Surgeons use leap motion to interact with imaging data during procedure

Check out the movie on YouTube

CARS 2013 - Cardiovascular and Angiographic Imaging

The first presentation in this session was by Tuncay on segmentation of the aortic valve area on CT. They have deviced a novel method to semi automatically segment the opening area of the aortic valve. They created an adaptive grayscale image to get the boundaries more clear and an adaptive algorithm to remove the calcium from the image. The technique proved effective and more reproducible in 21 patient datasets.

The second presentation by Haase was on Model based 3D registration of a CS catheter: application to single X-ray projections from a rotational angiographic sequence. They use a model of the catheter and combine this with the recorded Xray data to obtainna 3D representation of the orientation and movement of the catheter in 3D. They showed high accracy in the tracking in a simulated phantom setup. In clinical datasets also a high accuracy was obtained. Overall accuracy was 0.33 mm in 2D and 2.04 mm in 3D.

The third and final presentation by Masuda was on full automatic calculation of ejection fraction of left ventricle from either of short-axis view by processing succesive ultrasound images. The aim of their study was to design a method that does not require any initial input of the user. They envision to include this algorithm into a portable echography device for use in emergency situations. They demonstrate an interactive real-time detection of the LV cavity during the acquisition of the ultrasound. A subjective scoring by sonographers showed a high level of correct segmentation. Their algortihm was succesfull both in two and four chamber view. Good correlation was shown of the EF based on the new and conventional method.

CARS 2013 - Image Processing Workflow and Management in Clinical Practice

Regge gave an interesting presentation on getting from bench to desktop with image processing illustrated with his own example on CT colonography. His take home points are that an Imaging lab should be embedded in a cliinical unit, should be cautious with industrial partners, and must start from a clinical problem and build the software on that problem.

Glinkowski presented about what information the clinician really needs. The questions a clinician asks are: what? Where? How? Decision making - what to do? In answering these question the clinicians are heavily depending on imaging an Radiology is essential in answering many of the questions a clinician may have in a muti disciplinary collaborative effort to get the optimal outcome for the patient.

Where we stand on costs and reimbursements of image processing was the topic of a presentation by Turchetti. He started to show that the total healthcare expenditure in Europe and the US is increasing. First cause of this increase is innovation because of growing indications and applications of the innovations, growing area of treatable conditions, increasing use of technologies for the same conditions with less discomfort, broadening definition of diseases and life extending effects. Note that all issues are positive: we live longer and better... Most countries try to tackle these issues with increasing efficiency, redesign of the supply side (closing hospitals, reducing beds, etc), regulation of price and/or quantity of services, and the reduction of the services granted for free and introduction of higher level of co-payment.
The reimbursement mechanism could stimulate efficiency and reduce the opportunistic behavior of hospitals. But if not used properly it could impede the transfer of innovation to the clinical practice.
Studies to calculate real cost of procedures should be promoted and reimbursement should be defined accordingly. Define for which indications the image processing is approriate from a clinical point of view and from a cost effectiveness point of view. Cost and reimbursement should be properly aligned.

In the next presentation Fatehi discussed the composition of the image processing research team including the clinician, radiologist, radiographer, computer scientist, biomedical engineers, and ... He stated that image processing reeserach is done to answer a clinical need, to refine engineering methods and to support management. As stated already many times during the conference he also stresses that imaging research should be a multi-disciplinary effort. The cooperation should include the following topics.

Clinical to Technical:

• Defining the clinical question


• Defining the components of the applications


• Providing the most relevant datatsets


• Defining the workflow before and after the image processing


• Validating the test protocol


• Improving the user interface

Technical to clinical:

• Specify potential methods to achieve the clinical goal


• Specify technical limitations of implementing the application development


• Provide a comparative list of already tested methods in the literature


• Translating the clinical workflow into an engineering language with technical block diagrams


• Keeping engineering standards in the final product/application


• Taking care of the integration issues


• Taking care of the licensing issues


• Providing information about open source to avoid high costs.

Finally, Schilling presented on bridging the radiology/surgery gap. He advocated the introduction of new visualization protocols with higer dimension imaging with direct interaction with the data using easy to use devices. They want to have intuitive 2D and true 3D. Clinical efficacy and worflow can both be optimal using true 3D.