Digital PNAM device modeling and manufacturing systems and processes

Abstract

Provided herein are device generation methods, systems, and controllers for producing PNAM device models and devices for treating cleft palates. For example, a device generation system can include a controller configured to: generate an intraoral model of a subject having a cleft palate based on intraoral scan data captured by an intraoral scanner, identify a plurality of landmarks within the intraoral model based on an AI model, interpolate between at least one associated pair of the plurality of landmarks across a cleft region within the intraoral model to generate a smoothed intraoral model, generate a PNAM device model configured to abut a surface of the smoothed intraoral model, determine a center of gravity of the PNAM device model, define apertures for stability supports within the PNAM device model based on the center of gravity, and output the PNAM device model to a 3D printer configured to generate a PNAM device.

Description

DIGITAL PNAM DEVICE MODELING AND MANUFACTURING SYSTEMS AND PROCESSESCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to and the benefit of U.S. Provisional Application No. 63 / 468,344, filed May 23, 2023. The contents of the referenced application are incorporated into the present application by reference herein in its entirety.TECHNICAL FIELD

[0002] The present disclosure relates to device generation systems and, more particularly, to systems, devices, and methods of modeling and generating customized presurgical nasoalveolar molding (PNAM) devices for infants having cleft palates.BACKGROUND

[0003] Orofacial clefts or palatoschisis, such as cleft palates and cleft lips, are common birth defects that occur when an infant’s facial tissue does not form or connect correctly in utero. The cleft can occur through one or both sides of the palate and / or through one or both sides of the upper lip. It is often desirable to repair or fully close the cleft via surgery before the infant is six months or a year old to reduce difficulties that may be experienced during breathing, speech, feeding, and other activities. For example, certain cleft lips may be readily repaired via surgical connection of the muscles and skin lining the cleft. Additionally, cleft palates may be repaired over one or more surgeries that stretch, rearrange, and connect muscles and other tissues lining the palate.

[0004] Developments in orofacial cleft treatments are producing clinical outcomes that greatly improve an infant’s wellbeing and appearance after surgery. For example, a degree of clefting in certain palates may be reduced prior to surgery via alignment or molding devices that guide cleft edges closer together during infant growth. However, these existing devices are often prohibitively expensive or difficult to manufacture, while requiring multiple in-person visits to specialists. As such, there is an unmet demand for customizable, readily produced devices for treating cleft palates.SUMMARY

[0005] Computer-implemented methods of device generation systems for producing presurgical nasoalveolar molding (PNAM) devices for infants having cleft palates are disclosed. Non-transitorycomputer-readable media, devices, and systems for performing methods of the present disclosure are also disclosed.

[0006] In some aspects, the present disclosure provides a controller for producing presurgical nasoalveolar molding (PNAM) device models. The controller includes one or more processors and a non-transitory machine-readable storage medium storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to: generate an intraoral model of a subject having a cleft palate based on intraoral scan data captured by an intraoral scanner, identify a plurality of landmarks within the intraoral model based on an Al model, interpolate between at least one associated pair of the plurality of landmarks across a cleft region within the intraoral model to generate a smoothed intraoral model, generate a PNAM device model configured to abut a surface of the smoothed intraoral model, determine a center of gravity of the PNAM device model, define apertures for stability supports within the PNAM device model based on the center of gravity, and output the PNAM device model to a 3D printer configured to generate a PNAM device.

[0007] In some aspects, the present disclosure provides a device generation system for treating a subject having a cleft palate. The device generation system includes a controller having one or more processors and a non-transitory machine-readable storage medium storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to: generate an intraoral model of a subject having a palate with a cleft based on intraoral scan data captured by an intraoral scanner, identify a plurality of landmarks within the intraoral model based on an Al model, interpolate between at least one associated pair of the plurality of landmarks across a cleft region of the intraoral model to generate a smoothed intraoral model, generate a presurgical nasoalveolar molding (PNAM) device model configured to contour to a surface of the smoothed intraoral model, determine a center of gravity of the PNAM device model, define apertures for stability supports within the PNAM device model based on the center of gravity, and export the PNAM device model for printing by a 3D printer configured to generate a PNAM device to reduce the cleft of the palate.

[0008] In some aspects, the present disclosure provides a computer-implemented method of generating a presurgical nasoalveolar molding (PNAM) device model. The method includes generating, via one or more processors of a controller, an intraoral model of a subject having a cleft palate based on intraoral scan data captured by an intraoral scanner and identifying, via the one or more processors, a plurality of landmarks within the intraoral model based on an Al model. The method also includes interpolating, via the one or more processors, between at least one associatedpair of the plurality of landmarks across a cleft region within the intraoral model to generate a smoothed intraoral model. The method further includes generating, via the one or more processors, a presurgical nasoalveolar molding (PNAM) device model configured to abut a surface of the smoothed intraoral model and determining, via the one or more processors, a center of gravity of the PNAM device model. Additionally, the method includes forming, via the one or more processors, apertures for stability supports within the PNAM device model based on the center of gravity and outputting, via the one or more processors, the PNAM device model to a 3D printer configured to generate a PNAM device based on the PNAM device model.

[0009] Other aspects and features of the present disclosure will become apparent to those of ordinary skill in the art after reading the detailed description herein and the accompanying figures.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Embodiments described herein are illustrated by examples and not limitations in the accompanying drawings, in which like references indicate similar features. Furthermore, in the drawings some conventional details have been omitted so as not to obscure the inventive concepts described herein.

[0011] FIG. 1 is a block diagram of a device generation system for producing presurgical nasoalveolar molding (PNAM) devices, according to an embodiment of the present disclosure.

[0012] FIG. 2 is a flowchart of a method to use a device generation system to provide PNAM devices, according to an embodiment of the present disclosure.

[0013] FIG. 3 is a bottom perspective view of an intraoral model including a cleft palate, according to an embodiment of the present disclosure.

[0014] FIG. 4 is a bottom perspective view of a PNAM device model generated for the intraoral model of FIG. 3, according to an embodiment of the present disclosure.

[0015] FIG. 5 is a bottom perspective view illustrating positioning of the PNAM device model of FIG. 4 onto the intraoral model of FIG. 3, according to an embodiment of the present disclosure.

[0016] FIG. 6 is a side perspective view illustrating positioning of the PNAM device model and intraoral model of FIG. 5, according to an embodiment of the present disclosure.

