MIPG Lab at Penn Medicine: Segmentation of representative organs in thorax and abdomen from CT images.
Segmentation of representative organs in thorax and abdomen from CT images.


The Medical Image Processing Group (MIPG) at Penn Radiology is one of the oldest and longest active leading research groups in the world engaged in research on the processing, visualization, and analysis of medical images and the medical and clinical applications of these computerized methods.

Some areas of current research study include body-wide Automatic Anatomy Recognition (AAR), body-wide disease quantification (DQ), body composition assessment, radiation therapy planning, pre-treatment planning in thoracic insufficiency syndrome (TIS), and study of obstructive sleep apnea via dynamic MRI.

Faculty And Staff

Jayaram K. Udupa, PhD

Jayaram K. Udupa, PhD

Chief of Section
Professor of Radiologic Science in Radiology
View Full Profile
Drew A. Torigian, MD, Clinical Director, Medical Imaging Processing Group (MIPG)

Drew A. Torigian, MD, MA

Clinical Director

View Full Profile

Yubing Tong, PhD Senior Research Investigator, Medical Image Processing Group

Yubing Tong, PhD

Director of Operations
Senior Research Investigator

View Full Profile
Chris Ciesielski, PhD Adjunct Professor, Medical Image Processing Group

Chris Ciesielski, PhD

Adjunct Professor
Dewey Odhner, MA Systems Manager, Medical Image Processing Group

Dewey Odhner, MA

Systems Manager
Caiyun Wu, BS Technical Assistant, Medical Image Processing Group

Caiyun Wu, MS

Research Specialist D
Tiange Liu, PhD, Postdoc Research Fellow, Medical Image Processing Group

Tiange Liu, PhD

Post-Doctoral Fellow
You Hao, MS PhD Student, Medical Image Processing Group

You Hao, MS

Post-Doctoral Fellow
Yusuf Akhtar, Post-Doctoral Fellow, MIPG Lab

Yusuf Akhtar

Post-Doctoral Fellow
Ademola E Ilesanmi, Post-Doctoral Fellow, MIPG Lab

Ademola Ilesanmi

Post-Doctoral Fellow
Jieyu Li, MS PhD Student, Medical Image Processing Group

Jieyu Li, MS

PhD Student
Da He, PhD student, MIPG Lab

Da He

PhD Student

Recent Publications

  1. Hao Y, Udupa JK, Tong Y, Wu C, Li H, McDonough JM, Lott C, Qiu C, Galagedera N, Anari JB, Torigian DA, Cahill PJ. OFx: A method of 4D image construction from free-breathing non-gated MRI slice acquisitions of the thorax via optical flux. Medical Image Analysis, Volume 72, 2021, 102088, ISSN 1361-8415, https://doi.org/10.1016/j.media.2021.102088.
  2. Li J, Udupa JK, Tong Y, Wang L, Torigian DA. Segmentation evaluation with sparse ground truth data: Simulating true segmentations as perfect/imperfect as those generated by humans. Med Image Analysis. 2021;69:101980. doi: 10.1016/j.media.2021.101980. PubMed PMID: 33588116; PMCID: PMC7933105.
  3. Tong Y, Udupa, JK, McDonough JM, Wu C, Sun C, Qiu C, Lott C, Galagedera N, Anari JB, Mayer OH, Torigian DA, Cahill, PJ. Thoracic Quantitative Dynamic MRI to Understand Developmental Changes in Normal Ventilatory Dynamics. Chest. 2021;159(2):712-23. doi: 10.1016/j.chest.2020.07.066. PubMed PMID: 32768456; PMCID: PMC7856528.
  4. Xu G, Cao H, Udupa JK, Tong Y, Torigian DA. DiSegNet: A deep dilated convolutional encoder-decoder architecture for lymph node segmentation on PET/CT images. Comput Med Imaging Graph. 2021;88:101851. doi: 10.1016/j.compmedimag.2020.101851. PubMed PMID: 33465588.
  5. Yubing Tong, PhD; Udupa JK, McDonough JM, Wu C, Qiu C, Lott C, Galagedera N, Anari JB, Torigian DA, Cahill PJ. A Novel Imaging Study to Quantify Respiratory Function in Early Onset Scoliosis-Introducing Quantitative Dynamic Magnetic Resonance Imaging (QdMRI). Best Basic Science paper in Scoliosis Research Society (SRS), 55th Annual Meeting, Sep. 9 - Sep. 13, 2020.
  6. Yubing Tong, PhD; Udupa JK, McDonough JM, Wu C, Qiu C, Lott C, Galagedera N, Anari JB, Torigian DA, Cahill PJ. Rib-based Anchors do not Impair Chest Wall Motion, Best Science Paper award, in Early Onset Scoliosis, 14th International Congress (2020 ICEOS), November 14, 2020. 
  7. Udupa JK, Tong Y, Capraro A, McDonough JM, Mayer OH, Ho S, Wileyto P, Torigian DA, Campbell RM, Jr. Understanding Respiratory Restrictions as a Function of the Scoliotic Spinal Curve in Thoracic Insufficiency Syndrome: A 4D Dynamic MR Imaging Study. J Pediatr Orthop. 2020;40(4):183-9. doi: 10.1097/BPO.0000000000001258. PubMed PMID: 32132448; PMCID: PMC6426694.
  8. Liu T, Pan J, Torigian DA, Xu P, Miao Q, Tong Y, Udupa JK. ABCNet: A new efficient 3D dense-structure network for segmentation and analysis of body tissue composition on body-torso-wide CT images. Med Phys. 2020. doi: 10.1002/mp.14141. PubMed PMID: 32170754.
  9. Li J, Udupa JK, Tong Y, Wang L, Torigian DA. LinSEM: Linearizing segmentation evaluation metrics for medical images. Med Image Analysis. 2020;60:101601. doi: 10.1016/j.media.2019.101601. PubMed PMID: 31811980; PMCID: PMC6980787.
  10. Tong Y, Udupa JK, McDonough JM, Wileyto EP, Capraro A, Wu C, Ho S, Galagedera N, Talwar D, Mayer OH, Torigian DA, Campbell RM. Quantitative Dynamic Thoracic MRI: Application to Thoracic Insufficiency Syndrome in Pediatric Patients. Radiology. 2019;292(1):206-13. doi: 10.1148/radiol.2019181731. PubMed PMID: 31112090; PMCID: PMC6614911.
  11. Tong Y, Udupa JK, Odhner D, Wu C, Schuster SJ, Torigian DA. Disease quantification on PET/CT images without explicit object delineation. Med Image Analysis. 2019;51:169-83. doi: 10.1016/j.media.2018.11.002. PubMed PMID: 30453165.
  12. Jin Z, Udupa JK, Torigian DA. How many models/atlases are needed as priors for capturing anatomic population variations? Med Image Analysis. 2019;58:101550. doi: 10.1016/j.media.2019.101550. PubMed PMID: 31557632.

Open Positions

We are aggressively seeking to fill several postdoctoral researcher positions. It's a tremendous opportunity for creativity and to be part of fundamental advances within a group that has been engaged in medical imaging research for over 45 years. 

Tasks: Basic research in body-wide image segmentation of all major organs and conceptual body regions, automatic object recognition and delineation, disease quantification, and evaluation, implementing and evaluating algorithms, clinical evaluation in several large applications including cancer, radiation treatment planning, surgery planning, treatment response prediction, etc. 

Qualifications: PhD in computer science/ bioengineering/ electrical engineering/ information sciences; strong mathematical, computational, programming background, appropriate training in 3D image processing, computer vision, general machine learning, and deep learning; medical imaging and processing experience is preferred. Ability to think out of the box will be a plus. 

Please contact Jay Udupa for more information and to apply.
Email: jay@pennmedicine.upenn.edu 

Contact Us

Medical Image Processing Group
Department of Radiology
3710 Hamilton  Walk
#602W, 6th Floor, Goddard Laboratories
Philadelphia, Pennsylvania, 19104

Cathy Oliva
Phone: (215) 615-8042

Learn more about the MIPG

Share This Page: