The minimisation of the Aggregated Objective Function
f
can be interpreted as finding the value
f
for which the line with slope
–w
1
/w
2
just touches the boundary of
F
as it proceeds outwards
from the origin.
Pareto Front
Create a single Objective Function via
weighted Aggregation
Inverse Optimisation and Planning
Empirically estimated penalisation schemes,
found to result to „good“ dose distributions are
ussually saved as
presets / protocols / class
solutions
and can be used as starting points for the
individual patient plan optimisation process.
w1 f1 + w2 f2
???
The plan/solution which is obtained in the
Weighted
Aggregation
approach depends on the shape of the
Pareto Front
and the
importance factors/penalties
used.
Planner is not aware if there exist a better
“choice”
on
the
Pareto Front
just next door!