[0017] FIG. 7 is a flowchart of a method to use a device generation system to provide updated PNAM devices for various treatment periods, according to an embodiment of the present disclosure.

[0018] FIG. 8 is a flowchart of a method illustrating certain specific steps for using a device generation system to provide PNAM devices, according to an embodiment of the present disclosure.

[0019] FIG. 9 is a bottom perspective view of an intraoral model including a cleft palate and identified intraoral landmarks, according to an embodiment of the present disclosure.

[0020] FIG. 10 is a bottom perspective view of the intraoral model having a cleft region and / or noise identified and removed, according to an embodiment of the present disclosure.

[0021] FIG. 11 is a bottom perspective view illustrating closing a surface of the intraoral model across the cleft region by connecting intraoral landmarks, according to an embodiment of the present disclosure.

[0022] FIG. 12 is a bottom perspective view of the intraoral model having a smoothed surface in place of the cleft region, according to an embodiment of the present disclosure.

[0023] FIG. 13 is a bottom perspective view of the intraoral model having an outline generated for producing a PNAM device model, according to an embodiment of the present disclosure.

[0024] FIG. 14 is a bottom perspective view of the PNAM device model produced from the outline, according to an embodiment of the present disclosure.

[0025] FIG. 15 is a top perspective view of the PNAM device model having thickened edges for retainment against the cleft palate, according to an embodiment of the present disclosure.

[0026] FIG. 16 is a top perspective view of the PNAM device model having smoothed edges surfaces for improving patient comfort, according to an embodiment of the present disclosure.

[0027] FIG. 17 is a bottom perspective view of the PNAM device model, according to an embodiment of the present disclosure.

[0028] FIG. 18 is a bottom perspective view of the PNAM device model having apertures for receiving stabilizing wires suitable for a unilateral cleft palate, according to an embodiment of the present disclosure.

[0029] FIG. 19 is a bottom perspective view of the PNAM device model having apertures for receiving stabilizing wires suitable for a bilateral cleft palate, according to an embodiment of the present disclosure.

[0030] While the disclosure will be described in connection with the preferred embodiments, it will be understood that it is not intended to limit the disclosure to those embodiments. On the contrary, it is intended to cover all alternatives, modifications, and equivalents, as may be included within the spirit and scope of the disclosure as defined by the appended claims.DETAILED DESCRIPTION

[0031] In the following description, various embodiments will be described. For purposes of explanation, specific configurations and details are set forth in order to provide a thorough understanding of the embodiments. However, it will also be apparent to one skilled in the art that the embodiments may be practiced without the specific details. Furthermore, well-known features may be omitted or simplified in order not to obscure the embodiment being described.

[0032] To facilitate understanding, certain non-limiting definitions of terms are provided herein. As used herein, a “subject” refers to an animal, such as a mammal, including a primate (such as a human or a non-human primate) and a non-primate (such as a dog, cat, horse, ruminant, or camelid). In some aspects of the present disclosure, the subject is a human. In some aspects, the subject is a pediatric subject, such as a neonate, an infant, or a child. In other aspects, the subject may be an adult subject. As used herein, a “patient” refers to a subject who shows displays symptoms or indicators of a birth defect or congenital anomaly. A “patient” can include human or veterinary subjects. Any reference to a subject in the present disclosure should be understood to include the possibility that the subject is a “patient” unless clearly dictated otherwise by context. More specifically, the subject in certain aspects is a patient that has been identified as having a cleft palate, either with or without a cleft lip. As used herein, a “computing device” refers to an electronic device that can receive information from another electronic device and / or present information to a user of the computing device. The computing device may include any suitable electronic device having a communicating feature, such as a wireless connection component, and internet connection component, and so forth. In certain embodiments, the computing device is a cellular telephone, a smart phone, a smart watch, a pair of smart glasses, a tablet, a laptop, a desktop, and so forth.

[0033] Embodiments of the device generation system disclosed herein may be employed to produce presurgical nasoalveolar molding (PNAM) devices that provide efficient, customized care for treating infants, subjects, or patients having cleft palates, cleft lips, and / or palatoschisis. Around 1 in 700 infants, or 5000 infants per year, bom in the U.S. may have a cleft lip and cleft palate. Traditionally, clefts in palates have been repaired by palatoplasty surgery that closes the opening between the nose and mouth. Before and after the surgery, an infant with a cleft palate may be closely monitored by a craniofacial team to ensure desirable growth and development while preventing health issues. These licensed and trained professionals may include pediatric dentists, pediatric orthodontists, prosthodontists, oral or plastic surgeons, ear, nose, and throat specialists, feeding or speech consultants, and more.

[0034] Certain infants with cleft palates may have consultations and receive approval for a molding device that forms or shapes the palate and face to reduce the cleft therein before surgery. Advancements in the design of these molding devices have greatly improved treatment outcomes, which may include repairing or closing the cleft to a near perfect condition with as little as a single surgery. Unfortunately, producing these existing molding devices may be a costly, labor-intensive process that is not widely scalable and is performed in person. For example, an infant may be fitted with a molding device based on an in-person visit to a dentist or orthodontist, who prepares a dental impression or mold directly within the infant’s mouth with an impression material such as alginate, vinyl polysiloxane, or polyethers. Then, a dental cast representing surfaces within the infant’s mouth may be prepared from the dental impression or mold. A cleft within the dental cast may be manually smoothed with wax or another malleable substance, and this smoothed dental cast may be used as a physical mold for preparing the molding device from a resilient material such as one or more layers of acrylic material and / or resin material. The molding device may be further refined with sanding steps and lining steps before an initial fitting, and the sanding and lining steps may be repeated over time as an infant grows and revisits the dentist or orthodontist for subsequent fittings. As such, infants that are unable to physically travel to a center that prepares molding devices due to geographical or financial constraints may have previously been unable to benefit from the presurgical cleft reduction affected by these molding devices.

[0035] As an additional drawback, certain molding devices are also drilled or otherwise altered to enable a technician to add support components, such as a nasal stent and a stability button that permits facial taping for securing the molding device in place. However, these support components are often provided at traditional or impersonalized locations of the molding device. As such, the molding device may be imbalanced when installed and thus cause structural interference, rubbing, and discomfort to the infant.

[0036] To address these issues and more, the present techniques provide a device generation system for PNAM device models and resultant PNAM devices that are more effective, comfortable, affordable, and widely available than previously offered devices. For example, the device generation system of certain embodiments may leverage three-dimensional (3D) scanning technology of 3D scanners to capture 3D, intraoral scan data in a manner that is more convenient, more accurate, and less likely to obstruct breathing than traditional dental impressions. In some cases, the 3D scanners may be available at a clinic that is local or regional to the infant, such as a neonatal intensive care unit or other dental or medical practice. In some cases, the 3D scanners may be acquired and used bycaregivers or technicians that collect the intraoral scan data conveniently at the infant’s residence. The device generation system may thus reduce or obviate a demand for the infant to travel to or be close to a site at which molding devices are prepared.

[0037] Based on the intraoral scan data, a controller of the device generation system may generate a PNAM device model that is specifically customized to fit the infant’s particular intraoral geometry and reduce or close the cleft palate. In embodiments, the controller may generate an intraoral model based on the intraoral scan data and identify intraoral landmarks within the intraoral model. For example, the controller may implement or include at least one artificial intelligence (Al) model or software program trained for landmark recognition on a corpus of data that includes intraoral models with labeled or identified landmarks. The controller may further close or cover the cleft in the intraoral model with an estimated surface, based on interpolation across landmarks that are associated with the cleft. This smoothed and corrected intraoral model may be used as a reference surface or mold from which an accurate and precise PNAM device model is generated. For example, the reference surface may initially be identified as a two-dimensional (2D) mesh that is thickened and transformed into a 3D object having a palate-facing surface that perfectly matches the corrected intraoral model. The controller may also smooth or taper any sharp edges of the PNAM device model, in certain embodiments.

[0038] Further, the present embodiments of the device generation system provide force balance analysis to determine balanced positions for stability support installation. For example, the controller of the device generation system may determine a center of gravity of the PNAM device model based on analyzing the spatial positioning of numerous, or all, points along the outer surface of the PNAM device model. Based on the center of gravity, the controller may determine a target position for each stability support and remove material from each target position to form apertures for receiving stability supports. The controller may thus export the PNAM device model to a 3D printer of the device generation system, which generates a PNAM device or appliance for individualized treatment of the infant’s cleft palate. The 3D printer may be positioned in or nearby to the clinic that that the infant visited for 3D scanning, in certain embodiments, thus enabling a local care team to install the stability supports, such as two stability buttons and one or two nasal stents in the apertures of the PNAM device before an initial installation appointment with the infant. In embodiments, the 3D printer may be positioned with or near the controller of the device generation system to enable providers at a central technology center to collect the printed PNAM device, add any desired stability supports, and send the PNAM device to the local care team for the initial installation appointment.The ready availability of the device generation system may further enable updated PNAM devices to be printed for various stages of treatment to provide force-balanced nasoalveolar molding until a final repair surgery is performed. The cleft may be surgically sealed after the PNAM device guides the cleft to a closed position or a position in which cleft segments are less than 2 mm or another suitable threshold distance apart, thus finalizing a treatment schedule for improved cleft repair via embodiments of the presently disclosed device generation system.

[0039] FIG. 1 illustrates an example of a device generation system 10 for producing PNAM devices, in accordance with aspects of the present disclosure. As will be understood, the device generation system 10 may be implemented to efficiently manufacture PNAM devices that are customized and effective for reducing or correcting cleft palates. By molding growth and modification of intraoral structures, the PNAM devices may align edges of a cleft over time to be in close proximity with one another, thus enabling efficient cleft closure with a single surgery, in certain embodiments.

[0040] The illustrated embodiment of the device generation system 10 includes a controller 12 having a processor 14 and a memory 16. The memory 16 may include or store instructions executable by the processor 14. In embodiments, the device generation system 10 may include any suitable number of processors 14 and memories 16 distributed within any suitable enclosures or locations. The controller 12 may also include any suitable wireless communication components that facilitate wireless communication between various components. For example, wireless communication may be Wi-Fi®, Bluetooth®, ZigBee, or forms of near field communications. Certain embodiments of the controller 12 may also include one or more input and / or output (I / O) ports for enabling communication between the controller 12 and other components of the device generation system 10.

[0041] As used herein, a “processor”, processing resource, or processing circuitry may be a plurality of processors connected together in communication with an electronic communications network. In other embodiments, the processors may be a group of graphical processing units configured to work in parallel as a GPU cluster. A processor may include a single processor device and / or a plurality of processor devices, such as distributed processors. Additionally, a processor may be any suitable processor capable of executing / performing instructions. For example, a processor may include a central processing unit (CPU), a semiconductor-based microprocessor, a graphics processing unit (GPU), a field-programmable gate array (FPGA) to retrieve and execute instructions, and / or a realtime processor (RTP) that carries out program instructions to perform the basic arithmetical, logical, and input / output operations required to support the device generation system 10. A processor may include code, such as processor firmware, a protocol stack, a database management system, anoperating system, or a combination thereof, that creates an execution environment for program instructions. Processes and logic flows described herein may be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating corresponding output.

[0042] In an example, the memory 16 may be a non-transitory machine-readable storage medium. As used herein, a “machine-readable storage medium” may be any electronic, magnetic, optical, or other physical storage apparatus or cyber-physical separation storage to contain or store information such as executable instructions, data, and the like. For example, any machine-readable storage medium described herein may be any of random-access memory (RAM), volatile memory, non-volatile memory, flash memory, a storage drive such as hard drive, a solid-state drive, any type of storage disc, and the like, or a combination thereof. As noted, the memory 16 may store or include instructions executable by the processor 14. Accordingly, the processor 14 may execute machine-readable instructions of the memory 16 to produce PNAM device models and PNAM devices according to the present embodiments.

[0043] The device generation system 10 may include an intraoral scanner 30, in certain embodiments. The intraoral scanner 30 may be a 3D scanning device or 3D scanner that is suitable for capturing intraoral scan data 32 of a subject having a cleft palate. For example, the intraoral scanner 30 may include a sensing component that identifies and captures three-dimensional data or modeling data representative of internal surfaces and / or internal structures within the subject’s mouth. The surfaces captured by the intraoral scanner 30 may include an upper alveolar ridge, a maxillary arch, a hard palate, a soft palate, and any other suitable surfaces and structures associated with a roof of the subject’s mouth. In certain embodiments, soft tissues within the mouth may be manipulated during a scanning process so that hard tissues or structures, as well as a cleft through a roof of the mouth, are discernable based on their non-mobility across multiple scanning passes. In other words, data indicative of surfaces that do not persist during two or more scanning passes may be deleted, removed, or parsed from the intraoral scan data 32, in certain embodiments.

