medical imaging

During my work with the Celadon Research Division of Ellumen Inc., I have had three patents that I was a co-inventor on issue to date. The first patent was issued in August 2015, titled “Dielectric Encoding of Medical Images.” The second patent was issued in July 2016, titled “Distributed Microwave Image Processing System and Method.” The third patent was issued in July 2017, also titled “Dielectric Encoding of Medical Images.” In addition, a fourth patent titled “Microwave Imaging Device” is expected to issue later this month in January 2018, that I am also a co-inventor on. All of these patents were granted by the United States Patent and Trademark Office (USPTO) and currently assigned to Ellumen Inc. I wanted to provide a brief discussion of the first three issued patents.

The first and third patents titled “Dielectric Encoding of Medical Images” resulted from wanting a way to allow for doctors to easily read and understand images produced using electromagnetics represented in dielectric values. To accomplish this I worked with the chief executive officer (CEO) of Ellumen Inc. to explore the microwave imaging modality while also allowing for easy adaptability by doctors and hospitals. I researched the modality, developed algorithms, and developed programs to convert medical images in dielectric values to Hounsfield units, which are present in computed tomography (CT) scans, and to MRI intensity values, which are present in magnetic resonance imaging (MRI) scans. The code successfully worked for single frequencies and over a range of frequency values (using a Debye model). This allows for doctors to understand images producing using electromagnetics in readily understood CT and/or MRI formats without requiring any additional training, leading to timely and accurate medical diagnosis. The conversion method developed allows for existing medical diagnostic tools and analysis techniques to be used directly with microwave imaging. In addition, the method for conversion from an image in Hounsfield units to dielectric values and conversion from an image in dielectric values to Hounsfield units can go in both directions. Furthermore, the method for conversion from an image in dielectric values to MRI intensity values includes creating a water content map and a T1 map as an intermediary step. The patent also included a method to convert medical images in Hounsfield units to dielectric values using a frequency dependent model. Deriving dielectric models from CT scans is often useful when solving complex problems in computational electromagnetics. 

The second patent titled “Distributed Microwave Image Processing System and Method” resulted from the need to want all imaging centers, radiology groups, and/or doctor’s offices to be able to have access to images produced using electromagnetics without having to upgrade their computer hardware. A method was developed to allow for the majority of image processing and image reconstruction of microwave images to occur in a centralized computing environment. Instead of performing image processing and image reconstruction at the imaging centers, radiology groups, and/or doctor’s offices, these remote sites send the microwave data they collect to the the centralized computing environment.  The centralized computing environment also offers another distinct advantage; the data and results acquired at all the remote sites can be stored and used to enhance processing and reconstruction of microwave images. The centralized computing environment takes advantage of multiple processors to perform iterative reconstruction and seeds the reconstruction using prior data. In one embodiment of the invention, the seed is generated by first comparing collected and stored scattering fields to find a best or closest match and then using stored data of a prior reconstructed image reconstructed corresponding to the stored scattering fields of the best or closest match. In another embodiment of the invention, the seed is generated by both of (1) using the collected microwave data and (2) using stored data of a prior reconstructed image of a different patient which closely matches data of the current patient. The centralized computing environment also has the capability to convert medical images in dielectric values to Hounsfield units. The method developed and described allows for more accurate image reconstructions to occur in less time than if they were performed at remote sites.

It is exciting to work on new technology and methods that can have a real impact on the health of patients. Below are three patent certificates that were created to celebrate the accomplishment of having these three patents granted.

Todd McCollough Patents Ellumen Celadon

I was able to attend the Radiological Society of North America (RSNA) meeting at McCormick Place in Chicago, IL, which occurred from November 26 to December 1, 2017. The annual meeting is a very large gathering of industry leaders in medical imaging, radiologists, and other related industry professionals. This was the 103rd Scientific Assembly and Annual Meeting with the tagline: Explore, Invent, Transform. This year the meeting was heavily focused on topics around machine learning, virtual reality, and 3D printing. Like always, there were lots of exhibitors with many new medical imaging devices ready to discuss and provide demonstrations. There were also interesting plenary sessions, educational courses, and scientific sessions. Furthermore, there were numerous posters and presentations.

A popular feature this year at RSNA, was a deep learning classroom presented by the NVIDIA Deep Learning Institute (DLI), designed for attendees to engage with machine learning tools, write algorithms, and improve their understanding of emerging machine learning technology. In one of these sessions, attendees trained a deep neural network to recognize handwritten digits. In another session, attendees trained convolutional neural networks (CNNs) to create biomarkers to identify the genomics of a disease without the use of an invasive biopsy. In yet another session, attendees segmented magnetic resonance imaging (MRI) images to measure parts of the heart.

Another feature this year was a separate section for machine learning showcase exhibitors. This section allowed those interested in machine learning to easily network with those in the field. This section featured a machine learning theatre with presentations from industry leaders. For example, in one presentation, Google Cloud talked about machine learning in imaging and how to build your own models on the cloud. In another presentation, Siemens Healthineers discussed artificial intelligence solutions for clinical decision making by turning medical images into biomarkers to help increase effectiveness of care. There was also a 3D printing theater with many posters and actual 3D printed parts nearby. In addition, there were several virtual reality demos setup to allow attendees to try themselves.

I was able to attend many interesting courses on machine learning, radiomics, 3D printing, virtual reality, and predictive analytics. For example, in one course I attended there was discussion of how to use KNIME to incorporate radiology data sources into predictive modeling and interpret the results and make visualizations. There was an interesting talk in another course I attended about using virtual reality in medical education and how it can greatly decrease the amount of time needed to teach students when compared to PowerPoint presentations. In yet another course I attended, instructors walked attendees through using Mimics and 3-matic from Materialise. In this course participants were taught how to segment out musculoskeletal, body, neurological, and vascular systems from DICOM files into a Standard Tessellation Language (STL) file for use with a 3D printer.

I was also able to attend the plenary session by Michio Kaku titled “The Next 20 Years: How science and technology will revolutionize business, the economy, jobs, and our way of life.” In the talk Dr. Kaku discussed the next wave of wealth generation in our modern economy which he believes is advancements at the molecular level including in artificial intelligence, nanotechnology, and biotechnology linked together by the cloud. He believes that information will be everywhere and computers will become like the word electricity today, where it is not mentioned in language as it is ubiquitous. Dr. Kaku recognized robots will replace jobs in the future but said robots are weak in three areas: 1) pattern recognition, 2) common sense, and 3) human interactions. Thus he believes in many cases artificial intelligent systems will aid humans and not replace them.

Below are some of the pictures I took while at the RSNA annual meeting in 2017, in Chicago, IL.

RSNA McCormick Place

RSNA 2017 Chicago McCormick Place

Welcome RSNA 2017

RSNA South Technical Exhibits

RSNA Learning Center

RSNA Posters

RSNA Cardiac Informatics Machine Learning

RSNA Deep Learning Classroom


RSNA Virtual Reality

RSNA 3D Printing in Medicine

RSNA 3D Printing Posters

RSNA 3D Imaging in Anatomic Pathology

RSNA 3D Printing Technology

RSNA 3D Printing Schedule

RSNA National Cancer Institute Cancer Imaging Archive

RSNA QIRR Meet the Experts

RSNA Rontgen Reimagined

RSNA Welcome 2017

RSNA Booth Sitting

RSNA Canon Toshiba Medical

RSNA Toshiba

RSNA Machine Learning Google Cloud

RSNA Carestream

RSNA ziehm imaging



RSNA General Electric GE

RSNA Samsung


RSNA Konica Minolta

RSNA Bayer Angiography

RSNA Siemens Healthineers

RSNA Elsevier

RSNA Philips


RSNA Next 20 Years

RSNA Michio Kaku

RSNA Tours and Events

RSNA Technical Exhibit Map South

RSNA Technical Exhibit Map North

RSNA 2017 Chicago

RSNA Corporate Partners 2017

RSNA waterfront Chicago

RSNA 2017 Chicago Landscape