Colorectal Cancer Lymph Node Research Articles

In-depth analysis of lymph node metastasis-related sialylated protein profiling and their clinical and biological significance in colorectal cancer using mass spectrometry and multi-omics technologies

Colorectal cancer (CRC) lymph node metastasis (LNM) is a crucial factor affecting the prognosis and treatment outcomes of CRC patients. It has been confirmed that altered glycosylation is a key event during CRC lymphatic metastases. Sialylation is one of the most significant glycosylation alterations in tumors. However, the predictive role of sialylation and sialylated protein in CRC remains elusive, especially in CRC-LNM. In this study, we explored and identified 1102 sialylated glycoproteins in CRC-LNM using metabolic labeling strategy and proteomics analysis. Combined with comprehensive analysis with bioinformatics and machine learning algorithms, we screened 25 prognostic sialylation-related genes (SRGs) to construct a new molecular phenotype (LRSRGs-Phenotype) and a prognostic SRG signature (LRSRGs-related Gene Signature) in CRC. Then, we further confirmed that patients in different phenotypes had different prognosis, molecular biological characteristics, immune cell infiltration and could be closely linked to three previously reported immune phenotypes: immune-excluded (Phenotype A), immune-desert (Phenotype B), and immune-inflamed (Phenotype C). Besides, we evaluated and validated the LRSRGs-related gene (ACADM, EHD4, FLOT1, GPC1, GSR, LRRC8A, NGFR, SDHB, and SEC61G) signature and found the risk score was an independent risk factor for CRC prognosis. CRC patients in different risk groups had different somatic mutation, tumor microenvironment and immunotherapy response. Finally, we also identified the potential therapeutic agents for CRC patients in different risk groups. In conclusion, we explored the key sialylated glycoproteins, which may play a key role in tumor LNM and clinical outcomes. And constructed the LRSRGs-phenotype and signature with prognostic and therapeutic predictive value in CRC, hoping to provide reliable scientific basis for future treatments in CRC patients.

Deep-learning features based on F18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to predict preoperative colorectal cancer lymph node metastasis

The objective of this study was to create and authenticate a prognostic model for lymph node metastasis (LNM) in colorectal cancer (CRC) that integrates clinical, radiomics, and deep transfer learning features. In this study, we analyzed data from 119 CRC patients who underwent F18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) scanning. The patient cohort was divided into training and validation subsets in an 8:2 ratio, with an additional 33 external data points for testing. Initially, we conducted univariate analysis to screen clinical parameters. Radiomics features were extracted from manually drawn images using pyradiomics, and deep-learning features, radiomics features, and clinical features were selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Spearman correlation coefficient. We then constructed a model by training a support vector machine (SVM), and evaluated the performance of the prediction model by comparing the area under the curve (AUC), sensitivity, and specificity. Finally, we developed nomograms combining clinical and radiological features for interpretation and analysis. The deep learning radiomics (DLR) nomogram model, which was developed by integrating deep learning, radiomics, and clinical features, exhibited excellent performance. The area under the curve was (AUC=0.934, 95% confidence interval [CI]: 0.884-0.983) in the training cohort, (AUC=0.902, 95% CI: 0.769-1.000) in the validation cohort, and (AUC=0.836, 95% CI: 0.673-0.998) in the test cohort. We developed a preoperative predictive machine-learning model using deep transfer learning, radiomics, and clinical features to differentiate LNM status in CRC, aiding in treatment decision-making for patients.

Radiological Cutoff Values for Diagnosis of Lymph Node Metastasis in Colorectal Cancer With Multilevel Analysis.

A cutoff value for lymph node diameter in colorectal cancer lymph node metastases has not been established. This prospective study aimed to investigate the direct association between swollen lymph nodes identified on preoperative computed tomography (CT) and pathological findings and proposed a cutoff value. We enrolled patients scheduled to undergo curative surgery with lymph node dissection for colorectal adenocarcinoma who underwent preoperative contrast-enhanced CT and had swollen lymph nodes ≥7 mm in diameter. Two gastrointestinal surgeons intraoperatively identified the target lymph nodes to assess the association between lymph node diameter and pathological findings. The diagnostic performance for lymph node metastasis was determined using multi-level logistic modelling. A total of 109 patients were enrolled, and 225 swollen lymph nodes were pathologically evaluated. Using a cutoff value of ≥9 mm for the short diameter, the positive and negative predictive values, sensitivity, and specificity were 100.0% (99.6%-100.0%), 99.9% (99.1%-100.0%), 62.0% (45.6%-76.0%), and 84.9% (67.0%-94.0%), respectively. The cutoff value for improving the positive predictive value for the preoperative lymph node metastasis diagnosis in colorectal cancer patients should be at least 9 mm in diameter.

A commentary on the article entitled 'finding the minimum number of retrieved lymph nodes in Node-negative colorectal Cancer using Real-world data and the SEER database'.

A commentary on the article entitled 'finding the minimum number of retrieved lymph nodes in Node-negative colorectal Cancer using Real-world data and the SEER database'.

Miscategorized lymph nodes in colorectal cancer: A potential pitfall of pre-surgical imaging

Miscategorized lymph nodes in colorectal cancer: A potential pitfall of pre-surgical imaging

Prognostic value of lymph node distribution after laparoscopic colectomy with Japanese D3 dissection.

Positive pathologic lymph nodes in colorectal cancer represent an important prognostic indicator. Whether lymph node distribution or the number of metastatic nodes is more strongly associated with survival prediction remains controversial. Among 3449 colorectal cancer surgeries performed at Nagasaki University Hospital and five affiliated institutions from April 2016 to March 2022, we investigated 604 patients who underwent laparoscopic radical resection and were diagnosed with pathological stage III cancer. Patients were divided into two groups according to whether they had central vessel metastasis (LND3 group, n=42) or not (LND1/2 group, n=562). After adjusting for background factors using propensity score matching, the LND3 group included 42 patients and the LND1/2 group included 40 patients. Patient background characteristics and prognosis were compared between these two groups. Before matching, frequencies of right-side colon cancer (64.3% vs 38.1%, p=0.001), multivisceral resection (11.9% vs 4.4%, p=0.039), clinical N2 status (40.5% vs 22.6%, p=0.032), and pathological N2 (73.8% vs 22.6%, p<0.001) were all greater, and the number of lymph nodes retrieved was higher (24 vs 19, p=0.042) in the LND3 group. After matching, no differences in any clinical factors were evident between groups. Five-year RFS (44.8% vs 77.1%, p=0.004) and OS (43.1% vs 83.2%, p<0.001) were worse in the LND3 group. Adjuvant chemotherapy improved RFS (adjuvant chemotherapy (+) vs adjuvant chemotherapy (-): 62.1% vs 27.7%, p=0.047) in the LND3 group. LND3-positive patients show poorer prognosis than LND1/2 patients and should be treated with an appropriate perioperative treatment strategy.

Differential microbiota network according to colorectal cancer lymph node metastasis stages

Differential microbiota network according to colorectal cancer lymph node metastasis stages

Precisional detection of lymph node metastasis using tFCM in colorectal cancer.

The detection of colorectal cancer (CRC) lymph node (LN) metastases significantly influences treatment choices, yet identifying them in samples is time-consuming and error-prone. To enhance efficiency, we have established a LN metastasis detection method utilizing triple-parameter flow cytometry (tFCM) and have conducted a comparative assessment of its accuracy and cost-effectiveness in contrast to conventional pathological examinations. This technique utilized biomarkers cytokeratin 20 (CK20), epithelial cell adhesion molecules (EpCAM), and Pan-CK. tFCM's sensitivity was validated by analyzing known cell line concentrations (SW480 and SW620) in peripheral blood mononuclear cells (PBMCs), with CK20, EpCAM, and Pan-CK showing significant expression in CRC cell lines but not in PBMCs. A strong linear correlation was observed in the mixed leukocyte environment (R 2 = 0.9988). Subsequently, tFCM and pathological sections were employed to analyze LNs from CRC patients, enabling comparison of detection accuracy. Within the 36 LNs studied, tFCM successfully identified tumor cells with varying metastasis degrees, including micro-metastasis and isolated tumor cell clusters. Notably, relying solely on pathological sections led to a potential 25% misdiagnosis rate for LNs. In contrast, tFCM effectively minimized this risk. In summary, compared to traditional pathological sections, tFCM is a more advantageous method for detecting nodal metastasis in CRC patients, offering a more precise prognosis for these patients.

The Relationship Between the Resected Colon Length and the Number of Lymph Nodes in Colorectal Cancer: A Retrospective Cohort Study

Objective: The prognostic factors that are important for colorectal cancer are the pathological grade of the tumor and the existence of lymph node involvement. Currently, the curative treatment option is resection of the tumor with adequate length and margin along with complete dissection of lymph nodes draining the site of resection. Our study investigated into retrieving adequate lymph nodes for accurate staging as well as the relationship between lymph nodes and colon and rectum specimen length. Methods: This retrospective cross-sectional study examined the correlation between resected colon length and lymph node count in people with colorectal cancer diagnosed between January 2010 and June 2018. We defined a cutoff value for the segment length to be resected to allow adequate staging of the tumor. Furthermore, we examined the relationship between the resected segment lengths and survival. Results: Of the patients who were included in this study, 211 were men and 169 were women. The mean resected colon length was 26.47±17.09 cm and the mean dissected lymph node count was 29.05±20.84. There was a positive correlation between specimen length and total lymph node count as well as specimen length and the existence of reactive lymph nodes that were statistically significant (r=0.319, p=0.001; r=0.312, p=0.001, respectively). In our study, tumor localization was described in three regions: the right colon, left colon and rectum. The mean right colon region specimen length was 28.8±15.5 cm, while it was 22.0±11.0 cm for the left colon region, and 21.7±10.6 cm for the rectum region. The 5-year overall survival rate was 53.2%, whereas the 5-year disease-specific survival rate was 58.2%. Conclusion: The mean specimen length to achieve the cutoff value for adequate lymph node retrieval (least 12 lymph nodes) was 16 cm in our study (ROC curve, AUC=0.689±0.05, p=0.001). The resected colon length and the number of retrieved lymph nodes were positively correlated in our study. Based on this confirmation, a cutoff value of 16 cm was calculated to achieve an adequate segment length to be resected.

Targeting FAPα-positive lymph node metastatic tumor cells suppresses colorectal cancer metastasis

Lymphatic metastasis is the main metastatic route for colorectal cancer, which increases the risk of cancer recurrence and distant metastasis. The properties of the lymph node metastatic colorectal cancer (LNM-CRC) cells are poorly understood, and effective therapies are still lacking. Here, we found that hypoxia-induced fibroblast activation protein alpha (FAPα) expression in LNM-CRC cells. Gain- or loss-function experiments demonstrated that FAPα enhanced tumor cell migration, invasion, epithelial–mesenchymal transition, stemness, and lymphangiogenesis via activation of the STAT3 pathway. In addition, FAPα in tumor cells induced extracellular matrix remodeling and established an immunosuppressive environment via recruiting regulatory T cells, to promote colorectal cancer lymph node metastasis (CRCLNM). Z-GP-DAVLBH, a FAPα-activated prodrug, inhibited CRCLNM by targeting FAPα-positive LNM-CRC cells. Our study highlights the role of FAPα in tumor cells in CRCLNM and provides a potential therapeutic target and promising strategy for CRCLNM.

Finding the minimum number of retrieved lymph nodes in node-negative colorectal cancer using Real-world Data and the SEER database.

Current clinical guidelines recommend the removal of at least 12 lymph nodes (LNs) in resectable colorectal cancer (CRC). With advancements in lymphadenectomy technologies, the number of retrieved lymph nodes (rLNs) has markedly increased. This study aimed to investigate the lowest number of rLNs in node-negative patients. A total of 1103 N0 and 208 N1a stage patients were enrolled in our cohort, while 8503 N0 and 1276 N1a patients from the Surveillance, Epidemiology, and End Results CRC database were included. Propensity score matching and multivariate Cox regression analyses were performed to mitigate the influence of selection bias and control for potential confounding variables. The median number of rLNs in N0 patients increased from 13.5 (interquartile range [IQR]: 9-18) in 2013 to 17 (IQR: 15-20) in 2019. The restrictive cubic spline illustrated a nonlinear relationship between rLNs and prognosis (nonlinearity, P =0.009), with a threshold ( N =16) influencing clinical outcomes. Patients at either N0 or N1a stage with sufficient rLNs (≥16) demonstrated superior prognoses to those with a limited rLNs (<16). After adjusting for clinical confounders, similar prognoses were observed in N0 limited and N1a adequate populations. Furthermore, Kaplan-Meier curves revealed that N0 limited patients who received chemotherapy exhibited better outcomes than those who did not. Among patients with node-negative CRC, it is crucial to remove 16 or more LNs effectively. Fewer than 16 rLNs should be regarded as an independent risk factor, implying the need for adjuvant chemotherapy.

An Analysis of the Gene Expression Associated with Lymph Node Metastasis in Colorectal Cancer.

This study aimed to explore the genes regulating lymph node metastasis in colorectal cancer (CRC) and to clarify their relationship with tumor immune cell infiltration and patient prognoses. The data sets of CRC patients were collected through the Cancer Gene Atlas database; the differentially expressed genes (DEGs) associated with CRC lymph node metastasis were screened; a protein-protein interaction (PPI) network was constructed; the top 20 hub genes were selected; the Gene Ontology functions and the Kyoto Encyclopedia of Genes and Genomes pathways were enriched and analyzed. The Least Absolute Shrinkage and Selection Operator (LASSO) regression method was employed to further screen the characteristic genes associated with CRC lymph node metastasis in 20 hub genes, exploring the correlation between the characteristic genes and immune cell infiltration, conducting a univariate COX analysis on the characteristic genes, obtaining survival-related genes, constructing a risk score formula, conducting a Kaplan-Meier analysis based on the risk score formula, and performing a multivariate COX regression analysis on the clinical factors and risk scores. A total of 62 DEGs associated with CRC lymph node metastasis were obtained. Among the 20 hub genes identified via PPI, only calcium-activated chloride channel regulator 1 (CLCA1) expression was down-regulated in lymph node metastasis, and the rest were up-regulated. A total of nine characteristic genes associated with CRC lymph node metastasis (KIF1A, TMEM59L, CLCA1, COL9A3, GDF5, TUBB2B, STMN2, FOXN1, and SCN5A) were screened using the LASSO regression method. The nine characteristic genes were significantly related to different kinds of immune cell infiltration, from which three survival-related genes (TMEM59L, CLCA1, and TUBB2B) were screened. A multi-factor COX regression showed that the risk scores obtained from TMEM59L, CLCA1, and TUBB2B were independent prognostic factors. Immunohistochemical validation was performed in tissue samples from patients with rectal and colon cancer. TMEM59L, CLCA1, and TUBB2B were independent prognostic factors associated with lymphatic metastasis of CRC.

Use of iTRAQ-based quantitative proteomic identification of CHGA and UCHL1 correlated with lymph node metastasis in colorectal carcinoma.

Metastatic dissemination of colorectal cancer (CRC), the third most common cancer type, is responsible for CRC deaths. Understanding the transition of lymph node metastasis (LNM) from Stage II to Stage III is beneficial in the prognosis and intervention of CRC. In this study, a quantitative proteomic survey was conducted to investigate the LNM-associated proteins and evaluate the clinicopathological characteristics of these target proteins in CRC. By using the LC-MS/MS iTRAQ technology, we analysed the proteomic changes between LMN II and LMN III. Fresh tumours from the CRC specimens consisting of 12 node-negative (Stage II) and 12 node-positive (Stage III) cases were analysed by LC-MS/MS iTRAQ proteome analysis. Subsequently, tissue microarray with immunohistochemistry staining was conducted to access the clinicopathological characteristics of these proteins in 116 paraffin-embedded CRC samples, each for non-LNM and LNM CRC. To study the effects of the differentially expressed proteins on the potential mechanism, Boyden chamber assay, flow cytometry and shRNA-based assessments were conducted to examine the role of the epithelial-mesenchymal transition (EMT) and the invasiveness of CRC cells and others in vivo xenograft mouse model experiments. Forty-eight proteins were found differentially expressed between non-LNM and LNM CRC tissues. Protein abundances of chromogranin-A (CHGA) and ubiquitin carboxyl-terminal hydrolase isozyme L1 (UCHL1) were observed in node-positive CRC (p < 0.05). Knockdown of CHGA and UCHL1 significantly regulate cancer behaviours of HCT-116, including inhibition of cell migration, invasiveness, cell cycle G1/S arrest and reactive oxygen species (ROS) generation. Mechanistically, the CHGA and UCHL1 inactivation displayed decreased levels of UCH-L1, chromogranin A, β-catenin, cyclin E, twist-1/2, vimentin, MMP-9, N-cadherin and PCNA through the activation of the Rho-GTPase/AKT/NFκB pathways. Histone modification of H3K4 trimethylation of CHGA and UCHL1 promoter were increased to activate their transcription through the signalling transduction such as Rho-GTPase, AKT and NFκB pathways. Our results indicated that UCHL1 and chromogranin A are novel regulators in CRC lymph node metastasis to potentially provide new insights into the mechanism of CRC progression and serve as biomarkers for CRC diagnosis at the metastatic stage.

Histology of metastatic colorectal cancer in a lymph node.

A primary colorectal cancer (CRC) tumor can contain heterogeneous cancer cells. As clones of cells with different properties metastasize to lymph nodes (LNs), they could show different morphologies. Cancer histologies in LNs of CRC remains to be described. Our study enrolled 318 consecutive patients with CRC who underwent primary tumor resection with lymph node dissection between January 2011 and June 2016. 119 (37.4%) patients who had metastatic LNs (mLNs) were finally included in this study. Cancer histologies in LNs were classified and compared with pathologically diagnosed differentiation in the primary lesion. The association between histologies in lymph node metastasis (LNM) and prognosis in patients with CRC was investigated. The histologies of the cancer cells in the mLNs were classified into four types: tubular, cribriform, poorly differentiated, and mucinous. Same degree of pathologically diagnosed differentiation in the primary tumor produced various histological types in LNM. In Kaplan-Meier analysis, prognosis was worse in CRC patients with moderately differentiated adenocarcinoma who had at least some mLN also showing cribriform carcinoma than for those whose mLNs all showed tubular carcinoma. Histology in LNM from CRC might indicate the heterogeneity and malignant phenotype of the disease.

Colorectal cancer lymph node metastasis prediction with weakly supervised transformer-based multi-instance learning

Lymph node metastasis examined by the resected lymph nodes is considered one of the most important prognostic factors for colorectal cancer (CRC). However, it requires careful and comprehensive inspection by expert pathologists. To relieve the pathologists’ burden and speed up the diagnostic process, in this paper, we develop a deep learning system with the binary positive/negative labels of the lymph nodes to solve the CRC lymph node classification task. The multi-instance learning (MIL) framework is adopted in our method to handle the whole slide images (WSIs) of gigapixels in size at once and get rid of the labor-intensive and time-consuming detailed annotations. First, a transformer-based MIL model, DT-DSMIL, is proposed in this paper based on the deformable transformer backbone and the dual-stream MIL (DSMIL) framework. The local-level image features are extracted and aggregated with the deformable transformer, and the global-level image features are obtained with the DSMIL aggregator. The final classification decision is made based on both the local and the global-level features. After the effectiveness of our proposed DT-DSMIL model is demonstrated by comparing its performance with its predecessors, a diagnostic system is developed to detect, crop, and finally identify the single lymph nodes within the slides based on the DT-DSMIL and the Faster R-CNN model. The developed diagnostic model is trained and tested on a clinically collected CRC lymph node metastasis dataset composed of 843 slides (864 metastasis lymph nodes and 1415 non-metastatic lymph nodes), achieving the accuracy of 95.3% and the area under the receiver operating characteristic curve (AUC) of 0.9762 (95% confidence interval [CI]: 0.9607–0.9891) for the single lymph node classification. As for the lymph nodes with micro-metastasis and macro-metastasis, our diagnostic system achieves the AUC of 0.9816 (95% CI: 0.9659–0.9935) and 0.9902 (95% CI: 0.9787–0.9983), respectively. Moreover, the system shows reliable diagnostic region localizing performance: the model can always identify the most likely metastases, no matter the model’s predictions or manual labels, showing great potential in avoiding false negatives and discovering incorrectly labeled slides in actual clinical use.Graphical

Computer-Assisted Diagnosis of Lymph Node Metastases in Colorectal Cancers Using Transfer Learning With an Ensemble Model

Screening of lymph node metastases in colorectal cancer (CRC) can be a cumbersome task, but it is amenable to artificial intelligence (AI)-assisted diagnostic solution. Here, we propose a deep learning–based workflow for the evaluation of CRC lymph node metastases from digitized hematoxylin and eosin–stained sections. A segmentation model was trained on 100 whole-slide images (WSIs). It achieved a Matthews correlation coefficient of 0.86 (±0.154) and an acceptable Hausdorff distance of 135.59 μm (±72.14 μm), indicating a high congruence with the ground truth. For metastasis detection, 2 models (Xception and Vision Transformer) were independently trained first on a patch-based breast cancer lymph node data set and were then fine-tuned using the CRC data set. After fine-tuning, the ensemble model showed significant improvements in the F1 score (0.797-0.949; P <.00001) and the area under the receiver operating characteristic curve (0.959-0.978; P <.00001). Four independent cohorts (3 internal and 1 external) of CRC lymph nodes were used for validation in cascading segmentation and metastasis detection models. Our approach showed excellent performance, with high sensitivity (0.995, 1.0) and specificity (0.967, 1.0) in 2 validation cohorts of adenocarcinoma cases (n = 3836 slides) when comparing slide-level labels with the ground truth (pathologist reports). Similarly, an acceptable performance was achieved in a validation cohort (n = 172 slides) with mucinous and signet-ring cell histology (sensitivity, 0.872; specificity, 0.936). The patch-based classification confidence was aggregated to overlay the potential metastatic regions within each lymph node slide for visualization. We also applied our method to a consecutive case series of lymph nodes obtained over the past 6 months at our institution (n = 217 slides). The overlays of prediction within lymph node regions matched 100% when compared with a microscope evaluation by an expert pathologist. Our results provide the basis for a computer-assisted diagnostic tool for easy and efficient lymph node screening in patients with CRC.

Prediction model of colorectal cancer (CRC) lymph node metastasis based on intestinal bacteria.

Lymph node metastasis is the main metastatic mode of CRC. Lymph node metastasis affects patient prognosis. To screen differential intestinal bacteria for CRC lymph node metastasis and construct a prediction model. First, fecal samples of 119 CRC patients with lymph node metastasis and 110 CRC patients without lymph node metastasis were included for the detection of intestinal bacterial 16S rRNA. Then, bioinformatics analysis of the sequencing data was performed. Community structure and composition analysis, difference analysis, and intragroup and intergroup correlation analysis were conducted between the two groups. Finally, six machine learning models were used to construct a prediction model for CRC lymph node metastasis. The community richness and the community diversity at the genus level of the two groups were basically consistent. A total of 12 differential bacteria (Agathobacter, Catenibacterium, norank_f__Oscillospiraceae, Lachnospiraceae_FCS020_group, Lachnospiraceae_UCG-004, etc.) were screened at the genus level. Differential bacteria, such as Agathobacter, Catenibacterium, norank_f__Oscillospiraceae, and Lachnospiraceae_FCS020_group, were more associated with no lymph node metastasis in CRC. In the discovery set, the RF model had the highest prediction accuracy (AUC = 1.00, 98.89% correct, specificity = 55.21%, sensitivity = 55.95%). In the test set, SVM model had the highest prediction accuracy (AUC = 0.73, 72.92% correct, specificity = 69.23%, sensitivity = 88.89%). Lachnospiraceae_FCS020_group was the most important variable in the RF model. Lachnospiraceae_UCG - 004 was the most important variable in the SVM model. CRC lymph node metastasis is closely related to intestinal bacteria. The prediction model based on intestinal bacteria can provide a new evaluation method for CRC lymph node metastasis.

Atypical lymphogenous metastasis to the left supraclavicular lymph nodes in colorectal cancer. A clinical case and a literature review

Atypical lymphogenous metastasis to the left supraclavicular lymph nodes in colorectal cancer. A clinical case and a literature review

Development and application of artificial intelligence to detect metastases in lymph nodes in colorectal cancer

AIM: to create a marked data set (histoscans of lymph nodes) for use in the development of medical decision support systems (based on machine learning) in pathomorphology, which will allow determining the presence of metastatic lymph node lesions in CRC.RESULTS: the dataset included 432 files with digital images and markings of 1000 lymph nodes, including lymph nodes with and without metastases. Based on the marked-up data, a neural network model was trained to determine the probability of metastatic lesion for each pixel in the area of interest - the lymph node (Dice 0.863 for the replaced tissue, Dice macro 0.923). In addition, pre- and postprocessing methods were implemented to represent input data in a form acceptable for machine learning and to represent the AI model's response in a form convenient for user perception. Additionally, a neural network model has been developed that predicts the probability of finding artifacts in digital images of lymph nodes with the possibility of forming an artifact probability map (Dice macro0.776; Dice for artifacts 0.552; IoU macro 0.725 and IoU for artifacts 0.451).CONCLUSION: the developed model is a good basis for the implementation of a full-fledged solution, on the basis of which a system can be developed to assist doctors in finding and evaluating the replacement of tissue structures and determining metastatic lymph node lesions, detecting artifacts and evaluating the quality of digital images.

A study on the correlation between M2 macrophages and regulatory T cells in the progression of colorectal cancer.

M2 macrophages and regulatory T cells (Tregs) can promote tumors and development by inhibiting the anti-tumor immune response. This study investigated the effect of CD163-positive M2 macrophages and Foxp3-positive Tregs in the progression of colorectal cancer and lymph node metastasis. It also investigated the correlation between M2 macrophages and Tregs. Postoperative tissue specimens and clinical data were collected from 197 patients with colorectal cancer who underwent initial surgical treatment in The Second Ward of Colorectal Surgery of the First Affiliated Hospital of Jinzhou Medical University from March 2020 to December 2020. Immunohistochemical methods were used to detect the expression levels of CD163 protein-labeled M2 macrophages and Foxp3 protein-labeled Tregs in colorectal cancer tissues, matched paracancer tissues, and lymph node tissues. The correlation between CD163 and Foxp3 in cancer tissues and lymph node tissues were analyzed, as well as the relationship between clinicopathological characteristics and preoperative tumor markers. M2 macrophages and Tregs were importantly positively correlated in cancer and lymph node tissues, which significantly increased in cancer and metastatic lymph node tissues. Interestingly, M2 macrophages in non-metastatic lymph nodes also increased significantly in patients with metastatic lymph nodes. In addition, both CD163 and Foxp3 were upregulated with increasing tumor node metastasis stage, depth of infiltration, and lymphatic metastasis; and both were positively correlated with carcinoembryonic antigen. CD163 may be a good predictor of pre-metastatic status of colorectal cancer lymph nodes. carcinoembryonic antigen affects the distribution of M2 macrophages and Tregs in colorectal cancer. There is a certain correlation between the two types of cells. It is possible that M2 macrophages, together with suppressor Tregs cells, promote an immunosuppressive environment.