[0044] As an illustrative example, a first scan pass with the intraoral scanner 30 may collect data indicative of a surface having a first distinctive feature and a second distinctive feature. After manually repositioning tissues around or in the subject’s mouth, the intraoral scanner 30 may be used in a second scan pass that collects data indicative of the surface having the first distinctive feature and a different, third distinctive feature. The intraoral scanner 30 or the controller 12 may crossreference or compare data from the scan passes to identify that the first distinctive feature is a hard ornon-mobile structure within the mouth to be included in an intraoral model. Moreover, the intraoral scanner 30 or the controller 12 may determine that the second and third distinctive features are formed of soft tissue or transient fluids, which will be omitted in the intraoral model.

[0045] The controller 12 may receive the intraoral scan data 32 from the intraoral scanner 30 via any suitable wired or wireless communication protocol. For example, certain embodiments may include operating the intraoral scanner 30 at a location that is remote from the controller 12 and transmitting the intraoral scan data 32 to the controller 12 after its capture. This arrangement may be beneficial in certain embodiments for deploying the present techniques within multiple clinics or medical practices, thus expanding an availability of PNAM devices for subjects across a wide geological area. In certain embodiments, the device generation system 10 may include multiple intraoral scanners 30 communicatively coupled to, or in signal communication with, the controller 12 in parallel to enable receipt of intraoral scan data 32 for multiple subjects that may be associated with the multiple clinics. In some embodiments, the one or more intraoral scanners 30 may provide or upload the intraoral scan data 32 to a database or cloud network from which the controller 12 may receive or download the intraoral scan data 32.

[0046] As illustrated, the memory 16 of the controller 12 may include one or more Al models 40 therein to facilitate production of specifically customized PNAM devices based on the intraoral scan data 32. As will be understood, the controller 12 may leverage the Al models 40 to identify intraoral landmarks within the intraoral scan data 32 or a model thereof and generate a smoothed, corrected surface for the roof of the mouth. After further refinements for increased comfort and efficacy, the controller 12 may implement this surface as the basis of a PNAM device model 50. For example, the controller 12 of certain embodiments discussed in more detail below may provide apertures through the PNAM device model 50 for receiving stability supports based on a determined center of gravity.

[0047] The controller 12 may transmit the PNAM device model 50 to a 3D printer 52 of the device generation system 10, in certain embodiments. In some embodiments, the controller 12 may provide or upload the intraoral scan data 32 to a database or cloud network from which the 3D printer 52 may receive or download the intraoral scan data 32. The 3D printer 52 may be positioned in a same building or location as the controller 12, in certain embodiments. In such cases, the produced PNAM device may be picked up by or shipped to caregivers or providers for the subject, along with teaching materials for improving its use and comfort during subject growth. In some embodiments, the 3D printer 52 is positioned within a satellite office that is generally close to or accessible by the subject, such as within a same zip code, city, state, or country. For example, a primary physician, dentist, ororthodontist associated with the subject may be equipped with or be able to access a 3D printer 52 that outputs the PNAM device. As such, personnel that are local to the subject may output or receive a customized PNAM device for the specific subject and schedule an appointment for installing the PNAM device over the cleft palate of the subject.

[0048] FIG. 2 is a flowchart of a method 100 of using the device generation system 10 to provide PNAM devices or models thereof, in accordance with aspects of the present disclosure. The method 100 may be performed by one or more processors of the controller 12 of the device generation system 10, in certain embodiments. The following description may provide a high-level understanding of certain embodiments of the present techniques. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described blocks may be combined in any order and / or in parallel to implement the method 100. Additionally, FIGS. 3-6 illustrate certain example operations of the device generation system 10 to accompany the described embodiments of the method 100.

[0049] As illustrated at block 102 of the method 100, the controller 12 may identify landmarks in an intraoral model of a cleft palate. In embodiments, the controller 12 receives the intraoral model or scanning data thereof from based on an intraoral scan of the subject, performable with an intraoral scanner or 3D scanning wand. Then, the controller 12 may provide the intraoral model as input to the Al model, which may suitably identify, label, or tag intraoral landmarks at detected locations within surfaces of the intraoral model. The Al models of certain embodiments may be trained, or continuously training, via a corpus of previously labeled data including multiple intraoral models, with landmarks labeled or identified within each intraoral model to guide machine-learning based landmark detection. In embodiments, the Al model is a convolutional neural network that analyzes the intraoral model for patterns or features indicative of intraoral landmarks.

[0050] At block 104, the controller 12 may reconnect the landmarks to smooth the cleft region of intraoral model with an estimated surface. For example, FIG. 3 illustrates an embodiment of an intraoral model 140 having a cleft region 142. An estimated surface 150 or interpolated surface is overlaid or integrated into a modeled surface 152 of the subject’s intraoral anatomy in the illustrated embodiment. As such, the estimated surface 150 may cover the cleft region 142 to enable the modeled surface 152 to provide a smoothed and corrected surface or intraoral model for facilitating generation of a well-fitting PNAM device model.

[0051] At block 106 of the method 100, the controller 12 may generate a PNAM device model based on the smoothed intraoral model. For example, FIG. 4 illustrates an embodiment of a PNAM devicemodel 160 that is customized to fit against and guide closure of the cleft palate of the subject. As illustrated in FIG. 5, the PNAM device model 160 may closely or perfectly align with or contour to the modeled surface 152 of the subjects’ intraoral anatomy. Moreover, FIG. 6 illustrates another perspective of the close fit between the PNAM device model 160 and the intraoral model 140 having the modeled surface 152, which includes the estimated surface 150 for closing the cleft of the intraoral model 140.

[0052] At block 108 of the method 100, the controller 12 may determine a center of gravity of the PNAM device model. As will be described in detail below, the center of gravity may be determined based on a force balance analysis of the particular shape or geometry of the PNAM device model. The center of gravity may therefore be leveraged in certain embodiments to design an effective and comfortable PNAM device that is balanced or in a state of equilibrium when provided to a subject’s mouth.

