For a better experience, click the Compatibility Mode icon above to turn off Compatibility Mode, which is only for viewing older websites.

Mark Zarella

Mark Zarella, PhD

Research Assistant Professor; Technical Director, Advanced Pathology Imaging Lab

Department: Pathology & Laboratory Medicine


  • BS in Physics - University of Massachusetts
  • PhD in Neuroscience - SUNY Upstate Medical University
  • Postdoctoral Fellowship in Neurobiology - University of Rochester

Memberships / Professional Affiliations

  • White Paper Task Force, Digital Pathology Association
  • Web Task Force, Digital Pathology Association
  • Member, SPIE
  • Member, Association for Pathology Informatics
  • Member, Digital Pathology Association

Dr. Zarella is a research assistant professor in the Department of Pathology and Laboratory Medicine at Drexel University College of Medicine.

Research Interests

Breast cancer diagnostics, pathology imaging, bioinformatics, computer vision, digital pathology.


Dr. Zarella incorporates concepts in digital imaging, signal processing and bioinformatics toward the goal of understanding biological systems.

Current research projects include:

  • Breast cancer characterization from high-resolution image analysis of primary tumor histology
    Breast cancer is a heterogeneous disease encompassing multiple morphologies and different outcomes. Population-based analysis has shown that protein expression patterns as assessed by immunohistochemistry (IHC) can be exploited to divide breast tumors into groups that exhibit different prognostic outcomes and response to treatments. We believe that the predictive capabilities of histological image analysis may be harnessed to objectively and reproducibly characterize breast tumors in a similar manner. We use image feature extraction and deep learning to develop predictive models of breast tumors, to identify heterogeneity and to discover new histologic features with prognostic potential.
  • Image from the research of Mark Zarella

  • H&E color normalization and calibration
    Digital imaging of H&E stained slides has enabled the application of image processing to support pathology workflows. However, the intrinsic variability of biological tissue and the vast differences in tissue preparation protocols lead to significant image variability that can hamper the effectiveness of these computational tools. We are interested in alternative color metrics for image representation, and transformations to normalize pathology images for improved standardization and calibration in the anatomic pathology laboratory.
  • Optical coherence tomography (OCT) for cancer diagnostics
    OCT has been successfully used to diagnose retinal disease, detect bladder cancer, guide esophageal biopsies and improve cardiological imaging. We have developed a custom OCT system to physically penetrate tissue in order to advance cancer diagnostics and detection. Unlike ultrasound, OCT uses light to image tissue in depth, providing substantially improved spatial resolution at nearly the cellular level. In addition, the greater contrast when applied to soft tissue increases the ability to detect tumor margins. We apply this technology with the goal of introducing minimally-invasive diagnostic procedures in the pathology setting.
  • Image from the research of Mark Zarella

  • Pathologist gaze tracking for educational assessment and guidance
    As pathologists gain experience evaluating histology slides, their diagnostic efficiency and performance improves. We hypothesize that part of this improvement can be owed to the adoption of new slide viewing strategies that better equip the pathologist to integrate the most relevant information in the slide at a faster rate. Using synchronized eye tracking, image analysis, and visual psychophysics, we discovered that viewing strategies vary by training level and do so in a dynamic manner. We continue to investigate the differences in gaze habits between pathologists to identify optimal whole-slide viewing strategies.

Current lab members and collaborators:

  • Fernando U. Garcia, MD, Cancer Treatment Centers of America, Eastern Regional Medical Center
  • David E. Breen, PhD, College of Computing & Informatics, Drexel University
  • Zahra Riahy, student
  • Hanjie (Hollis) Liu, student
  • Dan Johnson, student

In the Media


See Dr. Zarella's Orcid publication list

"An alternative image representation for the reduced impact of H&E staining variability"
Zarella MD, Yeoh C, Breen DE, Garcia FU
PLoS One 12(3): p. e0174489 (2017)

"A template matching model for nuclear segmentation in digital images of H&E stained slides"
Zarella MD, Breen DE, Xin W, Garcia FU
Proceedings of the 9th International Conference on Bioinformatics and Biomedical Technology, Lisbon, Portugal (2017)

"Contextual modulation revealed by optical imaging exhibits figural asymmetry in macaque V1 and V2"
Zarella MD, Ts’o DY
Eye and Brain (9): 1-12 (2017)

"Cue combination encoding via contextual modulation of V1 and V2 neurons"
Zarella MD, Ts’o DY
Eye and Brain (8): 177-193 (2016)

"Lymph node metastasis status in breast carcinoma can be predicted via image analysis of tumor histology"
Zarella MD, Breen DE, Reza MdA, Milutinovic A, Garcia FU
Anal. Quant. Cytol. Histol. 37(5): 273-285 (2015)

"An optimized color transformation for the analysis of digital images of Hematoxylin and Eosin stained slides"
Zarella MD, Breen DE, Plagov A, Garcia FU
J Pathol Inform 6(1): 33-41 (2015)

"Painful Unilateral Temporalis Muscle Enlargement: Reactive Masticatory Muscle Hypertrophy"
Katsetos CD, Bianchi MA, Jaffery F, Koutzaki S, Zarella MD, Slater R
Head Neck Pathol. 8(2): 187-193 (2013)

"Whither the hypercolumn?"
Ts'o DY, Zarella MD, Burkitt G
J. Physiol. 587, 2791-2805 (2009)

Contact Information

Research Office

Department of Pathology & Laboratory Medicine
245 N. 15th Street
MS 435
Philadelphia, PA 19102
Phone: 215.762.8657
Fax: 215.762.3274