Fundamentals of Arthroscopic Surgery Training and beyond: a reinforcement learning exploration and benchmark.

PURPOSE: This work presents FASTRL, a benchmark set of instrument manipulation tasks adapted to the domain of reinforcement learning and used in simulated surgical training. This benchmark enables and supports the design and training of human-centric reinforcement learning agents which assist and evaluate human trainees in surgical practice. METHODS: Simulation tasks from the Fundamentals of Arthroscopic Surgery Training (FAST) program are adapted to the reinforcement learning setting for the purpose of training virtual agents that are capable of providing assistance and scoring to the surgical trainees. A skill performance assessment protocol is presented based on the trained virtual agents. RESULTS: The proposed benchmark suite presents an API for training reinforcement learning agents in the context of arthroscopic skill training. The evaluation scheme based on both heuristic and learned reward functions robustly recovers the ground truth ranking on a diverse test set of human trajectories. CONCLUSION: The presented benchmark enables the exploration of a novel reinforcement learning-based approach to skill performance assessment and in-procedure assistance for simulated surgical training scenarios. The evaluation protocol based on the learned reward model demonstrates potential for evaluating the performance of surgical trainees in simulation.

ChromaX: a fast and scalable breeding program simulator.

SUMMARY: ChromaX is a Python library that enables the simulation of genetic recombination, genomic estimated breeding value calculations, and selection processes. By utilizing GPU processing, it can perform these simulations up to two orders of magnitude faster than existing tools with standard hardware. This offers breeders and scientists new opportunities to simulate genetic gain and optimize breeding schemes. AVAILABILITY AND IMPLEMENTATION: The documentation is available at https://chromax.readthedocs.io. The code is available at https://github.com/kora-labs/chromax.

Weakly supervised inference of personalized heart meshes based on echocardiography videos.

Echocardiography provides recordings of the heart chamber size and function and is a central tool for non-invasive diagnosis of heart diseases. It produces high-dimensional video data with substantial stochasticity in the measurements, which frequently prove difficult to interpret. To address this challenge, we propose an automated framework to enable the inference of a high resolution personalized 4D (3D plus time) surface mesh of the cardiac structures from 2D echocardiography video data. Inferring such shape models arises as a key step towards accurate personalized simulation that enables an automated assessment of the cardiac chamber morphology and function. The proposed method is trained using only unpaired echocardiography and heart mesh videos to find a mapping between these distinct visual domains in a self-supervised manner. The resulting model produces personalized 4D heart meshes, which exhibit a high correspondence with the input echocardiography videos. Furthermore, the 4D heart meshes enable the automatic extraction of echocardiographic variables, such as ejection fraction, myocardial muscle mass, and volumetric changes of chamber volumes over time with high temporal resolution.

Natural Age-Related Slow-Wave Sleep Alterations Onset Prematurely in the Tg2576 Mouse Model of Alzheimer's Disease.

INTRODUCTION: Sleep insufficiency or decreased quality have been associated with Alzheimer's disease (AD) already in its preclinical stages. Whether such traits are also present in rodent models of the disease has been poorly addressed, somewhat disabling the preclinical exploration of sleep-based therapeutic interventions for AD. METHODS: We investigated age-dependent sleep-wake phenotype of a widely used mouse model of AD, the Tg2576 line. We implanted electroencephalography/electromyography headpieces into 6-month-old (plaque-free, n = 10) and 11-month-old (moderate plaque-burdened, n = 10) Tg2576 mice and age-matched wild-type (WT, 6 months old n = 10, 11 months old n = 10) mice and recorded vigilance states for 24 h. RESULTS: Tg2576 mice exhibited significantly increased wakefulness and decreased non-rapid eye movement sleep over a 24-h period compared to WT mice at 6 but not at 11 months of age. Concomitantly, power in the delta frequency was decreased in 6-month old Tg2576 mice in comparison to age-matched WT controls, rendering a reduced slow-wave energy phenotype in the young mutants. Lack of genotype-related differences over 24 h in the overall sleep-wake phenotype at 11 months of age appears to be the result of changes in sleep-wake characteristics accompanying the healthy aging of WT mice. CONCLUSION: Therefore, our results indicate that at the plaque-free disease stage, diminished sleep quality is present in Tg2576 mice which resembles aged healthy controls, suggesting an early-onset of sleep-wake deterioration in murine AD. Whether such disturbances in the natural patterns of sleep could in turn worsen disease progression warrants further exploration.

