International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from t...
International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.
This article's main contributions are twofold: 1) to demonstrate how to apply the general European Union's High-Level Expert group's (EU HLEG) guidelines for trustworthy AI in practice for the domain of he...
详细信息
Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that parti...
详细信息
A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-M...
详细信息
Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG...
详细信息
Autism has primarily been characterized at a social-cognitive level, with evidence suggesting impairments in action-perception and motor function. However, there is a lack of publicly available datasets that specifica...
Autism has primarily been characterized at a social-cognitive level, with evidence suggesting impairments in action-perception and motor function. However, there is a lack of publicly available datasets that specifically address the neural and behavioral mechanisms linking these functions in autism. The Move4AS dataset aims to fill this gap, having been designed to facilitate the study of the underlying mechanisms of motor function in the autism spectrum. It combines multiple data modalities, including electroencephalography (EEG) and 3D motion data, collected during motor imitation tasks - dancing and walking - designed to recruit motor function in emotional and social contexts. It comprises a control group of 20 participants and a clinical group of 14 participants. EEG was recorded through a 16-channel wireless EEG cap, and 3D motion was captured using marker-based motion capture suits tracked by a 10-camera setup. Additionally, the dataset includes neuropsychological characterization of the participants (IQ and autism score).
Iron-rich deep brain nuclei (DBN) of the human brain are involved in various motoric, emotional and cognitive brain functions. The abnormal iron alterations in the DBN are closely associated with multiple neurological...
详细信息
Iron-rich deep brain nuclei (DBN) of the human brain are involved in various motoric, emotional and cognitive brain functions. The abnormal iron alterations in the DBN are closely associated with multiple neurological and psychiatric diseases. Quantitative susceptibility mapping (QSM) provides the spatial distribution of tissue magnetic susceptibility in the human brain. Compared to traditional structural imaging, QSM has superiority for imaging the iron-rich DBN owing to the susceptibility difference existing between brain tissues. In this study, we construct a Montreal Neurological Institute (MNI) space unbiased QSM human brain atlas via group-wise registration from 100 healthy subjects aged 19-29 years. The atlas construction process is guided by hybrid images that fused from multi-modal Magnetic Resonance Images (MRI), thus named as Multi-modal-fused magnetic Susceptibility (MuSus-100) atlas. The high-quality susceptibility atlas provides extraordinary image contrast between iron-rich DBN with their surroundings. Parcellation maps of DBN and their sub-regions that are highly related to neurological and psychiatric pathology are then manually labeled based on the atlas set with the assistance of an image border-enhancement process. Especially, the bilateral thalamus is delineated into 64 detailed sub-regions referring to the Schaltenbrand and Wahren stereotactic atlas. To our best knowledge, the histological-consistent thalamic nucleus parcellation map is well defined for the first time in MNI space. Comparing with existing atlases emphasized on DBN parcellation, the newly proposed atlas outperforms on atlas-guided individual brain image DBN segmentation accuracy and robustness. Moreover, we apply the proposed DBN parcellation map to conduct detailed identification of the pathology-related iron content alterations in subcortical nuclei for Parkinson Disease (PD) patients. We envision that the MuSus-100 atlas could play a crucial role in improving the accuracy of
The field of computervision applied to videos of minimally invasive surgery is ever-growing. Workflow recognition pertains to the automated recognition of various aspects of a surgery: including which surgical steps ...
详细信息
Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not ref...
详细信息
BigNeuron is an open community bench-testing platform with the goal of setting open standards for accurate and fast automatic neuron tracing. We gathered a diverse set of image volumes across several species that is r...
BigNeuron is an open community bench-testing platform with the goal of setting open standards for accurate and fast automatic neuron tracing. We gathered a diverse set of image volumes across several species that is representative of the data obtained in many neuroscience laboratories interested in neuron tracing. Here, we report generated gold standard manual annotations for a subset of the available imaging datasets and quantified tracing quality for 35 automatic tracing algorithms. The goal of generating such a hand-curated diverse dataset is to advance the development of tracing algorithms and enable generalizable benchmarking. Together with image quality features, we pooled the data in an interactive web application that enables users and developers to perform principal component analysis, t-distributed stochastic neighbor embedding, correlation and clustering, visualization of imaging and tracing data, and benchmarking of automatic tracing algorithms in user-defined data subsets. The image quality metrics explain most of the variance in the data, followed by neuromorphological features related to neuron size. We observed that diverse algorithms can provide complementary information to obtain accurate results and developed a method to iteratively combine methods and generate consensus reconstructions. The consensus trees obtained provide estimates of the neuron structure ground truth that typically outperform single algorithms in noisy datasets. However, specific algorithms may outperform the consensus tree strategy in specific imaging conditions. Finally, to aid users in predicting the most accurate automatic tracing results without manual annotations for comparison, we used support vector machine regression to predict reconstruction quality given an image volume and a set of automatic tracings.
暂无评论