IP Library Granted Patent US 12,499,543
Granted Patent B2
US 12,499,543 · App. 17/888,798 · Granted Dec 16, 2025

Brain tumor types distinguish system, server computing device thereof and non-transitory computer readable storage medium

Inventors: Cheng-Chia Lee (Taipei, TW); Huai-Che Yang (Taipei, TW); Wen-Yuh Chung (Taipei, TW); Chih-Chun Wu (Taipei, TW); Wan-Yuo Guo (Taipei, TW); Ya-Xuan Yang (Taipei, TW); Tzu-Hsuan Huang (Taipei, TW); Chun-Yi Lin (Taipei, TW); Wei-Kai Lee (Taipei, TW); Chia-Feng Lu (Taipei, TW); Yu-Te Wu (Taipei, TW)
Assignees: NATIONAL YANG MING CHIAO TUNG UNIVERSITY; TAIPEI VETERANS GENERAL HOSPITAL
G06T7/0014G06V10/25G06V10/764G16H30/20G06T2207/20081G06T2207/30016G06T2207/30096G06V2201/031
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,499,543
App. No.
17/888,798
Granted
Dec 16, 2025
Kind
B2
Abstract

A brain tumor types distinguish system includes an image outputting device and a server computing device. The image outputting device outputs at least three brain images captured from the position of a brain tumor. The server computing device pre-stores a plurality of distinguish pathways corresponding to different types of brain tumors. The server computing device includes an image receiving module, an image pre-processing module, a data comparison module and a distinguish module. The image receiving module receives the brain images. The image pre-processing module pre-processes the brain images to obtain corresponding processed images thereof. The data comparison module compares the brain images and the processed images with the distinguish pathways to obtain at least three comparison results. The distinguish module statistically analyzes the comparison results to obtain a distinguish result.

Claims (40)

1 . A brain tumor types distinguish system, comprising:

an image outputting device outputting at least three brain images captured from a position of a brain tumor, wherein the brain images are magnetic resonance imaging images; and

a server computing device, wherein the server computing device pre-stores a plurality of distinguish pathways corresponding to different types of brain tumors, and the server computing device comprises:

an image receiving module receiving the brain images;

an image pre-processing module pre-processing the brain images to obtain corresponding processed images thereof;

a data comparison module comparing the brain images and the processed images with the distinguish pathways to obtain at least three comparison results; and

a distinguish module statistically analyzing the comparison results to obtain a distinguish result,

wherein the image pre-processing module comprises:

a mask processing unit performing an auto-detection with each of the brain images and selecting a position of the brain tumor so as to obtain a mask; and

a partial image capturing unit capturing a part of each of the brain images around the selected position to obtain a partial image, wherein the processed image is the mask or the partial image.

2 . The brain tumor types distinguish system of claim 1 , wherein the distinguish module comprises:

a scoring unit evaluating each of the comparison results to obtain a scoring result; and

a distinguish unit statistically analyzing the scoring results to obtain the distinguish result.

3 . The brain tumor types distinguish system of claim 2 , wherein the comparison result comprises Vestibular Schwannoma, Meningioma, Pituitary Adenoma, Schwannoma, Glioma, or Metastasis.

4 . The brain tumor types distinguish system of claim 3 , wherein the scoring unit further performs a weighting process to the comparison result of Meningioma so as to obtain a weighted scoring result.

5 . The brain tumor types distinguish system of claim 1 , wherein the server computing device further pre-stores favorite location information of the different types of brain tumors, the data comparison module further compares the brain images and the processed images with the favorite location information to obtain at least three favorite-location comparison results, and the distinguish module statistically analyzes the comparison results and the favorite-location comparison results to obtain the distinguish result.

6 . The brain tumor types distinguish system of claim 1 , wherein the server computing device further comprises a distinguish result outputting module for outputting the distinguish result.

7 . The brain tumor types distinguish system of claim 6 , wherein the server computing device further comprises a processor, and the processor executes the image receiving module, the image pre-processing module, the data comparison module, the distinguish module and the distinguish result outputting module; and

wherein the brain tumor types distinguish system further comprises a user computing device for receiving the distinguish result outputted from the server computing device.

8 . The brain tumor types distinguish system of claim 1 , wherein the server computing device analyzes a plurality of different types of brain tumor reference images to obtain the distinguish pathways.

9 . A server computing device, which is applied to a brain tumor types distinguish system, the brain tumor types distinguish system comprising an image outputting device and the server computing device, the image outputting device outputting at least three brain images captured from a position of a brain tumor, the server computing device pre-storing a plurality of distinguish pathways corresponding to different types of brain tumors, the server computing device comprising:

an image receiving module receiving the brain images;

an image pre-processing module pre-processing the brain images to obtain corresponding processed images thereof;

a data comparison module comparing the brain images and the processed images with the distinguish pathways to obtain at least three comparison results; and

a distinguish module statistically analyzing the comparison results to obtain a distinguish result,

wherein the brain images are magnetic resonance imaging images,

wherein the image pre-processing module comprises:

a mask processing unit performing an auto-detection with each of the brain images and selecting a position of the brain tumor so as to obtain a mask; and

a partial image capturing unit capturing a part of each of the brain images around the selected position to obtain a partial image, wherein the processed image is the mask or the partial image.

10 . The server computing device of claim 9 , wherein the distinguish module comprises:

a scoring unit evaluating each of the comparison results to obtain a scoring result; and

a distinguish unit statistically analyzing the scoring results to obtain the distinguish result.

11 . The server computing device of claim 10 , wherein the comparison result comprises Vestibular Schwannoma, Meningioma, Pituitary Adenoma, Schwannoma, Glioma, or Metastasis.

12 . The server computing device of claim 11 , wherein the scoring unit further performs a weighting process to the comparison result of Meningioma so as to obtain a weighted scoring result.

13 . The server computing device of claim 9 , wherein the server computing device further pre-stores favorite location information of the different types of brain tumors, the data comparison module further compares the brain images and the processed images with the favorite location information to obtain at least three favorite-location comparison results, and the distinguish module statistically analyzes the comparison results and the favorite-location comparison results to obtain the distinguish result.

14 . The server computing device of claim 9 , further comprising:

a distinguish result outputting module for outputting the distinguish result; and

a processor executing the image receiving module, the image pre-processing module, the data comparison module, the distinguish module and the distinguish result outputting module.

15 . The server computing device of claim 9 , wherein the server computing device analyzes a plurality of different types of brain tumor reference images to obtain the distinguish pathways.

16 . A non-transitory computer readable storage medium applied to a brain tumor types distinguish system and storing a program code, wherein the program code is executed by a processor of a computing device to implement the modules as recited in claim 1 .

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 1, 2023
From: NATIONAL YANG MING CHIAO TUNG UNIVERSITY
To: NATIONAL YANG MING CHIAO TUNG UNIVERSITY; TAIPEI VETERANS GENERAL HOSPITAL
Reel/Frame 065733/0084 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 16, 2022
From: LEE, CHENG-CHIA; YANG, HUAI-CHE; CHUNG, WEN-YUH; WU, CHIH-CHUN; GUO, WAN-YUO; YANG, YA-XUAN; HUANG, TZU-HSUAN; LIN, CHUN-YI; LEE, WEI-KAI; LU, CHIA-FENG; WU, YU-TE
To: NATIONAL YANG MING CHIAO TUNG UNIVERSITY
Reel/Frame 061790/0621 →
Priority Claims (1)
TW 111107109 · Feb 25, 2022 · national
Continuity (1)
Related Publication 20230274432A1 · Aug 31, 2023
References Cited (17)
US 20180096191A1 · Wan · 2018 [cited by examiner]
US 20190156159A1 · Kopparapu · 2019 [cited by applicant]
US 20200275857A1 · Lou · 2020 [cited by examiner]
US 20210353360A1 · Ito · 2021 [cited by examiner]
US 20220065788A1 · Chang · 2022 [cited by examiner]
CN 105447872A · 2016 [cited by applicant]
CN 109816657A · 2019 [cited by applicant]
CN 111047589A · 2020 [cited by applicant]
JP 2010012176A · 2010 [cited by applicant]
Alqudah, Ali Mohammad et al., “Brain Tumor Classification Using Deep Learning Technique- A Comparison between Cropped, Uncropped, and Segmented Lesion Images with Different Sizes,” International Journal of Advanced Tren… [cited by applicant]
Mondal Mrinmoy et al., “Deep Transfer Learning Based Multi-Class Brain Tumors Classification Using MRI Images”,2021 3rd International Conference on Electrical & Electronic Engineering(ICEEE), IEEE,Dec. 22, 2021(Dec. 22,… [cited by applicant]
Alnemer Alaa et al., “An Efficient Transfer Learning-based Model for Classification of Brain Tumor”, 2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies(ISMSIT), IEEE,Oct. 21, 2021(… [cited by applicant]
Ghavami Nooshin., “Automatic analysis of medical images for change detection in prostate cancer”, PhD Thesis, Aug. 28, 2020(Aug. 28, 2020), pp. 1-158,XP093100462, London, UK. [cited by applicant]
Ismael et al., “An enhanced deep learning approach for brain cancer MRI images classification using residual networks,” Artificial Intelligence in Medicine 102 (2020) pp. 1-8, 8 pages. [cited by applicant]
Deepak et al., “Brain tumor classification using deep CNN features via transfer learning,” Computers in Biology and Medicine 111 (2019), pp. 1-7, 7 pages. [cited by applicant]
Chelghoum et al., “Transfer Learning Using Convolutional Neural Network Architectures for Brain Tumor Classification from MRI Images,” IFIP International Conference on Artificial Intelligence Applications and Innovation… [cited by applicant]
Ge et al., “Enlarged Traning Dataset by Pairwise GANs for Molecular-Based Brain Tumor Classification,” IEEE Access, vol. 8 (2020) pp. 22560-22570, 11 pages. [cited by applicant]