Assessment of Artificial Intelligence in Echocardiography Diagnostics in Differentiating Takotsubo Syndrome From Myocardial Infarction.

Importance: Machine learning algorithms enable the automatic classification of cardiovascular diseases based on raw cardiac ultrasound imaging data. However, the utility of machine learning in distinguishing between takotsubo syndrome (TTS) and acute myocardial infarction (AMI) has not been studied. Objectives: To assess the utility of machine learning systems for automatic discrimination of TTS and AMI. Design, Settings, and Participants: This cohort study included clinical data and transthoracic echocardiogram results of patients with AMI from the Zurich Acute Coronary Syndrome Registry and patients with TTS obtained from 7 cardiovascular centers in the International Takotsubo Registry. Data from the validation cohort were obtained from April 2011 to February 2017. Data from the training cohort were obtained from March 2017 to May 2019. Data were analyzed from September 2019 to June 2021. Exposure: Transthoracic echocardiograms of 224 patients with TTS and 224 patients with AMI were analyzed. Main Outcomes and Measures: Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the machine learning system evaluated on an independent data set and 4 practicing cardiologists for comparison. Echocardiography videos of 228 patients were used in the development and training of a deep learning model. The performance of the automated echocardiogram video analysis method was evaluated on an independent data set consisting of 220 patients. Data were matched according to age, sex, and ST-segment elevation/non-ST-segment elevation (1 patient with AMI for each patient with TTS). Predictions were compared with echocardiographic-based interpretations from 4 practicing cardiologists in terms of sensitivity, specificity, and AUC calculated from confidence scores concerning their binary diagnosis. Results: In this cohort study, apical 2-chamber and 4-chamber echocardiographic views of 110 patients with TTS (mean [SD] age, 68.4 [12.1] years; 103 [90.4%] were female) and 110 patients with AMI (mean [SD] age, 69.1 [12.2] years; 103 [90.4%] were female) from an independent data set were evaluated. This approach achieved a mean (SD) AUC of 0.79 (0.01) with an overall accuracy of 74.8 (0.7%). In comparison, cardiologists achieved a mean (SD) AUC of 0.71 (0.03) and accuracy of 64.4 (3.5%) on the same data set. In a subanalysis based on 61 patients with apical TTS and 56 patients with AMI due to occlusion of the left anterior descending coronary artery, the model achieved a mean (SD) AUC score of 0.84 (0.01) and an accuracy of 78.6 (1.6%), outperforming the 4 practicing cardiologists (mean [SD] AUC, 0.72 [0.02]) and accuracy of 66.9 (2.8%). Conclusions and Relevance: In this cohort study, a real-time system for fully automated interpretation of echocardiogram videos was established and trained to differentiate TTS from AMI. While this system was more accurate than cardiologists in echocardiography-based disease classification, further studies are warranted for clinical application.

Automatic Detection of Atrial Fibrillation from Single-Lead ECG Using Deep Learning of the Cardiac Cycle.

Objective and Impact Statement. Atrial fibrillation (AF) is a serious medical condition that requires effective and timely treatment to prevent stroke. We explore deep neural networks (DNNs) for learning cardiac cycles and reliably detecting AF from single-lead electrocardiogram (ECG) signals. Introduction. Electrocardiograms are widely used for diagnosis of various cardiac dysfunctions including AF. The huge amount of collected ECGs and recent algorithmic advances to process time-series data with DNNs substantially improve the accuracy of the AF diagnosis. DNNs, however, are often designed as general purpose black-box models and lack interpretability of their decisions. Methods. We design a three-step pipeline for AF detection from ECGs. First, a recording is split into a sequence of individual heartbeats based on R-peak detection. Individual heartbeats are then encoded using a DNN that extracts interpretable features of a heartbeat by disentangling the duration of a heartbeat from its shape. Second, the sequence of heartbeat codes is passed to a DNN to combine a signal-level representation capturing heart rhythm. Third, the signal representations are passed to a DNN for detecting AF. Results. Our approach demonstrates a superior performance to existing ECG analysis methods on AF detection. Additionally, the method provides interpretations of the features extracted from heartbeats by DNNs and enables cardiologists to study ECGs in terms of the shapes of individual heartbeats and rhythm of the whole signals. Conclusion. By considering ECGs on two levels and employing DNNs for modelling of cardiac cycles, this work presents a method for reliable detection of AF from single-lead ECGs.

