Natural interactions for medical image analysis

Interaction-Design Master Thesis

Posts Tagged ‘ideas


leave a comment »

Dicom image viewers have the ability to show scanned images with different filters applied. It helps in situations where the radiologist is interested in only some of the body parts. For example there could be a filter that shows only the bones and another filter that shows only the blood vessels. I was thinking about how to combine these different “layers” of information and came up with this concept of “viewing-lenses”. You can drag these lenses over the picture and see different layers of information.
Imagine a touch table with tangible-sheets like in the Microsoft Second Light project… or maybe is better to be able to change the shape and size of the layers. Another idea that came to my mind was combining the lenses – one that shows the bones, another that shows the blood-vessels, put them over each other to see bones and blood-vessel at the same time.

Here is a quick flash prototype to illustrate the idea:


Taking the whole idea and mixing it with my cube interface concept could also be interesting…



Written by Jannes

March 12, 2009 at 18:41

First explorations in multitouch

leave a comment »

I took my paper-multitouch-sketches and transfered them into a video-sketch today. It’s still a rough concept and not all my ides work out so well, but while editing the video I already got a ton of new ideas how to change and improve the multitouch-concept. Also before the video I was thinking about adding some graphical user interface (GUI), but now I really like the simplicity of the visuals and I think it is really important for the radiologist not to get distracted by the GUI. That could be the real advantage in a touch interface for the radiologist.

Written by Jannes

March 11, 2009 at 22:12

Posted in Phase 02 - Ideation

Tagged with , ,

Tacticle “Displays” ?

leave a comment »

What does a radiologist do to locate and identify a tumor? He is looking at pictures and compares them to find known patterns or shapes in the images that are related to the tumor. But there is a lot more attributes to a tumor that would identify it. In mammography it is the first thing to do, touch the breast and get tacticle feedback about lumps. What if there were a sophisticated “tactile display”? So we could actually feel tissue with our hands to look for patterns/shapes. Hands are super sensitive, try to think how easy it is to feel a grain of sand or hair. It could give us additional feedback about softness/hardness, texture, surface, shape, composition…

This got me starting to think about other features that are not considered in radiology yet:
color, temperature and smell of tissue.


picture resources:
Foam Display
Nasa – Touch the invisble sky

further reading:
Wikipedia – Braille Display (display for the blind)

Written by Jannes

March 6, 2009 at 11:15

concepts for interfacing with a worldwide healthcare network

leave a comment »

I already showed some sketches around the idea of a new interface to interact and view 3D models (its obviously my favourite direction so far). But I think I need to focus on more than just this, so I decided to organize and categorize my other ideas and sketches.


So here are some concepts for interfaces that incorporate a world wide healthcare network and ubiquitous information. It’s less about new natural interfaces and more about service, social and information design.

I tried to think about some key aspects in these concepts.

– Crowd sourcing to analyse cases, avoid mistakes and link to similar cases.
– Make the radiologists reading room more social by implementing a social/professional network like LinkedIn.
– Get an emotional connection between the radiologist and his work.
– Link to other data sources from the internet.

See this pdf for more details and sketches.

Written by Jannes

March 5, 2009 at 16:50

Week 2 summary

leave a comment »

In last weeks summary I formulated 8 topics for my research. This week I mostly concentrated on visualization techniques. I reviewed my research plan and marked everything I covered this week in green. Next week I have meetings with Application Specialists and a hospital visit. I am also planning to start my official research on Natural Interfaces (but actually this is the field in which I have a lot of knowledge already, I just need to connect it to Radiology). I marked next weeks research areas in blue. I briefly touch all these areas, depending on my final direction I might need to continue my research on some of these topics later on.

Automated Image Comparison and CAD seems to be the most difficult research area for me. I tried to get some information, but it is hard to find. Papers I found are dealing mainly with math and algorithm for detecting patterns and comparing images. That’s not helping me at all…

– Natural Interfaces, Touchscreens and beyond
– Automated Image Comparison (and artificial Intelligence and CAD)
– Image viewing, editing and enhancement
Data Visualization (with medical 2D, 3D, 4D and 5D? data in mind)
Healthcare 2.0 (everything goes digital: teleradiology, PACS, EMR)
– Radiologists today (workflow, human interactions, technology usage, problems etc…)
– Medical Imaging (CT, MRI, Ultrasound, Fluoroscopy, Nuclear Medicine and how these work together)
– Market research of devices and concepts

Read the rest of this entry »

Written by Jannes

January 30, 2009 at 17:46

Posted in Phase 01 - Research, Weekly Summary

Tagged with