US 12,148,518 B2
Neural network for recommendation of shoulder surgery type
Jean Chaoui, Locmaria Plouzané (FR); Manuel Jean-Marie Urvoy, Brest (FR); and Marie-Charlotte Desseroit, Brest (FR)
Assigned to Howmedica Osteonics Corp., Mahwah, NJ (US)
Filed by HOWMEDICA OSTEONICS CORP., Mahwah, NJ (US)
Filed on Dec. 10, 2020, as Appl. No. 17/117,687.
Application 17/117,687 is a continuation of application No. PCT/US2019/036991, filed on Jun. 13, 2019.
Claims priority of provisional application 62/804,402, filed on Feb. 12, 2019.
Claims priority of provisional application 62/804,383, filed on Feb. 12, 2019.
Claims priority of provisional application 62/804,392, filed on Feb. 12, 2019.
Claims priority of provisional application 62/778,782, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,788, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,796, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,764, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,778, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,760, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,789, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,774, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,791, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,797, filed on Dec. 12, 2018.
Claims priority of provisional application 62/778,772, filed on Dec. 12, 2018.
Claims priority of provisional application 62/739,406, filed on Oct. 1, 2018.
Claims priority of provisional application 62/687,014, filed on Jun. 19, 2018.
Prior Publication US 2021/0100620 A1, Apr. 8, 2021
Int. Cl. G16H 20/40 (2018.01); A61B 5/00 (2006.01); A61B 5/11 (2006.01); A61B 17/14 (2006.01); A61B 17/16 (2006.01); A61B 17/17 (2006.01); A61B 34/00 (2016.01); A61B 34/10 (2016.01); A61B 90/00 (2016.01); A61B 90/92 (2016.01); A61F 2/40 (2006.01); G02B 27/00 (2006.01); G02B 27/01 (2006.01); G06F 3/01 (2006.01); G06F 3/04815 (2022.01); G06F 3/0482 (2013.01); G06F 30/10 (2020.01); G06F 30/20 (2020.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/55 (2017.01); G06T 11/00 (2006.01); G06T 19/00 (2011.01); G06T 19/20 (2011.01); G09B 5/06 (2006.01); G09B 9/00 (2006.01); G09B 19/00 (2006.01); G09B 23/28 (2006.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 40/20 (2018.01); G16H 40/60 (2018.01); G16H 40/63 (2018.01); G16H 40/67 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01); G16H 70/20 (2018.01); G16H 70/60 (2018.01); G16H 80/00 (2018.01); H04N 13/122 (2018.01); H04N 13/332 (2018.01); A61B 17/00 (2006.01); A61B 17/15 (2006.01); A61B 34/20 (2016.01); A61B 90/50 (2016.01); A61F 2/46 (2006.01); G06F 3/0483 (2013.01); G16H 50/20 (2018.01)
CPC G16H 20/40 (2018.01) [A61B 5/1114 (2013.01); A61B 5/1121 (2013.01); A61B 5/1127 (2013.01); A61B 5/681 (2013.01); A61B 17/142 (2016.11); A61B 17/1604 (2013.01); A61B 17/1626 (2013.01); A61B 17/1659 (2013.01); A61B 17/1684 (2013.01); A61B 17/1703 (2013.01); A61B 34/10 (2016.02); A61B 34/25 (2016.02); A61B 90/08 (2016.02); A61B 90/36 (2016.02); A61B 90/361 (2016.02); A61B 90/37 (2016.02); A61B 90/39 (2016.02); A61B 90/92 (2016.02); A61F 2/40 (2013.01); A61F 2/4081 (2013.01); G02B 27/0075 (2013.01); G02B 27/017 (2013.01); G02B 27/0172 (2013.01); G06F 3/011 (2013.01); G06F 3/04815 (2013.01); G06F 3/0482 (2013.01); G06F 30/10 (2020.01); G06F 30/20 (2020.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06T 7/55 (2017.01); G06T 11/00 (2013.01); G06T 19/006 (2013.01); G06T 19/20 (2013.01); G09B 5/06 (2013.01); G09B 9/00 (2013.01); G09B 19/003 (2013.01); G09B 23/28 (2013.