Skip to main content
Give
Edit Icon - Click to update your profileUpdate Your Profile

Edward H. Herskovits, MD, PhD

Academic Title:

Adjunct Professor

Primary Appointment:

Diagnostic Radiology and Nuclear Medicine

Email:

eherskovits@umm.edu

Location:

UMMC N2E23

Phone (Primary):

(410) 328-9313

Phone (Secondary):

(410) 328-4154

Download CV

Education and Training

1982   BS       Biochemistry, UCLA (Magna Cum Laude)             

1986   MD      UCLA    

1991   PhD     Medical Informatics, Stanford University, Thesis Advisor: Gregory F Cooper

1986 - 1987   Internship, Cedars Sinai Medial Center

1992 - 1996   Residency, Radiology, Johns Hopkins University

1996 - 1997   Fellowship, Neuroradiology, Johns Hopkins University

Biosketch

Dr. Herskovits, a board certified radiologist and neuroradiologist, has extensive experience in image analysis and data mining, including Bayesian methods for the analysis of multidimensional data (including image and genetic data), biostatistics, object-oriented software development, neuroinformatics and clinical neuroradiology. He has over 20 years of experience applying probability theory and information theory to data analysis and was Principal Investigator on the NIH-funded Brain-Image Database project from 1998-2013.

Dr. Herskovits developed the first, and co-developed the second, machine-learning algorithm for deriving a Bayesian network from data. He subsequently adapted these data-mining algorithms to accommodate spatial, temporal and genetic data by focusing on scalability and robustness to undersampling. Dr. Herskovits has worked with psychiatrists and neurologists to apply these algorithms to morphometric, lesion-deficit, and longitudinal data across a broad array of brain disorders, including traumatic brain injury, stroke, sickle cell disease, autism, and dementia.

Research/Clinical Keywords

Neuroradiology, Informatics, Machine Learning, Data Mining

Highlighted Publications

  • Cooper GF, Herskovits EH. The induction of probabilistic networks from data. Machine Learning. 1992;9(4):309-347.
  • Chen R, Hillis AE, Pawlak MA, Herskovits EH. Voxel-wise Bayesian lesion-deficit analysis. NeuroImage. 2008 May;40(4):1633-1642.
  • Jiao Y, Chen R, Ke X, Chu K, Lu Z, Herskovits EH. Predictive models of autism spectrum disorder based on brain regional cortical thickness. NeuroImage. 2010;50(2):589-599.
  • Chen R, Herskovits EH. Machine-learning techniques for building a diagnostic model for very mild dementia. NeuroImage. 2010;52(1):234-244.
  • Chen R, Herskovits EH. Voxel-based Bayesian lesion-symptom mapping. NeuroImage. 2010;49(1): 597-602.
  • Chen R, Resnick SM, Davatzikos C, Herskovits EH. Dynamic Bayesian network modeling for longitudinal brain morphometry. NeuroImage. 2012;59(3):2330-2338.
  • Herskovits EH, Hong EL, Kochunov P, Sampath H, Chen R. Edge-centered DTI connectivity analysis: application to schizophrenia. Neuroinformatics. 2015;13:501–509.
  • Chen R, Zheng Y, Nixon E, Herskovits EH. Dynamic network model with continuous valued nodes for longitudinal brain morphometry. NeuroImage. 2017;155:605–611.
  • Chen R, Krejza J, Arkuszewski M, Zimmerman RA, Herskovits EH, Melhem ER. Brain morphometric analysis predicts decline of intelligence quotient in children with sickle cell disease: A preliminary study. Advances in Medical Sciences. 2017;62(1):151–157.
  • Dashevsky BZ, Bercu ZL, Bhosale PR, Burton KR, Chatterjee AR, Frigini LAR, Heacock L, Herskovits EH, Lee JT, Subhas N, Wasnik AP, Gyftopoulos S. Multicenter research studies in Radiology. Academic Radiology, Academic Radiology, 25(1):18–25, 2018.

