DesR349P Mutation Results in Ultrastructural Disruptions and Compromise of Skeletal Muscle Biomechanics Already at Preclinical Stages in Young Mice before the Onset of Protein Aggregation

Diermeier, Stefanie; Haug, Michael; Reischl, Barbara; Buttgereit, Andreas; Schürmann, Sebastian; Spörrer, Marina; Goldmann, Wolfgang H.; Fabry, Ben; Elhimine, F.; Stehle, Robert; Pfitzer, Gabriele; Winter, Lilli; Clemen, Christoph S.; Schröder, Rolf; Friedrich, Oliver

doi:10.1016/j.bpj.2015.11.1629

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1), ML and especially DL are severely limited due to overfitting. Based on the identified associations of the same priors with the investigated labels in previous studies 5, 13, 35, 36 , we hypothesize that our muscle-specific learning tasks are related and the mean predictive performance over all tasks may assist SEMPAI to select a regularized model. Therefore, a total meta-loss is introduced, which is a weighted sum of all meta-losses for each task and provides an estimate of the model performance over all tasks.…”

Section: Resultsmentioning

confidence: 87%

“…In brief, these features include the cosine angle sum (CAS) taken from selected 2D planes (2D-CAS) and in 3D (3D-CAS), the vernier density (VD), the 3D sarcomere length (3D-SL), and the crosssectional area (CSA) of single fibers. Since these features have already been shown to be descriptive for a variety of rather specific remodeling patterns in muscle research, related to aging, chronic degenerative or inflammatory myopathies 5, 13, 35, 36 , we use them as prior information, and term them accordingly as priors . A more elaborate explanation of the extraction of priors is given in the Methods.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology

Mühlberg

Ritter

Langer

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning (DL) shows notable success in biomedical studies. However, most DL algorithms work as a black box, exclude biomedical experts, and need extensive data. We introduce the Self-Enhancing Multi-Photon Artificial Intelligence (SEMPAI), that integrates hypothesis-driven priors in a data-driven DL approach for research on multiphoton microscopy (MPM) of muscle fibers. SEMPAI utilizes meta-learning to optimize prior integration, data representation, and neural network architecture simultaneously. This allows hypothesis testing and provides interpretable feedback about the origin of biological information in MPM images. SEMPAI performs joint learning of several tasks to enable prediction for small datasets. The method is applied on an extensive multi-study dataset resulting in the largest joint analysis of pathologies and function for single muscle fibers. SEMPAI outperforms state-of-the-art biomarkers in six of seven predictive tasks, including those with scarce data. SEMPAI's DL models with integrated priors are superior to those without priors and to prior-only machine learning approaches.

show abstract

Section: Resultsmentioning

confidence: 87%

Section: Resultsmentioning

confidence: 99%

SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology

Mühlberg

Ritter

Langer

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…[ 46 ] In brief, these features include the cosine angle sum (CAS) taken from selected 2D planes (2D‐CAS) and in 3D (3D‐CAS), the vernier density (VD), the 3D sarcomere length (3D‐SL), and the cross‐sectional area (CSA) of single fibers. Since these features have already been shown to be descriptive for a variety of rather specific remodeling patterns in muscle research, related to aging, chronic degenerative or inflammatory myopathies, [ 30 , 31 , 33 , 34 ] we use them as priors.…”

Section: Resultsmentioning

confidence: 99%

“…For tasks with small data, i.e., pCa50 and passive force (Table 2 in the next Section 2.2), ML and especially DL are severely limited due to overfitting. Based on the identified associations of the same priors with the investigated labels in previous studies, [30][31][32][33][34] we hypothesize that muscle-specific learning tasks are related and the mean predictive performance over all tasks may assist SEMPAI to select an even more regularized model. Therefore, a total meta-loss is introduced, which is a weighted sum of all metalosses for each task and provides an estimate of the model performance over all tasks.…”

Section: Sempai Methods Overviewmentioning

confidence: 93%

SEMPAI: a Self‐Enhancing Multi‐Photon Artificial Intelligence for Prior‐Informed Assessment of Muscle Function and Pathology

et al. 2023

View full text Add to dashboard Cite

Deep learning (DL) shows notable success in biomedical studies. However, most DL algorithms work as black boxes, exclude biomedical experts, and need extensive data. This is especially problematic for fundamental research in the laboratory, where often only small and sparse data are available and the objective is knowledge discovery rather than automation. Furthermore, basic research is usually hypothesis‐driven and extensive prior knowledge (priors) exists. To address this, the Self‐Enhancing Multi‐Photon Artificial Intelligence (SEMPAI) that is designed for multiphoton microscopy (MPM)‐based laboratory research is presented. It utilizes meta‐learning to optimize prior (and hypothesis) integration, data representation, and neural network architecture simultaneously. By this, the method allows hypothesis testing with DL and provides interpretable feedback about the origin of biological information in 3D images. SEMPAI performs multi‐task learning of several related tasks to enable prediction for small datasets. SEMPAI is applied on an extensive MPM database of single muscle fibers from a decade of experiments, resulting in the largest joint analysis of pathologies and function for single muscle fibers to date. It outperforms state‐of‐the‐art biomarkers in six of seven prediction tasks, including those with scarce data. SEMPAI's DL models with integrated priors are superior to those without priors and to prior‐only approaches.

show abstract

DesR349P Mutation Results in Ultrastructural Disruptions and Compromise of Skeletal Muscle Biomechanics Already at Preclinical Stages in Young Mice before the Onset of Protein Aggregation

Cited by 2 publications

References 0 publications

SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology

SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology

SEMPAI: a Self‐Enhancing Multi‐Photon Artificial Intelligence for Prior‐Informed Assessment of Muscle Function and Pathology

Contact Info

Product

Resources

About