William Speier

Assistant Professor
  • Department of Radiological Sciences

Office: 924 Westwood Blvd, Suite 420, Room K

E-Mail: Speier@ucla.edu


Robotics, natural language processing, and machine learning have made amazing advances over the past few decades, with significant time and funding dedicated to development of countless applications of these fields. Nevertheless, no machine-based system can match the versatility or robustness of the human brain; human-created language and image processing systems are vastly inferior to their biological counterparts; and human decisions and mechanical actions remain the gold standard in the medical field. The goal of my research is to bridge the gap between the brain and machine applications through:

  • Learning the underlying processes in the function of the human brain
  • Creating interfacing software to facilitate brain-machine interaction
  • Developing closed-loop systems to modulate patient treatment based on their physiological state

An example of a brain-computer interface project from our lab can be seen below:



  1. Meng Y, Speier W, Dzubur E, Spiegel B, Arnold C. Predicting Patient Health Status using Activity Tracker Data. Proceedings of the 2018 American Medical Informatics Association Annual Symposium. San Francisco; 2018. PDF
  2. Matiasz NJ, Wood J, Doshi P, Speier W, Beckemeyer B, Wang W, Hsu W, Silva AJ. ResearchMaps.org for integrating and planning research. PLOS One. 2018;13(5):e0195271. DOI: 10.1371/journal.pone.0195271. PDF
  3. Speier W, Dzubur E, Zide M, Shufelt C, Joung S, Eyk JEV, Merz B, Noel C, Lopez M, Spiegel B, Arnold C. Evaluating utility and compliance in a patient-based eHealth study using continuous-time heart rate and activity trackers. JAMIA. 2018; DOI: 10.1093/jamia/ocy067. PDF
  4. Speier W, Arnold C, Chandravadia N, Roberts D, Pendekanti S, Pouratian N. Improving P300 spelling rate using language models and predictive spelling. Brain-Computer Interfaces. 2018;5(1):13–22. DOI: 10.1080/2326263X.2017.1410418. PDF
  5. Li J, Speier W, Ho KC, Sarma KV, Gertych A, Knudsen BS, Arnold CW. An EM-based semi-supervised deep learning approach for semantic segmentation of histopathological images from radical prostatectomies. Computerized Medical Imaging and Graphics. Elsevier; 2018;69:125–133.
  1. Ho K, Speier W, El-Saden S, Arnold C. Classifying Acute Ischemic Stroke Onset Time using Deep Imaging Features. AMIA Annu Symp Proc. 2017.
  2. Speier W, Deshpande A, Cui L, Chandravadia N, Roberts D, Pouratian N. A comparison of stimulus types in online classification of the P300 speller using language models. Plos One. 2017;12(4):e0175382.
  3. Hollada J, Zide M, Speier W, Roter E. Readability assessment of PCORI public abstracts in relation to accessibility. Epidemiology. 2017;28(4):e37–e38.
  4. Speier W, Chandravadia N, Roberts D, Pendekanti S, Pouratian N. Online BCI Typing using Language Model Classifiers by ALS Patients in their Homes. Brain-Computer Interfaces. 2017;4:114–121.
  5. Roberts D, Speier W, Chandravadia N, Pendekanti S, Pouratian N. Optimizing EEG Electrode Configuration in a P300 Speller Brain-Computer Interface: a step toward Clinical Implementation. UC BME Symposium. 2017.
  6. Chandravadia N, Speier W, Roberts D, Pendekanti S, Pouratian N. Evaluating the effect of stimulus paradigms on typing speed using the P300 speller in an online setting. UC BME Symposium. 2017.
  7. Mostafavi L, Hollada J, Speier W, Ruehm S. Patients’ Perceptions of Risks and Benefits of Cardiac Imaging. Annual Congress of the European Congress of Radiology. 2017.
  1. Speier W, Arnold C, Pouratian N. Integrating language models into classifiers for BCI communication: a review. Journal of Neural Engineering. 2016;12:031002.
  2. Speier W, Ong M, Arnold C. Using phrases and document metadata to improve topic modeling of clinical reports. Journal of Biomedical Informatics. 2016;61:260–266.
  3. Speier W, Chandravadia N, Pouratian N. Online BCI Typing using Language Models by ALS Patients in their Homes. International Brain-Computer Interface (BCI) Meeting. 2016.
  4. Panigrahi B, Hollada J, Speier W, Harvey S. Innovations in decreasing recall rates for screening mammography. SBI/ACR Breat Imaging Symposium. 2016.
  1. Speier W, Deshpande A, Pouratian N. A method for optimizing EEG electrode number and configuration for signal acquisition in P300 speller systems. Clin Neurophysiol. 2015;126:1171–7. DOI: 10.1016/j.clinph.2014.09.021. PDF
  2. Speier W, Arnold CW, Deshpande A, Knall J, Pouratian N. Incorporating advanced language models into the P300 speller using particle filtering. Journal of Neural Engineering. 2015;12:046018. PDF
  3. Arnold CW, Oh A, Chen S, Speier W. Evaluating topic model interpretability from a primary care physician perspective. Computer Methods and Programs in Biomedicine. 2015;In press. DOI: 10.1016/j.cmpb.2015.10.014. PDF
  4. Mostafavi L, Marfori W, Arellano C, Tognolini A, Speier W, Adibi A, Ruehm S. Prevalence of Coronary Artery Disease Evluated by Coronary CT Angiography in Women with Mammographically Detected Breast Arterial Calcifications. Plos One. 2015;10(4):e0122289.
  5. Hollada J, Speier W, Oshiro T, Marzan-McGill R, Ruehm S, Bassett L, Wells C. Patients’ Perceptions of Radiation Exposure Associated with Mammography. American Journal of Roentgenology. 2015;205:215–221.
  6. Hollada J, Mostafavi L, Speier W, Javidi S, Ruehm S. Cardiac Imaging Exams: Patient Awareness of Associated Utilization of Radiation. RSNA Annual Meeting. 2015.
  1. Ho KC, Speier W, El-Saden S, Liebeskind DS, Saver JL, Bui AAT, Arnold CW. Predicting discharge mortality after acute ischemic stroke using balanced data. AMIA Annu Symp Proc. 2014. p. 1787–96. PDF
  2. Singleton KW, Speier W, Bui AAT, Hsu W. Motivating the additional use of external validity: Examining transportability in a model of glioblastoma multiforme. AMIA Annu Symp Proc. 2014. p. 1930–9. PDF
  3. Speier W, Arnold CW, Lu J, Deshpande A, Pouratian N. Integrating language information with a hidden Markov model to improve communication rate in the P300 speller. IEEE Trans Neural Syst Rehabil Eng. 2014;22:678–84. DOI: 10.1109/TNSRE.2014.2300091. PDF
  4. Hollada J, Marfori W, Tognolini A, Speier W, Ristow L, Ruehm SG. Successful patient recruitment in CT imaging clinical trials: What factors influence patient participation? Acad Radiol. 2014;21:52–7. DOI: 10.1016/j.acra.2013.09.016. PDF
  5. Ho KC, Speier W, El-Saden S, Liebeskind DS, Saver JL, Bui AAT, Arnold CW. Predicting discharge mortality in acute ischemic stroke patients using support vector machines and affinity propagation. MUCMD. 2014.
  6. Malekmohammaki M, Speier W, Pouratian N. Pallidal-Cortical Beta Coherence is Activity-modulated by not Causally related in PD. ASSFN Biennial Meeting. 2014.
  1. Speier W, Knall J, Pouratian N. Unsupervised training of brain-computer interface systems using expectation maximization. Neural Engineering (NER) 2013 6th International IEEE/EMBS Conference. 2013. DOI: 10.1109/NER.2013.6696032. PDF
  2. Lu J, Speier W, Hu X, Pouratian N. The effects of stimulus timing features on P300 speller performance. Clin Neurophysiol. 2013;124:306–14. DOI: 10.1016/j.clinph.2012.08.002. PDF
  3. Speier W, Arnold CW, Pouratian N. Evaluating true BCI communication rate through mutual information and language models. PLoS One. 2013;8:e78432. DOI: 10.1371/journal.pone.0078432. PDF
  4. Speier W, Fried I, Pouratian N. Improved P300 speller performance using electrocorticography, spectral features, and natural language processing. Clinical Neurophysiology. 2013;124:1321\textendash1328. DOI: 10.1016/j.clinph.2013.02.002. PDF
  1. Speier W, Arnold CW, Lu J, Taira RK, Pouratian N. Natural language processing with dynamic classification improves P300 speller accuracy and bit rate. Journal of Neural Engineering. 2012;9:016004. DOI: 10.1088/1741-2560/9/1/016004. PDF
  2. Hsu W, Speier W, Taira RK. Automated extraction of reported statistical analyses: towards a logical representation of clinical trial literature. AMIA Annu Symp Proc. 2012. p. 350–9. PDF
  3. Speier W, Ochs MF. Updating annotations with the distributed annotation system and the automated sequence annotation pipeline. Bioinformatics. 2012;28:2858–9. DOI: 10.1093/bioinformatics/bts530. PDF
  4. Arnold CW, Speier W. A topic model of clinical reports. Proc ACM SIGIR Conf Research and Development in Information Retrieval. 2012. p. 1031–1032. PDF
  5. Speier W, Arnold CW, Lu J, Taira RK, Pouratian N. Using natural language processing methods to improve EEG classification in brain-computer interfaces. NLM Informatics Training Conference. 2012.
  6. Speier W, Fried I, Pouratian N. Improving P300 speller classification using electrocorticography. AANS Annual Scientific Meeting. 2012.
  1. Speier W, Iglesias JE, El-Kara L, Tu Z, Arnold CW. Robust skull stripping of clinical glioblastoma multiforme data. Med Image Comput Comput Assist Interv. 2011;14:659–66. PDF
  2. Speier W, Arnold CW, Hsu W, Bui AAT. Content-based image retrieval using feature density estimates. AMIA Annu Symp Proc. Washington DC; 2011. PDF
  3. Favorov A, Lvovs D, Speier W, Parmigiani G, Ochs M. OnionTree XML: A Format to Exchange Gene-Related probabilities. J Biomol Struct Dyn. 2011;29(2):417–423.
  1. Tong M, Wu JA, Chae S, Chern A, Speier W, Hsu W, Taira RK. Computer-assisted systematic review and interactive visualization of published literature. RSNA Annual Meeting. 2010.
  2. Favorov A, Lvovs D, Speier W, Parmigiani G, Ochs M. ONION: an XML format to exchange gene-related probabilities. Information Technologies and Systems. 2010.
  1. Wong Y-N, Meropol N, Speier W, Sargeant D, Goldberg R, Beck JR. Cost Implications of New Treatments for Advanced Colorectal Cancer. Cancer. 2009;115(10):2081–2091.