Artificial intelligence assisted prostate tumor early diagnosis method based on surface enhanced Raman spectroscopy

A surface-enhanced Raman and prostate tumor technology, applied in the medical field, can solve the problems of unsatisfactory early diagnosis of prostate tumors, excessive screening of benign diseases, and insufficient diagnosis of malignant diseases.

Inactive Publication Date: 2020-10-23
RENJI HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] The object of the present invention is to provide a method for early diagnosis of prostate tumors assisted by artificial intelligence based on surface-enhanced Raman spectroscopy. The problem of unsatisfactory early diagnosis of prostate tumors. At the same time, it is necessary to solve the low specificity and sensitivity of the early diagnosis of prostate tumors based on PSA, resulting in insufficient diagnosis of malignant diseases and over-screening of benign diseases. question

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Artificial intelligence assisted prostate tumor early diagnosis method based on surface enhanced Raman spectroscopy
  • Artificial intelligence assisted prostate tumor early diagnosis method based on surface enhanced Raman spectroscopy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as Figure 1-2 As shown, the establishment of the serum SERS spectrum database of prostate tumor patients

[0057] (1) Inclusion criteria:

[0058] 1) Patients with clear pathology who have undergone prostate biopsy or prostate surgery in the hospital;

[0059] 2) Through the evaluation of the patient's physical strength (ECOG 0-2), blood routine, liver and kidney function, heart function and tumor burden;

[0060] 3) After being fully informed of the purpose and possible risks of the study, the patient agreed to participate in the test and signed the "Informed Consent Form for the Use of Clinical Samples".

[0061] (2) Exclusion criteria:

[0062] 1) Those with previous history of other tumors;

[0063] 2) Previously received allogeneic hematopoietic stem cell transplantation or solid organ transplantation;

[0064] 3) Those who have a history of psychotropic drug abuse and cannot quit or have a history of mental disorders;

[0065] 4) Unable to cooperate or...

Embodiment 2

[0082] Such as Figure 1-2 As shown, the construction of an early artificial intelligence diagnosis system for prostate tumors

[0083] 1.2.1 Construct and train CNN network based on SERS data, construct classifier

[0084] (1) Use the Python script to call the Keras framework API to complete CNN construction, training and testing. The framework uses TensorFlow as the underlying driver. The CNN structure designed in this project consists of 6 layers: convolutional layer 1-pooling layer 1-convolutional layer 2-pooling layer 2-full connection layer 1-full connection layer 2 (output layer).

[0085] 1) The input data of the input layer is the preprocessed one-dimensional SERS spectral data.

[0086] 2) The first convolutional layer includes 60 convolutional kernels, each convolutional kernel has a size of 1×12, border padding, and the activation function is set to “relu”, and convolution operation is performed on the input data to extract data features.

[0087] 3) The second...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an artificial intelligence assisted prostate tumor early diagnosis method based on surface enhanced Raman spectroscopy. The method comprises the following steps of: collectinga serum sample; adopting a Raman spectrometer for detection; performing graphic analysis and data processing on an acquired Raman spectrum signal; selecting a biological tissue Raman spectrum concentration range of 400-1800cm<-1> for analysis, and preprocessing an original spectrum acquired by a spectrograph through Origin Pro 8 software, i.e. performing background reduction and spectrum area homogenization, drawing a serum average Raman spectrum, and then comparing changes and differences of related Raman characteristic peaks, thus finally obtaining a diagnosis result of prostate tumor earlydiagnosis. The method provided by the invention is higher in sensitivity and specificity, and unnecessary needle biopsy and missed diagnosis caused by an existing screening diagnosis method are reduced.

Description

technical field [0001] The present invention relates to the medical field, in particular to detection technology, in particular to an artificial intelligence-assisted early diagnosis method for prostate tumors based on surface-enhanced Raman spectroscopy. Background technique [0002] Prostate cancer is the most common malignant tumor among men in European and American countries, and it is also the second leading cause of death among male tumor-related deaths. With the development of my country's aging population and changes in lifestyle, the incidence of prostate cancer is increasing year by year in my country, ranking sixth among new male malignant tumors in my country. Unlike European and American countries, due to the lack of popularization of prostate cancer screening in my country, most prostate cancer patients are diagnosed in the middle and advanced stages, and the overall prognosis is far worse than that of European and American countries. Currently, the most commo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/65G06T7/00G06K9/62G06N3/04G06N3/08
CPCG01N21/658G06T7/0012G06N3/084G06T2207/30081G06T2207/30096G06N3/045G06F18/2414
Inventor 潘家骅薛蔚王琦朱寅杰忻志祥钱宏阳马泽华王岩
Owner RENJI HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap