Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all the supervised deep learning applications, data is the most ...critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g., visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between.
In our framework, an expert reviews the video and annotates a few video frames to verify the object's annotations for the non-expert. In a second step, a non-expert has visual confirmation of the given object and can annotate all following and preceding frames with AI assistance. After the expert has finished, relevant frames will be selected and passed on to an AI model. This information allows the AI model to detect and mark the desired object on all following and preceding frames with an annotation. Therefore, the non-expert can adjust and modify the AI predictions and export the results, which can then be used to train the AI model.
Using this framework, we were able to reduce workload of domain experts on average by a factor of 20 on our data. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated AI model enhances the annotation speed further. Through a prospective study with 10 participants, we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool.
In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.
•EndoCV2020, an endoscopy computer vision challenge addresses eminent problems in endoscopy.•Deep learning methods built to address artefacts and disease categories.•Comprehensive dataset comprising ...multi-center, multi-organ, multi-modal and multi-class.•Over 47,000 annotations and 3440 frames publicly released.•Detection and segmentation algorithms are devised, compared and dissected.•Hypothesis formulated to identify the gaps in current methods.
Display omitted
The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.
Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. ...However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24% on the open-source CVC-VideoClinicDB benchmark.
Myocardial depression is a frequent event during septic shock and may mimic a cardiogenic shock state with decreased cardiac output. Nevertheless, data are scarce regarding the myocardial effects of ...vasopressors used to treat hypotension. In this study, the authors compared the effects of three commonly used vasopressors acting on different adrenergic receptors on myocardial function in a rodent model of septic shock, as explored with conductance catheter and positron emission tomography.
Septic shock was induced in rats by peritonitis. Eighteen hours after septic insult, vasopressors were titrated to increase mean arterial pressure by 20% compared with baseline values.
We observed that peritonitis was associated with arterial hypotension and systolodiastolic dysfunction. Norepinephrine and epinephrine improved mean arterial pressure, cardiac output, and preload recruitable stroke work, a load-independent measure of systolic function, as well as diastolic function and ventriculoarterial coupling. Heart rate, myocardial oxygen consumption, and arrhythmia incidence were furthermore increased in the epinephrine group. Conversely, phenylephrine, a peripheral α-agonist, exhibited deleterious effects on systolodiastolic function and ventriculoarterial coupling. Conductance catheter and positron emission tomography yielded identical results with regard to myocardial function evolution under vasopressor treatment.
Phenylephrine, a drug without β-1 effects, was associated with decreased ventricular performance and ventriculoarterial uncoupling, whereas epinephrine and norepinephrine improved global hemodynamics and myocardial function in severely hypokinetic and hypotensive experimental septic shock. Nevertheless, epinephrine was associated with increased myocardial oxygen consumption. Thus, norepinephrine appears to be a more reliable and safer strategy as a first-line therapy in this particular setting.
Federated learning enables the training of machine learning models on distributed data without compromising user privacy, as data remains on personal devices and only model updates, such as ...gradients, are shared with a central coordinator. However, recent research has shown that the central entity can perfectly reconstruct private data from shared model updates by maliciously initializing the model's parameters. In this paper, we propose QBI, a novel bias initialization method that significantly enhances reconstruction capabilities. This is accomplished by directly solving for bias values yielding sparse activation patterns. Further, we propose PAIRS, an algorithm that builds on QBI. PAIRS can be deployed when a separate dataset from the target domain is available to further increase the percentage of data that can be fully recovered. Measured by the percentage of samples that can be perfectly reconstructed from batches of various sizes, our approach achieves significant improvements over previous methods with gains of up to 50% on ImageNet and up to 60% on the IMDB sentiment analysis text dataset. Furthermore, we establish theoretical limits for attacks leveraging stochastic gradient sparsity, providing a foundation for understanding the fundamental constraints of these attacks. We empirically assess these limits using synthetic datasets. Finally, we propose and evaluate AGGP, a defensive framework designed to prevent gradient sparsity attacks, contributing to the development of more secure and private federated learning systems.
The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest ...a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.