DCT
3:22-cv-07335
Dental Monitoring SAS v. Align Technology Inc
I. Executive Summary and Procedural Information
- Parties & Counsel:
- Plaintiff: Dental Monitoring SAS (France)
- Defendant: Align Technology, Inc. (Delaware)
- Plaintiff’s Counsel: Gibson, Dunn & Crutcher LLP
- Case Identification: 5:22-cv-07335, N.D. Cal., 11/18/2022
- Venue Allegations: Venue is alleged to be proper based on Defendant’s regional and historic global headquarters in San Jose, California, and alleged acts of infringement within the district, including research, design, and testing efforts.
- Core Dispute: Plaintiff alleges that Defendant’s Invisalign Virtual Care AI platform infringes patents related to AI-powered methods for remotely acquiring and analyzing images of a patient's dentition and orthodontic aligners.
- Technical Context: The technology involves using smartphone cameras and artificial intelligence to remotely monitor orthodontic treatment progress, reducing the need for in-person appointments.
- Key Procedural History: The complaint alleges that prior to launching the accused products, Defendant’s executives held meetings with Plaintiff to discuss potential business relationships, during which Plaintiff’s executives provided express reminders that its technology was protected by a patent portfolio. This history is cited to support allegations of willful infringement.
Case Timeline
| Date | Event |
|---|---|
| 2014-01-01 | Dental Monitoring founded (approximate, per complaint) |
| 2017-06-09 | Priority Date for ’945 Patent |
| 2017-07-21 | Priority Date for ’409 and ’248 Patents |
| 2020-03-01 | Align launches Invisalign Virtual Care platform (approximate) |
| 2020-08-25 | ’409 Patent Issued |
| 2021-06-29 | ’248 Patent Issued |
| 2021-09-07 | ’945 Patent Issued |
| 2022-09-01 | Align announces Invisalign Virtual Care AI platform (approximate) |
| 2022-11-18 | Complaint Filed |
II. Technology and Patent(s)-in-Suit Analysis
U.S. Patent No. 10,755,409 - Method for Analyzing an Image of a Dental Arch
The Invention Explained
- Problem Addressed: The patent describes an "ongoing need for a method simplifying the analysis of the images of dental arches of patients" to reduce the necessity of in-person appointments with an orthodontist for treatment assessment (’409 Patent, col. 1:16-19).
- The Patented Solution: The invention proposes a method where an image acquisition apparatus (e.g., a smartphone) is used to capture an image of a patient's dental arch. This "analysis image" is processed by a deep learning device to determine an "image attribute" (e.g., image quality, mouth opening). This attribute is compared to a "setpoint" to check if the image is suitable for analysis. If not, an information message is sent to guide the user in acquiring a new, better image, a process the patent calls "embedded monitoring" (’409 Patent, Abstract; col. 25:15-20). This feedback loop is designed to ensure high-quality images are captured remotely.
- Technical Importance: The method aims to make remote image acquisition more reliable and efficient by providing real-time, automated feedback to the user, thereby improving the quality of data available for remote orthodontic monitoring (’409 Patent, col. 25:12-20).
Key Claims at a Glance
- The complaint asserts at least independent claim 1 (Compl. ¶46).
- The essential elements of independent claim 1 are:
- Activating an image acquisition apparatus to acquire an "analysis image" of a dental arch.
- Analyzing the image using a deep learning device trained by a learning base.
- Determining a value for an "image attribute" based on the analysis.
- Comparing the image attribute value with a "setpoint".
- Sending an information message based on the comparison to guide the operator to acquire a new image if the setpoint is not met.
- The complaint reserves the right to identify additional infringing activities and claims during discovery (Compl. ¶46).
U.S. Patent No. 11,049,248 - Method for Analyzing an Image of a Dental Arch
The Invention Explained
- Problem Addressed: The patent addresses the need for solutions to assess the fit and suitability of orthodontic aligners remotely, which conventionally requires frequent in-person visits to an orthodontist (’248 Patent, col. 27:8-18).
- The Patented Solution: The invention is a method for assessing an aligner's shape after treatment has begun (more than one week). A user captures an image of the aligner as worn by the patient. A deep learning device analyzes this image to determine a value for an attribute related to the "separation" between a tooth and the aligner (’248 Patent, col. 28:1-24; Abstract). This analysis provides an assessment of whether the aligner is seated correctly and tracking with the treatment plan.
- Technical Importance: This technology allows for the remote, automated detection of ill-fitting aligners, a critical factor in the success of clear aligner therapy, thereby simplifying the assessment process for both patient and doctor (’248 Patent, col. 28:45-52).
Key Claims at a Glance
- The complaint asserts at least independent claim 15 (Compl. ¶57).
- The essential elements of independent claim 15 are:
- More than 1 week after starting treatment, acquiring at least one "analysis image" (a photograph or film image) partially representing the aligner in its service position on a patient's teeth.
- Analyzing the image with a deep learning device trained by a learning base.
- The analysis determines a value for an "image attribute" that relates to a "separation between at least one tooth represented on the analysis image, and the aligner represented on said analysis image."
- The complaint reserves the right to identify additional infringing activities and claims during discovery (Compl. ¶57).
Multi-Patent Capsule: U.S. Patent No. 11,109,945
- Patent Identification: U.S. Patent No. 11,109,945, Method of Evaluating an Orthodontic Aligner, issued September 7, 2021.
- Technology Synopsis: This patent addresses the need for reliable remote assessment of aligner treatment progress to reduce patient travel (’945 Patent, col. 1:53-59). The method involves acquiring separate images of the patient's teeth with the aligner on ("aligner image") and with it off ("dentition image"), determining interior and exterior tooth outlines from both images, and comparing these outlines to calculate a score, which evaluates how well the aligner fits (’945 Patent, col. 2:1-24).
- Asserted Claims: The complaint asserts at least independent claim 1 (Compl. ¶68).
- Accused Features: The complaint alleges that Align's system infringes by acquiring images of teeth with and without the aligner, determining tooth outlines, and comparing them to assess aligner fit (Compl. ¶¶ 68, 32, 39).
III. The Accused Instrumentality
Product Identification
- The "Align Accused Products and Services" collectively refer to the Invisalign Virtual Care AI platform and associated apparatus, including the "My Invisalign" mobile application ("Align App") and the backend "Align Server" (Compl. ¶¶ 15, 36).
Functionality and Market Context
- The accused platform is designed to help doctors remotely monitor Invisalign treatment progress (Compl. ¶31). Patients are required to download the Align App and are guided to take photos of their teeth, some with the aligner on and others with it off (Compl. ¶¶ 32, 37).
- The platform includes several AI-assisted features: "AI-assisted Photo Capture" assists the patient in taking required photos; "AI-assisted Automatic Assessment" measures and highlights the size of aligner spaces to determine fit; and "AI-assisted Automated Notification" informs patients whether to advance to the next aligner (Compl. ¶34). An image from the complaint shows the system providing guidance like "Come a bit closer" or "Move back a bit" during the photo capture process (Compl. p. 15).
- The complaint alleges these features were launched in response to the COVID-19 pandemic, which created an urgent need for remote monitoring and caught Align "flat-footed" (Compl. ¶¶ 14, 27). The complaint quotes doctors stating the platform "elevated the remote monitoring experience" (Compl. ¶35).
IV. Analysis of Infringement Allegations
’409 Patent Infringement Allegations
| Claim Element (from Independent Claim 1) | Alleged Infringing Functionality | Complaint Citation | Patent Citation |
|---|---|---|---|
| a') activation of an image acquisition apparatus so as to acquire an image, called “analysis image”, of said arch | The Align App, operating on a patient's phone, is activated to capture images of the patient's dental arch. | ¶¶ 36-40 | col. 25:62-65 |
| b') analysis of the analysis image by means of a deep learning device trained by means of a learning base | The Align App transmits images to the Align Server, which allegedly uses a neural network or deep learning device, trained on a base of at least 1,000 images, to analyze them. | ¶¶ 41-43 | col. 2:29-32 |
| c') determination, for the analysis image, as a function of the results of the analysis in the preceding step, of a value for an image attribute | The system determines attributes such as the position of the dental arch (too close/far) or the quality of the image based on the analysis. | ¶¶ 39-41 | col. 3:19-21 |
| d') comparison of said image attribute value with a setpoint | The system compares the determined attribute (e.g., position) against a pre-defined optimal position or distance (the "setpoint") to check if the image is acceptable. | ¶¶ 39-41 | col. 25:12-20 |
| e') sending of an information message as a function of said comparison, the information message being related to the quality of the image acquired or to the position of the acquisition apparatus . . . to check whether the analysis image respects the setpoint and, if it does not . . . to guide the operator . . . to acquire a new analysis image | The "Guided Photo Taking with Automatic Capture" feature provides real-time feedback messages like "Come a bit closer" or "Move back a bit" to guide the patient if the image does not meet the setpoint. A complaint visual depicts this functionality (Compl. p. 15). | ¶¶ 39-41 | col. 25:46-51; 31:32-42 |
- Identified Points of Contention:
- Scope Questions: A central question will be whether Align's process of guiding a user to a correct position for a photo constitutes a "comparison of said image attribute value with a setpoint" as required by the claim. The defense may argue its system uses general positional guidance rather than calculating a specific "image attribute value" and comparing it to a discrete "setpoint."
- Technical Questions: The complaint alleges the deep learning device is trained on a "learning base" of at least 1,000 images (Compl. ¶43). A factual question will be whether this allegation is accurate and whether the nature of Align's training data and methods meets the requirements of the claim as construed by the court.
’248 Patent Infringement Allegations
| Claim Element (from Independent Claim 15) | Alleged Infringing Functionality | Complaint Citation | Patent Citation |
|---|---|---|---|
| a") more than 1 week after the start of the treatment with the aligner, acquisition of at least one image at least partially representing the aligner in a service position in which it is worn by a patient, called “analysis image”... | The accused platform is used throughout a patient's treatment, which lasts longer than one week. It requires patients to take photos of their teeth with the aligner on. A complaint visual shows a user taking a photo with an aligner in place (Compl. p. 15). | ¶¶ 31-32, 36-39 | col. 27:3-9 |
| b") analysis of the analysis image by means of a deep learning device, trained by means of a learning base, so as to determine a value for an image attribute of the analysis image, the image attribute relating to a separation between at least one tooth... and the aligner... | The "AI-assisted Automatic Assessment" feature allegedly uses a deep learning device to analyze the captured image. This feature "measures and highlights the size of aligner spaces" and helps "determine aligner fit," which the complaint maps to the claimed determination of a "separation" between the tooth and aligner. This assessment is used to generate "On track" or "Instructions" feedback (Compl. p. 16). | ¶¶ 34-35, 41-43 | col. 27:10-24 |
- Identified Points of Contention:
- Scope Questions: The key dispute will likely center on the term "separation." The question will be whether Align's "measurement of aligner spaces" and determination of "aligner fit" constitutes determining a value for an attribute "relating to a separation" as claimed. Align may argue its "fit" assessment is a qualitative or different type of analysis than the "separation" contemplated by the patent.
- Technical Questions: Evidence will be required to demonstrate that Align's "AI-assisted Automatic Assessment" functions as alleged, specifically that it uses a deep learning device to analyze the image and quantify or otherwise determine a value related to the space between the tooth and the aligner.
V. Key Claim Terms for Construction
For the ’409 Patent:
- The Term: "setpoint"
- Context and Importance: This term is critical because the infringement theory hinges on whether Align’s "AI-assisted Photo Capture" guidance system (e.g., "move back a bit") is equivalent to comparing an image attribute to a "setpoint" to check image quality. The definition of "setpoint" will determine if a general guidance system meets this limitation or if a more specific, quantitative comparison is required.
- Intrinsic Evidence for Interpretation:
- Evidence for a Broader Interpretation: The claim language states the information message is sent to "check whether the analysis image respects the setpoint," which could be interpreted to cover any condition-checking, including qualitative checks on position or focus (’409 Patent, col. 32:1-5).
- Evidence for a Narrower Interpretation: The specification discusses the setpoint in the context of specific, measurable characteristics like "opening of the mouth" or "wearing of a dental appliance," suggesting it may be a specific, predefined condition rather than a general quality assessment (’409 Patent, col. 9:10-13).
For the ’248 Patent:
- The Term: "separation between at least one tooth... and the aligner"
- Context and Importance: The core of the infringement allegation for the ’248 patent is that Align's "AI-assisted Automatic Assessment" of "aligner spaces" and "aligner fit" meets this limitation. The construction of "separation" will be determinative; if construed narrowly to mean a specific type of measurement, Align's functionality may not infringe, whereas a broader construction covering general fit assessment could favor the plaintiff.
- Intrinsic Evidence for Interpretation:
- Evidence for a Broader Interpretation: The patent states the attribute can relate to "an overall acceptability of the separation of the teeth represented," which may support a more qualitative or holistic assessment of fit, rather than a precise numerical measurement (’248 Patent, col. 27:64-65).
- Evidence for a Narrower Interpretation: The claim requires determination of "a value for an image attribute... relating to a separation," which could imply a quantitative output. The specification also discusses attributes like "maximal separation along the free edge of the tooth," suggesting a specific, measurable distance is contemplated (’248 Patent, col. 27:58-60).
VI. Other Allegations
- Indirect Infringement: The complaint alleges both induced and contributory infringement for all patents. Inducement is based on Align providing the Accused Products and Services along with instructions (e.g., patient guides, app prompts) that allegedly direct patients and doctors to perform the patented methods (Compl. ¶¶ 49, 60, 71). Contributory infringement is based on allegations that the products are especially made for infringing use and have no substantial non-infringing uses (Compl. ¶¶ 50, 61, 72).
- Willful Infringement: Willfulness is alleged for all patents. The claim is based on alleged pre-suit knowledge, asserting that Align was aware of Dental Monitoring’s patent portfolio through direct communications and meetings between the companies before the launch of the accused products (Compl. ¶¶ 52, 63, 74).
VII. Analyst’s Conclusion: Key Questions for the Case
- A central issue will be one of technical equivalence: Does the accused "AI-assisted Photo Capture" feature, which provides general user guidance, perform the specific claimed steps of the ’409 patent, namely determining an "image attribute" and comparing it to a "setpoint," or is this a fundamentally different technical operation?
- A second core issue will be one of definitional scope: Can the claim term "separation" in the ’248 patent be construed broadly to encompass Align's more general assessment of "aligner spaces" and "fit," or does the patent require a more specific, quantitative measurement that Align's system does not perform?
- A key evidentiary question will concern willfulness: What was the substance of the alleged pre-suit communications between the parties, and can Dental Monitoring prove that Align had knowledge of the specific patents-in-suit and their asserted relevance to the accused technology before the complaint was filed?