Additional Publication Citations

  1. Kaye DB, Herskovits EH. A CRT graphics system for experimental research. Behavior Research Methods, Instruments, and Computers. 1984;16(5):463-467.
  2. Herskovits E: A hybrid classifier for automated radiologic diagnosis: preliminary results and clinical applications. Computer Methods & Programs in Biomedicine. 1990 May;32(1):45-52.
  3. Herskovits EH. Cooper GF. Algorithms for Bayesian belief-network precomputation. Methods of Information in Medicine 1991 Apr;30(2):81-89.
  4. Cooper GF, Herskovits EH. The induction of probabilistic networks from data. Machine Learning, 1992;9(4):309-347.
  5. Letovsky SI, Whitehead SH, Paik CH, Miller GA, Gerber J, Herskovits EH, Fulton TK, Bryan RN. A brain-image database for structure/function analysis. American Journal of Neuroradiology. 1998 Nov-Dec;19(10):1869-1877.
  6. Herskovits EH, Megalooikonomou V, Davatzikos C, Chen A, Bryan RN, Gerring JP. Is the spatial distribution of brain lesions associated with closed-head injury predictive of subsequent development of attention-deficit/hyperactivity disorder? Analysis with a brain-image database. Radiology. 1999 Nov;213(2):389-394.
  7. Horská A, Naidu S, Herskovits EH, Wang PY, Kaufmann WE, Barker PB. Quantitative 1H MR spectroscopic imaging in early Rett syndrome. Neurology. 2000 Feb;54(3):715-722.
  8. Gerring J, Brady K, Chen A, Quinn C, Herskovits E, Bandeen-Roche K, Denckla MB, Bryan RN. Neuroimaging variables related to development of secondary attention deficit hyperactivity disorder after closed head injury in children and adolescents. Brain Injury. 2000 Mar;14(3):205-218.
  9. Megalooikonomou V, Davatzikos C, Herskovits EH. A simulator for evaluating methods for the detection of lesion-deficit associations. Human Brain Mapping. 2000 Jun;10(2):61-73.
  10. McClelland R, Kronmal R, Bryan RN, Herskovits EH, O'Leary D, Price T, Kuller L. Neurologic correlates of large infarct location in the Cardiovascular Health Study. Journal of Stroke and Cerebrovascular Diseases. 2000 Sep;9(5):218-228.
  11. Herskovits EH. An architecture for a brain-image database. Methods of Information in Medicine. 2000 Dec;39(4-5):291-297.
  12. Davatzikos C, Li HH, Herskovits E, Resnick SM. Accuracy and sensitivity of detection of activation foci in the brain via statistical parametric mapping: a study using a PET simulator. NeuroImage. 2001 Jan;13(1):176-184.
  13. Shen D, Herskovits EH, Davatzikos C. An adaptive-focus statistical shape model for segmentation and shape modeling of 3-D brain structures. IEEE Transactions on Medical Imaging. 2001 Apr;20(4):257-270.
  14. Herskovits EH, Itoh R, Melhem ER. Accuracy for detection of simulated lesions: comparison of fluid-attenuated inversion-recovery, proton density-weighted, and T2-weighted synthetic brain MR imaging. American Journal of Roentgenology. 2001 May;176(5):1313-1318.
  15. Avellino, AM, Wang PP, Miller NH, Herskovits EH. FLAIR magnetic resonance image of a pediatric spinal epidermoid cyst. Pediatric Neurosurgery. 2002 Apr;36(4):220-222.
  16. Herskovits EH, Gerring JP, Davatzikos C, Bryan RN. Is the spatial distribution of brain lesions associated with closed-head injury in children predictive of subsequent development of posttraumatic stress disorder? Radiology. 2002 Aug;224(2):345-351.
  17. Oguz KK, Yousem DM, Deluca T, Herskovits EH, Beauchamp, NJ. Impact of pager notification on report verification times. Academic Radiology. 2002 Aug;9(8):954-959.
  18. Davatzikos C, Liu D, Shen D, Herskovits EH. Spatial normalization of spine MR images for statistical correlation of lesions with clinical symptoms. Radiology. 2002 Sep;224(3):919-926.
  19. Oguz KK, Yousem DM, Deluca T, Herskovits EH, Beauchamp, NJ. Effect of emergency department CT on neuroimaging case volume and positive scan rates. Academic Radiology. 2002 Sep;9(9):1018-1024.
  20. Melhem ER, Herskovits EH, Oguz KK, Golay X, Hammoud DA, Fortman BJ, Munter FM, Itoh R. Defining thresholds for changes in size of simulated T2-hyperintense brain lesions on the basis of qualitative comparisons. American Journal of Roentgenology. 2003 Jan;180(1):65-69.
  21. Hammoud DA, Belden CJ, Ho AC, Dal Pan GJ, Herskovits EH, HiltDC, Brem H, Pomper MG. The surgical bed after BCNU polymer wafer placement for recurrent glioma: serial assessment on CT and MR imaging. American Journal of Roentgenology. 2003 May;180(5):1469-1475.
  22. Herskovits EH, Gerring JP. Application of a data-mining method based on Bayesian networks to lesion-deficit analysis. NeuroImage. 2003 Aug;19(4):1664-1673.
  23. Jacobs MA, Barker PB, Bluemke DA, Maranto C, Arnold C, Herskovits EH, Bhujwalla Z. Benign and malignant breast lesions: diagnosis with multiparametric MR imaging. Radiology. 2003 Oct;229(1):225-232.
