I am now posting my news on LinkedIn and on the Kitware blog site:

Great management philosophy...from Netflix.

posted Oct 3, 2014, 10:34 AM by Stephen Aylward   [ updated Oct 3, 2014, 10:34 AM ]

In the following slides, the presenter does an outstanding job of calling out the standard corporate practice of not matching words with actions, using trite phrases instead of meaningful messages, and equating corporate growth with increased bureaucracy.

Summary of select medical research projects at Kitware

posted Oct 2, 2014, 4:40 PM by Stephen Aylward

I've been asked to give internal and industry presentations on medical research at Kitware.   I cannot do justice to many of the research projects at Kitware in bioinformatics, digital pathology, and electronic health records; but I have made a set of slides that summarize some of my research projects.    I am making those available online.

All Things Open: companion tutorials on CMake, VTK, and ParaView

posted Sep 30, 2014, 4:08 AM by Stephen Aylward

The annual All Things Open conference is being held in Raleigh, NC on October 22 and 23, 2014.

In conjunction with that conference, Kitware is offering two tutorials:

We are expecting a large turn-out for these tutorials, so register early!

Duke Visualization Friday Forum: Kitware's software processes and 3D Slicer for open-source medical image visualzation

posted Sep 30, 2014, 3:48 AM by Stephen Aylward

Julien Finet and I gave a talk at Duke University's Visualization Friday Forum on September 26, 2014.   Attended by over 70 students, faculty, and staff; the talk featured (1) how Kitware's software processes can help academic research groups and help with the lofty goal of reproducible science and (2) how 3D Slicer uses those software processes to become a highly capable medical image visualization and analysis system that can be easily extended using command-line programs and python scripts.

A video recording of our slides and talk is online at:

Interactive Visualization of Google Project Tango Data with ParaView

posted Apr 11, 2014, 9:28 AM by Stephen Aylward

Imagine capturing a 3D model of a room from your phone. This may completely change how we buy furniture, choose paint colors, and have teleconferences. 

Publication: Localizing target structures in ultrasound video – A phantom study

posted Mar 4, 2014, 1:44 PM by Stephen Aylward

Roland Kwitt, Nuno Vasconcelos, Sharif Razzaque, Stephen R. Aylward: Localizing target structures in ultrasound video - A phantom study. Medical Image Analysis 17(7): 712-722 (2013)


The problem of localizing specific anatomic structures using ultrasound (US) video is considered. This involves automatically determining when an US probe is acquiring images of a previously defined object of interest, during the course of an US examination.

Localization using US is motivated by the increased availability of portable, low-cost US probes, which inspire applications where inexperienced personnel and even first-time users acquire US data that is then sent to experts for further assessment. This process is of particular interest for routine examinations in underserved populations as well as for patient triage after natural disasters and large-scale accidents, where experts may be in short supply.

The proposed localization approach is motivated by research in the area of dynamic texture analysis and leverages several recent advances in the field of activity recognition. For evaluation, we introduce an annotated and publicly available database of US video, acquired on three phantoms. Several experiments reveal the challenges of applying video analysis approaches to US images and demonstrate that good localization performance is possible with the proposed solution.

HackNC - productive fun!

posted Mar 4, 2014, 1:37 PM by Stephen Aylward

Had a great time serving as a mentor at the HackNC 2014 hackathon.  240 students were amazingly productive in 24 hours. Congratulations to the organizers, mentors, participants, and winning hacks!  More info is in my blog at:

Publication: A Locally Adaptive Regularization Based on Anisotropic Diffusion for Deformable Image Registration of Sliding Organs

posted Nov 12, 2013, 7:02 AM by Stephen Aylward   [ updated Mar 4, 2014, 1:38 PM ]

We have developed a new medical image registration method for studying changes in an abdomen over time.  We can now find more subtle changes arising from tumors, diseases, and treatments by more accurately modeling the normal sliding motions of internal organs.

The work is published in the November issue of IEEE Transactions on Medical Imaging.  It is available via the IEEE open-access policy:

Interview with me at MICCAI 2013

posted Sep 18, 2013, 8:00 AM by Stephen Aylward

Are you going to be at MICCAI next week?  Are you hoping to start a new job within the next year?   Please upload your resume using the link below and send me ( an email to arrange an interview at MICCAI!

Publication involving TubeTK: Functional ultrasound imaging for assessment of extracellular matrix scaffolds used for liver organoid formation

posted Sep 8, 2013, 8:50 AM by Stephen Aylward

TubeTK is being used to process ultrasound images of liver tissues grown in a lab. The image-based measurements are helping to refine the tissue growth process so that, one day, livers grown in a lab can help address the dire shortage of liver donors.

Ryan C. Gessner, Ariel D. Hanson, Steven Feingold, Avery T. Cashion, Ana Corcimaru, Bryant T. Wu, Christopher R. Mullins, Stephen R. Aylward, Lola M. Reid, Paul A. Dayton “Functional ultrasound imaging for assessment of extracellular matrix scaffolds used for liver organoid formation” Biomaterials, 4 September 2013, ISSN 0142-9612


A method of 3D functional ultrasound imaging has been developed to enable non-destructive assessment of extracellular matrix scaffolds that have been prepared by decellularization protocols and are intended for recellularization to create organoids. A major challenge in organ decellularization is retaining patent micro-vascular structures crucial for nutrient access and functionality of organoids. The imaging method described here provides statistical distributions of flow rates throughout the tissue volumes, 3D vessel network architecture visualization, characterization of microvessel volumes and sizes, and delineation of matrix from vascular circuits. The imaging protocol was tested on matrix scaffolds that are tissue-specific, but not species-specific, matrix extracts, prepared by a process that preserved >98% of the collagens, collagen-associated matrix components, and matrix-bound growth factors and cytokines. Image-derived data are discussed with respect to assessment of scaffolds followed by proof-of-concept studies in organoid establishment using Hep3B, a human hepatoblast-like cell line. Histology showed that the cells attached to scaffolds with patent vasculature within minutes, achieved engraftment at near 100%, expressed liver-specific functions within 24 h, and yielded evidence of proliferation and increasing differentiation of cells throughout the two weeks of culture studies. This imaging method should prove valuable in analyses of such matrix scaffolds.

1-10 of 57