[0053] For example, at block 110, the controller 12 may define apertures for one or more stability supports based on the center of gravity. In some embodiments, the stability supports added to the PNAM device may include two flexible stability buttons or retainment protrusions that are positioned to protrude from the mouth and be linked, banded, and / or taped to an outer surface of the subject’s cheeks. The stability supports may also include one or two flexible nasal stents for guiding and / or correcting alignment of nasal passages, in certain embodiments. For example, a single nasal stent may be provided for subjects having a unilateral cleft palate, and two nasal stents may be provided for subjects having a bilateral cleft palate. The stability supports of certain embodiments may include a flexible wire component or stem that extends between the apertures of a PNAM device and a respective distal protrusion for a nasal stent or stability button. The flexibility in the stability supports may enhance force distribution, device stability, and subject comfort during use of the PNAM device. In other embodiments, the stability buttons may be integral components of a body of the PNAM device. In such cases, the controller 12 may add surfaces or protrusions to the PNAM device model to form the integrated stability buttons, based on the force balance analysis.

[0054] At block 112, the controller 12 may export the PNAM device model for 3D printing, such as via a 3D printer. In some embodiments, the controller 12 may directly send the PNAM device model to a 3D printer, which outputs the corresponding PNAM device. In embodiments, the controller 12 may upload the PNAM device model to a cloud-based storage, from which a printer controller of the 3D printer may download the PNAM device model. The 3D printer may output a PNAM device from one or more suitable biocompatible, rigid materials. For example, the PNAM device of certainembodiments includes a resin or plastic material. Moreover, certain embodiments of the PNAM device may include two or more printed layers, such as a gum-facing, internal layer printed from a relatively soft material for comfort and an external layer printed from a relatively harder material to provide resilience to the PNAM device. The controller 12 of these embodiments may design the PNAM device model with a bisecting line or division to indicate a respective, target thickness for each of the multiple layers. Accordingly, embodiments of the method 100 may result in PNAM devices that are particularly efficient to manufacture and that provide improved cleft closure and treatment comfort for subjects.

[0055] FIG. 7 is a flowchart of a method 200 of using the device generation system 10 to provide additional PNAM devices iteratively or during a course of treatment, in accordance with aspects of the present disclosure. The method 200 may be performed by the controller 12 of the device generation system 10, in certain embodiments. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described blocks may be combined in any order and / or in parallel to implement the method 200.

[0056] As illustrated at block 202, the controller 12 may generate PNAM device model based on initial intraoral scan data. In certain embodiments, the PNAM device model is generated by performing the method 100 of FIG. 2 or another suitable embodiment of PNAM device model generation disclosed herein. At block 204, the controller 12 may determine whether an additional PNAM device has been requested. For example, the controller 12 may determine that an additional PNAM device has been requested in response to receiving user input from a communicatively coupled user input device. In some embodiments, the controller 12 makes the determination of block 204 based on the receipt of additional scanning data for a subject that was previously fitted with a PNAM device.

[0057] At block 206, the controller 12 may receive updated intraoral scan data after a treatment period has elapsed. The treatment period of certain embodiments may be a threshold amount of time, such as a day, a week, a month, or another suitable period of time after which measuring or analyzing changes in the subject’s intraoral surfaces is desirable. Moreover, at block 208, the controller 12 may generate the requested updated PNAM device model based on the updated intraoral scan data. This updated PNAM device model may be printed, fitted with updated or repositioned stability supports, and provided to the subject for further molding of the cleft palate.

[0058] At block 210, in response to determining that an additional PNAM device is not requested, the controller 12 may update the Al model based on treatment and results. In some embodiments, thedetermination that an additional PNAM device is not requested is indicative of a palate molding process being completed. In certain embodiments, the determination that an additional PNAM device is not requested is indicative of a single PNAM device being suitable for providing the desired palate molding process. In either case, after generation of a PNAM device model and PNAM device, the controller 12 of the device generation system 10 may update the Al model to learn or be trained based on results, insights, and / or data based on the treatment of the subject. For example, each intraoral model, identified intraoral landmark, PNAM device model, and any other relevant information associated with treatment of the cleft palate may be added to a database or corpus of data from which the Al model may be trained. In certain embodiments, the corpus of data includes a first portion of data associated with unilateral cleft palates and a second portion of data associated with bilateral cleft palates, where each previously intraoral model is labeled or annotated with previous landmarks. A practitioner may also manually provide feedback to the controller 12 regarding the molding outcomes or final surgical outcomes for the subject. As one non-limiting example, the feedback may include data linking a particular PNAM device with an associated distance reduction between cleft edges over a treatment time period. This feedback loop may therefore enable the controller 12 to provide continuous improvement and training to the PNAM device models generated based on the Al model, in certain embodiments.

[0059] FIG. 8 is a flowchart of a method 250 of using the device generation system 10 to efficiently provide PNAM devices for improved treatment outcomes, at higher accessibility and lower costs than certain previous devices, in accordance with aspects of the present disclosure. The method 250 may be performed by the controller 12 of the device generation system 10, in certain embodiments. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described blocks may be combined in any order and / or in parallel to implement the method 250. For improved understanding, the following discussion of the method 250 will refer to certain embodiments illustrated in FIGS. 9-19 as illustrative examples of certain method steps.

[0060] As illustrated at block 252, the controller 12 may generate an intraoral model based on intraoral scan data 32. The intraoral scan data 32 of certain embodiments is collected by an intraoral scanner or 3D scanner that senses and stores data indicative of oral surfaces and / or structures within a subject having a cleft palate. The intraoral scan data may be provided to the controller 12 via any suitable wireless and / or wired communication pathways. After receipt of the intraoral scan data 32, the controller 12 may import, load, or open the intraoral scan data within a 3D modeling program, in certain embodiments, thus generating an intraoral model. The intraoral scan data or model thereofmay be provided in a format suitable for storing data that describes structure or geometry of the intraoral surfaces and / or structures. In some embodiments, the data is received in an STL (STereoLithography) file format, which may represent or approximate surface geometry of objects via a triangulated surface composed of triangular units or planes. The STL format of certain embodiments may be particularly efficient for use within computer-aided design systems, in some embodiments. In certain embodiments, the data is received in any suitable 3D digital file format that is readable by the controller 12. For example, the 3D digital format may additionally or alternatively include PLY (Polygon File Format), STEP (Standard for the Exchange of Product model data), and / or IGES (Initial Graphics Exchange Specification), in embodiments.

[0061] At block 254, the controller 12 may receive a selection indicative of the subject having a unilateral or a bilateral cleft. As such, the controller 12 may access models and data that are specific to the cleft type in future steps. For example, intraoral models may include different landmarks and PNAM devices may include different stability supports based on the cleft type. In certain embodiments, the controller 12 may automatically identify whether the cleft is unilateral or bilateral based on distinctive features that are different between the two cleft types. In some embodiments, the controller 12 may receive the selection indicative of the cleft type based on user input provided to a user input device communicatively coupled to the controller 12.

[0062] At block 256, the controller 12 may identify landmarks in the intraoral model to facilitate further processing steps of the device generation system. In some embodiments, the landmark identification is based on one or more Al models 40. The Al models 40 may be trained based on a database having various intraoral models or data with landmarks that are selected, tagged, or annotated with reference to their location and shape within the intraoral models. In certain embodiments, the intraoral models and corresponding landmarks of the database are separated or grouped based on the cleft type, such that future intraoral models are processed with reference to other, labeled models of the same cleft type. This database may be continuously updated as new intraoral models are tagged with landmarks, similar to the above discussion of FIG. 7, in embodiments. In certain embodiments, the landmark identification may be confirmed by or performed by a technician or professional associated with cleft treatment.

[0063] Looking now to the example embodiment of FIG. 9, a set of landmarks may be identified along a surface 302 of an intraoral model 300. As non-limiting examples, the controller 12 may identify the following landmarks for a unilateral cleft, which are labeled as indicated in FIG. 9: incisal papilla 1L, maxillary central labial frenum 2L, posterior left labial frenum 3L, posterior right labialfrenum 4L, right maxilla tuberosity 5L, left maxilla tuberosity 6L, greater section labial anterior point 7L, lesser section labial anterior point 8L, lesser section alveolar ridge top point 9L, lesser section palatal point 10L, and greater section alveolar ridge top point 11L.

[0064] In certain embodiments, additional landmarks may be identified and / or one or more of the above-listed landmarks may be omitted. Indeed, the controller 12 may identify a targeted set of landmarks that are specific to the particular subject being evaluated for a PNAM device, as well as the type of cleft through the palate. For example, unilateral clefts such as the example shown in the intraoral model 300 of FIG. 9 may include landmarks associated with a greater section and a lesser section of the palate. Moreover, bilateral clefts may form a palate having three sections, such that landmarks may be associated with an A section, a B section, and a C section of the palate.

[0065] Returning to FIG. 8, at block 260 of the method 250, the controller 12 may identify a cleft region and / or noise within the intraoral model. In some embodiments, the controller 12 may also remove associated, residual surfaces of the cleft region and / or any noise from the intraoral model. The intraoral model of certain embodiments may therefore be cleansed of surfaces or components that are not used as reference for generation of the PNAM device, including a cleft concavity and any noise that may have been generated during the scan reconstruction of the alveolar ridge and other intraoral structures. In embodiments, the identification step of block 260 may be omitted, and subsequent processing may correct or smooth over the cleft region without a specifically performed removal step.

[0066] At block 262, the controller 12 may condition a mesh or surface of the intraoral model via smoothing processes, adjusting an offset across the cleft, or both. In certain embodiments, the mesh of the intraoral model may be initially generated in a suitable form, such that this step may be omitted. The example embodiment of the intraoral model 320 in FIG. 10 may represent an intraoral surface 322 or mesh that has been conditioned based on removal or clearing of a cleft region, removal of any noise, smoothing, and / or offset adjustment, in certain embodiments.

[0067] At block 264 of FIG. 8, the controller 12 may close or seal a surface of the intraoral model via interpolation between corresponding landmarks at cleft edges. This step may generally transform the intraoral model into a smoothed or partially corrected model of the subject’s palate, in certain embodiments. For example, the cleft palate of certain subjects may be formed based on an incomplete joining of facial tissues during pregnancy, and the present modeling step may function to estimate a surface that completes the unfinished or truncated palate formation process.

[0068] An example embodiment is illustrated in FIG. 11, in which certain, associated pairs of the intraoral landmarks in an intraoral model 330 are connected via guidelines 332. For example, in certain embodiments, the greater section labial anterior point may be connected to the lesser section labial anterior point and the greater section alveolar ridge top point may be connected to the lesser section alveolar ridge top point. Other corresponding pairs of landmarks may also be connected via respective guidelines 332. The guidelines 332 may each extend in a 3D space to define a basis or curve for surface formation, in certain embodiments. In other words, the guidelines 332 may provide an outline or skeleton from which the controller 12 may fill in the estimated surface. For subjects having a bilateral cleft, additional landmarks may be present to denote the cleft between a primary and two secondary palate portions. FIG. 12 illustrates an example of an intraoral model 340 having an estimated surface 342 provided in place of a previously present cleft, based on the interpolation between the mesh at the sides of the previously visible cleft.

[0069] At block 266 of the method 250, the controller 12 may generate a PNAM device model based on tracing a polyline drawing of contours on a surface of the mesh or intraoral model. This step may be completed manually based on user input, in certain embodiments. In some embodiments, this step may be performed automatically or semi-automatically, such as based on an Al model that is trained based on a database storing polyline drawings for PNAM device models and their associated intraoral model. In the example embodiment of FIG. 13, a polyline drawing 352 is illustrated as superimposed onto an intraoral model 350, which has been smoothed based on interpolation. This smoothed surface may define a palate-facing or gum-facing surface of a PNAM device model 360 that may include the polyline drawing 352 as outer boundaries, as illustrated in FIG. 14. At block 270 of the method 250, the controller 12 may transform the 2D mesh into a 3D object using an offset to thicken the PNAM device model. An example is illustrated in FIG. 15, in which a PNAM device model 370 has been adjusted or offset to a target thickness 372, which may be selected to provide suitable resilience to the later formed PNAM device, without compromising subject comfort.

