Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods

A machine learning-based clinical tool for diagnosing myopathy using multi-cohort microarray expression profiles

BACKGROUND

Myopathies are a heterogenous collection of disorders characterized by dysfunction of skeletal muscle. In practice, myopathies are frequently encountered by physicians and precise diagnosis remains a challenge in primary care. Molecular expression profiles show promise for disease diagnosis in various pathologies. We propose a novel machine learning-based clinical tool for predicting muscle disease subtypes using multi-cohort microarray expression data.

MATERIALS AND METHODS

Muscle tissue samples originating from 1260 patients with muscle weakness. Data was curated from 42 independent cohorts with expression profiles in public microarray gene expression repositories, which represent a broad range of patient ages and peripheral muscles. Cohorts were categorized into five muscle disease subtypes: immobility, inflammatory myopathies, intensive care unit acquired weakness (ICUAW), congenital, and chronic systemic disease. The data contains expression data on 34,099 genes. Data augmentation techniques were used to address class imbalances in the muscle disease subtypes. Support vector machine (SVM) models were trained on two-thirds of the 1260 samples based on the top selected gene signature using analysis of variance (ANOVA). The model was validated in the remaining samples using area under the receiver operator curve (AUC). Gene enrichment analysis was used to identify enriched biological functions in the gene signature.

RESULTS

The AUC ranges from 0.611 to 0.649 in the observed imbalanced data. Overall, using the augmented data, chronic systemic disease was the best predicted class with AUC 0.872 (95% confidence interval (CI): 0.824-0.920). The least discriminated classes were ICUAW with AUC 0.777 (95% CI: 0.668-0.887) and immobility with AUC 0.789 (95% CI: 0.716-0.861). Disease-specific gene set enrichment results showed that the gene signature was enriched in biological processes including neural precursor cell proliferation for ICUAW and aerobic respiration for congenital (false discovery rate q-value < 0.001).

CONCLUSION

Our results present a well-performing molecular classification tool with the selected gene markers for muscle disease classification. In practice, this tool addresses an important gap in the literature on myopathies and presents a potentially useful clinical tool for muscle disease subtype diagnosis.

Diagnostic Value of Muscle Ultrasound for Myopathies and Myositis

Purpose of Review

The purpose of this review is to critically discuss the use of ultrasound in the evaluation of muscle disorders with a particular focus on the emerging use in inflammatory myopathies.

Recent Findings

In myopathies, pathologic muscle shows an increase in echogenicity. Muscle echogenicity can be assessed visually, semi-quantitatively, or quantitatively using grayscale analysis. The involvement of specific muscle groups and the pattern of increase in echogenicity can further point to specific diseases. In pediatric neuromuscular disorders, the value of muscle ultrasound for screening and diagnosis is well-established. It has also been found to be a responsive measure of disease change in muscular dystrophies. In chronic forms of myositis like inclusion body myositis, ultrasound is very suitable for detecting markedly increased echogenicity and atrophy in affected muscles. Acute cases of muscle edema show only a mild increase in echogenicity, which can also reverse with successful treatment.

Summary

Muscle ultrasound is an important imaging modality that is highly adaptable to study various muscle conditions. Although its diagnostic value for neuromuscular disorders is high, the evidence in myositis has only begun to accrue in earnest. Further systematic studies are needed, especially in its role for detecting muscle edema.

Review of Machine Learning Technologies and Neural Networks in Drug Synergy Combination pharmacological research

Introduction: Nowadays an increase in the amount of information creates the need to replace and update data processing technologies. One of the tasks of clinical pharmacology is to create the right combination of drugs for the treatment of a particular disease. It takes months and even years to create a treatment regimen. Using machine learning (in silico) allows predicting how to get the right combination of drugs and skip the experimental steps in a study that take a lot of time and financial expenses. Gradual preparation is needed for the Deep Learning of Drug Synergy, starting from creating a base of drugs, their characteristics and ways of interacting.

Aim: Our review aims to draw attention to the prospect of the introduction of Deep Learning technology to predict possible combinations of drugs for the treatment of various diseases.

Materials and methods: Literary review of articles based on the PUBMED project and related bibliographic resources over the past 5 years (2015–2019).

Results and discussion: In the analyzed articles, Machine or Deep Learning completed the assigned tasks. It was able to determine the most appropriate combinations for the treatment of certain diseases, select the necessary regimen and doses. In addition, using this technology, new combinations have been identified that may be further involved in preclinical studies.

Conclusions: From the analysis of the articles, we obtained evidence of the positive effects of Deep Learning to select “key” combinations for further stages of preclinical research.

Myopathies with finger flexor weakness: Not only inclusion-body myositis

Muscle disorders are characterized by differential involvement of various muscle groups. Among these, weakness predominantly affecting finger flexors is an uncommon pattern, most frequently found in sporadic inclusion-body myositis. This finding is particularly significant when the full range of histopathological findings of inclusion-body myositis is not found on muscle biopsy. Prominent finger flexor weakness, however, is also observed in other myopathies. It occurs commonly in myotonic dystrophy types 1 and 2. In addition, individual reports and small case series have documented finger flexor weakness in sarcoid and amyloid myopathy, and in inherited myopathies caused by ACTA1, CRYAB, DMD, DYSF, FLNC, GAA, GNE, HNRNPDL, LAMA2, MYH7, and VCP mutations. Therefore, the finding of finger flexor weakness requires consideration of clinical, myopathological, genetic, electrodiagnostic, and sometimes muscle imaging findings to establish a diagnosis.

Deep learning-based classification of rectal fecal retention and analysis of fecal properties using ultrasound images in older adult patients

AIM

The present study aimed to analyze the use of machine learning in ultrasound (US)-based fecal retention assessment.

METHODS

The accuracy of deep learning techniques and conventional US methods for the evaluation of fecal properties was compared. The presence or absence of rectal feces was analyzed in 42 patients. Eleven patients without rectal fecal retention on US images were excluded from the analysis; thus, fecal properties were analyzed in 31 patients. Deep learning was used to classify the transverse US images into three types: absence of feces, hyperechoic area, and strong hyperechoic area in the rectum.

RESULTS

Of the 42 patients, 31 tested positive for the presence of rectal feces, zero were false positive, zero were false negative, and 11 were negative, indicating a sensitivity of 100% and a specificity of 100% for the detection of rectal feces in the rectum. Of the 31 positive patients, 14 had hard stools and 17 had other types. Hard stool was detected by US findings in 100% of the patients (14/14), whereas deep learning-based classification detected hard stool in 85.7% of the patients (12/14). Other stool types were detected by US findings in 88.2% of the patients (15/17), while deep learning-based classification also detected other stool types in 88.2% of the patients (15/17).

CONCLUSIONS

The results showed that US findings and deep learning-based classification can detect rectal fecal retention in older adult patients and distinguish between the types of fecal retention.

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

Artificial intelligence (AI) has become a progressively prevalent Research Topic in medicine and is increasingly being applied to dermatology. There is a need to understand this technology's progress to help guide and shape the future for medical care providers and recipients. We reviewed the literature to evaluate the types of publications on the subject, the specific dermatological topics addressed by AI, and the most challenging barriers to its implementation. A substantial number of original articles and commentaries have been published to date and only few detailed reviews exist. Most AI applications focus on differentiating between benign and malignant skin lesions, however; others exist pertaining to ulcers, inflammatory skin diseases, allergen exposure, dermatopathology, and gene expression profiling. Applications commonly analyze and classify images, however, other tools such as risk assessment calculators are becoming increasingly available. Although many applications are technologically feasible, important implementation barriers have been identified including systematic biases, difficulty of standardization, interpretability, and acceptance by physicians and patients alike. This review provides insight into future research needs and possibilities. There is a strong need for clinical investigation in dermatology providing evidence of success overcoming the identified barriers. With these research goals in mind, an appropriate role for AI in dermatology may be achieved in not so distant future.

A Novel Bio-Inspired Deep Learning Approach for Liver Cancer Diagnosis

Current research on computer-aided diagnosis (CAD) of liver cancer is based on traditional feature engineering methods, which have several drawbacks including redundant features and high computational cost. Recent deep learning models overcome these problems by implicitly capturing intricate structures from large-scale medical image data. However, they are still affected by network hyperparameters and topology. Hence, the state of the art in this area can be further optimized by integrating bio-inspired concepts into deep learning models. This work proposes a novel bio-inspired deep learning approach for optimizing predictive results of liver cancer. This approach contributes to the literature in two ways. Firstly, a novel hybrid segmentation algorithm is proposed to extract liver lesions from computed tomography (CT) images using SegNet network, UNet network, and artificial bee colony optimization (ABC), namely, SegNet-UNet-ABC. This algorithm uses the SegNet for separating liver from the abdominal CT scan, then the UNet is used to extract lesions from the liver. In parallel, the ABC algorithm is hybridized with each network to tune its hyperparameters, as they highly affect the segmentation performance. Secondly, a hybrid algorithm of the LeNet-5 model and ABC algorithm, namely, LeNet-5/ABC, is proposed as feature extractor and classifier of liver lesions. The LeNet-5/ABC algorithm uses the ABC to select the optimal topology for constructing the LeNet-5 network, as network structure affects learning time and classification accuracy. For assessing performance of the two proposed algorithms, comparisons have been made to the state-of-the-art algorithms on liver lesion segmentation and classification. The results reveal that the SegNet-UNet-ABC is superior to other compared algorithms regarding Jaccard index, Dice index, correlation coefficient, and convergence time. Moreover, the LeNet-5/ABC algorithm outperforms other algorithms regarding specificity, F1-score, accuracy, and computational time.

Objective Analysis of Neck Muscle Boundaries for Cervical Dystonia Using Ultrasound Imaging and Deep Learning

OBJECTIVE

To provide objective visualization and pattern analysis of neck muscle boundaries to inform and monitor treatment of cervical dystonia.

METHODS

We recorded transverse cervical ultrasound (US) images and whole-body motion analysis of sixty-one standing participants (35 cervical dystonia, 26 age matched controls). We manually annotated 3,272 US images sampling posture and the functional range of pitch, yaw, and roll head movements. Using previously validated methods, we used 60-fold cross validation to train, validate and test a deep neural network (U-net) to classify pixels to 13 categories (five paired neck muscles, skin, ligamentum nuchae, vertebra). For all participants for their normal standing posture, we segmented US images and classified condition (Dystonia/Control), sex and age (higher/lower) from segment boundaries. We performed an explanatory, visualization analysis of dystonia muscle-boundaries.

RESULTS

For all segments, agreement with manual labels was Dice Coefficient (64 ± 21%) and Hausdorff Distance (5.7 ± 4 mm). For deep muscle layers, boundaries predicted central injection sites with average precision 94 ± 3%. Using leave-one-out cross-validation, a support-vector-machine classified condition, sex, and age from predicted muscle boundaries at accuracy 70.5%, 67.2%, 52.4% respectively, exceeding classification by manual labels. From muscle boundaries, Dystonia clustered optimally into three sub-groups. These sub-groups are visualized and explained by three eigen-patterns which correlate significantly with truncal and head posture.

CONCLUSION

Using US, neck muscle shape alone discriminates dystonia from healthy controls.

SIGNIFICANCE

Using deep learning, US imaging allows online, automated visualization, and diagnostic analysis of cervical dystonia and segmentation of individual muscles for targeted injection.

Use of Deep Learning for Detailed Severity Characterization and Estimation of 5-Year Risk Among Patients With Age-Related Macular Degeneration

Importance

Although deep learning (DL) can identify the intermediate or advanced stages of age-related macular degeneration (AMD) as a binary yes or no, stratified gradings using the more granular Age-Related Eye Disease Study (AREDS) 9-step detailed severity scale for AMD provide more precise estimation of 5-year progression to advanced stages. The AREDS 9-step detailed scale's complexity and implementation solely with highly trained fundus photograph graders potentially hampered its clinical use, warranting development and use of an alternate AREDS simple scale, which although valuable, has less predictive ability.

Objective

To describe DL techniques for the AREDS 9-step detailed severity scale for AMD to estimate 5-year risk probability with reasonable accuracy.

Design, Setting, and Participants

This study used data collected from November 13, 1992, to November 30, 2005, from 4613 study participants of the AREDS data set to develop deep convolutional neural networks that were trained to provide detailed automated AMD grading on several AMD severity classification scales, using a multiclass classification setting. Two AMD severity classification problems using criteria based on 4-step (AMD-1, AMD-2, AMD-3, and AMD-4 from classifications developed for AREDS eligibility criteria) and 9-step (from AREDS detailed severity scale) AMD severity scales were investigated. The performance of these algorithms was compared with a contemporary human grader and against a criterion standard (fundus photograph reading center graders) used at the time of AREDS enrollment and follow-up. Three methods for estimating 5-year risk were developed, including one based on DL regression. Data were analyzed from December 1, 2017, through April 15, 2018.

