Patents by Inventor Deepankar Chanda

Deepankar Chanda 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).

  • Publication number: 20260290050
    Abstract: Disclosed embodiments include a digital Polymerase chain reaction (dPCR) operative system having a method of digital image processing that corrects for illumination bias in data relating to an array of a sample plate comprising one or more arrays of sample partitions. In some embodiments, the method includes obtaining background image data corresponding to a digital image captured by the camera of the dPCR system after a background cycle of a dPCR assay. With respect to each partition, a local flat-fielding coefficient is derived and applied to the background image data to obtain local-bias-corrected background image data. Next, the local bias-corrected background data is used to determine a set of global flat-fielding coefficients. The local and global flat-fielding coefficients are subsequently used to correct illumination bias endpoint image data to generate endpoint bias-corrected illumination values.
    Type: Application
    Filed: April 17, 2024
    Publication date: September 24, 2026
    Inventors: Deepankar Chanda, Christopher Brandon Thomas, Noah Graham Schissell Elder
  • Patent number: 12580045
    Abstract: Embodiments of the invention are disclosed that implement deep learning methods using artificial neural networks to provide improved automated predictions regarding whether a particular sample comprises a target molecule. In some embodiments, a convolutional neural network is used. In some embodiments, an artificial neural network is trained using a class-weighted error determination. These and other embodiments are disclosed herein.
    Type: Grant
    Filed: June 11, 2021
    Date of Patent: March 17, 2026
    Assignee: Life Technologies Corporation
    Inventors: Wallace George, Deepankar Chanda
  • Publication number: 20250210143
    Abstract: Embodiments of the invention are disclosed that provide improved computer systems, computerized methods, and computer program products for generating and evaluating automated predictions regarding whether a particular amplification curve from a qPCR assay indicates presence of a target molecule in a sample. In some embodiments, predictions are generated using deep learning networks. In some embodiments, curve-quality predictions are generated and used to assess whether an amplification prediction can be reliably made from a particular amplification curve or whether the curve reflects an anomaly in the qPCR assay. In various embodiments, prediction confidence data is also generated and used, along with prediction data, in an electronic user interface to improve qPCR measurement.
    Type: Application
    Filed: March 15, 2023
    Publication date: June 26, 2025
    Inventors: Yong Chu, Deepankar Chanda, Nivedita Sumi Majumdar, Wallace George, Ming Jiang, Anurag Gautam, Nicolas Zun Yu Wong, Yun Zhu, Avi Moshe Shapiro, Vadim Mozhayskiy, Jasmine Patil, Dhvani Pratik Patel
  • Publication number: 20210391033
    Abstract: Embodiments of the invention are disclosed that implement deep learning methods using artificial neural networks to provide improved automated predictions regarding whether a particular sample comprises a target molecule. In some embodiments, a convolutional neural network is used. In some embodiments, an artificial neural network is trained using a class-weighted error determination. These and other embodiments are disclosed herein.
    Type: Application
    Filed: June 11, 2021
    Publication date: December 16, 2021
    Applicant: Life Technologies Corporation
    Inventors: Wallace George, Deepankar Chanda