[0070] At block 272, the controller 12 may determine a center of gravity of PNAM device model. As reference, the center of gravity may correspond to a point or an average location onto which the weight of an object acts and at which the total gravitational torque on the object is zero. In certain embodiments, the controller calculates the center of gravity based on analysis of a volume or mass of the PNAM device model. In some cases, the controller 12 may assign a density to the PNAM device model based on one or more materials from which the PNAM device may be constructed. As mentioned above, certain PNAM devices may be printed with two or more layers of different material,which may include different densities. In embodiments, the controller 12 may determine the center of gravity based on analysis of a weight of the PNAM device model, simulated to include one or more layers of material. In embodiments, the controller 12 may determine the center of gravity for the irregular, customized shape of the PNAM device based on calculating a weight distance moment for each point of the PNAM device model. The calculations may include calculating the force, counter force, and rotational forces that the PNAM device may exert on intraoral surfaces. The present techniques therefore improve upon certain traditional molding devices that may not be prepared based on any force balance analyses or considerations.

[0071] At block 274, the controller 12 may smooth edges of PNAM device model. In some embodiments, this step may be performed before the determination of the center of gravity. The smoothed edges of certain embodiments may be formed along a full outline of the PNAM device model, in certain embodiments, and thus maintain the specifically calculated center of gravity in the PNAM device model. In embodiments, the center of gravity of the PNAM device model may not change by more than a threshold distance in response to the edges being smoothed. FIGS. 16 and 17 illustrate top and bottom perspective views, respectively, of embodiments of PNAM device models 380, 384 having smoothed edges 382, 386 for improved subject comfort.

[0072] At block 276, the controller 12 may determine suitable, target positions for adding stability supports, based on the center of gravity analysis. Utilizing the center of gravity for positioning stability supports may desirably enhance a comfort level associated with wearing the PNAM device, in certain embodiments. For example, the resulting PNAM device may be entirely or fully balanced when applied to the cleft palate, and thus unlikely to attempt to drift, rotate, or chafe intraoral structures. In other words, the target positions for the stability supports may balance the PNAM device model relative to a horizontally extending plane. As such, the device generation system may produce a PNAM device model that is uniquely customized for the specific anatomy of a subject having a cleft palate, while offering further advances to wearability over traditional, fully manually created devices.

[0073] At block 280, the controller 12 may remove material from the target positions to form apertures within the PNAM device model. In embodiments, these apertures or integrated receptacles for stability supports may reduce an assembly complexity, while conserving materials that may otherwise be removed and discarded from a PNAM device. In certain embodiments, the controller 12 may iterate or repeat steps of block 272, block 276, and block 280 to redetermine the center of gravity after forming the apertures, redetermine target positions for the stability supports, and adjust theformed apertures until the PNAM device model having apertures is completely balanced with respect to the force balance analysis. In some embodiments, forming the apertures may not significantly or noticeably change the center of gravity of the PNAM device or model thereof because the added stability supports provide suitable counterweight to a front portion of the PNAM device for establishing a suitable state of equilibrium.

[0074] As a first example, FIG. 18 illustrates a PNAM device model 400 for a subject having a unilateral cleft. The PNAM device model 400 of the illustrated embodiment includes three apertures or cylindrical receptacles for receiving stability supports after printing or production of the PNAM device model 400. In particular, a first lateral aperture 402 and a second lateral aperture 404 are provided for receiving a first stability button and a second stability button, respectively. A central aperture 406 is also provided between the lateral apertures 402, 404 for receiving a nasal stent. The second example of FIG. 19 illustrates another PNAM device model 410 for a subject having a bilateral cleft, which may benefit from treatment with two nasal stents. As such, the PNAM device model 410 of FIG. 19 includes a first central aperture 412 and a second central aperture 414 for receiving a first nasal stent and a second nasal stent therein. The PNAM device model 410 also includes a first lateral aperture 416 and a second lateral aperture 418 for first and second stability buttons.

[0075] Returning to FIG. 8, at block 282, the controller 12 may verify a device fit based on comparison between the intraoral model and a corresponding surface of the PNAM device model. The verification may be a quality checking step performed in certain embodiments to confirm an absence of interference of the between the intraoral model and the PNAM device model, in certain embodiments. In embodiments, the PNAM device model is verified against an original or as-received version of the intraoral model to check the device fit compared to untreated or unmolded surfaces of the subject’s mouth. In embodiments, should a portion of the PNAM device model be identified as abutting an intraoral surface or structure, the identified portion may be adjusted or removed by the controller for improved subject comfort. The controller 12 may additionally or alternatively identify and correct any portions of the PNAM device model that are beyond a threshold distance from the intraoral model or that may be adjusted for a more comfortable and / or effective fit against the intraoral model. At block 284, the controller 12 may export the PNAM device model for 3D printing. A 3D printer may thus receive the PNAM device model and output a corresponding PNAM device 286 for treating a cleft within a palate. As such, the present embodiments of the device generation systemprovide controllers that may generate balanced, customized models of PNAM devices having improved treatment efficacy, comfort, and accessibility over manually prepared molding devices.

[0076] The present disclosure described herein, therefore, is well adapted to carry out the objects and attain the ends and advantages mentioned, as well as others inherent therein. While a presently preferred embodiment of the disclosure has been given for purposes of disclosure, numerous changes exist in the details of procedures for accomplishing the desired results. These and other similar modifications will readily suggest themselves to those skilled in the art and are intended to be encompassed within the spirit of the present disclosure disclosed herein and the scope of the appended claims.

Claims

CLAIMSWhat is claimed is:

1. A controller for producing presurgical nasoalveolar molding (PNAM) device models, the controller comprising: one or more processors; and a non-transitory machine-readable storage medium storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to: generate an intraoral model of a subject having a cleft palate based on intraoral scan data captured by an intraoral scanner; identify a plurality of landmarks within the intraoral model based on an Al model; interpolate between at least one associated pair of the plurality of landmarks across a cleft region within the intraoral model to generate a smoothed intraoral model; generate a PNAM device model configured to abut a surface of the smoothed intraoral model; determine a center of gravity of the PNAM device model; define apertures for stability supports within the PNAM device model based on the center of gravity; and output the PNAM device model to a 3D printer configured to generate a PNAM device.

2. The controller of claim 1, wherein the non-transitory machine-readable storage medium includes processor-executable instructions, when executed by the one or more processors, to cause the one or more processors to determine the center of gravity of the PNAM device model based on a force balance analysis of surface geometry of the PNAM device model.