Self-supervised representation learning for surgical activity recognition.

PURPOSE: Virtual reality-based simulators have the potential to become an essential part of surgical education. To make full use of this potential, they must be able to automatically recognize activities performed by users and assess those. Since annotations of trajectories by human experts are expensive, there is a need for methods that can learn to recognize surgical activities in a data-efficient way. METHODS: We use self-supervised training of deep encoder-decoder architectures to learn representations of surgical trajectories from video data. These representations allow for semi-automatic extraction of features that capture information about semantically important events in the trajectories. Such features are processed as inputs of an unsupervised surgical activity recognition pipeline. RESULTS: Our experiments document that the performance of hidden semi-Markov models used for recognizing activities in a simulated myomectomy scenario benefits from using features extracted from representations learned while training a deep encoder-decoder network on the task of predicting the remaining surgery progress. CONCLUSION: Our work is an important first step in the direction of making efficient use of features obtained from deep representation learning for surgical activity recognition in settings where only a small fraction of the existing data is annotated by human domain experts and where those annotations are potentially incomplete.

Improving 1-year mortality prediction in ACS patients using machine learning.

BACKGROUND: The Global Registry of Acute Coronary Events (GRACE) score is an established clinical risk stratification tool for patients with acute coronary syndromes (ACS). We developed and internally validated a model for 1-year all-cause mortality prediction in ACS patients. METHODS: Between 2009 and 2012, 2'168 ACS patients were enrolled into the Swiss SPUM-ACS Cohort. Biomarkers were determined in 1'892 patients and follow-up was achieved in 95.8% of patients. 1-year all-cause mortality was 4.3% (n = 80). In our analysis we consider all linear models using combinations of 8 out of 56 variables to predict 1-year all-cause mortality and to derive a variable ranking. RESULTS: 1.3% of 1'420'494'075 models outperformed the GRACE 2.0 Score. The SPUM-ACS Score includes age, plasma glucose, NT-proBNP, left ventricular ejection fraction (LVEF), Killip class, history of peripheral artery disease (PAD), malignancy, and cardio-pulmonary resuscitation. For predicting 1-year mortality after ACS, the SPUM-ACS Score outperformed the GRACE 2.0 Score which achieves a 5-fold cross-validated AUC of 0.81 (95% CI 0.78-0.84). Ranking individual features according to their importance across all multivariate models revealed age, trimethylamine N-oxide, creatinine, history of PAD or malignancy, LVEF, and haemoglobin as the most relevant variables for predicting 1-year mortality. CONCLUSIONS: The variable ranking and the selection for the SPUM-ACS Score highlight the relevance of age, markers of heart failure, and comorbidities for prediction of all-cause death. Before application, this score needs to be externally validated and refined in larger cohorts. CLINICAL TRIAL REGISTRATION: NCT01000701.

Neural collaborative filtering for unsupervised mitral valve segmentation in echocardiography.

The segmentation of the mitral valve annulus and leaflets specifies a crucial first step to establish a machine learning pipeline that can support physicians in performing multiple tasks, e.g. diagnosis of mitral valve diseases, surgical planning, and intraoperative procedures. Current methods for mitral valve segmentation on 2D echocardiography videos require extensive interaction with annotators and perform poorly on low-quality and noisy videos. We propose an automated and unsupervised method for the mitral valve segmentation based on a low dimensional embedding of the echocardiography videos using neural network collaborative filtering. The method is evaluated in a collection of echocardiography videos of patients with a variety of mitral valve diseases, and additionally on an independent test cohort. It outperforms state-of-the-art unsupervised and supervised methods on low-quality videos or in the case of sparse annotation.

SPINDLE: End-to-end learning from EEG/EMG to extrapolate animal sleep scoring across experimental settings, labs and species.

Understanding sleep and its perturbation by environment, mutation, or medication remains a central problem in biomedical research. Its examination in animal models rests on brain state analysis via classification of electroencephalographic (EEG) signatures. Traditionally, these states are classified by trained human experts by visual inspection of raw EEG recordings, which is a laborious task prone to inter-individual variability. Recently, machine learning approaches have been developed to automate this process, but their generalization capabilities are often insufficient, especially across animals from different experimental studies. To address this challenge, we crafted a convolutional neural network-based architecture to produce domain invariant predictions, and furthermore integrated a hidden Markov model to constrain state dynamics based upon known sleep physiology. Our method, which we named SPINDLE (Sleep Phase Identification with Neural networks for Domain-invariant LEearning) was validated using data of four animal cohorts from three independent sleep labs, and achieved average agreement rates of 99%, 98%, 93%, and 97% with scorings from five human experts from different labs, essentially duplicating human capability. It generalized across different genetic mutants, surgery procedures, recording setups and even different species, far exceeding state-of-the-art solutions that we tested in parallel on this task. Moreover, we show that these scored data can be processed for downstream analyzes identical to those from human-scored data, in particular by demonstrating the ability to detect mutation-induced sleep alteration. We provide to the scientific community free usage of SPINDLE and benchmarking datasets as an online server at https://sleeplearning.ethz.ch. Our aim is to catalyze high-throughput and well-standardized experimental studies in order to improve our understanding of sleep.

Pipeline validation for connectivity-based cortex parcellation.

Structural connectivity plays a dominant role in brain function and arguably lies at the core of understanding the structure-function relationship in the cerebral cortex. Connectivity-based cortex parcellation (CCP), a framework to process structural connectivity information gained from diffusion MRI and diffusion tractography, identifies cortical subunits that furnish functional inference. The underlying pipeline of algorithms interprets similarity in structural connectivity as a segregation criterion. Validation of the CCP-pipeline is critical to gain scientific reliability of the algorithmic processing steps from dMRI data to voxel grouping. In this paper we provide a proof of concept based upon a novel model validation principle that characterizes the trade-off between informativeness and robustness to assess the validity of the CCP pipeline, including diffusion tractography and clustering. We ultimately identify a pipeline of algorithms and parameter settings that tolerate more noise and extract more information from the data than their alternatives.

A generative model of whole-brain effective connectivity.

The development of whole-brain models that can infer effective (directed) connection strengths from fMRI data represents a central challenge for computational neuroimaging. A recently introduced generative model of fMRI data, regression dynamic causal modeling (rDCM), moves towards this goal as it scales gracefully to very large networks. However, large-scale networks with thousands of connections are difficult to interpret; additionally, one typically lacks information (data points per free parameter) for precise estimation of all model parameters. This paper introduces sparsity constraints to the variational Bayesian framework of rDCM as a solution to these problems in the domain of task-based fMRI. This sparse rDCM approach enables highly efficient effective connectivity analyses in whole-brain networks and does not require a priori assumptions about the network's connectivity structure but prunes fully (all-to-all) connected networks as part of model inversion. Following the derivation of the variational Bayesian update equations for sparse rDCM, we use both simulated and empirical data to assess the face validity of the model. In particular, we show that it is feasible to infer effective connection strengths from fMRI data using a network with more than 100 regions and 10,000 connections. This demonstrates the feasibility of whole-brain inference on effective connectivity from fMRI data - in single subjects and with a run-time below 1 min when using parallelized code. We anticipate that sparse rDCM may find useful application in connectomics and clinical neuromodeling - for example, for phenotyping individual patients in terms of whole-brain network structure.

Semiautomatic Assessment of the Terminal Ileum and Colon in Patients with Crohn Disease Using MRI (the VIGOR++ Project).

RATIONALE AND OBJECTIVES: The objective of this study was to develop and validate a predictive magnetic resonance imaging (MRI) activity score for ileocolonic Crohn disease activity based on both subjective and semiautomatic MRI features. MATERIALS AND METHODS: An MRI activity score (the "virtual gastrointestinal tract [VIGOR]" score) was developed from 27 validated magnetic resonance enterography datasets, including subjective radiologist observation of mural T2 signal and semiautomatic measurements of bowel wall thickness, excess volume, and dynamic contrast enhancement (initial slope of increase). A second subjective score was developed based on only radiologist observations. For validation, two observers applied both scores and three existing scores to a prospective dataset of 106 patients (59 women, median age 33) with known Crohn disease, using the endoscopic Crohn's Disease Endoscopic Index of Severity (CDEIS) as a reference standard. RESULTS: The VIGOR score (17.1 × initial slope of increase + 0.2 × excess volume + 2.3 × mural T2) and other activity scores all had comparable correlation to the CDEIS scores (observer 1: r = 0.58 and 0.59, and observer 2: r = 0.34-0.40 and 0.43-0.51, respectively). The VIGOR score, however, improved interobserver agreement compared to the other activity scores (intraclass correlation coefficient = 0.81 vs 0.44-0.59). A diagnostic accuracy of 80%-81% was seen for the VIGOR score, similar to the other scores. CONCLUSIONS: The VIGOR score achieves comparable accuracy to conventional MRI activity scores, but with significantly improved reproducibility, favoring its use for disease monitoring and therapy evaluation.

Regression DCM for fMRI.

The development of large-scale network models that infer the effective (directed) connectivity among neuronal populations from neuroimaging data represents a key challenge for computational neuroscience. Dynamic causal models (DCMs) of neuroimaging and electrophysiological data are frequently used for inferring effective connectivity but are presently restricted to small graphs (typically up to 10 regions) in order to keep model inversion computationally feasible. Here, we present a novel variant of DCM for functional magnetic resonance imaging (fMRI) data that is suited to assess effective connectivity in large (whole-brain) networks. The approach rests on translating a linear DCM into the frequency domain and reformulating it as a special case of Bayesian linear regression. This paper derives regression DCM (rDCM) in detail and presents a variational Bayesian inversion method that enables extremely fast inference and accelerates model inversion by several orders of magnitude compared to classical DCM. Using both simulated and empirical data, we demonstrate the face validity of rDCM under different settings of signal-to-noise ratio (SNR) and repetition time (TR) of fMRI data. In particular, we assess the potential utility of rDCM as a tool for whole-brain connectomics by challenging it to infer effective connection strengths in a simulated whole-brain network comprising 66 regions and 300 free parameters. Our results indicate that rDCM represents a computationally highly efficient approach with promising potential for inferring whole-brain connectivity from individual fMRI data.

Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation.

We present a novel method to segment retinal images using ensemble learning based convolutional neural network (CNN) architectures. An entropy sampling technique is used to select informative points thus reducing computational complexity while performing superior to uniform sampling. The sampled points are used to design a novel learning framework for convolutional filters based on boosting. Filters are learned in several layers with the output of previous layers serving as the input to the next layer. A softmax logistic classifier is subsequently trained on the output of all learned filters and applied on test images. The output of the classifier is subject to an unsupervised graph cut algorithm followed by a convex hull transformation to obtain the final segmentation. Our proposed algorithm for optic cup and disc segmentation outperforms existing methods on the public DRISHTI-GS data set on several metrics.

Image-based computational quantification and visualization of genetic alterations and tumour heterogeneity.

Recent large-scale genome analyses of human tissue samples have uncovered a high degree of genetic alterations and tumour heterogeneity in most tumour entities, independent of morphological phenotypes and histopathological characteristics. Assessment of genetic copy-number variation (CNV) and tumour heterogeneity by fluorescence in situ hybridization (ISH) provides additional tissue morphology at single-cell resolution, but it is labour intensive with limited throughput and high inter-observer variability. We present an integrative method combining bright-field dual-colour chromogenic and silver ISH assays with an image-based computational workflow (ISHProfiler), for accurate detection of molecular signals, high-throughput evaluation of CNV, expressive visualization of multi-level heterogeneity (cellular, inter- and intra-tumour heterogeneity), and objective quantification of heterogeneous genetic deletions (PTEN) and amplifications (19q12, HER2) in diverse human tumours (prostate, endometrial, ovarian and gastric), using various tissue sizes and different scanners, with unprecedented throughput and reproducibility.

