US 11049248

US Patent 11049248B2, titled "Method for analyzing an image of a dental arch," was issued to Dental Monitoring SAS on June 29, 2021, from an application filed on July 9, 2018. The inventors are Philippe Salah, Thomas PELLISSARD, Guillaume GHYSELINCK, and Laurent DEBRAUX.

Abstract:
The patent describes a method for assessing the shape of an orthodontic aligner. This involves acquiring an analysis image showing the aligner on a patient's teeth. A deep learning device, trained using a specific database, then analyzes this image to determine a value for at least one tooth attribute, which relates to the separation between a tooth and the aligner, or an image attribute for the entire image, also related to this separation.

Plain-language Overview of Independent Claims:

• Independent Claim 1: This claim outlines a method for analyzing an image of a patient's dental arch. It involves:

  1. Creating a "learning base" of over 1000 "historical images" of dental arches. Each tooth in these historical images has assigned "tooth attribute values" (e.g., tooth type, number).
  2. Training a deep learning device (preferably a neural network) using this learning base.
  3. Submitting a new "analysis image" to the trained deep learning device, which then determines probabilities related to the attribute values of teeth represented in specific "analysis tooth zones" within the image.
  4. Based on these probabilities, determining the presence of a tooth at a given analysis tooth zone and its corresponding attribute value.

• Independent Claim 14: This claim describes a method specifically for evaluating the fit of an orthodontic aligner. It involves:

  1. Acquiring at least one "analysis image" that shows the aligner worn by a patient.
  2. Analyzing this image with a deep learning device, which has been trained using a learning base. The analysis determines a "value" for either:
     • At least one "tooth attribute" for an "analysis tooth zone" (representing a tooth), where this attribute relates to the separation between that tooth and the aligner.
     • An "image attribute" for the entire analysis image, where this attribute relates to the separation between at least one tooth and the aligner.

Litigation Information:
As of July 7, 2026 (a date in the future relative to the current date of April 26, 2026), the U.S. Court of Appeals for the Federal Circuit (CAFC) issued a decision in Dental Monitoring SAS v. Align Technology, Inc.. This decision affirmed a district court ruling that found several claims, including claim 14 of US11049248, invalid as directed to ineligible subject matter under 35 U.S.C. § 101. Specifically, claim 14 was determined to be directed to the abstract idea of collecting and analyzing image information through a deep learning device. The district court had granted summary judgment of ineligibility in July 2023, which Dental Monitoring SAS appealed.