Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method used for differentiating benign tumor and malignant tumor based on infrared light spectrums

A malignant tumor and infrared spectroscopy technology, applied in the field of prediction of tumor properties, can solve problems such as different treatment plans and prognosis, confusion, and difficulties in the pathological diagnosis of lung adenocarcinoma in situ, to overcome spectral interference, improve accuracy, Favorable Effects for Diagnosis

Active Publication Date: 2018-11-02
CHONGQING MEDICAL UNIVERSITY
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the pathological diagnosis of lung adenocarcinoma in situ is difficult, and its morphology under the microscope is very similar to a benign lung tumor—sclerosing alveolar cell tumor
Although sclerosing alveolar cell tumor is a benign tumor, it has some morphological characteristics of malignant tumors under the microscope, such as mild to obvious atypia of the nucleus, so it is easily confused and misdiagnosed as adenocarcinoma in situ of the lung. The treatment options and prognosis of patients are different

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
  • Method used for differentiating benign tumor and malignant tumor based on infrared light spectrums
  • Method used for differentiating benign tumor and malignant tumor based on infrared light spectrums
  • Method used for differentiating benign tumor and malignant tumor based on infrared light spectrums

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Example 1 A method for distinguishing benign and malignant tumors based on infrared spectroscopy (including unstained paraffin sections and HE-stained sections)

[0033] 1. Collection of samples

[0034] A total of 100 tumor tissue sections from different patients in hospital 1 and 2 were collected. Among them, 50 sclerosing alveolar cell tumor tissue sections included 25 unstained paraffin sections and 25 HE-stained sections, and 50 lung adenocarcinoma in situ tissue sections included 25 unstained paraffin sections and 25 HE-stained sections.

[0035] 2. Spectral measurement

[0036] After preheating the infrared spectrometer for 2 hours, set the spectral measurement parameters: resolution 8cm -1 , Scan times 64 times, scan range 4000 ~ 1900cm -1 , measure the infrared transmission spectrum of each slice, scan with the same parameters before each scan and subtract the background, and measure a spectrum at 3 different positions for each slice, sclerosing alveolar cel...

Embodiment 2

[0053] Example 2 A method for distinguishing benign and malignant tumors based on infrared spectroscopy (only including unstained paraffin sections)

[0054] 1. Collection of samples

[0055] The tumor tissue sections used in this example were the unstained paraffin sections collected in Example 1.

[0056] 2. Spectral measurement

[0057] With embodiment 1.

[0058] 3. Extraction and modeling of spectral characteristic variables

[0059] (1) Selection of spectral pretreatment scheme

[0060] In order to make the built model have excellent predictive performance, various spectral preprocessing techniques including NP, MSC, SNV, FD, SD, SGS, and NDS were screened and combined, as shown in Table 3 and Table 4. The results show that when the obtained spectra are preprocessed by NP or SGS, the prediction performance of the model is the best, such as model 1 in Table 3; model 1 in Table 4.

[0061] (2) Selection of modeling spectral range

[0062] Using the above-mentioned op...

Embodiment 3

[0074] Example 3 A method for distinguishing benign and malignant tumors based on infrared spectroscopy (only HE stained sections are included)

[0075] 1. Collection of samples

[0076] The tumor tissue sections used in this example were the HE-stained sections collected in Example 1.

[0077] 2. Spectral measurement

[0078] With embodiment 1.

[0079] 3. Extraction and modeling of spectral characteristic variables

[0080] (1) Selection of spectral pretreatment scheme

[0081] In order to make the built model have excellent predictive performance, various spectral preprocessing techniques including NP, MSC, SNV, FD, SD, SGS, and NDS were screened and combined, as shown in Table 5 and Table 6. The results show that when the obtained spectra are preprocessed by NP or SGS, the prediction performance of the model is the best, such as model 1 in Table 5; model 1 in Table 6.

[0082] (2) Selection of modeling spectral range

[0083] Using the above-mentioned optimal spectra...

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 a method used for differentiating benign tumor (pulmonary sclerosing pneumocytoma) and malignant tumor (adenocarcinoma in situ) based on infrared light spectrums. The method comprises following steps: benign tumor and malignant tumor tissue slices are collected, slice infrared transmitted spectrums are collected at 4000 to 1900cm<-1> range at a resolution ratio of 8cm<-1> and scanning time of 64; the obtained spectrums are not subjected to pretreatment, or are subjected to SGS pretreatment, mole construction spectrum range upper limit is determined to be 4000 to 3960cm<-1>, the lower limit is determined to be 1960cm<-1>, the former 4 to 9 main ingredients are selected, discriminant analysis method or counter propagation network are adopted to construct a model usedfor differentiating benign tumor and malignant tumor; a property unknown tumor tissue slice is selected, and spectrum data processing is carried out through the above steps, and at last the constructed model is adopted for prediction. The method can be used for accurate, objective, rapid, and economical differentiating of benign tumor and malignant tumor.

Description

technical field [0001] The invention relates to a method for predicting tumor properties, more specifically, a method for distinguishing benign and malignant tumors based on infrared spectroscopy. Background technique [0002] Tumors are divided into benign and malignant categories. Benign tumors usually grow slowly and have a good prognosis after complete resection; whereas malignant tumors usually grow rapidly and are prone to systemic metastasis leading to patient death. In recent years, the incidence and mortality of malignant tumors such as lung cancer have increased the fastest. Lung adenocarcinoma accounts for a large proportion of lung cancer. Lung adenocarcinoma is a malignant tumor of the bronchial epithelium of the lung. Because its cancer tissue can invade blood vessels and is prone to distant metastasis, the prognosis is poor. It is worth noting that it has been clinically shown that timely surgical resection of lung adenocarcinoma patients after early diagno...

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
IPC IPC(8): G01N21/3563
CPCG01N21/3563
Inventor 范琦杨洋王娅兰唐怡张雪
Owner CHONGQING MEDICAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com