Prediction of outcome in Parkinson’s disease patients from DAT SPECT images using a convolutional neural network

Adams, Matthew P.; Bao, Yong; Rahmim, Arman; Tang, Jing

doi:10.1109/nssmic.2018.8824369

Cited by 10 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, in our recent ongoing efforts involving deep learning based prediction of outcome [30], significant improvements (3.22 ± 2.71, p-value < 0.05) were observed, involving implicit discovery of patterns in images, although fluctuation of results (STD = 2.71) were high. Similarly, another study of ours [31] only used MDS_UPDRS III and DAT SPECT images in year 0, showing significant improvement (Accuracy: 70.6%+/-7.7%, p-value < 0.001) of outcome prediction based on discovering of patterns in images using deep learning. In other words, our present research indicates that there is a need to move beyond conventional imaging metrics for improved prediction of outcome.…”

Section: Discussionmentioning

confidence: 52%

“…In our past efforts we used radiomic (texture) measures to show improved correlation with clinical measures [29] and, when combined with clinical measures, improved prediction of motor outcome (MDS_UPDRS III) [20]. Furthermore, our recent studies confirmed significant improvement of outcome prediction based on discovering of patterns in images using deep learning (see the Section 4) [30,31]. Emrani et al [32], using machine learning methods, introduced a new combination of PD biomarkers (SCNA-3UTR, total cholesterol, SBR in left and right putamen, α-Syn, GUSB, DJ-1 and UPSIT are identified as significant diagnostic biomarkers), showing significantly improved prediction of outcome (total MDS_UPDRS) in PD including discovery of the high effect of CFS in prediction.…”

Section: Introductionmentioning

confidence: 91%

See 1 more Smart Citation

Machine learning methods for optimal prediction of motor outcome in Parkinson’s disease

et al. 2020

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 52%

Section: Introductionmentioning

confidence: 91%

Machine learning methods for optimal prediction of motor outcome in Parkinson’s disease

et al. 2020

Self Cite

View full text Add to dashboard Cite

“…Recently, with the developments of new techniques such as convolutional neural network [ 101 ] and transfer learning [ 63 ], deep learning gained significant advances in the computer vision tasks, e.g., ImageNet [ 77 ]. Therefore, most of the studies used different imaging data to diagnose PD, such as MRI ( n = 12) [ 41 , 47 , 54 , 56 , 58 , 66 , 72 , 78 , 82 , 86 , 90 , 95 ] and handwritten images ( n = 9) [ 3 , 19 , 25 , 30 , 69 , 75 , 101 , 102 ], as well as PET and CT imaging ( n = 6) [ 28 , 59 , 67 , 71 , 88 , 90 ] and DaTscan imaging ( n = 4) [ 54 , 76 , 99 , 103 ]. However, CNN and transfer learning techniques were not limited to imaging data; they also learn complex features from voices and signal data [ 29 ].…”

Section: Resultsmentioning

confidence: 99%

“…Furthermore, for imaging dataset including MRI, PET CT, and DaTSCAN were mainly obtained from Parkinson Progression Markers Initiative (PPMI) to train classifier, as seen in [ 20 , 28 , 41 , 47 , 59 , 66 , 67 , 76 , 82 , 86 , 88 , 90 , 94 , 95 ]; hence, among all studies, CNN in [ 20 ] and FNN in [ 28 ] achieved an outstanding result for image classification.…”

Section: Discussionmentioning

confidence: 99%

The Role of Neural Network for the Detection of Parkinson’s Disease: A Scoping Review

et al. 2021

View full text Add to dashboard Cite

Background: Parkinson’s Disease (PD) is a chronic neurodegenerative disorder that has been ranked second after Alzheimer’s disease worldwide. Early diagnosis of PD is crucial to combat against PD to allow patients to deal with it properly. However, there is no medical test(s) available to diagnose PD conclusively. Therefore, computer-aided diagnosis (CAD) systems offered a better solution to make the necessary data-driven decisions and assist the physician. Numerous studies were conducted to propose CAD to diagnose PD in the early stages. No comprehensive reviews have been conducted to summarize the role of AI tools to combat PD. Objective: The study aimed to explore and summarize the applications of neural networks to diagnose PD. Methods: PRISMA Extension for Scoping Reviews (PRISMA-ScR) was followed to conduct this scoping review. To identify the relevant studies, both medical databases (e.g., PubMed) and technical databases (IEEE) were searched. Three reviewers carried out the study selection and extracted the data from the included studies independently. Then, the narrative approach was adopted to synthesis the extracted data. Results: Out of 1061 studies, 91 studies satisfied the eligibility criteria in this review. About half of the included studies have implemented artificial neural networks to diagnose PD. Numerous studies included focused on the freezing of gait (FoG). Biomedical voice and signal datasets were the most commonly used data types to develop and validate these models. However, MRI- and CT-scan images were also utilized in the included studies. Conclusion: Neural networks play an integral and substantial role in combating PD. Many possible applications of neural networks were identified in this review, however, most of them are limited up to research purposes.

show abstract

“…Many researchers have suggested a model predict and diagnose the disease. Deep learning for image analysis has yielded some of the most impressive progress in recent years ( Adams et al, 2018 ). Various deep learning and machine learning approaches have been used to predict PD in multiple studies.…”

Section: Related Workmentioning

confidence: 99%

Soft Attention Based DenseNet Model for Parkinson’s Disease Classification Using SPECT Images

Thakur

Kuresan

Dhanalakshmi

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

ObjectiveDeep learning algorithms have long been involved in the diagnosis of severe neurological disorders that interfere with patients’ everyday tasks, such as Parkinson’s disease (PD). The most effective imaging modality for detecting the condition is DaTscan, a variety of single-photon emission computerized tomography (SPECT) imaging method. The goal is to create a convolutional neural network that can specifically identify the region of interest following feature extraction.MethodsThe study comprised a total of 1,390 DaTscan imaging groups with PD and normal classes. The architecture of DenseNet-121 is leveraged with a soft-attention block added before the final classification layer. For visually analyzing the region of interest (ROI) from the images after classification, Soft Attention Maps and feature map representation are used.OutcomesThe model obtains an overall accuracy of 99.2% and AUC-ROC score 99%. A sensitivity of 99.2%, specificity of 99.4% and f1-score of 99.1% is achieved that surpasses all prior research findings. Soft-attention map and feature map representation aid in highlighting the ROI, with a specific attention on the putamen and caudate regions.ConclusionWith the deep learning framework adopted, DaTscan images reveal the putamen and caudate areas of the brain, which aid in the distinguishing of normal and PD cohorts with high accuracy and sensitivity.

show abstract

Prediction of outcome in Parkinson’s disease patients from DAT SPECT images using a convolutional neural network

Cited by 10 publications

References 10 publications

Machine learning methods for optimal prediction of motor outcome in Parkinson’s disease

Machine learning methods for optimal prediction of motor outcome in Parkinson’s disease

The Role of Neural Network for the Detection of Parkinson’s Disease: A Scoping Review

Soft Attention Based DenseNet Model for Parkinson’s Disease Classification Using SPECT Images

Contact Info

Product

Resources

About