Active learning based segmentation of Crohns disease from abdominal MRI.

This paper proposes a novel active learning (AL) framework, and combines it with semi supervised learning (SSL) for segmenting Crohns disease (CD) tissues from abdominal magnetic resonance (MR) images. Robust fully supervised learning (FSL) based classifiers require lots of labeled data of different disease severities. Obtaining such data is time consuming and requires considerable expertise. SSL methods use a few labeled samples, and leverage the information from many unlabeled samples to train an accurate classifier. AL queries labels of most informative samples and maximizes gain from the labeling effort. Our primary contribution is in designing a query strategy that combines novel context information with classification uncertainty and feature similarity. Combining SSL and AL gives a robust segmentation method that: (1) optimally uses few labeled samples and many unlabeled samples; and (2) requires lower training time. Experimental results show our method achieves higher segmentation accuracy than FSL methods with fewer samples and reduced training effort.

Is There an Association Between Pain and Magnetic Resonance Imaging Parameters in Patients With Lumbar Spinal Stenosis?

STUDY DESIGN: A prospective multicenter cohort study. OBJECTIVE: The aim of this study was to identify an association between pain and magnetic resonance imaging (MRI) parameters in patients with lumbar spinal stenosis (LSS). SUMMARY OF BACKGROUND DATA: At present, the relationship between abnormal MRI findings and pain in patients with LSS is still unclear. METHODS: First, we conducted a systematic literature search. We identified relationships of relevant MRI parameters and pain in patients with LSS. Second, we addressed the study question with a thorough descriptive and graphical analysis to establish a relationship between MRI parameters and pain using data of the LSS outcome study (LSOS). RESULTS: In the systematic review including four papers about the associations between radiological findings in the MRI and pain, the authors of two articles reported no association and two of them did. Of the latters, only one study found a moderate correlation between leg pain measured by Visual Analog Scale (VAS) and the degree of stenosis assessed by spine surgeons. In the data of the LSOS study, we could not identify a relevant association between any of the MRI parameters and buttock, leg, and back pain, quantified by the Spinal Stenosis Measure (SSM) and the Numeric Rating Scale (NRS). Even by restricting the analysis to the level of the lumbar spine with the most prominent radiological "stenosis," no relevant association could be shown. CONCLUSION: Despite a thorough analysis of the data, we were not able to prove any correlation between radiological findings (MRI) and the severity of pain. There is a need for innovative "methods/techniques" to learn more about the causal relationship between radiological findings and the patients' pain-related complaints. LEVEL OF EVIDENCE: 2.

Visual saliency-based active learning for prostate magnetic resonance imaging segmentation.

We propose an active learning (AL) approach for prostate segmentation from magnetic resonance images. Our label query strategy is inspired from the principles of visual saliency that have similar considerations for choosing the most salient region. These similarities are encoded in a graph using classification maps and low-level features. Random walks are used to identify the most informative node, which is equivalent to the label query sample in AL. To reduce computation time, a volume of interest (VOI) is identified and all subsequent analysis, such as probability map generation using semisupervised random forest classifiers and label query, is restricted to this VOI. The negative log-likelihood of the probability maps serves as the penalty cost in a second-order Markov random field cost function, which is optimized using graph cuts for prostate segmentation. Experimental results on the Medical Image Computing and Computer Assisted Intervention (MICCAI) 2012 prostate segmentation challenge show the superior performance of our approach to conventional methods using fully supervised learning.

Crowdsourcing the creation of image segmentation algorithms for connectomics.

To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test set of images, and were scored based on their agreement with a consensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This "deep learning" approach has since become accepted as a standard for segmentation of EM images. The challenge has continued to accept submissions, and the best so far has resulted from cooperation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test dataset. Retrospective evaluation of the challenge scoring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge.