Applications of machine learning to diagnosis and treatment of neurodegenerative diseases

Myszczynska, Monika A.; Ojamies, Poojitha N.; Lacoste, Alix M. B.; Neil, Daniel; Saffari, Amir; Mead, Richard; Hautbergue, Guillaume M.; Holbrook, Joanna D.; Ferraiuolo, Laura

doi:10.1038/s41582-020-0377-8

Cited by 353 publications

(232 citation statements)

References 186 publications

(182 reference statements)

Supporting

Mentioning

182

Contrasting

Unclassified

Order By: Relevance

“…It is a variant of Stochastic Neighbor Embedding and performs better in visualizing high dimensional data into two dimensional map [64]. This technique helps in a graphical analysis of deep learned features and have been very popularly used in many recent works [65][66][67][68].…”

Section: Visualization Techniquesmentioning

confidence: 99%

Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization

Rahman

Khandakar²,

Kadir³

et al. 2020

IEEE Access

340

196

View full text Add to dashboard Cite

Tuberculosis (TB) is a chronic lung disease that occurs due to bacterial infection and is one of the top 10 leading causes of death. Accurate and early detection of TB is very important, otherwise, it could be life-threatening. In this work, we have detected TB reliably from the chest X-ray images using image pre-processing, data augmentation, image segmentation, and deep-learning classification techniques. Several public databases were used to create a database of 3500 TB infected and 3500 normal chest X-ray images for this study. Nine different deep CNNs (ResNet18, ResNet50, ResNet101, ChexNet, InceptionV3, Vgg19, DenseNet201, SqueezeNet, and MobileNet) were used for transfer learning from their pre-trained initial weights and were trained, validated and tested for classifying TB and non-TB normal cases. Three different experiments were carried out in this work: segmentation of X-ray images using two different U-net models, classification using X-ray images and that using segmented lung images. The accuracy, precision, sensitivity, F1-score and specificity of best performing model, ChexNet in the detection of tuberculosis using X-ray images were 96.47%, 96.62%, 96.47%, 96.47%, and 96.51% respectively. However, classification using segmented lung images outperformed that with whole X-ray images; the accuracy, precision, sensitivity, F1-score and specificity of DenseNet201 were 98.6%, 98.57%, 98.56%, 98.56%, and 98.54% respectively for the segmented lung images. The paper also used a visualization technique to confirm that CNN learns dominantly from the segmented lung regions that resulted in higher detection accuracy. The proposed method with state-of-theart performance can be useful in the computer-aided faster diagnosis of tuberculosis.

show abstract

Section: Visualization Techniquesmentioning

confidence: 99%

Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization

Rahman

Khandakar²,

Kadir³

et al. 2020

IEEE Access

340

196

View full text Add to dashboard Cite

show abstract

“…Although presently not really informative, this type of analysis is nevertheless extremely important and one can hope that in the future it will yield valuable information [47]. As a matter of fact, ML approaches applied to neuroimaging already provide good insight into latent features contained in images [4].…”

Section: Clinical Datamentioning

confidence: 99%

“…Deep neural network algorithms attain performances similar to those of well-trained radiologists in examining medical images, and AI algorithms are being approved by regulatory agencies (see [3] for a recent meta-analysis). This general frame applies also to neurology, with neuroradiology at the forefront of ML application [4].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Use for Prognostic Purposes in Multiple Sclerosis

Seccia

Romano

Salvetti

et al. 2021

Life

View full text Add to dashboard Cite

The course of multiple sclerosis begins with a relapsing-remitting phase, which evolves into a secondarily progressive form over an extremely variable period, depending on many factors, each with a subtle influence. To date, no prognostic factors or risk score have been validated to predict disease course in single individuals. This is increasingly frustrating, since several treatments can prevent relapses and slow progression, even for a long time, although the possible adverse effects are relevant, in particular for the more effective drugs. An early prediction of disease course would allow differentiation of the treatment based on the expected aggressiveness of the disease, reserving high-impact therapies for patients at greater risk. To increase prognostic capacity, approaches based on machine learning (ML) algorithms are being attempted, given the failure of other approaches. Here we review recent studies that have used clinical data, alone or with other types of data, to derive prognostic models. Several algorithms that have been used and compared are described. Although no study has proposed a clinically usable model, knowledge is building up and in the future strong tools are likely to emerge.

show abstract

“…The complexity of patient profiles makes the interpretation of transplant response extremely complex. The use of new outcome measures and biomarkers combined with innovative statistical methods, including machine learning approaches able to analyze high‐dimensional sources of data and enable inferences from fewer samples, all have the potential to improve patient stratification for inclusion in trials and/or to identify subsets of patients with differential response to treatment 102,103 . They will improve the design and evaluation of cell therapy strategies in a cost‐effective and efficient manner.…”

Section: Future Challengesmentioning

confidence: 99%

Cell therapy in Huntington's disease: Taking stock of past studies to move the field forward

2020

View full text Add to dashboard Cite

Huntington's disease (HD) is a rare inherited neurodegenerative disease that manifests mostly in adulthood with progressive cognitive, behavioral, and motor dysfunction. Neuronal loss occurs predominantly in the striatum but also extends to other brain regions, notably the cortex. Most patients die around 20 years after motor onset, although there is variability in the rate of progression and some phenotypic heterogeneity. The most advanced experimental therapies currently are huntingtin-lowering strategies, some of which are in stage 3 clinical trials. However, even if these approaches are successful, it is unlikely that they will be applicable to all patients or will completely halt continued loss of neural cells in all cases. On the other hand, cellular therapies have the potential to restore atrophied tissues and may therefore provide an important complementary therapeutic avenue. Pilot studies of fetal cell grafts in the 2000s reported the most dramatic clinical improvements yet achieved for this disease, but subsequent studies have so far failed to identify methodology to reliably reproduce these results. Moving forward, a major challenge will be to generate suitable donor cells from (nonfetal) cell sources, but in parallel there are a host of procedural and trial design issues that will be important for improving reliability of transplants and so urgently need attention. Here, we consider findings that have emerged from clinical transplant studies in HD to date, in particular new findings emerging from the recent multicenter intracerebral transplant HD study, and consider how these data may be used to inform future cell therapy trials.

show abstract

Applications of machine learning to diagnosis and treatment of neurodegenerative diseases

Abstract: This is a repository copy of Applications of machine learning to diagnosis and treatment of neurodegenerative diseases.

Cited by 353 publications

References 186 publications

Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization

Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization

Machine Learning Use for Prognostic Purposes in Multiple Sclerosis

Cell therapy in Huntington's disease: Taking stock of past studies to move the field forward

Contact Info

Product

Resources

About