The present disclosure relates generally to bone assessment. In
particular, it relates to a system and method for automatically estimating bones characteristics of mammals.
BACKGROUND OF THE INVENTION
[002] Millions of sensors have been deployed on earth and in space for
getting information required for predictions in an un-deterministic system such as
weather. However, the sensors must work together and must offer seamless
integration of multiple devices. Same setup is required track and/or predict
multiple diseases or epicentres of diseases, especially those diseases which are
diagnosed with the help of medical imaging devices. Hence, there is a need to
have an integrated system that can work across the world to produce accurate
predictions based on information obtained from places such as hospitals,
diagnosis performed at various medical imaging centres, which are now getting
mobile. There is a need to synchronize these millions of medical imaging centres
and hospitals for tracing, analysing and predicting diseases that cannot be
diagnosed without contemporary medical imaging technologies.
[003] Aforementioned requirements may be realized with the advent of
'cloud' technologies which may be configured to work with medical imaging workflows. One such workflow is bone parameter assessment such as bone age assessment, which is a time bound workflow and has incommodious radiology task nature. The bone parameter assessment process consists of multi-steps which are generally subjective in nature and are dependent on the radiologist skills and biases.
[004] In the bone parameter assessment process, many sets of bone features
are examined with respect to epiphyseal distances and may further be compared with standard atlas to final give assessment of the bone parameters such as age for either predicting puberty age of the child or detecting bone related problems like growth disorder, chromosomal disorder, endocrine disorders, and the like. The most popular bone parameter assessment methods include Greulich-Pyle (GP),

Point Distribution Models (PDM), Tanner-Whitehouse (TW) and many other approaches that help in build mathematical orders for assessment of bone age. Recently, French authorities have suggested to do bone age assessments for the migrants/refugees coming to their borders in the wake of Syrian crisis. The bone age assessment approaches may help to identify migrants under the age of 18 so that an asylum seekers do not take undue advantage especially when it is difficult to estimate the age of person, as some young adults can easily pretend to be minors and thus usurp the migrant support system. In such cases an automated radiology parameter estimation system may help to process large volumes of radiology data to assess one or more parameters of interest.
[005] Any automated radiology parameter estimation system will require
use of artificial intelligence (AI) techniques for accurate detection of bone related parameters or issues. However, most of the automated radiology systems suffer from problems such as low accuracy, which may be due to limited amount of training data. The interoperable systems that work with heterogeneous medical devices (e.g., X-ray or other medical imaging devices) with cloud connectivity are yet to focus on bone parameter estimation. Further, deep/hybrid learning technologies for predicting bone related parameters have been rarely used in contemporary systems.
[006] There is, therefore, a need in the art for an efficient system for
automatic bone parameter assessment to obviate above mentioned problems in the art.
OBJECTS OF THE INVENTION
[007] A general object of this disclosure is to provide an efficient system for
automatic bone parameter assessment to obviate above mentioned problems in the
art.
[008] An object of the present disclosure is to provide a system and method
for automatic bone parameter assessment with the capability of effectively
managing large volume of radiology data to automatically assess parameters of
interest.

[009] An object of the present disclosure is to provide a system and method
for automatic bone parameter assessment with the capability of accurate
estimation of parameters of interest.
[010] An object of the present disclosure is to provide a system and method
for secure and time efficient bone parameter assessment over a network.
[Oil] An object of the present disclosure is to provide a system and method
for automatic bone parameter assessment with the capability to efficiently process
data received from multiple imaging or radiology devices.
SUMMARY
[012] Aspects of the present disclosure relate to mammal bone assessment.
In particular, it relates to a system and method for automatically estimating parameters related to bones.
[013] In an aspect, the present disclosure provides a system for estimating
one or more parameters related to one or more bones of a mammal. The system may include a processing unit which may in turn include one or more processors associated with a memory, the memory may store a set of instructions which may configure the one or more processors to perform one or more features described in one or more embodiments. The system may be configured to receive a first set of data packets including information pertaining to a set of digital images over a network, wherein the set of images are captured by at least one radiology equipment, wherein the set of images pertain to the one or more bones. The system may be configured to extract one or more features based on processing of the information pertaining to a set of digital images. The system may be configured to predict, using a machine learning engine operatively coupled to the one or more processors, the one or more parameters related to the mammal based on said extracting, wherein the machine learning engine is configured to take as input the one or more features. Further, the system may be configured to transmit, over the network, a second set of data packets including information pertaining to the one or more parameters to one or more computing devices.

[014] In another aspect, the processing of the first set of data packets may
include at least one or more of applying at least one image processing technique to analyze the set of digital images, or comparing at least one image in the set of digital images with one or more pre-stored medical images.
[015] In another aspect, the machine learning engine may be any or a
combination of a deep learning engine or a hybrid learning engine.
[016] In yet another aspect, the one or more parameters may include any or
a combination of age, puberty, height, weight, or one or more parameters pertaining to at least one disease.
[017] In still another aspect, the system may be further configured to receive
a third set of data packets, over the network, from the one or more computing devices, wherein the third set of data packets may include information pertaining to a query. The system may process the query using any or a combination of information pertaining to a set of digital images, or the one or more pre-stored medical images. The system may transmit, over the network, a fourth set of data packets to the one or more computing devices, wherein the fourth set of data packets may include information pertaining to at least one output of said processing.
[018] In an aspect, the present disclosure provides method for estimating
one or more parameters related to one or more bones of a mammal. The method may include a step of receiving, by one or more processors, a first set of data packets including information pertaining to a set of digital images over a network, wherein the set of images are captured by at least one radiology equipment, wherein the set of images pertain to the one or more bones. The method may include a step of extracting, by the one or more processors, one or more features based on processing of the information pertaining to a set of digital images. The method may include a step of predicting, by the one or more processors, using a machine learning engine operatively coupled to the one or more processors, the one or more parameters related to the mammal based on said extracting, wherein the machine learning engine is configured to take as input the one or more features. Further, the method may include a step of transmitting, by the one or

more processors, over the network, a second set of data packets including
information pertaining to the one or more parameters to one or more computing
devices.
[019] Various objects, features, aspects and advantages of the inventive
subject matter will become more apparent from the following detailed description
of preferred embodiments, along with the accompanying drawing figures in which
like numerals represent like components.
BRIEF DESCRIPTION OF THE DRAWINGS
[020] The accompanying drawings are included to provide a further
understanding of the present disclosure and are incorporated in and constitute a
part of this specification. The drawings illustrate exemplary embodiments of the
present disclosure and, together with the description, serve to explain the
principles of the present disclosure.
[021] FIG. 1 illustrates exemplary architecture in which or with which a
proposed bone assessment system may be implemented, in accordance with an
embodiment of the present disclosure.
[022] FIG. 2 illustrates an exemplary high-level representation of a bone
parameter assessment system, in accordance with an embodiment of the present
disclosure.
[023] FIG. 3 illustrates an exemplary flow diagram of a method for
estimating bone parameters, in accordance with an embodiment of the present
disclosure.
[024] FIG. 4 illustrates a computer system with which embodiments of the
present invention can be utilized.
DETAILED DESCRIPTION
[025] The following is a detailed description of embodiments of the
disclosure depicted in the accompanying drawings. The embodiments are in such details as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the

contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[026] Embodiments explained herein relate to a technique for mammal bone
assessment. In particular, it relates to a system and method for automatically estimating parameters related to bones.
[027] With the advent of technology, many medical diagnostics therapeutic,
screening devices, in some cases, are getting replaced by mobile health care devices. All such medical devices may need to work together to provide critical physiological or screening functionalities or even provide needed therapy remotely. One of the ways to bring these devices to a common platform and provide one or more services using these devices may be to use cloud technology. The could may host the one or more services to service clients across the globe. Cloud technology may also allow easy maintenance and management of the one or more services using service management console which may be used for managing input of a set of medical images (e.g., x -ray images of bones), operation and output of the one or more services. Cloud technology may also be leveraged for storage services which may provide Picture Archive and Communication System (PACS) repository for keeping set of medical images (e.g., x -ray images of bones). The PACS repository may store a set of blobs objects (e.g., a representation of the set of medical images) for retrieval and/or query processing. Cloud technology may also be used for data processing and/or image processing tasks. Any suitable bone assessment approach/algorithm may be run on the cloud which may perform one or more data processing and/or image processing tasks for bone parameter (e.g., age) prediction and/or classification. Processing capabilities of the cloud may also be used for other related tasks such as relevant feature extraction from the input data. The bone assessment approach/algorithm may perform prediction and/or classification using one or more hybrid or deep learning algorithms.
[028] FIG. 1 illustrates exemplary architecture in which or with which a
proposed bone assessment system 100 may be implemented, in accordance with

an embodiment of the present disclosure. As illustrated, a bone parameter assessment system 100 may include one or more computing devices 102, one or more cloud services 104, one or more image processing services 106, one or more image data storage services 108, one or more Business Associate Agreement (BAA) services 110, and one or more client interface or presentation components 112. At least a portion of the one or more cloud services 104, the one or more image processing services 106, the one or more image data storage services 108, and/or the one or more Business Associate Agreement (BAA) exchange services 110 may run, as a centralized or distributed service, in cloud, fog layer, and/or the one or more computing devices 102.
[029] In an exemplary aspect, the one or more computing devices 102 may
be associated with one or more users. The one or more computing devices 102 may include any of a mobile device, laptop computer, desktop computer, tablet, wearable device, head-mounted device, portable computing device, television, PDA, IoT device, home appliance, and/or medical device. The one or more computing devices 102 may run one or more applications which may communicate with the one or more cloud services 104 for sending a user request or query to the one or more cloud services 104 and/or receiving information from the one or more cloud services 104.
[030] In another exemplary aspect, the one or more cloud services 104 may
be configured to interface with the one or more image processing services 106 for processing the request or query received from the one or more computing devices 102. The one or more image processing services 106 may be configured to determine and extract one or more features from imaging data where the imaging data may be included in the request or query or otherwise stored in repository accessible to the one or more image processing services 106. The one or more image processing services 106 may employ one or more suitable image processing techniques (well known in the art) to process the imaging data. The imaging data may be a set of images and/or any suitable format or representation of the set of images such as BLOB. The one or more image processing services 106 may also be configured to manage imaging data and perform one or more

operations on the imaging data such as format conversion or other image processing operations.
[031] In another exemplary aspect, the one or more image processing
services 106 may be configured to interface with the one or more image data storage services 108 for handling imaging data and/or information extracted from the imaging data. The one or more image data storage services 108 may be configured to efficiently store and retrieve the imaging data, information extracted from the imaging data, and/or metadata associated with the imaging data or the extracted information. The one or more image data storage services 108 may store data across one or more distributed or centralized repositories. The one or more image data storage services 108 may be configured to interface with one or more services such as one or more cloud services 104, one or more BAA exchange services 110, one or more client interface or presentation components 112, and/or one or more external services or devices to receive/send imaging data, data associated with imaging data, and/or metadata. The one or more image data storage services 108 may also be configured to aggregate and/or archive data in the one or more repositories.
[032] In yet another aspect, the one or more BAA exchange services 110
may be configured to obtain (e.g., via push or pull mechanisms) data stored in one
or more repositories managed by the one or more image data storage services 108.
The one or more BAA exchange services 110 may be configured to perform one
or more tasks on the obtained data such as object identification, data caching for
performance enhancement, and/or interoperable exchange of the data with the one
or more computing devices 102 and/or external devices/systems.
[033] In still another aspect, the one or more client interface or presentation
components 112 may be configured to interface with the one or more BAA exchange services 110 to retrieve presentable data such as formatted data (e.g., XML, JSON, or object), reports, dashboard, visualizations, user interfaces, charts, graphs, and the like from the one or more BAA exchange services 110. The one or more client interface or presentation components 112 may be configured to provide one or more commands to the one or more BAA exchange services 110 to

manage/regulate data exchange. The one or more client interface or presentation
components 112 may run, partly or fully, in the cloud, the one or more computing
devices 102, external devices/systems, and/or a combination thereof.
[034] FIG. 2 illustrates an exemplary high-level representation of a bone
parameter assessment system 100, in accordance with an embodiment of the
present disclosure. As illustrated, users 202 may use an associated computing
device to send HTTP/HTTPS requests or queries to the system and receive
HTTP/HTTPS responses. The HTTP/HTTPS requests may include imaging data,
metadata, and/or other data/instructions required for bone parameter assessment.
A device service console 204 may manage sending or receiving of HTTP/HTTPS
requests or responses. The device service console 204 may provide the
HTTP/HTTPS requests to at least one data processing server 206 which may use
one or more services and/or perform one or more operations to process the
HTTP/HTTPS requests. The at least one data processing server 206 may store
data related to the HTTP/HTTPS requests, such as received data, output data,
and/or intermediate processing data, into an image database 208 and retrieve the
stored data from the image database 208. Further, a resource management console
210 may be configured to provision and/or free resources required for processing
the HTTP/HTTPS requests on-the-fly. Furthermore, the HTTP/HTTPS responses
may include output, in any suitable format, of the processing performed by the at
least one data processing server and/or any associated component and/or service.
[035] In an aspect, a set of images of bones or skeletal of a person or animal,
scanned using an x-ray imaging system or any other medical imaging device, may be uploaded to a remote server (e.g., cloud server) over Internet. The remote server may be configured to use one or more cloud services/resources and/or one or more external systems/services for comparing information (e.g., bone area, bone length, bone mineral content, bone mineral density, and the like) extracted from the set of images to at least one reference image or information extracted from the at least one reference image, using a machine learning model, to automatically determine one or more parameters of interest such as bone/skeletal age of the person or animal based on the comparison.

[036] In another aspect, at least one of the set of images may be selected or
discarded for processing based on one or more factors such as image resolution,
relevance to the one or more parameters of interest, and the like. The selected
images may be processed by one or more services, components and/or processing
engines to measure one or more bone characteristics. The at least one of the set of
images may be stored, along with metadata and/or the data obtained after
processing of the set of images, in the one or more repositories for training or
optimizing parameters of the machine learning engine/model.
[037] In another aspect, the one or more parameters predicted by the
machine learning engine may be fed to another learning engine or service for further prediction. For example, bone age predicted by a first learning model may be used as input to a second learning model to predict/estimate adult stature or other aspects of the maturation process.
[038] In another aspect, the processing of the first set of data packets may
include at least one or more of applying at least one image processing technique to analyze the set of digital images, or comparing at least one image in the set of digital images with one or more pre-stored medical images.
[039] In another aspect, the machine learning engine may be any or a
combination of a deep learning engine or a hybrid learning engine.
[040] In yet another aspect, the one or more parameters may include any or
a combination of age, puberty, height, weight, or one or more parameters pertaining to at least one disease.
[041] In still another aspect, a third set of data packets may be received,
over the network, from the one or more computing devices, wherein the third set of data packets may include information pertaining to a query. The query may be processed using any or a combination of information pertaining to a set of digital images, or the one or more pre-stored medical images. A fourth set of data packets may be transmitted, over the network, to the one or more computing devices, wherein the fourth set of data packets may include information pertaining to at least one output of said processing.

[042] FIG. 3 illustrates an exemplary flow diagram of a method for
estimating bone parameters, in accordance with an embodiment of the present disclosure.
[043] In an aspect, the method 300 may describe steps for estimating one or
more parameters (e.g., age, height, or disease related parameters) related to one or
more bones of a mammal (e.g., human or animal). At step 302, the method may
include receiving, by one or more processors, a first set of data packets including
information (e.g., image representation such as BLOB or any other suitable
format) pertaining to a set of digital images (e.g., a set of image files such as
PNG, JPEG, GIF, and the like) over a network (e.g., Internet or Intranet), wherein
the set of images may be captured by at least one radiology equipment, wherein
the set of images may pertain to the one or more bones. At step 304, the method
may include extracting, by the one or more processors, one or more features (e.g.,
RGB, depth, occlusion, and the like) based on processing (e.g., image processing)
of the information pertaining to the set of digital images. At step 306, the method
may include predicting, by the one or more processors, using a machine learning
engine (e.g., hybrid or deep learning engine or a combination thereof) operatively
coupled to the one or more processors, the one or more parameters related to the
mammal based on said extracting, wherein the machine learning engine may be
configured to take as input the one or more features. At step 308, the method may
include transmitting, by the one or more processors, over the network, a second
set of data packets including information (e.g., representation or metadata)
pertaining to the one or more parameters to one or more computing devices.
[044] FIG. 4 illustrates a computer system with which embodiments of the
present invention can be utilized.
[045] As shown in FIG. 4, computer system 400 includes an external storage
device 410, a bus 420, a main memory 430, a read only memory 440, a mass storage device 450, communication port 460, and a processor 470. A person skilled in the art will appreciate that computer system may include more than one processor and communication port. Examples of processor 470 include, but are not limited to, an Intel® Itanium® or Itanium 2 processor(s), or AMD®

Opteron® or Athlon MP® processor(s), Motorola® lines of processors, FortiSOC™ system on chip processors or other future processors. Processor 470 may include various modules associated with embodiments of the present invention. Communication port 460 can be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fibre, a serial port, a parallel port, or other existing or future ports. Communication port 460 may be chosen depending on a network, such as a Local Area Network (LAN), Wide Area Network (WAN), or any network to which computer systems connects.
[046] Memory 430 can be Random Access Memory (RAM), or any other
dynamic storage device commonly known in the art. Read only memory 440 can be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chip for storing static information e.g., start-up or BIOS instructions for processor 470. Mass storage 450 may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces), e.g. those available from Seagate (e.g., the Seagate Barracuda 7200 family) or Hitachi (e.g., the Hitachi Deskstar 7K1000), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks (e.g., SATA arrays), available from various vendors including Dot Hill Systems Corp., LaCie, Nexsan Technologies, Inc. and Enhance Technology, Inc.
[047] Bus 420 communicatively couples processor(s) 470 with the other
memory, storage and communication blocks. Bus 420 can be, e.g. a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB or the like, for connecting expansion cards, drives and other subsystems as well as other buses, such a front side bus (FSB), which connects processor 470 to the software system.

[048] Optionally, operator and administrative interfaces, e.g. a display,
keyboard, and a cursor control device, may also be coupled to bus 420 to support direct operator interaction with computer system 400. Other operator and administrative interfaces can be provided through network connections connected through communication port 460. External storage device 410 can be any kind of external hard-drives, floppy drives, IOMEGA® Zip Drives, Compact Disc - Read Only Memory (CD-ROM), Compact Disc - Re-Writable (CD-RW), or Digital Video Disk - Read Only Memory (DVD-ROM). Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system limit the scope of the present disclosure.
[049] While the foregoing describes various embodiments of the invention,
other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
ADVANTAGES OF THE INVENTION
[050] The present disclosure provides an efficient system for automatic bone
parameter assessment to obviate above mentioned problems in the art.
[051] The present disclosure provides a system and method for automatic
bone parameter assessment with the capability of effectively managing large
volume of radiology data to automatically assess parameters of interest.
[052] The present disclosure provides a system and method for automatic
bone parameter assessment with the capability of accurate estimation of
parameters of interest.

[053] The present disclosure provides a system and method for secure and
time efficient bone parameter assessment over a network.
[054] The present disclosure provides a system and method for automatic
bone parameter assessment with the capability to efficiently process data received from multiple imaging or radiology devices.

We Claim:

1. A system for estimating one or more parameters related to one or more
bones of a mammal, the system comprising:
a processing unit comprising one or more processors coupled with a memory, the memory storing instructions executable by the one or more processors to:
receive a first set of data packets including information pertaining to a set of digital images over a network, wherein the set of images are captured by at least one radiology equipment, wherein the set of images pertain to the one or more bones;
extract one or more features based on processing of the information pertaining to the set of digital images;
predict, using a machine learning engine operatively coupled to the one or more processors, the one or more parameters related to the mammal based on said extracting, wherein the machine learning engine is configured to take as input the one or more features; and
transmit, over the network, a second set of data packets including information pertaining to the one or more parameters to one or more computing devices.
2. The system as claimed in claim 1, wherein the processing of the first set of
data packets comprises at least one or more of:
applying at least one image processing technique to analyze the set of digital images; or
comparing at least one image in the set of digital images with one or more pre-stored medical images.
3. The system as claimed in claim 1, wherein the machine learning engine is
any or a combination of a deep learning engine or a hybrid learning
engine.

The system as claimed in claim 1, wherein the one or more parameters comprise any or a combination of age, puberty, height, weight, or one or more parameters pertaining to at least one disease.
The system as claimed in claim 1, wherein said system is further configured to:
receive a third set of data packets, over the network, from the one or more computing devices, wherein the third set of data packets include information pertaining to a query;
process the query using any or a combination of information pertaining to a set of digital images, or the one or more pre-stored medical images; and
transmit, over the network, a fourth set of data packets to the one or more computing devices, wherein the fourth set of data packets include information pertaining to at least one output of said processing. A method for estimating one or more parameters related to one or more bones of a mammal, the method comprising:
receiving, by one or more processors, a first set of data packets including information pertaining to a set of digital images over a network, wherein the set of images are captured by at least one radiology equipment, wherein the set of images pertain to the one or more bones;
extracting, by the one or more processors, one or more features based on processing of the information pertaining to the set of digital images;
predicting, by the one or more processors, using a machine learning engine operatively coupled to the one or more processors, the one or more parameters related to the mammal based on said extracting, wherein the machine learning engine is configured to take as input the one or more features; and
transmitting, by the one or more processors, over the network, a second set of data packets including information pertaining to the one or more parameters to one or more computing devices.

7. The method as claimed in claim 6, wherein the processing of the first set
of data packets comprises at least one or more of:
applying at least one image processing technique to analyze the set of digital images; or
comparing at least one image in the set of digital images with one or more pre-stored medical images.
8. The method as claimed in claim 6, wherein the machine learning engine is any or a combination of a deep learning engine or a hybrid learning engine.
9. The method as claimed in claim 6, wherein the one or more parameters comprise any or a combination of age, puberty, height, weight, or one or more parameters pertaining to at least one disease.
10. The method as claimed in claim 6, wherein said method further comprises:
receiving, by the one or more processors, a third set of data packets, over the network, from the one or more computing devices, wherein the third set of data packets include information pertaining to a query;
processing, by the one or more processors, the query using any or a combination of information pertaining to a set of digital images, or the one or more pre-stored medical images; and
transmitting, by the one or more processors, over the network, a fourth set of data packets to the one or more computing devices, wherein the fourth set of data packets include information pertaining to at least one output of said processing.