US 12,475,555 B2
Artificial intelligence-based hyperspectrally resolved detection of anomalous cells
Tapashree Roy, Bangalore (IN); Shubhayan Bhattacharya, Bangalore (IN); Kiran Rangaswamy Aatre, Bangalore (IN); Sumit Kumar Jha, Bangalore (IN); Suraj Rengarajan, Bangalore (IN); and Riya Dutta, West Bengal (IN)
Assigned to Applied Materials, Inc., Santa Clara, CA (US)
Filed by Applied Materials, Inc., Santa Clara, CA (US)
Filed on Nov. 23, 2022, as Appl. No. 17/993,144.
Claims priority of provisional application 63/282,803, filed on Nov. 24, 2021.
Prior Publication US 2023/0162354 A1, May 25, 2023
Int. Cl. G06T 7/00 (2017.01); G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06T 7/0012 (2013.01) [G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/10036 (2013.01); G06T 2207/30024 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for detection of anomalous cells, comprising:
a hyperspectral imaging system;
memory having executable instructions stored thereon; and
a processor configured to execute the executable instructions to cause the system to:
receive a patient hyperspectral image comprising a respective pixel spectral signature for each pixel of the received patient hyperspectral image;
classify the patient hyperspectral image by a machine learning model trained to classify hyperspectral images based on pixel spectral signatures, wherein the patient hyperspectral image is classified by:
identifying a normal primary peak wavelength, a stroma primary peak wavelength, and an anomalous primary peak wavelength of the respective pixel spectral signatures of the patient hyperspectral image; and
determining a cell type within the patient hyperspectral image based on at least one of:
a difference between the normal primary peak wavelength and the anomalous primary peak wavelength;
a difference between the normal primary peak wavelength and the stroma primary peak wavelength; or
a difference between the stroma primary peak wavelength and the anomalous primary peak wavelength; and
provide an indication that the patient hyperspectral image contains an anomalous cell type, responsive to the classifying.