  24. Vasa RA, Grados M, Slomine B, Herskovits EH, Thompson, RE, Salorio C, Christensen J, Wursta C, Riddle MA, Gerring, JP. Neuroimaging correlates of anxiety after pediatric traumatic brain injury. Biological Psychiatry. 2004 Feb;55(3):208-216.
  25. Herskovits EH, Peng H, Davatzikos C. A Bayesian morphometry algorithm. IEEE Transactions on Medical Imaging. 2004 Jun;23(6):723-737.
  26. Shen D, Lao Z, Zeng J, Zhang W, Sesterhenn IA, Sun L, Moul JW, Herskovits EH, Fichtinger G, Davatzikos C. Optimized prostate biopsy via a statistical atlas of cancer spatial distribution. Medical Image Analysis. 2004 Jun;8(2):139-150.
  27. Hillis AE, Newhart M, Heidler J, Barker P, Herskovits EH, Degaonkar M. The roles of the "visual word form area" in reading. NeuroImage. 2005 Jan;24(2):548-559.
  28. Hillis AE, Newhart M, Heidler J, Barker P, Herskovits EH, Degaonkar M. Anatomy of spatial attention: insights from perfusion imaging and hemispatial neglect in acute stroke. Journal of Neuroscience. 2005 Mar;25(12):3161-3167.
  29. Jacobs MA, Herskovits EH, Kim HS. Uterine fibroids: diffusion-weighted MR imaging for monitoring therapy with focused ultrasound surgery—preliminary study. Radiology. 2005 Jul;236(1):196-203.
  30. Chen R, Herskovits EH. Graphical-model-based morphometric analysis. IEEE Transactions on Medical Imaging. 2005 Oct;24(10):1237-1248.
  31. Chen R, Herskovits EH. Network analysis of mild cognitive impairment. NeuroImage. 2006 Feb;29(4):1252-1259.
  32. Pikus L, Woo JH, Wolf RL, Herskovits EH, Moonis G, Jawad AF, Krejza J, Melhem ER. Artificial multiple sclerosis lesions on simulated FLAIR brain MR images: echo time and observer performance in detection. Radiology. 2006 Apr;239(1):238-245. 
  33. Bilello M, Lao Z, Krejza J, Hillis AE, Herskovits EH. Statistical atlas of acute stroke from magnetic resonance diffusion-weighted-images of the brain. Neuroinformatics. 2006 Summer;4(3):235-242.
  34. Chen R, Herskovits EH. Graphical-model–based multivariate analysis of functional magnetic-resonance data. NeuroImage. 2007 Apr;35(2):635-647. 
  35. Chen R, Herskovits EH. Clinical diagnosis based on Bayesian classification of functional magnetic-resonance data. Neuroinformatics. 2007 Sep;5(3):178-188.
  36. Philipose LE, Gottesman RF, Newhart M, Kleinman JT, Herskovits EH, Pawlak MA, Marsh EB, Davis C, Heidler-Gary J, Hillis AE: Neural regions essential for reading and spelling of words and pseudowords. Annals of Neurology. 2007 Nov;62(5):481-492.
  37. Bizzi A, Castelli G, Bugiani, M, Barker PB, Herskovits EH, Danesi U, Erbetta A, Moroni I, Farina L, Uziel G. Classification of childhood white-matter disorders using proton MR spectroscopic imaging. American Journal of Neuroradiology. 2008 Aug;29(7):1270-1275.
  38. Chen R, Hillis AE, Pawlak MA, Herskovits EH. Voxel-wise Bayesian lesion-deficit analysis. NeuroImage. 2008 May;40(4):1633-1642.
  39. Herskovits EH, Bryan RN, Yang F. Automated Bayesian segmentation of microvascular white-matter lesions in the ACCORD-MIND study. Advances in Medical Sciences. 2008;53(2):182-190.
  40. Herskovits EH, Chen R: Integrating data-mining support into a brain-image database using open-source components. Advances in Medical Sciences. 2008;53(2):172-181.
  41. Chen R, Pawlak M, Flynn T, Krejza J, Herskovits EH, Melhem ER. Brain morphometry and intelligence-quotient measurements in children with sickle-cell disease. Journal of Developmental and Behavioral Pediatrics. 2009;30(6):509-517.
  42. Cloutman L, Gottesman R, Chaudhry P, Davis C, Kleinman JT, Pawlak M, Herskovits EH, Kannan V, Lee A, Newhart M, Heidler-Gary J, Hillis AE. Where (in the brain) do semantic errors come from. Cortex. 2009;45(5):641-649.
  43. Medina J, Kannan V, Pawlak M, Kleinman JT, Newhart M, Davis C, Heidler-Gary JE, Herskovits EH, Hillis AE. Neural substrates of visuospatial processing in distinct reference frames: evidence from unilateral spatial neglect. Journal of Cognitive Neuroscience. 2009;21(11):2073-2084.
  44. Chen R, Herskovits EH. Voxel-based Bayesian lesion-symptom mapping. NeuroImage. 2010;49(1): 597-602.
  45. Chen R, Herskovits EH. Machine-learning techniques for building a diagnostic model for very mild dementia. NeuroImage. 2010;52(1):234-244.
  46. Jiao Y, Chen R, Ke X, Chu K, Lu Z, Herskovits EH. Predictive models of autism spectrum disorder based on brain regional cortical thickness. NeuroImage. 2010;50(2):589-599.
  47. Chen R, Jiao Y, Herskovits EH. Structural MRI in autism spectrum disorder. Neuropsychiatric Disorders and Pediatric Psychiatry 2011;69(5 Pt 2):63R-68R.
  48. Jiao Y, Chen R, Ke X, Cheng L, Chu K, Lu Z, Herskovits EH. Single nucleotide polymorphisms predict symptom severity of autism spectrum disorder. Journal of Autism and Developmental Disorders. 2012;42(6):971-983.
  49. Jiao Y, Chen R, Ke X, Cheng L, Chu K, Lu Z, Herskovits EH. Predictive models for subtypes of autism spectrum disorder based on single-nucleotide polymorphisms and magnetic resonance imaging. Advances in Medical Sciences. 2011;56(2):334-342.
  50. Chen R, Herskovits EH. Graphical model based multivariate analysis (GAMMA): an open-source, cross-platform neuroimaging data analysis software package. Neuroinformatics. 2012;10(2):119-127.
  51. Chen R, Resnick SM, Davatzikos C, Herskovits EH. Dynamic Bayesian network modeling for longitudinal brain morphometry. NeuroImage. 2012;59(3):2330-2338.
  52. Chen R, Young K, Chao LL, Miller B, Yaffe K, Weiner M, Herskovits EH. Prediction of conversion from mild cognitive impairment to Alzheimer disease based on Bayesian data mining with ensemble learning. The Neuroradiology Journal. 2012;25(1):5-16.
  53. Chen R, Wang S, Poptani H, Melhem ER, Herskovits EH. A Bayesian diagnostic system to differentiate glioblastomas from solitary brain metastases. NRJ Digital, 3(7):245–253, 2013.
  54. Heidler-Gary J, Pawlak M, Herskovits EH, Newhart M, Davis C, Trupe LA, Hillis AE. Motor extinction in distinct reference frames: A double dissociation. Behavioural Neurology, 26(1-2):111–119, 2013.
  55. Chen R, Herskovits EH. Examining the multifactorial nature of a cognitive process using Bayesian brain-behavior modeling. Computerized Medical Imaging and Graphics, (41):117–125, 2015.
  56. Chen R, Arkuszewski M, Krejza J, Zimmerman RA, Herskovits EH, Melhem ER. A prospective longitudinal brain-morphometry study of children with sickle-cell disease. American Journal of Neuroradiology, (36):403–410, 2015.
  57. Hickok G, Rogalsky C, Chen R, Herskovits EH, Townsley S, Hillis A. Partially overlapping sensorimotor networks underlie speech praxis and verbal short-term memory: Evidence from apraxia of speech following acute stroke. Frontiers in Human Neuroscience, (8):649, 2014.
  58. Herskovits EH. Quantitative Radiology: Applications to Oncology. Advances in Cancer Research, 124:1–30, 2014.
  59. Maralani PJ, Melhem ER, Wang S, Herskovits EH, Voluck MR, Kim SJ, O'Rourke DM, Mohan S. Association of dynamic susceptibility contrast enhanced MR perfusion parameters with prognosis in elderly patients with glioblastomas. European Radiology, 25(9): 2738–2744, 2015.
  60. Chen R, Herskovits EH. The Alzheimer's Disease Neuroimaging Initiative. Predictive structural dynamic network analysis. Journal of Neuroscience Methods, 245:58–63, 2015.
  61. Herskovits EH, Hong EL, Kochunov P, Sampath H, Chen R. Edge-centered DTI connectivity analysis: application to schizophrenia. Neuroinformatics, 13:501–509, 2015.
  62. Chen R, Herskovits EH. Bayesian predictive modeling based on multidimensional connectivity profiling. The Neuroradiology Journal, 28:5–11, 2015.
  63. Wang Q, Chen R, JaJa J, Jin Y, Hong EL, Herskovits EH. Connectivity-based brain parcellation: a connectivity-based atlas for schizophrenia research. Neuroinformatics, in press, 14(1):83–97, 2015.
  64. Sajedi P, Herskovits EH, Mitchell J, Raghavan P. Routine cross-sectional head imaging prior to electroconvulsive therapy: A tertiary center experience. The Journal of the AmericanCollege of Radiology, 13(4)429–434, 015.
  65. Chen R, Nixon E, Herskovits EH. Advanced Connectivity Analysis (ACA): A large scale functional connectivity data mining environment. Neuroinformatics, 14(2): 191–199, 2016.
  66. Dreizin D, Bodanapally UK, Neerchal N, Tirada N, Patlas M, Herskovits EH. Volumetric analysis of pelvic hematomas after blunt trauma using semi-automated seeded region growing segmentation: a method validation study. Abdominal Radiology, 41(11):2203–2208, 2016.
  67. Chen R, Zheng Y, Nixon E, Herskovits EH. Dynamic network model with continuous valued nodes for longitudinal brain morphometry. NeuroImage, 155:605–611, 2017.
  68. Chen R, Krejza J, Arkuszewski M, Zimmerman RA, Herskovits EH, Melhem ER. Brain morphometric analysis predicts decline of intelligence quotient in children with sickle cell disease: A preliminary study. Advances in Medical Sciences, 62(1):151–157, 2017.
  69. Dashevsky BZ, Bercu ZL, Bhosale PR, Burton KR, Chatterjee AR, Frigini LAR, Heacock L, Herskovits EH, Lee JT, Subhas N, Wasnik AP, Gyftopoulos S. Multicenter research studies in Radiology. Academic Radiology, 25(1):18–25, 2018..
  70. Kim DC, Herskovits EH, Johnson PT. Science to practice: IT solutions to drive standardized report recommendations for abdominal aortic aneurysm surveillance. Journal of the American College of Radiology, 15(6):865–869, 2018.
  71. Bryan RN, Davatzikos C, Herskovits EH, Mohan S, Rudie JD, Rauschecker AM. Medical Image Analysis: Human and Machine. Academic Radiology, 27(1):76–81, 2020.

