Apparatus comprising a memory, a control circuit, a user interface, and a radiation treatment platform to facilitate an administration of a knowledge-based radiation treatment plan
A control circuit accesses information regarding a plurality of pre-existing vetted radiation treatment plans for a variety of patients and uses that information to train at least one model (such as a dose volume histogram estimation model). The control circuit then uses that model to develop estimates for a radiation treatment plan for a particular patient. The control circuit can then use those estimates to develop a candidate radiation treatment plan.
1 . An apparatus comprising:
a memory having stored therein information regarding a plurality of pre-existing vetted radiation treatment plans for a variety of patients, wherein the information regarding the plurality of pre-existing vetted radiation treatment plans for a variety of patients includes, at least in part, an abridged version of at least some of the plurality of pre-existing vetted radiation treatment plans for a variety of patients such that the abridged version is anonymous; and
a control circuit operably coupled to the memory and configured to:
use the information to train at least one model; and
use the at least one model to develop estimates for a radiation treatment plan for a particular patient.
2 . The apparatus of claim 1 wherein the information regarding the plurality of pre-existing vetted radiation treatment plans for a variety of patients constitutes an abridged version of each of the plurality of pre-existing vetted radiation treatment plans for a variety of patients such that the information is anonymous and not intrinsically correlated to any of the variety of patients.
3 . The apparatus of claim 1 wherein at least some of the plurality of pre-existing vetted radiation treatment plans for a variety of patients have original formats that are different from one another, and wherein the information regarding the plurality of pre-existing vetted radiation treatment plans for a variety of patients presents contents of the pre-existing vetted radiation treatment plans for a variety of patients in a single consistent format.
4 . The apparatus of claim 1 wherein the control circuit is further configured to use the information to train the at least one model by, at least in part:
identifying outlier data in the information; and
disregarding the outlier data in the information when training the at least one model.
5 . The apparatus of claim 1 wherein the control circuit is further configured to use the information to train the at least one model by, at least in part, using original prescription dose levels as correspond to at least some of the plurality of pre-existing vetted radiation treatment plans for a variety of patients when training the at least one model.
6 . The apparatus of claim 5 wherein the control circuit is further configured to use the original prescription dose levels when training the at least one model by, at least in part, using the original prescription dose levels when normalizing dose volume histograms.
7 . The apparatus of claim 1 wherein the control circuit is further configured to:
select the at least one model to use to develop the estimates for the radiation treatment plan for the particular patient.
8 . The apparatus of claim 7 wherein the control circuit is further configured to select the at least one model to use to develop the estimates for the radiation treatment plan for the particular patient by, at least in part, using metadata as corresponds to the information used to train the at least one model.
9 . The apparatus of claim 1 wherein the control circuit is further configured to:
use geometric limits as correspond to the information used to train the at least one model to assess how well the particular patient fits the information used to train the at least one model.
10 . The apparatus of claim 9 wherein the control circuit is further configured to:
present a user warning upon determining that the particular patient does not fit the information used to train the at least one model within at least a predetermined range of suitability.
11 . The apparatus of claim 1 wherein the control circuit is further configured to:
determine at least one radiation treatment plan objective for the radiation treatment plan for the particular patient.
12 . The apparatus of claim 11 wherein the control circuit is further configured to determine the at least one radiation treatment plan objective, at least in part, by forming the at least one radiation treatment plan objective based upon dose volume histogram estimates formed using the at least one model.
13 . The apparatus of claim 12 wherein forming the at least one radiation treatment plan objective based upon dose volume histogram estimates formed using the at least one model includes emphasizing at least one sub-region, but not all, of a corresponding dose volume histogram during an objective generation process.
14 . The apparatus of claim 12 wherein the control circuit is further configured to:
provide a user opportunity to modify the at least one radiation treatment plan objective for the radiation treatment plan for the particular patient.
15 . The apparatus of claim 1 wherein the control circuit is further configured to:
determine a validation status of the at least one model; and
inhibit an availability of the at least one model unless the validation status of the at least one model has at least a predetermined value.
16 . The apparatus of claim 15 wherein the control circuit is further configured to inhibit the availability of the at least one model unless the validation status of the at least one model has at least a predetermined value by, at least in part, preventing a publication of the at least one model.
17 . The apparatus of claim 1 wherein the control circuit is further configured to:
use the estimates for the radiation treatment plan for the particular patient to develop a candidate radiation treatment plan; and
when displaying the candidate radiation treatment plan, also simultaneously displaying an overall target dose level as corresponds to the candidate radiation treatment plan.
18 . An apparatus comprising:
a memory having stored therein information regarding a plurality of pre-existing vetted radiation treatment plans for a variety of patients, wherein the information regarding the plurality of pre-existing vetted radiation treatment plans for a variety of patients includes, at least in part, an abridged version of at least some of the plurality of pre-existing vetted radiation treatment plans for a variety of patients such that the abridged version is anonymous; and
a control circuit operably coupled to the memory and configured to:
use the information to train at least one model by, at least in part:
identifying outlier data in the information as a function, at least in part, of at least one of:
dose volume histogram graphs;
a regression analysis; and
a particular dose volume histogram that is estimated by comparing the at least one model against every patient geometry in the information; and
disregarding the outlier data in the information when training the at least one model; and
use the at least one model to develop estimates for a radiation treatment plan for a particular patient.
19 . An apparatus comprising:
a memory having stored therein information regarding a plurality of pre-existing vetted radiation treatment plans for a variety of patients,
wherein the information regarding the plurality of pre-existing vetted radiation treatment plans for a variety of patients includes, at least in part, an abridged version of at least some of the plurality of pre-existing vetted radiation treatment plans for a variety of patients such that the abridged version is anonymous; and
a control circuit operably coupled to the memory and configured to:
use the information to train at least one model by, at least in part:
identifying outlier data in the information as a function, at least in part, of a single numerical index for each of the plurality of pre-existing vetted radiation treatment plans for a variety of patients; and
disregarding the outlier data in the information when training the at least one model; and
use the at least one model to develop estimates for a radiation treatment plan for a particular patient.
20 . An apparatus comprising:
a memory having stored therein information regarding a plurality of pre-existing vetted radiation treatment plans for a variety of patients, wherein the information regarding the plurality of pre-existing vetted radiation treatment plans for a variety of patients includes, at least in part, an abridged version of at least some of the plurality of pre-existing vetted radiation treatment plans for a variety of patients such that the abridged version is anonymous; and
a control circuit operably coupled to the memory and configured to:
use the information to train at least one model by, at least in part:
identifying outlier data in the information as a function, at least in part, of particular data comprising at least one of a geometric outlier, a dosimetric outlier, and an influence point outlier; and
disregarding the outlier data in the information when training the at least one model; and
use the at least one model to develop estimates for a radiation treatment plan for a particular patient.