Main Outcomes and Measures

Weighted κ scores and mean unsigned errors for estimating 5-year risk probability of progression to advanced AMD.

Results

This study used 67 401 color fundus images from the 4613 study participants. The weighted κ scores were 0.77 for the 4-step and 0.74 for the 9-step AMD severity scales. The overall mean estimation error for the 5-year risk ranged from 3.5% to 5.3%.

Conclusions and Relevance

These findings suggest that DL AMD grading has, for the 4-step classification evaluation, performance comparable with that of humans and achieves promising results for providing AMD detailed severity grading (9-step classification), which normally requires highly trained graders, and for estimating 5-year risk of progression to advanced AMD. Use of DL has the potential to assist physicians in longitudinal care for individualized, detailed risk assessment as well as clinical studies of disease progression during treatment or as public screening or monitoring worldwide.

Recent developments in classification criteria and diagnosis guidelines for idiopathic inflammatory myopathies

Purpose of review

The aim of this review was to summarize key developments in classification and diagnosis of the idiopathic inflammatory myopathies (IIMs).

Recent findings

The recently published European League Against Rheumatism/American College of Rheumatology (EULAR/ACR) classification criteria for the IIMs provide a comprehensive, accurate and data-driven approach to identification of IIM cases appropriate for inclusion in research studies. Further, recent studies have advanced understanding of clinical manifestations of the IIMs and delineated the role of imaging, particularly magnetic resonance.

Summary

The recent publication of the EULAR/ACR classification criteria will potentially greatly improve IIM research through more accurate case identification and standardization across studies.

Future inclusion of newly recognized clinical associations with the MSAs may further improve the criteria's accuracy and utility. Clear and comprehensive understanding of associations between clinical manifestations, prognosis and multisystem involvement can aid diagnostic assessment; recent advances include delineation of such associations and expansion of the role of imaging.

US-Pro: An Application Enabling Efficient, High-Throughput Ultrasound Video Processing

We describe a new graphical user interface-based application, US-Pro, designed to enable customized, high-throughput ultrasound video anonymization and dynamic cropping before output to video or high-efficiency disk storage. This application is distributed in a Docker container environment, which supports facile software installation on the most commonly used operating systems, as well as local processing of data sets, precluding the external transfer of electronic protected health information. The US-Pro application will facilitate the reproducible production of large-scale ultrasound video data sets for varied applications, including machine-learning analysis, educational distribution, and quality assurance review.

Deep learning based retinal OCT segmentation

We look at the recent application of deep learning (DL) methods in automated fine-grained segmentation of spectral domain optical coherence tomography (OCT) images of the retina. We describe a new method combining fully convolutional networks (FCN) with Gaussian Processes for post processing. We report performance comparisons between the proposed approach, human clinicians, and other machine learning (ML) such as graph based approaches. The approach is demonstrated on an OCT dataset consisting of mild non-proliferative diabetic retinopathy from the University of Miami. The method is shown to have performance on par with humans, also compares favorably with the other ML methods, and appears to have as small or smaller mean unsigned error (equal to 1.06), versus errors ranging from 1.17 to 1.81 for other methods, and compared with human error of 1.10.

Enhanced Point-of-Care Ultrasound Applications by Integrating Automated Feature-Learning Systems Using Deep Learning

Recent applications of artificial intelligence (AI) and deep learning (DL) in health care include enhanced diagnostic imaging modalities to support clinical decisions and improve patients' outcomes. Focused on using automated DL-based systems to improve point-of-care ultrasound (POCUS), we look at DL-based automation as a key field in expanding and improving POCUS applications in various clinical settings. A promising additional value would be the ability to automate training model selections for teaching POCUS to medical trainees and novice sonologists. The diversity of POCUS applications and ultrasound equipment, each requiring specialized AI models and domain expertise, limits the use of DL as a generic solution. In this article, we highlight the most advanced potential applications of AI in POCUS tailored to high-yield models in automated image interpretations, with the premise of improving the accuracy and efficacy of POCUS scans.

Impact of the rise of artificial intelligence in radiology: What do radiologists think?

PURPOSE

The purpose of this study was to assess the perception, knowledge, wishes and expectations of a sample of French radiologists towards the rise of artificial intelligence (AI) in radiology.