3. The controller of claim 1, wherein the non-transitory machine-readable storage medium includes processor-executable instructions, when executed by the one or more processors, to cause the one or more processors to generate the PNAM device model configured to abut the surface of the smoothed intraoral model by: tracing a polyline drawing on the surface of the smoothed intraoral model; and thickening the polyline drawing with an offset to generate the PNAM device model.

4. The controller of claim 1, wherein the non-transitory machine-readable storage medium includes processor-executable instructions, when executed by the one or more processors, to cause the one or more processors to define the apertures for the stability supports at target positions that balance the PNAM device model relative to a horizontally extending plane.

5. The controller of claim 4, wherein the apertures comprise a first lateral aperture for receiving a first stability button and a second lateral aperture for receiving a second stability button.

6. The controller of claim 4, wherein the apertures comprise at least one central aperture for receiving a nasal stent.

7. The controller of claim 1, wherein the Al model is trained based on a corpus of data comprising a plurality of previous intraoral models, each labeled with a plurality of previous landmarks.

8. The controller of claim 7, wherein the controller is configured to add the intraoral model of the subject and the plurality of landmarks to the corpus of data.

9. The controller of claim 7, wherein the corpus of data comprises a first portion of data associated with unilateral cleft palates and a second portion of data associated with bilateral cleft palates.

10. The controller of claim 1, wherein the at least one associated pair of the plurality of landmarks comprises a greater section labial anterior point and a lesser section labial anterior point, a greater section alveolar ridge top point and a lesser section alveolar ridge top point, or both.

11. The controller of claim 1, wherein the non-transitory machine-readable storage medium includes processor-executable instructions, when executed by the one or more processors, to cause the one or more processors to provide the PNAM device model with an internal layer formed of a first material and an external layer formed of a second material, wherein the second material is different from the first material.

12. The controller of claim 1, wherein the non-transitory machine-readable storage medium includes processor-executable instructions, when executed by the one or more processors, to cause the one or more processors to smooth one or more edges of the PNAM device model before defining the apertures for the stability supports.

13. A device generation system for treating a subject having a cleft palate, comprising: a controller comprising one or more processors and a non-transitory machine-readable storage medium storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to: generate an intraoral model of a subject having a palate with a cleft based on intraoral scan data captured by an intraoral scanner; identify a plurality of landmarks within the intraoral model based on an Al model;interpolate between at least one associated pair of the plurality of landmarks across a cleft region of the intraoral model to generate a smoothed intraoral model; generate a presurgical nasoalveolar molding (PNAM) device model configured to contour to a surface of the smoothed intraoral model; determine a center of gravity of the PNAM device model; define apertures for stability supports within the PNAM device model based on the center of gravity; and export the PNAM device model for printing by a 3D printer configured to generate a PNAM device to reduce the cleft of the palate.

14. The device generation system of claim 13, wherein the non-transitory machine-readable storage medium includes processor-executable instructions, when executed by the one or more processors, to cause the one or more processors to determine the center of gravity of the PNAM device model via a force balance analysis of a plurality of points along a surface of the PNAM device model.

15. The device generation system of claim 13, further comprising the 3D printer, wherein the 3D printer is configured to generate the PNAM device with a first layer of first material and a second layer of second material, wherein the second material is more rigid than the first material.

16. The device generation system of claim 13, further comprising the 3D printer, wherein the 3D printer is positioned in a same building or region as the controller.

17. The device generation system of claim 13, further comprising the intraoral scanner, wherein the intraoral scanner is configured to capture the intraoral scan data based on measuring intraoral surfaces of the subject.

18. The device generation system of claim 13, wherein the controller is positioned in a different location than the intraoral scanner.

19. The device generation system of claim 13, wherein the at least one associated pair of the plurality of landmarks comprises a greater section labial anterior point and a lesser section labial anterior point.

20. The device generation system of claim 13, wherein the at least one associated pair of the plurality of landmarks comprises a greater section alveolar ridge top point and a lesser section alveolar ridge top point.21 . A computer-implemented method of generating a presurgical nasoalveolar molding (PNAM) device model, the method comprising: generating, via one or more processors of a controller, an intraoral model of a subject having a cleft palate based on intraoral scan data captured by an intraoral scanner; identifying, via the one or more processors, a plurality of landmarks within the intraoral model based on an Al model; interpolating, via the one or more processors, between at least one associated pair of the plurality of landmarks across a cleft region within the intraoral model to generate a smoothed intraoral model; generating, via the one or more processors, a presurgical nasoalveolar molding (PNAM) device model configured to abut a surface of the smoothed intraoral model; determining, via the one or more processors, a center of gravity of the PNAM device model; forming, via the one or more processors, apertures for stability supports within the PNAM device model based on the center of gravity; and outputting, via the one or more processors, the PNAM device model to a 3D printer configured to generate a PNAM device based on the PNAM device model.

22. The method of claim 21, wherein determining the center of gravity of the PNAM device model comprises performing a force balance analysis of surface geometry of the PNAM device model.

23. The method of claim 21, wherein generating the PNAM device model configured to abut the surface of the smoothed intraoral model comprises: tracing a polyline drawing on the surface of the smoothed intraoral model; thickening the polyline drawing with an offset to generate the PNAM device model; and smoothing one or more edges of the PNAM device model.

24. The method of claim 21, comprising training the Al model based on a database storing a plurality of intraoral models labeled with one or more corresponding landmarks.

25. The method of claim 24, comprising storing the intraoral model and the plurality of landmarks in the database for further Al training.

26. The method of claim 21, comprising verifying a fit of the PNAM device model after defining the apertures for the stability supports by comparing a surface of the PNAM device model to a corresponding surface of the intraoral model.

27. The method of claim 21, comprising: receiving updated intraoral scan data for the subject after a treatment period; andgenerating and outputing an updated PNAM device model based on the updated intraoral scan data.

28. The method of claim 21, comprising: receiving, via the 3D printer, the PNAM device model from the controller; and printing the PNAM device model from at least one material to form the PNAM device.

29. The method of claim 28, wherein printing the PNAM device model from at least one acrylic material comprises printing a first layer comprising a first material and a second layer comprising a second material, different from the first material.

Images