Machine learning and radiology

Wang, Shijun; Summers, Ronald M.

doi:10.1016/j.media.2012.02.005

Cited by 519 publications

(323 citation statements)

References 214 publications

Supporting

Mentioning

319

Contrasting

Unclassified

Order By: Relevance

“…30 The most significant contribution of machine learning to clinical practice is that it provides an automatic and objective way to extend knowledge obtained from training data to unknown (i.e., first seen) cases. Compared to previous work, we explicitly circumvented several sources of bias.…”

Section: Resultsmentioning

confidence: 99%

Automated detection of cortical dysplasia type II in MRI-negative epilepsy

et al. 2014

View full text Add to dashboard Cite

Objective: To detect automatically focal cortical dysplasia (FCD) type II in patients with extratemporal epilepsy initially diagnosed as MRI-negative on routine inspection of 1.5 and 3.0T scans. Methods:We implemented an automated classifier relying on surface-based features of FCD morphology and intensity, taking advantage of their covariance. The method was tested on 19 patients (15 with histologically confirmed FCD) scanned at 3.0T, and cross-validated using a leave-one-out strategy. We assessed specificity in 24 healthy controls and 11 disease controls with temporal lobe epilepsy. Cross-dataset classification performance was evaluated in 20 healthy controls and 14 patients with histologically verified FCD examined at 1.5T.Results: Sensitivity was 74%, with 100% specificity (i.e., no lesions detected in healthy or disease controls). In 50% of cases, a single cluster colocalized with the FCD lesion, while in the remaining cases a median of 1 extralesional cluster was found. Applying the classifier (trained on 3.0T data) to the 1.5T dataset yielded comparable performance (sensitivity 71%, specificity 95%). Conclusion:In patients initially diagnosed as MRI-negative, our fully automated multivariate approach offered a substantial gain in sensitivity over standard radiologic assessment. The proposed method showed generalizability across cohorts, scanners, and field strengths. Machine learning may assist presurgical decision-making by facilitating hypothesis formulation about the epileptogenic zone. Classification of evidence:This study provides Class II evidence that automated machine learning of MRI patterns accurately identifies FCD among patients with extratemporal epilepsy initially diagnosed as MRI-negative. Neurology ® 2014;83:48-55 GLOSSARY FCD 5 focal cortical dysplasia; GM 5 gray matter; LDA 5 linear discriminant analysis; MNI 5 Montreal Neurological Institute; RI 5 relative intensity; SEEG 5 stereotactic implanted depth electrodes; TE 5 echo time; TLE 5 temporal lobe epilepsy; TR 5 repetition time; WM 5 white matter.Focal cortical dysplasia (FCD) type II, an epileptogenic developmental malformation, 1 is characterized by cortical dyslamination, hypertrophic and dysmorphic neurons, and balloon cells 2 ; it is the most common histopathology in surgical series of extratemporal lobe epilepsy.3 Reliable detection of this lesion is critical for successful surgery. 4 On MRI, FCD type II is characterized by cortical thickening, blurring of the gray-white matter junction, and hyperintense signal.5 Many lesions, however, elude best-practice neuroimaging protocols. To enhance visibility, previous studies have modeled its main features using voxel-based methods, such as texture and morphometric analysis. 6 The evaluation of multiple maps generated through these quantitative techniques is done visually, so that the yield and diagnostic confidence depend on the reader's familiarity with the algorithm. Limited generalizability also stems from the fact that these approaches have been validated mainly with lesion...

show abstract

Section: Resultsmentioning

confidence: 99%

Automated detection of cortical dysplasia type II in MRI-negative epilepsy

et al. 2014

View full text Add to dashboard Cite

show abstract

“…In contrast, the unsupervised learning has no training dataset and the goal is to discover the relationships between the samples or reveal the latent variables behind the observations [5]. The semi-supervised learning falls between the supervised and the unsupervised learning by utilizing both of the labeled and the unlabeled data during the training phase [24]. Among the three categories of the machine learning, the supervised learning is the best fit to solve the prediction problem in the auto-scaling area [5].…”

Section: Theoretical Investigation Of the Hypothesismentioning

confidence: 99%

An autonomic prediction suite for cloud resource provisioning

2017

View full text Add to dashboard Cite

One of the challenges of cloud computing is effective resource management due to its auto-scaling feature. Prediction techniques have been proposed for cloud computing to improve cloud resource management. This paper proposes an autonomic prediction suite to improve the prediction accuracy of the auto-scaling system in the cloud computing environment. Towards this end, this paper proposes that the prediction accuracy of the predictive auto-scaling systems will increase if an appropriate time-series prediction algorithm based on the incoming workload pattern is selected. To test the proposition, a comprehensive theoretical investigation is provided on different risk minimization principles and their effects on the accuracy of the time-series prediction techniques in the cloud environment. In addition, experiments are conducted to empirically validate the theoretical assessment of the hypothesis. Based on the theoretical and the experimental results, this paper designs a self-adaptive prediction suite. The proposed suite can automatically choose the most suitable prediction algorithm based on the incoming workload pattern.

show abstract

“…equations and numerical coefficients or weights) that "link" x to y. (Wang & Summers, 2012). Unsupervised learning, generally, involves the analysis of unlabelled data (i.e.…”

Section: Discussion: Why This Is a Good Case Study Of Big Data Analyticsmentioning

confidence: 99%

Exploring the depths of the global earth observation system of systems

et al. 2017

View full text Add to dashboard Cite

This paper explores for the first time the contents, structure and relationships across institutions and disciplines of a global Big Earth Data cyber-infrastructure: the Global Earth Observation System of System (GEOSS). The analysis builds on 1.8 million metadata records harvested in GEOSS. Because this set includes almost all the major large data collections in GEOSS, the analysis represents more than 80% of all the data made available through this global system. We explore two major aspects: the collaborative networks and the thematic coverage in GEOSS. The first connects the contributing organisations through the more than 200,000 keywords used in the systems, and then explores who is citing whom, a proxy for of institutional thickness. The thematic coverage is analysed through neural network algorithms, first on the keywords, and then on the corpus of 653 million lemmatised lower case words built from the titles and abstracts of all 1.8 million metadata records. The findings not only give a good overview of the GEOSS data universe, but offer immediate priorities on how to increase the usability of GEOSS through improved data management, and the opportunity to augment the metadata with high level concept that synthetise well the contents of the dataset.

show abstract

Machine learning and radiology

Cited by 519 publications

References 214 publications

Automated detection of cortical dysplasia type II in MRI-negative epilepsy

Automated detection of cortical dysplasia type II in MRI-negative epilepsy

An autonomic prediction suite for cloud resource provisioning

Exploring the depths of the global earth observation system of systems

Contact Info

Product

Resources

About