Systems, methods, and bone mapper devices for real-time mapping and analysis of bone tissue
Apparatuses, systems, and methods for performing real-time analysis of bone tissue during a surgical procedure are disclosed herein. In some embodiments, the method includes receiving at least one measurement of at least one tissue sample from a hybrid multi-wavelength photoacoustic measurements (MWPM) component. The method can also include identifying one or more reference cases, from a plurality of reference cases, based on correlations between the at least one measurement and previous measurements in each of the plurality of reference cases. Once the reference cases are identified, the method can include determining at least one bone condition of the patient and sending the at least one determined bone condition to a computing device accessible by a surgeon. In some embodiments, the method also includes creating a three-dimensional (3D) map the tissue sample using the at least one measurement and sending the 3D map to the computing device.
1 . A computer-implemented method for analyzing target tissue, the method comprising:
receiving, from a tissue mapping device, at least one image of the target tissue of a first patient and at least two wavelength-based measurements of the target tissue, wherein the tissue mapping device comprises a hybrid imaging component;
identifying at least one reference case based on the at least two wavelength-based measurements, wherein the at least one reference case is associated with a second patient different from the first patient;
determining, based on the at least one reference case, a diagnosis of the target tissue;
generating a diagnostic map of the target tissue based on the at least one image and a set of one or more measurements of the at least one reference case; and
sending the diagnostic map and the diagnosis to a computing device.
2 . The method of claim 1 , wherein the at least two wavelength-based measurements comprise at least one of an ultrasound image, a multiwavelength photoacoustic measurement, a μ3 measurement, an x-ray image, or a computerized tomography scan.
3 . The method of claim 1 , wherein the at least two wavelength-based measurements comprise at least a first x-ray image taken at a first wavelength and a second x-ray image taken at a second wavelength different from the first wavelength.
4 . The method of claim 1 , wherein identifying the at least one reference case comprises:
extracting features from the at least two wavelength-based measurements, the features comprising at least a bone material density; and
providing the at least one reference case to a machine learning model trained to generate reference cases based on multi-wavelength photoacoustic measurements (MWPMs).
5 . The method of claim 1 , wherein the diagnostic map includes a three-dimensional (3D) bone map of a bone in the target tissue, the method comprising:
analyzing the 3D bone map using a machine learning model trained using bone tissue training sets to determine at least one surgical step; and
performing, using a surgical robot, the at least one surgical step.
6 . The method of claim 5 , wherein the diagnosis comprises at least two diagnoses of a bone condition, wherein the 3D bone map includes at least two selectable layers, and wherein each of the at least two selectable layers is associated with an individual one of the at least two diagnoses.
7 . The method of claim 1 , wherein the diagnosis comprises at least one of osteoporosis, clinical osteopenia, bone cancer, normal bone with low or high bone mineral density (BMD), or osteomyelitis.
8 . A system for analyzing target tissue, the system comprising:
one or more computer processors; and
a non-transitory computer-readable storage medium storing computer instructions, which when executed by the one or more computer processors, cause the system to:
receive, from a tissue mapping device, at least one image of the target tissue of a first patient and at least two wavelength-based measurements of the target tissue, wherein the tissue mapping device comprises a hybrid imaging component;
identify at least one reference case based on the at least two wavelength-based measurements, wherein the at least one reference case is associated with a second patient different from the first patient;
determine, based on the at least one identified-reference case, a diagnosis of the target tissue;
generate a diagnostic map of the target tissue based on the at least one image and a set of one or more measurements of the at least one reference case; and
send the diagnostic map and the diagnosis to a computing device.
9 . The system of claim 8 , wherein the at least two wavelength-based measurements comprise at least one of an ultrasound image, a multiwavelength photoacoustic measurement, a μ3 measurement, an x-ray image, or a computerized tomography scan.
10 . The system of claim 8 , wherein the at least two wavelength-based measurements comprise at least a first x-ray image taken at a first wavelength and a second x-ray image taken at a second wavelength different from the first wavelength.
11 . The system of claim 8 wherein the computer instructions to identify the at least one reference case cause the system to:
extract features from the at least two wavelength-based measurements, the features comprising at least a bone material density; and
provide the at least one reference case to a machine learning model trained to generate reference cases based on multi-wavelength photoacoustic measurements (MWPMs).
12 . The system of claim 8 , wherein the diagnostic map includes a three-dimensional (3D) bone map of a bone in the target tissue, and the computer instructions to identify the at least one reference case cause the system to:
analyze the 3D bone map using a machine learning model trained using bone tissue training sets to determine at least one surgical step; and
perform, using a surgical robot, the at least one surgical step.
13 . The system of claim 12 , wherein the diagnosis comprises at least two diagnoses of a bone condition, wherein the 3D bone map includes at least two selectable layers, and wherein each of the at least two selectable layers is associated with an individual one of the at least two diagnoses.
14 . The system of claim 8 , wherein the diagnosis comprises at least one of osteoporosis, clinical osteopenia, bone cancer, normal bone with low or high bone mineral density (BMD), or osteomyelitis.
15 . A surgical robot for analyzing target tissue, the surgical robot configured to:
receive, from a tissue mapping device, at least one image of the target tissue of a first patient and at least two wavelength-based measurements of the target tissue, wherein the tissue mapping device comprises a hybrid imaging component;
identify at least one reference case based on the at least two wavelength-based measurements, wherein the at least one reference case is associated with a second patient different from the first patient;
determine, based on the at least one identified-reference case, a diagnosis of the target tissue;
generate a diagnostic map of the target tissue based on the at least one image and a set of one or more measurements of the at least one reference case; and
send the diagnostic map and the diagnosis to a computing device.
16 . The surgical robot of claim 15 , comprising a hybrid MWPM component comprising a laser device configured to emit a light beam used in performing the at least two wavelength-based measurements, and wherein the surgical robot is configured to:
split the light beam, using a beam splitter, into a first portion directed at bone mass in the patient and a second portion directed at a calibration material;
receive, from the hybrid MWPM component, at least one calibration measurement associated with the second portion of the light beam; and
adjust the at least two wavelength-based measurements associated with the bone mass based on the at least one calibration measurement before identifying the at least one reference patient.
17 . The surgical robot of claim 16 , wherein the hybrid MWPM component includes a neodymium-doped yttrium aluminum garnet laser.
18 . The surgical robot of claim 15 , wherein the surgical robot is configured to determine the diagnosis by determining whether a metric in the at least one measurement exceeds a threshold value.
19 . The surgical robot of claim 15 , wherein the at least two wavelength-based measurements comprise at least one of an ultrasound image, a multiwavelength photoacoustic measurement, a μ3 measurement, an x-ray image, or a computerized tomography scan.
20 . The surgical robot of claim 15 , wherein the at least two wavelength-based measurements comprise at least a first x-ray image taken at a first wavelength and a second x-ray image taken at a second wavelength different from the first wavelength.