Application of Deep Learning Algorithm in Feature Mining and Rapid Identification of Colorectal Image

Abstract

Based on deep learning technology, this paper proposes a two-stage colorectal image feature mining and fast recognition model to achieve fully automatic medical image pathology discrimination. Drawing on the ideas of multi-factor Meta-regression analysis widely used in the medical field and the model aggregation framework based on Bayesian prior probability theory, a prognostic model of colorectal tumors suitable for various situations and scenarios is constructed. And using a combination of public data sets and real data sets, design two sets of experiments to verify these models from different angles. The algorithm was used to select one, four, and five related features from three sequences to construct three sets of prediction models. The application of the six algorithms failed to obtain a better predictive model (AUC value range 0.439 ~ 0.640). The algorithm (AUC value 0.750±0.137) and the algorithm (AUC value 0.764±0.128) can be used to obtain models with better predictive performance, and the four models are less effective (AUC value<0.7). In the joint model, the algorithm (AUC value 0.742± 0.101) and the algorithm (AUC value 0.718±0.069) can also be used to obtain a model with better prediction performance. Imagebased imaging histology tags can be used as a non-invasive auxiliary tool for preoperative evaluation of histological grading of CRAC, and are expected to be applied in clinical practice to assist in the development of individualized treatment plans. INDEX TERMS deep learning; colorectal imaging; feature mining; rapid identification.

Correlation Analysis of Gene and Radiomic Features in Colorectal Cancer Liver Metastases

“…According to study data, by 2030, there will be more than 2.2 million new colon cancer cases in the world [ 2 ], including more than 1.1 million deaths [ 1 ]. Some medical researches showed that the liver was the most prone organ for colorectal cancer to produce hematogenous metastasis [ 3 , 4 ]. Therefore, the discovery of CRLM biomarkers was useful for the diagnosis and targeting of anticancer drugs.…”

Analysis of Co-Expression Module of Liver Metastasis Genes in Colorectal Cancer and Mining of Potential High-Expression Biomarkers

“…According to relevant data, more than 2.2 million new cases of colon cancer are expected to occur globally by 2030, including more than 1.1 million deaths [2,3]. According to some authoritative medical data, liver is the target organ that is most likely to produce blood metastasis in colorectal cancer [4,5].Therefore, the treatment of liver metastasis in colorectal cancer is one of the key and di cult points in current medical technology.16% 26% of colorectal cancer patients had liver metastases at the time of diagnosis, and 14%~24% of patients had liver metastases after primary radical resection [6][7][8][9]. Most patients with liver metastases were unable to undergo radical resection.…”