevents patch artifacts. Also, it ensures constant GPU memory demand independent from the image size, allowing for the generation of arbitrarily large images.
The treatment of age-related macular degeneration (AMD) requires continuous eye exams using optical coherence tomography (OCT). The need for treatment is determined by the presence or change of disease-specific OCT-based biomarkers. Therefore, the monitoring frequency has a significant influence on the success of AMD therapy. However, the monitoring frequency of current treatment schemes is not individually adapted to the patient and therefore often insufficient. While a higher monitoring frequency would have a positive effect on the success of treatment, in practice it can only be achieved with a home monitoring solution. One of the key requirements of a home monitoring OCT system is a computer-aided diagnosis to automatically detect and quantify pathological changes using specific OCT-based biomarkers. In this paper, for the first time, retinal scans of a novel self-examination low-cost full-field OCT (SELF-OCT) are segmented using a deep learning-based approach. A convolutional neural network (CNN) is utilized to segment the total retina as well as pigment epithelial detachments (PED). It is shown that the CNN-based approach can segment the retina with high accuracy, whereas the segmentation of the PED proves to be challenging. In addition, a convolutional denoising autoencoder (CDAE) refines the CNN prediction, which has previously learned retinal shape information. It is shown that the CDAE refinement can correct segmentation errors caused by artifacts in the OCT image.
Purpose: Radio-frequency ablations play an important role in the therapy of malignant liver lesions. The navigation of a needle to the lesion poses a challenge for both the trainees and intervening physicians. Methods: This publication presents a new GPU-based, accurate method for the simulation of radio-frequency ablations for lesions at the needle tip in general and for an existing visuo-haptic 4D VR simulator. The method is implemented real-time capable with Nvidia CUDA. Results: It performs better than a literature method concerning the theoretical characteristic of monotonic convergence of the bioheat PDE and a in vitro gold standard with significant improvements (p < 0.05) in terms of Pearson correlations. It shows no failure modes or theoretically inconsistent individual simulation results after the initial phase of 10 seconds. On the Nvidia 1080 Ti GPU it achieves a very high frame rendering performance of >480 Hz. Conclusion: Our method provides a more robust and safer real-time ablation planning and intraoperative guidance technique, especially avoiding the over-estimation of the ablated tissue death zone, which is risky for the patient in terms of tumor recurrence. Future in vitro measurements and optimization shall further improve the conservative estimate.
Currently generative adversarial networks (GANs) are rarely applied to medical images of large sizes, especially 3D volumes, due to their large computational demand. We propose a novel multi-scale patch-based GAN approach to generate large high resolution 2D and 3D images. Our key idea is to first learn a low-resolution version of the image and then generate patches of successively growing resolutions conditioned on previous scales. In a domain translation use-case scenario, 3D thorax CTs of size 512x512x512 and thorax X-rays of size 2048x2048 are generated and we show that, due to the constant GPU memory demand of our method, arbitrarily large images of high resolution can be generated. Moreover, compared to common patch-based approaches, our multi-resolution scheme enables better image quality and prevents patch artifacts.
We present a novel algorithm for the registration of pulmonary CT scans. Our method is designed for large respiratory motion by integrating sparse keypoint correspondences into a dense continuous optimization framework. The detection of keypoint correspondences enables robustness against large deformations by jointly optimizing over a large number of potential discrete displacements, whereas the dense continuous registration achieves subvoxel alignment with smooth transformations. Both steps are driven by the same normalized gradient fields data term. We employ curvature regularization and a volume change control mechanism to prevent foldings of the deformation grid and restrict the determinant of the Jacobian to physiologically meaningful values. Keypoint correspondences are integrated into the dense registration by a quadratic penalty with adaptively determined weight. Using a parallel matrix-free derivative calculation scheme, a runtime of about 5 min was realized on a standard PC. The proposed algorithm ranks first in the EMPIRE10 challenge on pulmonary image registration. Moreover, it achieves an average landmark distance of 0.82 mm on the DIR-Lab COPD database, thereby improving upon the state of the art in accuracy by 15%. Our algorithm is the first to reach the inter-observer variability in landmark annotation on this dataset.
Virtual reality (VR) training simulators of liver needle insertion in the hepatic area of breathing virtual patients currently need 4D data acquisitions as a prerequisite. Here, first a population-based breathing virtual patient 4D atlas can be built and second the requirement of a dose-relevant or expensive acquisition of a 4D data set for a new static 3D patient can be mitigated by warping the mean atlas motion. The breakthrough contribution of this work is the construction and reuse of population-based learned 4D motion models.
Current virtual reality (VR) training simulators of liver punctures often rely on static 3D patient data and use an unrealistic (sinusoidal) periodic animation of the respiratory movement. Existing methods for the animation of breathing motion support simple mathematical or patient-specific, estimated breathing models. However with personalized breathing models for each new patient, a heavily dose relevant or expensive 4D data acquisition is mandatory for keyframe-based motion modeling. Given the reference 4D data, first a model building stage using linear regression motion field modeling takes place. Then the methodology shown here allows the transfer of existing reference respiratory motion models of a 4D reference patient to a new static 3D patient. This goal is achieved by using non-linear inter-patient registration to warp one personalized 4D motion field model to new 3D patient data. This cost- and dose-saving new method is shown here visually in a qualitative proof-of-concept study.
This work presents an evaluation study using a force feedback evaluation framework for a novel direct needle force volume rendering concept in the context of liver puncture simulation. PTC/PTCD puncture interventions targeting the bile ducts have been selected to illustrate this concept. The haptic algorithms of the simulator system are based on (1) partially segmented patient image data and (2) a non-linear spring model effective at organ borders. The primary aim is to quantitatively evaluate force errors caused by our patient modeling approach, in comparison to haptic force output obtained from using gold-standard, completely manually-segmented data. The evaluation of the force algorithms compared to a force output from fully manually segmented gold-standard patient models, yields a low mean of 0.12 N root mean squared force error and up to 1.6 N for systematic maximum absolute errors. Force errors were evaluated on 31,222 preplanned test paths from 10 patients. Only twelve percent of the emitted forces along these paths were affected by errors. This is the first study evaluating haptic algorithms with deformable virtual patients in silico. We prove haptic rendering plausibility on a very high number of test paths. Important errors are below just noticeable differences for the hand-arm system.