A system for diagnosing brain tumor via artificial intelligence

Abstract

The present invention relates to a system (1) for diagnosing brain tumors in a rapid and accurate way upon classifying the type, size and location of a brain tumor by performing image analysis via artificial intelligence and using data received from the patient's MRI or CT scans.

Description

[0001] A SYSTEM FOR DIAGNOSING BRAIN TUMOR VIA ARTIFICIAL INTELLIGENCE

[0002] Technical Field

[0003] The present invention relates to a system for diagnosing brain tumors in a rapid and accurate way upon classifying the type, size and location of a brain tumor by performing image analysis via artificial intelligence and using data received from the patient’s MRI (Magnetic Resonance Imaging) or CT (Computerized Tomography) scans.

[0004] Background of the Invention

[0005] Today, artificial intelligence is used to analyze medical images and to identify diseases. Detection of brain tumor requires more precise and faster results. However, the use of artificial intelligence is limited to identify and classify brain tumors accurately.

[0006] Therefore, considering the studies and the shortcomings included in the current technique, it is understood that there is need for a system for diagnosing brain tumors in a rapid and accurate way upon classifying the type, size and location of a brain tumor by performing image analysis via artificial intelligence and using data received from the patient’s MRI or CT scans.

[0007] The United States patent document no. US11227387B2, an application included in the state of the art, discloses a system which is based on image processing and deep learning and which is configured to diagnose and classify a brain tumor. The invention relates to a method and system configured to detect and model a brain tumor in an electronic image, and to predict features of the brain tumor based on the model. The method comprises classifying one or more magnetic resonance imaging (MRI) images of a brain into one or more one or more tumorous images containing an image of a tumor or one or more non-tumorous images. Here, the classification is performed by a deep learning CNN system. The method also involves segmenting a tumor region from one or more tumorous images. The segmenting involves a neighboring Fuzzy C-Means (FCM) process. The method also involves classifying the segmented tumor region into one of four classes of brain tumor types. The segmented tumor region is classified as a particular brain tumor type by using a deep learning CNN system. The method also includes reconstructing a 3D model of the tumor region and measuring one or more locations of the tumor, the shape of the tumor or the volume of the tumor.

[0008] Summary of the Invention

[0009] An objective of the present invention is to realize a system which is developed for diagnosing brain tumors in a rapid and accurate way upon classifying the type, size and location of a brain tumor by performing image analysis via artificial intelligence and using data received from the patient’s MRI or CT scans.

[0010] Another objective of the present invention is to realize a system which is developed for enabling doctors to make a faster and more precise diagnosis, to treat patients better, and to provide important information for treatment planning.

[0011] Detailed Description of the Invention

[0012] “A System for Diagnosing Brain Tumor via Artificial Intelligence” realized to fulfil the objectives of the present invention is shown in the figure attached, in which:

[0013] Figure l is a schematic view of the inventive system. The components illustrated in the figure are individually numbered, where the numbers refer to the following:

[0014] 1. System

[0015] 2. Electronic Device

[0016] 3. Server

[0017] The inventive system (1) developed for diagnosing brain tumors in a rapid and accurate way via artificial intelligence comprises

[0018] - at least one electronic device (2) which is configured to realize data exchange by using any remote communication protocol and to run at least one application thereon;

[0019] - at least one server (3) which is configured to establish connection with the electronic device (2) by using any communication protocol; to access MRI, CT and / or PET images via the electronic device (2) and to process these images via medical image processing software such as MATLAB and / or Python-based image processing libraries; to analyze the features of brain tumors in more detail and in various aspects by using Gabor Filters and / or Morlet Waves on the processed images; to identify and to classify brain tumors; to analyze the texture patterns of tissues through LBP and / or HOG algorithms; to define structural features of brain tumors; to analyze these features; to extract features by using OpenCV image processing and image analysis algorithms; to train the artificial intelligence model via deep learning algorithms such as TensorFlow or PyTorch and to perform tumor classification processes; to ensure that analysis results and reports are produced with special software and / or workflow management software such as Apache NiFi; to present the results of analysis with medical imaging software to healthcare professionals and / or patients on the electronic device (2). The electronic device (2) included in the inventive system (1) is configured to realize data exchange by using any remote communication protocol and to run at least one application thereon. The electronic device (2) is a device such as tablet, desktop computer and / or portable computer. The electronic device (2) is configured to establish connection with the server (3) by using any remote communication protocol included in the state of the art. The electronic device (2) is configured to upload MRI (Magnetic Resonance Imaging), CT (Computerized Tomography) and / or PET (Positron Emission Tomography) images.

[0020] The server (3) included in the inventive system (1) is configured to establish connection with the electronic device (2) by using any communication protocol included in the state of the art. The server (3) is configured to access MRI (Magnetic Resonance Imaging), CT (Computerized Tomography) and / or PET (Positron Emission Tomography) images via the electronic device (2). The server (3) is configured to process MRI (Magnetic Resonance Imaging), CT (Computerized Tomography) and / or PET (Positron Emission Tomography) images via medical image processing software such as MATLAB and / or Pythonbased image processing libraries. The server (3) is configured to use Gabor Filters and / or Morlet Waves on the processed images in order to analyze the features of brain tumors in more detail and in various aspects, to highlight certain structural features in the images, to highlight textural or structural features, to highlight frequency features in the images, and to identify and classify brain tumors. The server (3) is configured to analyze the texture patterns of tissues through LBP (Local Binary Patterns) and / or HOG (Histogram of Oriented Gradients) algorithms, to identify structural features of brain tumors, to identify edge and shape features of tissues, to highlight certain edge or shape features in the image and to perform analysis on these features, to identify certain textural or shape features of tumors. The server (3) is configured to extract features in order to analyze the features of the brain tumor by using OpenCV image processing and image analysis algorithms. The server (3) is configured to train the artificial intelligence model and to perform tumor classification by using deep learning algorithms such as TensorFlow or PyTorch. The server (3) is configured to generate analysis results and reports with specialized software and / or workflow management software such as Apache NiFi. The server (3) is configured to provide medical imaging software and analysis results to healthcare professionals and / or patients on the electronic device (2).

[0021] Industrial Application of the Invention

[0022] In the inventive system (1), the server (3) accesses MRI (Magnetic Resonance Imaging), CT (Computerized Tomography) and / or PET (Positron Emission Tomography) images via the electronic device (2). The server (3) processes the MRI (Magnetic Resonance Imaging), CT (Computerized Tomography) and / or PET (Positron Emission Tomography) images via medical image processing software such as MATLAB and / or Python-based image processing libraries. The server (3) uses Gabor Filters and / or Morlet Waves on the processed images in order to analyze the features of brain tumors in more detail and in various aspects, to highlight certain structural features in the images, to highlight textural or structural features, to highlight frequency features in the images, and to identify and classify brain tumors. The server (3) uses LBP (Local Binary Patterns) and / or HOG (Histogram of Oriented Gradients) algorithms in order to analyze texture patterns of tissues, identify structural features of brain tumors, identify edge and shape features of tissues, highlight and analyze specific edge or shape features in the image, and to identify specific textural or shape features of tumors. The server (3) extracts features in order to analyze the features of a brain tumor by using OpenCV image processing and image analysis algorithms. The server (3) uses deep learning algorithms such as TensorFlow or PyTorch in order to train the artificial intelligence model and to perform tumor classification. The server (3) generates analysis results and reports with specialized software and / or workflow management software such as Apache NiFi. The server (3), with medical imaging software, presents the analysis results to healthcare professionals and / or patients on the electronic device (2). This enables doctors to make a faster and more precise diagnosis, patients to be treated better and provides important information for treatment planning.

[0023] Within these basic concepts; it is possible to develop various embodiments of the inventive “System (1) for Diagnosing Brain Tumor via Artificial Intelligence”; the invention cannot be limited to examples disclosed herein and it is essentially according to claims.

Claims

CLAIMS1. A system (1) developed for diagnosing brain tumors in a rapid and accurate way via artificial intelligence; comprising- at least one electronic device (2) which is configured to realize data exchange by using any remote communication protocol and to run at least one application thereon; and characterized by- at least one server (3) which is configured to establish connection with the electronic device (2) by using any communication protocol; to access MRI, CT and / or PET images via the electronic device (2) and to process these images via medical image processing software such as MATLAB and / or Python-based image processing libraries; to analyze the features of brain tumors in more detail and in various aspects by using Gabor Filters and / or Morlet Waves on the processed images; to identify and to classify brain tumors; to analyze the texture patterns of tissues through LBP and / or HOG algorithms; to define structural features of brain tumors; to analyze these features; to extract features by using OpenCV image processing and image analysis algorithms; to train the artificial intelligence model via deep learning algorithms such as TensorFlow or PyTorch and to perform tumor classification processes; to ensure that analysis results and reports are produced with special software and / or workflow management software such as Apache NiFi; to present the results of analysis with medical imaging software to healthcare professionals and / or patients on the electronic device (2).

2. A system (1) according to Claim 1; characterized by the electronic device (2) which is configured to realize data exchange by using any remote communication protocol and to run at least one application thereon, andwhich is a device such as tablet, desktop computer and / or portable computer.

3. A system (1) according to Claim 1 or 2; characterized by the electronic device (2) which is configured to establish connection with the server (3) by using any remote communication protocol.

4. A system (1) according to Claim 3; characterized by the electronic device (2) which is configured to upload MRI (Magnetic Resonance Imaging), CT (Computerized Tomography) and / or PET (Positron Emission Tomography) images.

5. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to establish connection with the electronic device (2) by using any communication protocol.

6. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to access MRI, CT and / or PET images via the electronic device (2).

7. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to process MRI, CT and / or PET images via medical image processing software such as MATLAB and / or Pythonbased image processing libraries.

8. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to use Gabor Filters and / or Morlet Waves on the processed images in order to analyze the features of brain tumors in more detail and in various aspects, to highlight certain structural features in the images, to highlight textural or structural features, tohighlight frequency features in the images, and to identify and classify brain tumors.

9. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to analyze the texture patterns of tissues through LBP and / or HOG algorithms, to identify structural features of brain tumors, to identify edge and shape features of tissues, to highlight certain edge or shape features in the image and to perform analysis on these features, to identify certain textural or shape features of tumors.

10. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to extract features in order to analyze the features of the brain tumor by using OpenCV image processing and image analysis algorithms.

11. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to train the artificial intelligence model and to perform tumor classification by using deep learning algorithms such as TensorFlow or PyTorch.

12. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to generate analysis results and reports with specialized software and / or workflow management software such as Apache NiFi.

13. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to provide medical imaging software and analysis results to healthcare professionals and / or patients on the electronic device (2).

Images