US 12,453,518 B2
Apparatus and method for validating labeled data generated by a prediction generator
Rohit Jain, Danville, CA (US); Anand Ramani, Fresno, CA (US); Kappagantula Gopalakrishna Murty, Nanaimo (CA); Yogisha H J, Bengaluru (IN); Sanjeev Shrinivas Nadapurohit, Thane (IN); Karthik K. Bharadwaj, Bengaluru (IN); and Leon Ptaszek, Boston, MA (US)
Assigned to Anumana, Inc., Cambridge, MA (US)
Filed by Anumana, Inc., Cambridge, MA (US)
Filed on Dec. 8, 2024, as Appl. No. 18/973,037.
Claims priority of provisional application 63/614,870, filed on Dec. 26, 2023.
Prior Publication US 2025/0204863 A1, Jun. 26, 2025
Int. Cl. A61B 5/00 (2006.01); A61B 5/318 (2021.01)
CPC A61B 5/7221 (2013.01) [A61B 5/318 (2021.01); A61B 5/7267 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An apparatus for validating, using user input, labeled data generated by a prediction generator, wherein the apparatus comprises:
at least a catheter configured for intracardiac use, the at least a catheter comprising at least a transducer configured to detect a cardiac phenomenon and output at least a potential signal, as a function of the cardiac phenomenon;
at least a localization system configured to detect at least a position signal as a function of a location of the at least a catheter; and
at least a computing device, wherein the computing device comprises:
a memory; and
at least a processor communicatively connected to the memory, wherein the memory contains instructions configuring the at least a processor to:
receive the at least a potential signal, wherein the at least a potential signal corresponds to temporal data;
generate, using the at least a processor, processed data using the at least a potential signal;
train a prediction generator on a plurality of labeled training data, wherein the plurality of labeled training data comprises archive data associated with at least an annotation;
generate, using the prediction generator, a plurality of labeled data as a function of the processed data;
display, using a downstream device, the plurality of labeled data to a user interface of a graphical user interface;
receive a user input associated with the plurality of labeled data, wherein the user input comprises one or more of a correction datum and a confirmation datum and wherein the correction datum comprises one or more of a signal segment correction and a segment annotation correction;
retrain the prediction generator using the user input.