Multi-task Learning with Weak Class Labels: Leveraging iEEG to Detect Cortical Lesions in Cryptogenic Epilepsy
Preprint
Abstract
Multi-task learning (MTL) is useful for domains in which data originates from multiple sources that are individually under-sampled. MTL methods are able to learn classification models that have higher performance as compared to learning a single model by aggregating all the data together or learning a separate model for each data source. The performance of these methods relies on label accuracy. We address the problem of simultaneously learning multiple classifiers in the MTL framework when the training data has imprecise labels. We assume that there is an additional source of information that provides a score for each instance which reflects the certainty about its label. Modeling this score as being generated by an underlying ranking function, we augment the MTL framework with an added layer of supervision. This results in new MTL methods that are able to learn accurate classifiers while preserving the domain structure provided through the rank information. We apply these methods to the task of detecting abnormal cortical regions in the MRIs of patients suffering from focal epilepsy whose MRI were read as normal by expert neuroradiologists. In addition to the noisy labels provided by the results of surgical resection, we employ the results of an invasive intracranial-EEG exam as an additional source of label information. Our proposed methods are able to successfully detect abnormal regions for all patients in our dataset and achieve a higher performance as compared to baseline methods.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Multi-task seizure detection: addressing intra-patient variation in seizure morphologiesMachine Learning, 2015
- Cortical feature analysis and machine learning improves detection of “MRI-negative” focal cortical dysplasiaEpilepsy & Behavior, 2015
- Intracranial electrodes in the presurgical evaluation of epilepsyNeurological Sciences, 2012
- Advances in MRI for 'cryptogenic' epilepsiesNature Reviews Neurology, 2011
- Semiology of epileptic seizures: A critical reviewEpilepsy & Behavior, 2009
- Different features of histopathological subtypes of pediatric focal cortical dysplasiaAnnals of Neurology, 2008
- Quick Shift and Kernel Methods for Mode Seeking2008
- Surface-Based Texture and Morphological Analysis Detects Subtle Cortical Dysplasia2008
- Class Noise Mitigation Through Instance Weighting2007
- Measuring the thickness of the human cerebral cortex from magnetic resonance imagesProceedings of the National Academy of Sciences, 2000