A deep learning tool without muscle-by-muscle grading to differentiate myositis from facio-scapulo-humeral dystrophy using MRI

Fabry, Vincent; Mamalet, Franck; Laforet, Anne; Capelle, Mikaël; Acket, Blandine; Sengenès, Coralie; Cintas, Pascal; Faruch-Bilfeld, Marie

doi:10.1016/j.diii.2022.01.012

Cited by 13 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent report suggests that an automatic deep learning (DL) method based on a pre-trained neural network may be helpful in differentiating IIM patients from controls with high sensitivity and specificity (43). These automatic tolls, may also be helpful for differential diagnosis, discriminating between type 1 facioscapulohumeral dystrophy (FSHD1) and IIM with similar performances to those achieved by two experienced radiologists (44). B-mode ultrasound and shear wave elastography (SWE) may be helpful in the diagnosis of IIM.…”

Section: Muscular Imagingmentioning

confidence: 99%

Idiopathic inflammatory myopathies: one year in review 2023

Conticini,

Dourado,

Bottazzi

et al. 2024

Clinical and Experimental Rheumatology

View full text Add to dashboard Cite

Idiopathic inflammatory myopathies are a group of rare, autoimmune, diseases typically involving striate muscle and also variously affecting several other systems or organs, such as joints, skin, lungs, heart and gastrointestinal tract. IIM are mainly characterised by subacute onset and chronic course and are burdened by significant morbidity and mortality. Despite the rarity of these conditions, several efforts have been undertaken in the last years to better understand their pathogenesis, as well as to achieve a more precise classification and to define the optimal therapeutic approach. The aim of this review is to provide an up-to-date digest of the most relevant studies published on this topic over the last year.

show abstract

Section: Muscular Imagingmentioning

confidence: 99%

Idiopathic inflammatory myopathies: one year in review 2023

Conticini,

Dourado,

Bottazzi

et al. 2024

Clinical and Experimental Rheumatology

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms have been applied to muscle segmentation (to assess muscle volume and localize muscles for quantitative analysis), and have been shown to be more accurate than manual segmentation in preparation for surgery [ 68 ]. More importantly, deep learning can be trained to differentiate between myopathies, and is thereby potentially useful in the diagnosis of IIM [ 69 ▪ ].…”

Section: Future Directionsmentioning

confidence: 99%

Update on muscle imaging in myositis

Tan,

Di Matteo,

Wakefield

et al. 2023

Current Opinion in Rheumatology

View full text Add to dashboard Cite

Purpose of review Imaging techniques such as MRI, ultrasound and PET/computed tomography (CT) have roles in the detection, diagnosis and management of myositis or idiopathic inflammatory myopathy (IIM). Imaging research has also provided valuable knowledge in the understanding of the pathology of IIM. This review explores the latest advancements of these imaging modalities in IIM. Recent findings Recent advancements in imaging of IIM have seen a shift away from manual and qualitative analysis of the images. Quantitative MRI provides more objective, and potentially more sensitive characterization of fat infiltration and inflammation in muscles. In addition to B-mode ultrasound changes, shearwave elastography offers a new dimension to investigating IIM. PET/CT has the added advantage of including IIM-associated findings such as malignancies. Summary It is evident that MRI, ultrasound and PET/CT have important roles in myositis. Continued technological advancement and a quest for more sophisticated applications help drive innovation; this has especially been so of machine learning/deep learning using artificial intelligence and the developing promise of texture analysis.

show abstract

“…102 DL models have also been able to differentiate between facioscapulohumeral muscular dystrophy and myositis using muscle MRI data, performing at a level on par with radiology experts. 103 ML also enhances clinical trial efficiency by improving participant recruitment, enabling simulated trials, aiding remote monitoring, and fostering digital therapeutics (evidence-based, clinically evaluated software to manage or prevent diseases). These advancements streamline trials, enhance data analysis, mitigate traditional trial constraints, and introduce innovative treatment modalities, potentially transforming healthcare intervention methodologies.…”

Section: Ai In Other Aspects Of Nmmentioning

confidence: 99%

“…Furthermore, ML and specifically DL have found additional diverse clinical applications, including in the diagnosis of sporadic or familial ALS patients using gene expression, 99 the prediction of cognitive impairment in ALS patients based on genetic data, 100 the diagnosis of ALS using surface EMG signals, 101 and the identification of gait features specific to Duchenne muscular dystrophy patients using accelerometer data 102 . DL models have also been able to differentiate between facioscapulohumeral muscular dystrophy and myositis using muscle MRI data, performing at a level on par with radiology experts 103 …”

Section: Ai In Other Aspects Of Nmmentioning

confidence: 99%

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

Taha,

Morren

2023

Muscle and Nerve

View full text Add to dashboard Cite

The rapid advancements in artificial intelligence (AI), including machine learning (ML), and deep learning (DL) have ushered in a new era of technological breakthroughs in healthcare. These technologies are revolutionizing the way we utilize medical data, enabling improved disease classification, more precise diagnoses, better treatment selection, therapeutic monitoring, and highly accurate prognostication. Different ML and DL models have been used to distinguish between electromyography signals in normal individuals and those with amyotrophic lateral sclerosis and myopathy, with accuracy ranging from 67% to 99.5%. DL models have also been successfully applied in neuromuscular ultrasound, with the use of segmentation techniques achieving diagnostic accuracy of at least 90% for nerve entrapment disorders, and 87% for inflammatory myopathies. Other successful AI applications include prediction of treatment response, and prognostication including prediction of intensive care unit admissions for patients with myasthenia gravis. Despite these remarkable strides, significant knowledge, attitude, and practice gaps persist, including within the field of electrodiagnostic and neuromuscular medicine. In this narrative review, we highlight the fundamental principles of AI and draw parallels with the intricacies of human brain networks. Specifically, we explore the immense potential that AI holds for applications in electrodiagnostic studies, neuromuscular ultrasound, and other aspects of neuromuscular medicine. While there are exciting possibilities for the future, it is essential to acknowledge and understand the limitations of AI and take proactive steps to mitigate these challenges. This collective endeavor holds immense potential for the advancement of healthcare through the strategic and responsible integration of AI technologies.

show abstract

A deep learning tool without muscle-by-muscle grading to differentiate myositis from facio-scapulo-humeral dystrophy using MRI

Cited by 13 publications

References 29 publications

Idiopathic inflammatory myopathies: one year in review 2023

Idiopathic inflammatory myopathies: one year in review 2023

Update on muscle imaging in myositis

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

Contact Info

Product

Resources

About