Granted Patent B2

US 12,324,677 · App. 18/009,303 · Granted Jun 10, 2025

Inventors: Siva Teja Kakileti (Kakinada, IN); Geetha Manjunath (Bangalore, IN); V. N Ratna Kumari T (Hyderabad, IN); Kanchana Gopinath (Bangalore, IN); Himanshu J Madhu (Bangalore, IN)

Assignee: NIRAMAI HEALTH ANALYTIX PVT. LTD

A61B5/4312A61B5/015A61B5/7264G06T7/0012G16H10/60G16H15/00G06T2207/10048G06T2207/30068

Abstract

Claims (71)

1. A method for a quantitative evaluation of a breast health of a woman for clinical management of a breastfeeding, the method comprising:

receiving a thermal image of a breast region of the woman captured by at least one of a thermal imaging camera, thermal sensor, or a wearable contact-based thermal device, the thermal imaging device comprising:

an array of sensors that converts an infrared energy into electrical signals on a per-pixel basis; and

a specialized processor that processes the detected temperature values into at least one block of pixels to generate the thermal image;

characterized in that,

automatically determining network structures associated with ductal or vascular thermal patterns of the woman by analysing the thermal images of the woman, wherein the network structures are determined by:

finding cylindrical structures in the thermal image of the woman using a machine learning model or image processing techniques; and

creating a graphical network using branch points and endpoints as vertices and edges as an obtained skeleton, wherein the graphical network comprises schematics of the ductal and vascular network which represents the ductal or vascular thermal patterns;

estimating quantitative parameters corresponding to the ductal or vascular thermal patterns from the determined network structures using the machine learning model; and

generating a breast health report with the estimated quantitative parameters and the schematics of vascular network to enable clinical management of breastfeeding,

wherein the method comprises comparing the quantitative parameters of a left breast of a pregnant and lactating woman with a right breast of the pregnant and lactating woman to determine an asymmetry in the ductal and vascular network, wherein the identified asymmetry is included in the breast health report, wherein the asymmetry in the vascular network is used to provide a lactation guidance to new mothers.

2. The method of claim 1 , wherein the method comprises comparing the quantitative parameters for each breast is compared with the previous breast health report of same person to provide a longitudinal view across trimesters to identify early weaning of new mothers or a positive development of milk ducts in a pregnant and lactating woman.

3. The method of claim 1 , wherein the method comprises:

receiving the thermal image of the breast region of a pregnant and lactating woman from at least one of a thermal imaging camera, thermal sensor, or a wearable contact-based thermal device, wherein the thermal image represents the temperature distribution on the breast region of the pregnant and lactating woman as pixels in the thermal image with a highest temperature value being displayed in a first color and pixels with a lowest temperature value being displayed in a second color, pixels with temperature values between the lowest and highest temperature values being displayed in gradations of color between the first and second color;

characterized in that,

automatically determining thermally active regions in the breast region of the pregnant and lactating woman by analyzing the thermal image of the pregnant and lactating woman using the machine learning model, wherein said determination of the thermally active regions comprises;

identifying a temperature threshold (T) using temperature distribution represented in the received thermal image(s);

generating a hotspot structure by identifying the pixels which are higher than the temperature threshold (T); and

determining hotspot structure parameters and a schematics of the hotspot structure by analyzing the shape and temperature parameters of the generated hotspot structures;

estimating quantitative parameters corresponding to the hotspot structures parameters using the machine learning model; and

generating the breast health report with the estimated quantitative parameters and the schematics of hotspot structures to enable the clinical management of breastfeeding.

4. The method of claim 3 , wherein the method comprises determining an asymmetry by comparing the quantitative parameters of a left breast with a right breast of the pregnant and lactating woman, wherein the determined asymmetry is included in the breast health report.

5. The method of claim 4 , wherein the asymmetry in the hotspot structures is used to provide lactation guidance to new mothers.

6. The method of claim 3 , wherein the method comprises comparing the quantitative parameters for each breast with the previous breast health report of same person to provide a longitudinal view across trimesters to identify early weaning of new mothers or positive development of milk ducts in the pregnant and lactating woman.

7. A system for a quantitative evaluation of a breast health of a pregnant and lactating woman for clinical management of a breastfeeding, the system comprising:

a storage device storing a set of machine-readable instructions; and

a processor configured to retrieve the machine-readable instructions from the storage device which, when executed by the processor, enable the processor to:

receive a thermal image of a breast region of the pregnant and lactating woman, captured by a thermal imaging camera, thermal sensor or a wearable contact based thermal device, the thermal imaging camera comprising:

an array of sensors that converts an infrared energy into electrical signals on a per-pixel basis;

and

a specialized processor that processes the detected temperature values into at least one block of pixels to generate the thermal image;

characterized in that,

automatically determine network structures associated with ductal or vascular thermal patterns of the pregnant and lactating woman by analysing the thermal images of the pregnant and lactating woman, wherein the network structures determined by:

finding cylindrical structures in the thermal image of the pregnant and lactating woman using a machine learning model or image processing techniques; and

creating a graphical network using branch points and endpoints as vertices and edges as an obtained skeleton, wherein the graphical network comprises schematics of the ductal and vascular network which represents the ductal or vascular thermal patterns;

estimate quantitative parameters corresponding to the network structures associated with the ductal or vascular thermal patterns from the determined network structures using the machine learning model; and

generate a breast health report with the estimated quantitative parameters and the schematics of vascular network to enable clinical management of breastfeeding,

wherein the processor is configured to determine an asymmetry by comparing the quantitative parameters of a left breast of a pregnant and lactating woman with a right breast of the pregnant and lactating woman, wherein the determined asymmetry is included in the breast health report, wherein the asymmetry in the vascular network is used to provide a lactation guidance to new mothers.

8. The system of claim 7 , wherein the processor is configured to determine an asymmetry by comparing the quantitative parameters of a left breast with a right breast of the pregnant and lactating woman, wherein the determined asymmetry is included in the breast health report.

9. The system of claim 8 , wherein the processor is configured to

receive the thermal image of the breast region of the pregnant and lactating woman, which represents the temperature distribution on the breast region of the pregnant and lactating woman as pixels in the thermal image with a highest temperature value being displayed in a first color and pixels with a lowest temperature value being displayed in a second color, pixels with temperature values between the lowest and highest temperature values being displayed in gradations of color between the first and second color, characterizing in that,

automatically determine thermally active regions in the breast region of the pregnant and lactating woman by analyzing the thermal image of the pregnant and lactating woman using the machine learning model, wherein said determination of thermally active regions comprises:

identifying a temperature threshold (T) using temperature distribution represented in the received thermal image(s);

generating a hotspot structure by identifying the pixels which are higher than the temperature threshold (T); and

determining hotspot structure parameters and a schematics of the hotspot structure by analyzing shape and temperature parameters of the generated hotspot structures;

estimate quantitative parameters corresponding to the hotspot structures parameters using the machine learning model; and

generate the breast health report with the estimated quantitative parameters and the schematics of hotspot structures to enable the clinical management of breastfeeding.

10. The system of claim 7 , wherein the processor is configured to compare the quantitative parameters for each breast is compared with the previous breast health report of same person to provide a longitudinal view across trimesters to identify early weaning of new mothers or a positive development of milk ducts in the pregnant and lactating woman.

11. A non-transitory computer-readable storage medium storing the one or more sequence of instructions, which when executed by one or more processors, causes to perform a method for a quantitative evaluation of a breast health of a woman for clinical management of a breast feeding, by performing the steps of:

receiving a thermal image of a breast region of the woman captured by at least one of a thermal imaging camera, thermal sensor or a wearable contact based thermal device, the thermal imaging device comprising:

an array of sensors that converts an infrared energy into electrical signals on a per-pixel basis; and

a specialized processor that processes the detected temperature values into at least one block of pixels to generate the thermal image;

characterized in that,

automatically determining network structures associated with ductal or vascular thermal patterns of the woman by analysing the thermal images of the woman, wherein the network structures determined by:

finding cylindrical structures in the thermal image of the woman using a machine learning model or image processing techniques; and

creating a graphical network using branch points and endpoints as vertices and edges as an obtained skeleton, wherein the graphical network comprises schematics of the ductal and vascular network which represents the ductal or vascular thermal patterns;

estimating quantitative parameters corresponding to the ductal or vascular thermal patterns from the determined network structures using the machine learning model; and

generating a breast health report with the estimated quantitative parameters and the schematics of vascular network to enable clinical management of breastfeeding,

wherein the method comprises comparing the quantitative parameters of a left breast of a pregnant and lactating woman with a right breast of the pregnant and lactating woman to determine an asymmetry in the ductal and vascular network, wherein the identified asymmetry is included in the breast health report, wherein the asymmetry in the vascular network is used to provide a lactation guidance to new mothers.

12. The non-transitory computer-readable storage medium storing the one or more sequence of instructions of claim 11 , wherein the method comprises comparing the quantitative parameters for each breast is compared with the previous breast health report of same person to provide a longitudinal view across trimesters to identify early weaning of new mothers or a positive development of milk ducts in a pregnant and lactating woman.

13. The non-transitory computer-readable storage medium storing the one or more sequence of instructions of claim 11 , wherein the method comprises:

receiving the thermal image of the breast region of a pregnant and lactating woman from at least one of a thermal imaging camera, thermal sensor or a wearable contact based thermal device, wherein the thermal image represents the temperature distribution on the breast region of the pregnant and lactating woman as pixels in the thermal image with a highest temperature value being displayed in a first color and pixels with a lowest temperature value being displayed in a second color, pixels with temperature values between the lowest and highest temperature values being displayed in gradations of color between the first and second color;

characterizing in that

automatically determining thermally active regions in the breast region of the pregnant and lactating woman by analyzing the thermal image of the pregnant and lactating woman using the machine learning model, wherein said determination of the thermally active regions comprises;

identifying a temperature threshold (T) using temperature distribution represented in the received thermal image(s);

generating a hotspot structure by identifying the pixels which are higher than the temperature threshold (T); and

determining hotspot structure parameters and a schematics of the hotspot structure by analyzing shape and temperature parameters of the generated hotspot structures;

estimating quantitative parameters corresponding to the hotspot structures parameters using the machine learning model; and

generating the breast health report with the estimated quantitative parameters and the schematics of hotspot structures to enable the clinical management of breastfeeding.

14. The non-transitory computer-readable storage medium storing the one or more sequence of instructions of claim 13 , wherein the method comprises determining an asymmetry by comparing the quantitative parameters of a left breast with a right breast of the pregnant and lactating woman, wherein the determined asymmetry is included in the breast health report.

15. The non-transitory computer-readable storage medium storing the one or more sequence of instructions of claim 13 , wherein the method comprises comparing the quantitative parameters for each breast with the previous breast health report of same person to provide a longitudinal view across trimesters to identify early weaning of new mothers or positive development of milk ducts in the pregnant and lactating woman.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (10)