Software tool for breast cancer screening
What is disclosed is a software tool which enables medical practitioners to manually or automatically analyze a thermal image of an area of breast tissue for the presence of tumorous tissue. In one embodiment, the software interface tool disclosed herein comprises a patient details object which enables the display of a patient details screen wherein a user can enter/edit patient information. A thermal analysis object enables a user to analyze a displayed thermal image of a breast of a patient for breast cancer screening and to classify tissue identified in the thermal image as being tumorous. A modalities object concludes the patient evaluation, persists all data collected from other sections of the tool, and generates reports for documentation purposes. The information can be captured from a database and edited and analyzed further using the tool. Also, report containing all the relevant data is generated for doctor's reference.
1. A system for processing a thermal image, the system comprising:
a computing device comprising:
a memory that stores a thermal image and a set of instructions; and
a processor that executes the set of instructions for processing the thermal image by performing the steps of:
receiving the thermal image of a patient's breast, wherein the thermal image is captured by a thermal imaging camera, the thermal imaging camera comprising:
an array of sensors that converts infrared energy into electrical signals on a per-pixel basis;
a lens that focuses the infrared energy from the patient's breast onto the array of sensors, wherein the array of sensors detects temperature values from the patient's breast; and
a specialized processor that processes the detected temperature values into at least one block of pixels to generate the thermal image;
uploading the thermal image of the patient's breast captured in different views onto the computing device;
comparing the temperature values of the at least one block of pixels in the thermal image with temperature thresholds, wherein the temperature thresholds comprises a threshold θ1, a threshold (T max −θ2), and a threshold θ3, wherein values of the threshold θ1, the threshold (T max −θ2), and the threshold θ3 are obtained based on a temperature distribution in the patient's breast;
computing multiple percentage values (k1, k2, k3, k4) of the at least one block of pixels in the thermal image with a temperature satisfying the compared temperature thresholds;
determining whether an edge length of a block of pixels is k 4 % of a perimeter of the block;
processing a decision rule R to determine pixels in the thermal image that indicate a malignant tumor based on the percentage values (k1, k2, k3, k4); and
displaying a boundary of a block of pixels in the thermal image indicating the malignant tumor in a first color and displaying a boundary of a block of pixels in the thermal image indicating a non-malignant tumor in a second color.
2. The system of claim 1 , wherein the decision rule R determines whether a pixel is tumorous or not based on a weighted sum of decision rules (R 1 , R 2 , R 3 , R 4 ).
3. The system of claim 1 , wherein the method of detecting the tumorous region in the thermal image comprises normalizing a body temperature of the patient to minimize external heat condition before taking the thermal image.
4. A non-transitory computer-readable storage medium that stores a thermal image capture from a thermal imaging camera and set of instructions for processing the thermal image by performing the steps of:
receiving the thermal image of a patient's breast, wherein the thermal image is captured by a thermal imaging camera, the thermal imaging camera comprising:
an array of sensors that converts infrared energy into electrical signals on a per-pixel basis;
a lens that focuses the infrared energy from the patient's breast onto the array of sensors, wherein the array of sensors detects temperature values from the patient's breast; and
a specialized processor that processes the detected temperature values into at least one block of pixels to generate the thermal image;
uploading the thermal image of the patient's breast captured in different views onto the computing device;
comparing temperature values of at least one block of pixels in the thermal image with temperature thresholds, wherein the temperature thresholds comprises a threshold θ 1 , a threshold (T max −θ 2 ), and a threshold θ 3 , wherein values of the threshold θ 1 , the threshold (T max −θ 2 ), and the threshold θ 3 are obtained from temperature distribution in a patient's breast;
computing multiple percentage values (k1, k2, k3, k4) of the at least one block of pixels in the thermal image with a temperature satisfying the compared temperature thresholds;
determining whether an edge length of a block of pixels is k 4 % of a perimeter of the block;
processing a decision rule R to determine pixels in the thermal image that indicate a malignant tumor based on the percentage values (k1, k2, k3, k4); and
displaying a boundary of a block of pixels in the thermal image indicating the malignant tumor in a first color and displaying a boundary of a block of pixels in the thermal image indicating a non-malignant tumor in a second color.
5. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises identifying a block of pixels from the thermal image using a tissue segmentation object.
6. The non-transitory computer-readable storage medium of claim 4 , wherein the method of detecting tumorous region in the thermal image comprising:
identifying a suspected tumor region by highlighting the suspected tumor region using an auto-detection; and
identifying the suspected tumor region by selecting the suspected tumor region using a manual select object.
7. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing a statistical analysis object for performing a statistical analysis with respect to any of: patient information, tumor detection, diagnosis, demographics and thermal images.
8. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing a modalities object which enables a user to enter, edit, view, save and retrieve a patient data comprising any of: surgeries, mammography details, sonomammography findings, x-rays, biopsies, pathology reports, physician notes, and images.
9. The non-transitory computer-readable storage medium of claim 4 , wherein a dynamic representation of data inputs are shown depending on an entry of the inputs.
10. The non-transitory computer-readable storage medium of claim 4 , wherein the patient data including data modalities are dynamically and automatically parsed and retrieved through an information architecture and displayed to the user.
11. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing a transmit object which enables the user to upload any patient data to a remote device.
12. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing a thermal camera object which enables the user to manipulate and configure the thermal camera acquiring the thermal images or video.
13. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprising providing an orientation object which enables the user to change a view angle of the breast in the thermal image.
14. The non-transitory computer-readable storage medium of claim 4 , wherein the thermal image is pre-processed using image processing techniques to obtain a visualization suitable for further examination by a user.
15. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing an isotherm object which enables the user to display 2D and 3D contour lines on the thermal image at a desired resolution, the contour lines bounding pixels in the thermal image having substantially similar temperature values.
16. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing a view angle object which automatically determines a view angle of the breast in the thermal image views using the body contours and shape.
17. The non-transitory computer-readable storage medium of claim 4 , wherein the method comprises providing a comments object which enables the user to enter the thermo-biological score of the patient and quadrant-wise comments for right breast and left breast with respect to the captured thermal images along with any other medically relevant comments deemed necessary.
18. The non-transitory computer-readable storage medium of claim 4 , wherein a software interface for breast cancer screening is implemented in a networked architecture comprising a plurality of computer workstations.
19. The non-transitory computer-readable storage medium of claim 18 , wherein the networked architecture further comprises a cloud-based storage and processing.