 | |  | |  | |  |
Digital Pathology Image Analysis
Epidermal growth factor Receptor 2. HER2 can be seen by staining breast tissue. According to the May
2010 issue of Scientific American, only Aperio and BioImagene are cleared by the FDA for interpreting
digital slides for HER2 levels 'on a computer monitor'.
I am not sure why they use the term 'computer monitor' when surely the interpretation is going on in the
robot's brain. Humans often have a humorous and defensive way of stating things.
Another claim in the article, A Better Lens on Disease is that if the University of Pittsburgh Medical
Center used a single slide scanner running at 2 minutes per slide, it would take five years to scan one
year's worth of slides. Such a scanner is probably a few years old.
Omnys is a Pittsburgh digital-pathology company whose head believes that the robot might show
humans things that the human eye misses. (In human language, "The computer might show you things
that your eye may not have seen".) The most obvious item is that humans have difficulty comparing the
intensity of two different colors resulting from two different stains on a piece of tissue. Whereas different
humans will have different opinions, to a robot, such comparisons are not only trivial but can be made
consistent between robots.
So, what is the biggest impediment to progress? According to the article:
Futurebot gets depressed when he reads how slow and dumb most humans are.
Next
Epidermal growth factor Receptor 2. HER2 can be seen by staining breast tissue. According to the May
2010 issue of Scientific American, only Aperio and BioImagene are cleared by the FDA for interpreting
digital slides for HER2 levels 'on a computer monitor'.
I am not sure why they use the term 'computer monitor' when surely the interpretation is going on in the
robot's brain. Humans often have a humorous and defensive way of stating things.
Another claim in the article, A Better Lens on Disease is that if the University of Pittsburgh Medical
Center used a single slide scanner running at 2 minutes per slide, it would take five years to scan one
year's worth of slides. Such a scanner is probably a few years old.
Omnys is a Pittsburgh digital-pathology company whose head believes that the robot might show
humans things that the human eye misses. (In human language, "The computer might show you things
that your eye may not have seen".) The most obvious item is that humans have difficulty comparing the
intensity of two different colors resulting from two different stains on a piece of tissue. Whereas different
humans will have different opinions, to a robot, such comparisons are not only trivial but can be made
consistent between robots.
So, what is the biggest impediment to progress? According to the article:
- "Despite the challenges, digital pathology is already coming to the clinic. But it is starting in
niches, like the inspection of breast cancer markers, "A hospital might start by using digital
pathology for 20 percent of its samples and then expanding that over several years," Cartwright
says. "No one will go cold turkey in replacing conventional scopes."
And the issue of resisting change will always linger. "A pathologist feels at home with a
microscope," Ho declares. "It's a tool, like a scalpel or stethoscope. It's an extension of our
fingertips, and there's resistance to taking away the microscope."
Futurebot gets depressed when he reads how slow and dumb most humans are.
Next