 

Awards and Affiliations

1998   Richard S. Ross Clinician Scientist Award, Johns Hopkins University, awarded for promise and distinguished performance in research

 

1982 Phi Beta Kappa

Grants and Contracts

2018-2020    Principal Investigator

“Connectivity and Genetic Associations in Parkinson's Disease”       

NIH R21 AG058118

 

2018-2020    Principal Investigator

“Connectivity and Genetic Associations in Alzheimer's Disease”       

NIH R21 AG058118 (Supplement)

 

2018-2020    Principal Investigator

“Machine Learning to Generate a Multivariate Model of Brain Injury in HIV Patients”       

NIH R21 NS108811

 

2013-2015    Principal Investigator

“Brain Atlas Generation from DTI”        

MarylandCenter for Health Informatics and Biotechnology

 

1998-2013    Principal Investigator

“Spatially Oriented Database for Digital Brain Images”       

NIH R01 AG013743

 

2007-2012    Co-Investigator

“Neural Basis of Lexical Deficits in Hyperacute Stroke”

Johns Hopkins University (subcontract)

NIH R01 DC05375

 

2003-2008    Co-Investigator

“Cognitive and Spatial Systems in Action”        

Moss Rehabilitation Center (subcontract)

NIH R01 NS036387

 

 2004-2008    Co-Investigator

“The Cognitive Neuroscience of Body Knowledge”      

NIH R01 NS048130

 

2004-2010      Co-investigator 

“Study of Fiber Anatomy in Mouse Development via MRI/DTI”

NIH, R01 MH070365

 

2005-2010      Co-investigator 

“Database System for Patient-Based Neuroscience Research”

NIH, R01 MH073529

 

2005-2011      Co-investigator 

"Computational Neuroanatomy of Aging Using Shape Analysis"

NIH, R01 AG014971

 

2005-2011      Co-investigator 

“Cognitive and Neuroimaging Studies in Sickle Cell Disease”

NIH, R01 NS046717

Edit Icon - Click to update your profileUpdate Your Profile