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 40/20 (2018.01); G16H 40/60 (2018.01); G16H 40/63 (2018.01); G16H 40/67 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01); G16H 70/20 (2018.01); G16H 70/60 (2018.01); G16H 80/00 (2018.01); H04N 13/122 (2018.05); H04N 13/332 (2018.05); A61B 5/744 (2013.01); A61B 2017/00115 (2013.01); A61B 2017/00119 (2013.01); A61B 2017/00123 (2013.01); A61B 17/151 (2013.01); A61B 17/1775 (2016.11); A61B 17/1778 (2016.11); A61B 2034/102 (2016.02); A61B 2034/104 (2016.02); A61B 2034/105 (2016.02); A61B 2034/107 (2016.02); A61B 2034/108 (2016.02); A61B 2034/2048 (2016.02); A61B 2034/2051 (2016.02); A61B 2034/2055 (2016.02); A61B 2034/2065 (2016.02); A61B 2034/2068 (2016.02); A61B 2034/252 (2016.02); A61B 2034/254 (2016.02); A61B 2090/062 (2016.02); A61B 2090/067 (2016.02); A61B 2090/0801 (2016.02); A61B 2090/0807 (2016.02); A61B 2090/365 (2016.02); A61B 2090/366 (2016.02); A61B 2090/367 (2016.02); A61B 2090/368 (2016.02); A61B 2090/373 (2016.02); A61B 2090/374 (2016.02); A61B 2090/3762 (2016.02); A61B 2090/378 (2016.02); A61B 2090/3937 (2016.02); A61B 2090/3945 (2016.02); A61B 2090/397 (2016.02); A61B 2090/502 (2016.02); A61B 2505/05 (2013.01); A61B 2562/0219 (2013.01); A61F 2002/4011 (2013.01); A61F 2/4606 (2013.01); A61F 2/4612 (2013.01); A61F 2002/4633 (2013.01); A61F 2002/4658 (2013.01); A61F 2002/4668 (2013.01); G02B 2027/0141 (2013.01); G02B 2027/0174 (2013.01); G06F 3/0483 (2013.01); G06N 3/04 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20036 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30008 (2013.01); G06T 2207/30052 (2013.01); G06T 2207/30204 (2013.01); G06T 2210/41 (2013.01); G06T 2219/2004 (2013.01); G06V 2201/03 (2022.01); G16H 50/20 (2018.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating, by a computing system, a plurality of training datasets, wherein:
a neural network (NN) has an input layer, an output layer, and one or more hidden layers between the input layer and the output layer,
the input layer includes a plurality of input layer neurons, each input layer neuron in the plurality of input layer neurons corresponding to a different input element in a plurality of input elements,
the output layer includes a plurality of output layer neurons, each output layer neuron in the plurality of output layer neurons corresponding to a different output element in a plurality of output elements, the plurality of output elements including a plurality of surgery type output elements, each surgery type output element in the plurality of surgery type output elements corresponding to a different type of shoulder surgery in a plurality of types of shoulder surgery, wherein the plurality of types of shoulder surgery includes a standard total shoulder arthroplasty and a reverse shoulder arthroplasty;
each respective training dataset corresponds to a different training data patient in a plurality of training data patients and comprises a respective training input vector and a respective target output vector,
for each respective training dataset, the training input vector of the respective training dataset comprises a value for each element of the plurality of input elements,
for each respective training dataset, the target output vector of the respective training dataset comprises a value for each element of the plurality of output elements;
using, by the computing system, the plurality of training datasets to train the NN;
obtaining, by the computing system, a current input vector that corresponds to a current patient;
applying, by the computing system, the NN to the current input vector to generate a current output vector; and
determining, by the computing system, based on the current output vector, a recommended type of shoulder surgery for the current patient, wherein the recommended type of shoulder surgery is one of the plurality of types of shoulder surgery including the standard total shoulder arthroplasty and the reverse shoulder arthroplasty.