MATERIAL AND METHOD

A general data protection regulation-compliant electronic survey was sent by e-mail to the 617 radiologists registered in the French departments of Nord and Pas-de-Calais (93 radiology residents and 524 senior radiologists), from both public and private institutions. The survey included 42 questions focusing on AI in radiology, and data were collected between January 16^th and January 31^st, 2019. The answers were analyzed together by a senior radiologist and a radiology resident.

RESULTS

A total of 70 radiology residents and 200 senior radiologists participated to the survey, which corresponded to a response rate of 43.8% (270/617). One hundred ninety-eight radiologists (198/270; 73.3%) estimated they had received insufficient previous information on AI. Two hundred and fifty-five respondents (255/270; 94.4%) would consider attending a generic continuous medical education in this field and 187 (187/270; 69.3%) a technically advanced training on AI. Two hundred and fourteen respondents (214/270; 79.3%) thought that AI will have a positive impact on their future practice. The highest expectations were the lowering of imaging-related medical errors (219/270; 81%), followed by the lowering of the interpretation time of each examination (201/270; 74.4%) and the increase in the time spent with patients (141/270; 52.2%).

CONCLUSION

While respondents had the feeling of receiving insufficient previous information on AI, they are willing to improve their knowledge and technical skills on this field. They share an optimistic view and think that AI will have a positive impact on their future practice. A lower risk of imaging-related medical errors and an increase in the time spent with patients are among their main expectations.

Convolutional Neural Networks for Radiologic Images: A Radiologist's Guide

Deep learning has rapidly advanced in various fields within the past few years and has recently gained particular attention in the radiology community. This article provides an introduction to deep learning technology and presents the stages that are entailed in the design process of deep learning radiology research. In addition, the article details the results of a survey of the application of deep learning-specifically, the application of convolutional neural networks-to radiologic imaging that was focused on the following five major system organs: chest, breast, brain, musculoskeletal system, and abdomen and pelvis. The survey of the studies is followed by a discussion about current challenges and future trends and their potential implications for radiology. This article may be used as a guide for radiologists planning research in the field of radiologic image analysis using convolutional neural networks.

Advances in the early diagnosis and therapy of inclusion body myositis

PURPOSE OF REVIEW

To describe recent advancements in diagnostic and therapeutic approaches to inclusion body myositis (IBM).

RECENT FINDINGS

Our understanding of the implications of anti-cytosolic 5'-nucleotidase 1A autoantibody status in IBM and other diseases is increasing. Muscle imaging using magnetic resonance techniques and ultrasound is increasingly being performed and characteristic patterns of muscle involvement may help with diagnosis. Longitudinal imaging studies are likely to help with monitoring and as an outcome measure in clinical trials. Recent small-scale studies of Arimoclomol and Rapamycin have shown promising results and further investigation of these medications is ongoing. Exercise is likely to form an increasingly important facet of management of patients with IBM, but the optimal type of exercise programme to enrol patients in is not yet determined.

SUMMARY

Antibody testing and muscle imaging results may improve our ability to diagnose IBM and the availability of effective disease modifying treatments targeting novel non-inflammatory pathways could soon become a reality. It remains the duty of those involved in the management of patients with IBM to facilitate involvement in clinical trials and other research studies.

Current Classification and Management of Inflammatory Myopathies

Inflammatory disorders of the skeletal muscle include polymyositis (PM), dermatomyositis (DM), (immune mediated) necrotizing myopathy (NM), overlap syndrome with myositis (overlap myositis, OM) including anti-synthetase syndrome (ASS), and inclusion body myositis (IBM). Whereas DM occurs in children and adults, all other forms of myositis mostly develop in middle aged individuals. Apart from a slowly progressive, chronic disease course in IBM, patients with myositis typically present with a subacute onset of weakness of arms and legs, often associated with pain and clearly elevated creatine kinase in the serum. PM, DM and most patients with NM and OM usually respond to immunosuppressive therapy, whereas IBM is largely refractory to treatment. The diagnosis of myositis requires careful and combinatorial assessment of (1) clinical symptoms including pattern of weakness and paraclinical tests such as MRI of the muscle and electromyography (EMG), (2) broad analysis of auto-antibodies associated with myositis, and (3) detailed histopathological work-up of a skeletal muscle biopsy. This review provides a comprehensive overview of the current classification, diagnostic pathway, treatment regimen and pathomechanistic understanding of myositis.

Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey

The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.