Digital histopathology poses several challenges such as label noise, class imbalance, limited availability of labelled data, and several latent biases to deep learning, negatively influencing transparency, reproducibility, and classification performance. In particular, biases are well known to cause poor generalization. Proposed tools from explainable artificial intelligence (XAI), bias detection, and bias discovery suffer from technical challenges, complexity, unintuitive usage, inherent biases, or a semantic gap. A promising XAI method, not studied in the context of digital histopathology is automated concept-based explanation (ACE). It automatically extracts visual concepts from image data. Our objective is to evaluate ACE’s technical validity following design science principals and to compare it to Guided Gradient-weighted Class Activation Mapping (Grad-CAM), a conventional pixel-wise explanation method. To that extent, we created and studied five convolutional neural networks (CNNs) in four different skin cancer settings. Our results demonstrate that ACE is a valid tool for gaining insights into the decision process of histopathological CNNs that can go beyond explanations from the control method. ACE validly visualized a class sampling ratio bias, measurement bias, sampling bias, and class-correlated bias. Furthermore, the complementary use with Guided Grad-CAM offers several benefits. Finally, we propose practical solutions for several technical challenges. In contradiction to results from the literature, we noticed lower intuitiveness in some dermatopathology scenarios as compared to concept-based explanations on real-world images.

Accurate synchronization between magnetic resonance imaging data acquisition and a subject’s cardiac activity (“triggering”) is essential for reducing image artifacts but conventional, contact-based methods for this task are limited by several factors, including preparation time, patient inconvenience, and susceptibility to signal degradation. The purpose of this work is to evaluate the performance of a new contact-free triggering method developed with the aim to eventually replace conventional methods in non-cardiac imaging applications. In this study, the method’s performance is evaluated in the context of 7 Tesla non-enhanced angiography of the lower extremities. Our main contribution is a basic algorithm capable of estimating in real-time the phase of the cardiac cycle from reflection photoplethysmography signals obtained from skin color variations of the forehead recorded with a video camera. Instead of finding the algorithm’s parameters heuristically, they were optimized using videos of the forehead as well as electrocardiography and pulse oximetry signals that were recorded from eight healthy volunteers in and outside the scanner, with and without active radio frequency and gradient coils. Based on the video characteristics, synthetic signals were generated and the “best available” values of an objective function were determined using mathematical optimization. The performance of the proposed method with optimized algorithm parameters was evaluated by applying it to the recorded videos and comparing the computed triggers to those of contact-based methods. Additionally, the method was evaluated by using its triggers for acquiring images from a healthy volunteer and comparing the result to images obtained using pulse oximetry triggering. During evaluation of the videos recorded inside the bore with active radio frequency and gradient coils, the pulse oximeter triggers were labeled in 62.5% as “potentially usable” for cardiac triggering, the electrocardiography triggers in 12.5%, and the proposed method’s triggers in 62.5%. Evaluation of the angiography images demonstrated that under appropriate conditions the method is feasible to produce an image quality comparable to pulse oximetry. We conclude that cardiac triggering using the proposed method is technically feasible. However, for improved reliability the signal-to-noise ratio of the videos will have to be addressed by either replacing the camera sensor, improving the illumination, or by use of additional signal filtering techniques.

The continuing interest in unobtrusive electrocardiography requires the development of algorithms, compensating for an increased number of artifacts. In previous work, we proposed a framework for robust parameter estimation of signals following a piecewise Gaussian derivative model, well suited for describing all waves of a heartbeat. The framework is based on a numeric and analytic representation of applying the Wavelet Transform at arbitrary scale to the input model. For robustly estimating model parameters, it processes lines of zero-crossings in scale-space, showing high accuracy for various noise models in synthetic signals. An initial evaluation with electrocardiography signals revealed that our basic classifier for identifying the correct lines often fails, leading to false parameter estimates. In this work, we propose a general delineation method based on a solid mathematical framework that treats each heartbeat, wave and fiducial point in the same way, tailored only by intuitive parameters and not relying on any heuristically found decision rules. The steps include a novel line classifier based on pre-filtering using domain knowledge, followed by an exhaustive search among all possible combinations of zero-crossing lines and an error-measure quantifying their agreement with the model. The combination with highest agreement is processed by the parameter estimation framework, customized to the computation of all nine fiducial points. Evaluation using the expert-annotated QT database, shows high sensitivity (P: 99.91%, QRS: 99.92%, T: 99.89%) and mean errors below 1ms for all onset and offset fiducial points. The proposed combination of line classification and parameter estimation is well suited for delineating electrocardiograms.

In sport science, athlete tracking and motion analysis are essential for monitoring and optimizing training programs, with the goal of increasing success in competition and preventing injury. At present, contact-free, camera-based, multi-athlete detection and tracking have become a reality, mainly due to the advances in machine learning regarding computer vision and, specifically, advances in artificial convolutional neural networks (CNN), used for human pose estimation (HPE-CNN) in image sequences. Sport science in general, as well as coaches and athletes in particular, would greatly benefit from HPE-CNN-based tracking, but the sheer amount of HPE-CNNs available, as well as their complexity, pose a hurdle to the adoption of this new technology. It is unclear how many HPE-CNNs which are available at present are ready to use in out-of-the-box inference to squash, to what extent they allow motion analysis and if detections can easily be used to provide insight to coaches and athletes. Therefore, we conducted a systematic investigation of more than 250 HPE-CNNs. After applying our selection criteria of open-source, pre-trained, state-of-the-art and ready-to-use, five variants of three HPE-CNNs remained, and were evaluated in the context of motion analysis for the racket sport of squash. Specifically, we are interested in detecting player’s feet in videos from a single camera and investigated the detection accuracy of all HPE-CNNs. To that end, we created a ground-truth dataset from publicly available squash videos by developing our own annotation tool and manually labeling frames and events. We present heatmaps, which depict the court floor using a color scale and highlight areas according to the relative time for which a player occupied that location during matchplay. These are used to provide insight into detections. Finally, we created a decision flow chart to help sport scientists, coaches and athletes to decide which HPE-CNN is best for player detection and tracking in a given application scenario.

Videos of the human skin contain subtle color variations associated with the blood volume pulse. This remote photoplethysmography signal can be used for heart rate monitoring and represents an alternative to signals obtained from contact-based hardware. We developed an algorithm that estimates the heart rate in real-time from photoplethysmography signals and evaluate its performance in the context of ultra-high-field magnetic resonance imaging. We compare its accuracy to heart rate values estimated from electrocardiography and finger pulse oximetry triggers, obtained from MR vendor-provided hardware. For eight subjects, two experiments are conducted with the patient table outside and inside a 7 Tesla scanner. During both 5 min setups, heart rates from the algorithm and contact-based methods are stored. Their comparison suggests technical feasibility of the contactless method but that it is inferior in accuracy compared to contact-based hardware and that low heart rates (≤50 beats per minute) and adequate illumination are major challenges for practical feasibility.

We present our results of applying wavelet theory to the classic problem of estimating the unknown parameters of a model function subject to noise. The model function studied in this context is a generalization of the second order Gaussian derivative of which the Gaussian function is a special case. For all five model parameters (amplitude, width, location, baseline, undershoot-size), scale-dependent algebraic expressions are derived. Based on this analytical framework, our first method estimates all parameters by substituting into a given expression numerically obtained values, such as the zero-crossings of the multiscale decompositions of the noisy input signal, using Gaussian derivative wavelets. Our second method takes these estimates as starting values for iterative least-squares optimization to fit our algebraic zero-crossing model to observed numeric zero-crossings in scale-space. For evaluation, we apply our method together with three reference methods to the three-parameter Gaussian model function. The results show that our method is on average 3.7 times more accurate than the respective best reference method for signal-to-noise-ratios (SNR) from -10 to 70 dB, using a synthetic test scenario proposed by a competitor. For our full five-parameter model we investigate overall estimation error as well as per-parameter error and -uncertainty as a function of SNR and various noise models, including correlated noise. To demonstrate practical effectiveness and relevance, we apply our method to the well-studied problem of QRS complex delineation in electrocardiography signals. Out-of-the-box results show a performance comparable to the best algorithms known to date, without relying on problem-specific heuristic decision rules.