if the cell is positive for this protein and appears blue from the background staining if it is not.

In the design of an ML pipeline, two apparent choices of class labels for this problem exist: pixel labels and nuclei labels placed on the center of the nuclei.

If pixel labels are used, pixels belonging to positive and negative nuclei can be visualized to the user as an overlay on top of the original image, occluding the nuclei. If nuclei labels are used, the result can be visualized by placing glyphs on the center of each detected nucleus. Using glyphs makes it easier for the user to detect errors, since less ink is used to visualize the result and the original image becomes more visible. It also becomes easier to correct misplaced markers, since less precision is needed to click on markers than on pixels. The second approach was implemented as a product, shown in Figure 5.

For the user to be able to correct the
results, in addition to actually seeing
the underlying phenomena they must
also be able to perform the validation
with reasonable effort in relation to
perceived gain. For this design, we
borrowed an heuristic from the light
microscope and limited predictions
to only 200 nuclei in the most prolific
region.

This design also illustrates the seminal principle of direct manipulation [ 3]; the result is presented in an input-output symmetric way in which the user can directly manipulate the labeled data. By designing the system to allow for such direct manipulation, making the validation possible with reasonable effort and providing an intrinsic incentive in terms of the actual nuclei count, user corrections can be used to directly retrain and improve the underlying machine-learning model.

Our final example of an ML direct-manipulation interface is the patch gallery prototype shown in Figure

6, where the goal is to estimate the distribution of classes in an area. In this prototype, we generate a grid pattern over a user-selected area and extract a small image patch for each point in the grid. We then feed each

We look forward to the point when our
user interfaces need to be redesigned
or augmented with interactions that are
adapted to ML components with much
higher performance.

ACM Conference
Proceedings
Now Available via
Print-on-Demand!

Did you know that you can
now order many popular
ACM conference proceedings
via print-on-demand?

Institutions, libraries and individuals can choose from more than 100 titles on a continually updated list through Amazon, Barnes

& Noble, Baker & Taylor, Ingram and NACSCORP: CHI, KDD, Multimedia, SIGIR, SIGCOMM, SIGCSE, SIGMOD/PODS, and many more.

For available titles and ordering info, visit: librarians.acm.org/pod

ACM Conference
Proceedings
Now Available via
Print-on-Demand!

Figure 5. An example of a symmetric input-output ML-system of a cell-counting system for KI- 67 stainings.