Ruben Kuzniecky
Research Subjects
Ruben Kuzniecky has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Bilal Ahmed1 shared publication
- Carla E. Brodley
College of Computer and Information Science, Northeastern University, 440 Huntington Avenue, 202 West Village H, Boston, MA 02115, USA
1 shared publication - Jennifer Dy
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
1 shared publication - Karen E. Blackmon1 shared publication
Orrin Devinsky
1 shared publication- Thomas Thesen
NYU Langone Medical Center
1 shared publication
Latest Publications
- Open Access
Multi-task Learning with Weak Class Labels: Leveraging iEEG to Detect Cortical Lesions in Cryptogenic Epilepsy
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.
Open AccessMulti-task Learning with Weak Class Labels: Leveraging iEEG to Detect Cortical Lesions in Cryptogenic Epilepsy
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.