Method and system for cataract tissue sensing
Systems and methods for sensing tissue in a phacoemulsification procedure are provided herein. A method may include generating a sensing signal through a frequency range centered at a local resonant frequency of an ultrasonic handpiece and measuring impedance characteristics of the signal at a distal end of a needle of an ultrasonic handpiece. A method may further include comparing the measured impedance characteristics of the generated sensing signal with one or more stored impedance profiles. A method may further include classifying, based on the comparison between the measured impedance characteristics and the stored one or more impedance profiles, a medium contacting the distal end of the needle. A method may further include controlling an output of the ultrasonic handpiece based on the classification of the medium contacting the tip of the needle.
1 . A system for use in a phacoemulsification procedure comprising:
a console comprising a processor and a memory device; and
an ultrasonic handpiece comprising a needle coupled with a distal end of the ultrasonic handpiece, wherein the needle comprises a distal end and wherein the ultrasonic handpiece is coupled with the console;
the processor configured to generate a sensing signal through a frequency range centered at a local resonant frequency of the ultrasonic handpiece;
the processor configured to measure impedance characteristics of the sensing signal at the distal end of the needle;
the processor configured to compare the measured impedance characteristics of the generated sensing signal with one or more impedance profiles stored in the memory device;
the processor and the memory device configured to classify, based on the comparison between the measured impedance characteristics and the stored one or more impedance profiles, a medium contacting the distal end of the needle; and
the processor configured to control an output of the ultrasonic handpiece based on the classification of the medium contacting the distal end of the needle.
2 . The system of claim 1 , wherein the measured impedance characteristics comprise impedance magnitude and impedance phase measurements.
3 . The system of claim 1 , wherein the processor is configured to classify the medium contacting the distal end of the needle using a machine learning algorithm.
4 . The system of claim 3 , wherein the machine learning algorithm uses, to classify the medium contacting the distal end of the needle, one or more of: a Fuzzy K-Means model, a Support Vector Machine (SVM) model, a Random Forest model, a Nearest Neighbors model, or a Logistic Regression model.
5 . The system of claim 1 , wherein the processor is configured to compare the measured impedance characteristics of the generated sensing signal with one or more impedance profiles stored in the memory device by calculating deviation values at a plurality of frequencies of the frequency range between the measured impedance characteristics and the one or more stored impedance profiles, wherein the processor is configured to calculate a sum, for each stored impedance profile, of the deviation values at the plurality of frequencies, and to classify the medium contacting the distal end of the needle based on the impedance profile corresponding to the lowest calculated sum.
6 . The system of claim 1 , wherein the processor is configured to classify the medium contacting the distal end of the needle as one of cataract or non-cataract material.
7 . The system of claim 1 , wherein, on a condition the medium contacting the distal end of the needle is classified as non-cataract, the processor is configured to control the output of the ultrasonic handpiece by ceasing delivery of ultrasonic power or by preventing delivery of the ultrasonic power.
8 . The system of claim 1 , wherein the processor is configured to classify the medium contacting the distal end of the needle based on a diameter or gauge of the distal end of the needle.
9 . The system of claim 1 , wherein the processor is configured to adjust a sensitivity level to be used in classifying the medium contacting the distal end of the needle in response to a user input received at a user interface.
10 . The system of claim 1 , wherein the processor is configured to determine, based on the classified medium contacting the distal end of the needle, based on aspiration flow data, and based on vacuum pressure data, that an occlusion is present at the distal end of the needle.
11 . A method for sensing tissue during a phacoemulsification procedure, the method comprising:
generating a sensing signal through a frequency range centered at a local resonant frequency of an ultrasonic handpiece, wherein the ultrasonic handpiece comprises a needle coupled with the distal end of the ultrasonic handpiece;
measuring impedance characteristics of the sensing signal at a distal end the needle;
comparing the measured impedance characteristics of the generated sensing signal with one or more stored impedance profiles;
classifying, based on the comparison between the measured impedance characteristics and the stored one or more impedance profiles, a medium contacting the distal end of the needle; and
controlling an output of the ultrasonic handpiece based on the classification of the medium contacting the distal end of the needle.
12 . The method of claim 11 , wherein the measured impedance characteristics comprise impedance magnitude and impedance phase measurements.
13 . The method of claim 12 , further comprising comparing the impedance characteristics of the generated sensing signal with one or more impedance profiles stored in the memory device by calculating deviation values at a plurality of frequencies of the frequency range between the measured impedance characteristics and the one or more stored impedance profiles; and
calculating a sum, for each stored impedance profile, of the deviation values at the plurality of frequencies, and classifying the medium contacting the distal end of the needle based on the impedance profile corresponding to the lowest calculated sum.
14 . The method of claim 11 , further comprising classifying the medium contacting the distal end of the needle using a machine learning algorithm.
15 . The method of claim 14 , wherein the machine learning algorithm uses, to classify the medium contacting the distal end of the needle, one or more of: a Fuzzy K-Means model, a Support Vector Machine (SVM) model, a Random Forest model, a Nearest Neighbors model, or a Logistic Regression model.
16 . The method of claim 11 , further comprising classifying the medium contacting the distal end of the needle as one of cataract or non-cataract material.
17 . The method of claim 11 , wherein, on a condition the medium contacting the distal end of the needle is classified as non-cataract, controlling the output of the ultrasonic handpiece by ceasing delivery of ultrasonic power or by preventing delivery of ultrasonic power.
18 . The method of claim 11 , further comprising classifying the medium contacting the distal end of the needle based on a diameter or gauge of the distal end of the needle.
19 . The method of claim 11 , further comprising adjusting a sensitivity level to be used in classifying the medium contacting the distal end of the needle in response to a user input received at a user interface.
20 . The method of claim 11 , further comprising determining, based on the classified medium contacting the distal end of the needle, based on aspiration flow data, and based on vacuum pressure data, that an occlusion is present at the distal end of the needle.