Patents by Inventor Vasant Kearney
Vasant Kearney has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11398013Abstract: A novel GAN is trained to predict high fidelity synthetic images based on low quality input dental images. The GAN further takes input anatomic masks as inputs with each image, the masks labeling pixels of the image corresponding to dental features. The GAN includes an encoder-decoder generator with semantically aware normalization between stages of the decoder according to the masks. The predicted synthetic dental image and an unpaired dental image are evaluated by a first discriminator of the GAN to obtain a realism estimate. The synthetic image and an unpaired dental image may be processed using a pretrained dental encoder to obtain a perceptual loss. The GAN is trained with the realism estimate, perceptual loss, and L1 loss. Utilization may include inputting noisy, low contrast, low resolution, blurry, or degraded dental images and outputting high resolution, denoised, high contrast, deobfuscated, and sharp dental images.Type: GrantFiled: September 25, 2020Date of Patent: July 26, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Hamid Hekmatian, Ali Sadat
-
Patent number: 11366985Abstract: In medicine and dentistry, image quality affects computer vision accuracy. However, some problems are more tolerant of noise depending on disease severity and radiographic obviousness. There is a need to have a noise estimation model that adapts to each specific domain. A noise estimation model is trained to output a set of domain noise estimates for an input image, each estimate indicating an impact of noise present in the input image on a particular domain, e.g. labeling of a dental feature such as a dental anatomy, pathology, or treatment. The noise estimation model is trained by processing image pairs with a set of machine learning models for a plurality of domains, the image pairs including a raw image and a modified image obtained by adding noise to the raw image. Outputs of the set of machine learning models for the raw and modified images are compared to obtain measured noise metrics. The noise estimation model processes the modified image and is trained to estimate noise metrics.Type: GrantFiled: August 4, 2021Date of Patent: June 21, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Hamid Hekmatian, Ali Sadat
-
Patent number: 11367188Abstract: A GAN is trained to process input images and produce a synthetic dental image. The GAN further takes masks as inputs with each image, the masks labeling pixels of the image corresponding to dental features (anatomy and/or treatments). The GAN includes an encoder-decoder with normalization between stages of the decoder according to the masks. A synthetic image and an unpaired dental image is evaluated by a first discriminator of the GAN to obtain a realism estimate. The synthetic image and an unpaired dental image may be processed using a pretrained dental encoder to obtain a perceptual loss. The GAN is trained with the realism estimate and perceptual loss. Utilization may include modifying a mask for an input image to include or exclude a shape of a feature such that the synthetic image includes or excludes a dental feature.Type: GrantFiled: September 25, 2020Date of Patent: June 21, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Hamid Hekmatian, Stephen Chan, Ali Sadat
-
Patent number: 11357604Abstract: A comprehensive dental readiness platform is presented. Dental patient data including an image, proposed treatments, and a dental form are received and processed by first machine learning models to obtain clinical findings and predicted values for fields of the dental form. The clinical findings and other results are processed by a second machine learning model to obtain predictions of a future dental condition of a patient. The second machine learning model utilizes an ensemble of Transformer Neural Networks, Long-Short-Term-Memory Networks, Convolutional Neural Networks, and Tree-Based Algorithms to predict the dental readiness classification, dental readiness durability, dental readiness error, dental emergency likelihood, prognosis, and alternative treatment options.Type: GrantFiled: June 15, 2021Date of Patent: June 14, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Hamid Hekmatian, Wenxiang Deng, Ming Ted Wong, Ali Sadat
-
Publication number: 20220180447Abstract: Patient meta information, narratives, charts, and images are processed according to a first machine learning model to determine hidden features relating to the adjudication outcome of a proposed claim packet. Image are concatenated and processed using a second machine learning model to label anatomy including periodontal, endodontic, restorative, orthodontic, decay, and other general clinical findings. The meta information, anatomy labels, and image are concatenated and processed using a third machine learning model to obtain feature measurements, such as decay quantifications and periodontal measurements. The feature measurements, anatomy labels, teeth labels, and image information may be concatenated and input to a fourth machine learning model to obtain a diagnosis for a periodontal, decay, endodontic, orthodontic, or restorative condition.Type: ApplicationFiled: February 2, 2022Publication date: June 9, 2022Inventors: Vasant Kearney, Hamid Hekmatian, Ali Sadat
-
Patent number: 11348237Abstract: Dental images are processed according to a first machine learning model to determine teeth labels. The teeth labels and image are concatenated and processed using a second machine learning model to label anatomy including CEJ, JE, GM, and Bone. The anatomy labels, teeth labels, and image are concatenated and processed using a third machine learning model to obtain feature measurements, such as pocket depth and clinical attachment level. The feature measurements, anatomy labels, teeth labels, and image may be concatenated and input to a fourth machine learning model to obtain a diagnosis for a periodontal condition. Feature measurements and/or the diagnosis may be processed according to a diagnosis hierarchy to determine whether a treatment is appropriate. Machine learning models may further be used to reorient, decontaminate, and restore the image prior to processing. Machine learning models may be embodied as CNN, GAN, and cyclic GAN.Type: GrantFiled: May 15, 2020Date of Patent: May 31, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Ali Sadat, Stephen Chan, Hamid Hakmatian, Yash Patel
-
Patent number: 11311247Abstract: Training a generator includes processing a dental image using the generator to obtain a synthetic pathology label, such has a pixel mask indicating portions of the dental image representing caries. The synthetic pathology label is compared to a target pathology label for the dental image and the generator is updated according to the comparison. The synthetic pathology may be evaluated by a discriminator along with a real pathology label to obtain a realism estimate. The discriminator and generator may be updated according to accuracy of the realism estimate. Inputs to the generator may further include tooth labels and/or labels of restorations. Machine learning models may be trained to label restorations and defects in restorations. A machine learning model may be trained to identify the surface of a tooth having a pathology thereon.Type: GrantFiled: June 25, 2020Date of Patent: April 26, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Ali Sadat
-
Patent number: 11276151Abstract: Dental images are processed according to a first machine learning model to determine teeth labels. The teeth labels and image are processed using a second machine learning model to label anatomy. The anatomy labels, teeth labels, and image are processed using a third machine learning model to obtain feature measurements, such as pocket depth and clinical attachment level. The feature measurements, labels, and image may be input to a fourth machine learning model to obtain a diagnosis for a periodontal condition. Machine learning models may further be used to reorient, decontaminate, and restore the image prior to processing. A machine learning model may be trained with images and randomly generated masks in order to perform inpainting of dental images with missing information.Type: GrantFiled: June 12, 2020Date of Patent: March 15, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Hamid Hekmatian, Ali Sadat
-
Publication number: 20220012815Abstract: A dental procedure, one or more dental images, and documentation are processed to extract data and label and/or measure dental anatomy or pathologies using a first stage. The extracted data and labels are processed with a second stage to obtain predictions of deficiencies of the dental images and documentation. The predictions may include tasks to remedy the deficiencies, adjudication likelihood, instant payment amount, patient fee, and average time to payment. The first stage and second stage may each include a plurality of machine learning models. The second stage may include a plurality of machine learning models coupled to a concatenation layer. Inputs to the concatenation layer may include outputs of hidden layers of the plurality of machine learning models. The concatenation layer may take the extracted data and labels as inputs.Type: ApplicationFiled: September 27, 2021Publication date: January 13, 2022Inventors: Vasant Kearney, Hamid Hekmatian, Wenxiang Deng, Kevin Yang, Ali Sadat
-
Patent number: 11217350Abstract: A first machine learning model is trained to classify dental anatomy and/or pathologies represented in an input dental image or to generate a label (pixel mask) for dental anatomy and/or pathologies represented in the input dental image. A final layer, such as one of two fully connected layers, may be removed from the first machine learning model to obtain a modified machine learning model. Hidden features output from the modified machine learning model may be input to a LSTM model that outputs a text sequence. The LSTM model may be trained with images labeled with text sequences to output a text sequence for a given input dental image.Type: GrantFiled: June 25, 2020Date of Patent: January 4, 2022Assignee: Retrace LabsInventors: Vasant Kearney, Ali Sadat
-
Patent number: 11189028Abstract: A machine learning model is trained to predict pixel spacing, distance, and volumetric measurements. Training images are obtained by inpainting around an original image and scaling the inpainted image to obtain the training image having a different pixel spacing than the original image. The machine learning model may include an encoder, a transformer, a first TC layer, and a second TC layer. During training, loss may be obtained from a comparison of the output to the first TC layer to a coarse pixel spacing matrix and a comparison of the output of the second TC layer to a fine pixel spacing matrix. During utilization, the pixel spacing of an image may be obtained using the machine learning model and used to correct the image or measurements obtained from the image.Type: GrantFiled: April 14, 2021Date of Patent: November 30, 2021Assignee: Retrace LabsInventors: Vasant Kearney, Ashwini Jha, Wenxiang Deng, Hamid Hekmatian, Ali Sadat
-
Publication number: 20210365736Abstract: In medicine and dentistry, image quality affects computer vision accuracy. However, some problems are more tolerant of noise depending on disease severity and radiographic obviousness. There is a need to have a noise estimation model that adapts to each specific domain. A noise estimation model is trained to output a set of domain noise estimates for an input image, each estimate indicating an impact of noise present in the input image on a particular domain, e.g. labeling of a dental feature such as a dental anatomy, pathology, or treatment. The noise estimation model is trained by processing image pairs with a set of machine learning models for a plurality of domains, the image pairs including a raw image and a modified image obtained by adding noise to the raw image. Outputs of the set of machine learning models for the raw and modified images are compared to obtain measured noise metrics. The noise estimation model processes the modified image and is trained to estimate noise metrics.Type: ApplicationFiled: August 4, 2021Publication date: November 25, 2021Inventors: Vasant Kearney, Hamid Hekmatian, Ali Sadat
-
Publication number: 20210358604Abstract: An interface enables a user to select a block type, place an instance of that block type in a schematic and connect the instance to other instances. Each block type defines processing of dental data, such as dental images according to any of a plurality of modalities and defines logic, such as if statements, to determine an output (positive/negative) for instances of that block type. Logic may include Boolean expressions relating to results of the inf statements. The logic may operate with respect to data derived from patient data using a machine learning model trained to measure dental anatomy, measure dental pathologies, or diagnose dental conditions. A workflow may be created with instances to determine the appropriateness of a dental treatment.Type: ApplicationFiled: March 26, 2021Publication date: November 18, 2021Inventors: Vasant Kearney, Stephen Chan, Jiahong Weng, Hamid Hekmatian, Wenxiang Deng, Ashwini Jha, Ali Sadat
-
Publication number: 20210358123Abstract: A machine learning model is trained to predict pixel spacing, distance, and volumetric measurements. Training images are obtained by inpainting around an original image and scaling the inpainted image to obtain the training image having a different pixel spacing than the original image. The machine learning model may include an encoder, a transformer, a first TC layer, and a second TC layer. During training, loss may be obtained from a comparison of the output to the first TC layer to a coarse pixel spacing matrix and a comparison of the output of the second TC layer to a fine pixel spacing matrix. During utilization, the pixel spacing of an image may be obtained using the machine learning model and used to correct the image or measurements obtained from the image.Type: ApplicationFiled: April 14, 2021Publication date: November 18, 2021Inventors: Vasant Kearney, Ashwini Jha, Wenxiang Deng, Hamid Hekmatian, Ali Sadat
-
Publication number: 20210357688Abstract: A dental form image may be processed with a segmentation network to identify point labels corresponding to reference point labels of a reference form. The image and the point labels along with a reference image and the reference point labels may be processed by a pair of encoders to obtain offsets. Text blobs may be identified from portions of the image corresponding to the reference point labels, such as with correction according to the offsets. Image portions and text blobs for each field of the dental form may be processed to extract text. Intermediate values of machine learning models used to extract text may be input to a machine learning model estimating a procedure code for the dental form. Machine learning models may be used to correctly identify a provider referenced by the dental form.Type: ApplicationFiled: December 16, 2020Publication date: November 18, 2021Inventors: Vasant Kearney, Wenxiang Deng, Ashwini Jha, Hamid Hekmatian, Ali Sadat
-
Publication number: 20210353393Abstract: A comprehensive dental readiness platform is presented. Dental patient data including an image, proposed treatments, and a dental form are received and processed by first machine learning models to obtain clinical findings and predicted values for fields of the dental form. The clinical findings and other results are processed by a second machine learning model to obtain predictions of a future dental condition of a patient. The second machine learning model utilizes an ensemble of Transformer Neural Networks, Long-Short-Term-Memory Networks, Convolutional Neural Networks, and Tree-Based Algorithms to predict the dental readiness classification, dental readiness durability, dental readiness error, dental emergency likelihood, prognosis, and alternative treatment options.Type: ApplicationFiled: June 15, 2021Publication date: November 18, 2021Inventors: Vasant Kearney, Hamid Hekmatian, Wenxiang Deng, Ming Ted Wong, Ali Sadat
-
Publication number: 20210118132Abstract: A first machine learning model (e.g., GAN) is trained to take as inputs a dental image and masks of dental features in the image and outputs a set of orthodontic points. A second machine learning model may additionally take the orthodontic points as inputs and output distances between the orthodontic points. A third machine learning model may additionally take the orthodontic points and distances as inputs and output a deformation vector field for the orthodontic points. A fourth machine learning model may additionally take the orthodontic points as inputs and generate a vector indicating risk associated with orthodontic treatment. A fifth machine learning model may additionally take the orthodontic points, deformation vector field, and distances as inputs and output a treatment plan, including point clouds for brackets, retainers, appliances, mandibular surgery or movement, and/or maxillary surgery or movement.Type: ApplicationFiled: October 16, 2020Publication date: April 22, 2021Inventors: Vasant Kearney, Ali Sadat
-
Publication number: 20210118099Abstract: A novel GAN is trained to predict high fidelity synthetic images based on low quality input dental images. The GAN further takes input anatomic masks as inputs with each image, the masks labeling pixels of the image corresponding to dental features. The GAN includes an encoder-decoder generator with semantically aware normalization between stages of the decoder according to the masks. The predicted synthetic dental image and an unpaired dental image are evaluated by a first discriminator of the GAN to obtain a realism estimate. The synthetic image and an unpaired dental image may be processed using a pretrained dental encoder to obtain a perceptual loss. The GAN is trained with the realism estimate, perceptual loss, and L1 loss. Utilization may include inputting noisy, low contrast, low resolution, blurry, or degraded dental images and outputting high resolution, denoised, high contrast, deobfuscated, and sharp dental images.Type: ApplicationFiled: September 25, 2020Publication date: April 22, 2021Inventors: Vasant Kearney, Hamid Hekmatian, Ali Sadat
-
Publication number: 20210118129Abstract: A GAN is trained to process input images and produce a synthetic dental image. The GAN further takes masks as inputs with each image, the masks labeling pixels of the image corresponding to dental features (anatomy and/or treatments). The GAN includes an encoder-decoder with normalization between stages of the decoder according to the masks. A synthetic image and an unpaired dental image is evaluated by a first discriminator of the GAN to obtain a realism estimate. The synthetic image and an unpaired dental image may be processed using a pretrained dental encoder to obtain a perceptual loss. The GAN is trained with the realism estimate and perceptual loss. Utilization may include modifying a mask for an input image to include or exclude a shape of a feature such that the synthetic image includes or excludes a dental feature.Type: ApplicationFiled: September 25, 2020Publication date: April 22, 2021Inventors: Vasant Kearney, Hamid Hekmatian, Stephen Chan, Ali Sadat
-
Patent number: 10891539Abstract: A system and method may be used to evaluate content on one or more social media networks. A deep learning model may be stored. A communication may be received, that has been or is to be communicated on a social network. The deep learning model may be applied to the communication to obtain an automated evaluation of the communication. User input may be received, and may include a user evaluation of the communication. The user evaluation may be applied to train the deep learning model. The steps of receiving the communication, applying the deep learning model to obtain the automated evaluation, receiving the user evaluation, and applying the user evaluation to train the model, may be iterated to enhance the accuracy of the automated evaluations.Type: GrantFiled: October 30, 2018Date of Patent: January 12, 2021Assignee: STA Group, Inc.Inventors: Vasant Kearney, Samuel Haaf, John Dorsey, Aaron Schoenberger