1
|
Huang X, Yang Z, Qin W, Li X, Su S, Huang J. Construction of machine learning models based on transrectal ultrasound combined with contrast-enhanced ultrasound to predict preoperative regional lymph node metastasis of rectal cancer. Heliyon 2024; 10:e26433. [PMID: 38390137 PMCID: PMC10882134 DOI: 10.1016/j.heliyon.2024.e26433] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 02/12/2024] [Accepted: 02/13/2024] [Indexed: 02/24/2024] Open
Abstract
Purpose Constructing a machine learning model based on transrectal ultrasound (TRUS) combined with contrast-enhanced ultrasound (CEUS) to predict preoperative regional lymph node metastasis (RLNM) of rectal cancer and provide new references for decision-making. Materials and methods 233 patients with rectal cancer were enrolled and underwent TRUS and CEUS prior to surgery. Clinicopathological and ultrasound data were collected to analyze the correlation of RLNM status, clinical features and ultrasound parameters. A 75% training set and 25% test set were utilized to construct seven machine learning algorithms. The DeLong test was used to assess the model's diagnostic performance, then chose the best one to predict RLNM of rectal cancer. Results The diagnostic performance was most dependent on the following: MMT difference (36), length (30), location (29), AUC ratio (27), and PI ratio (24). The prediction accuracy, sensitivity, specificity, precision, and F1 score range of KNN, Bayes, MLP, LR, SVM, RF, and LightGBM were (0.553-0.857), (0.000-0.935), (0.600-1.000), (0.557-0.952), and (0.617-0.852), respectively. The LightGBM model exhibited the optimal accuracy (0.857) and F1 score (0.852). The AUC for machine learning analytics were (0.517-0.941, 95% CI: 0.380-0.986). The LightGBM model exhibited the highest AUC (0.941, 95% CI: 0.843-0.986), though no statistic significant showed in comparison with the SVM, LR, RF, and MLP models (P > 0.05), it was significantly higher than that of the KNN and Bayes models (P < 0.05). Conclusion The LightGBM machine learning model based on TRUS combined with CEUS may help predict RLNM prior to surgery and provide new references for clinical treatment in rectal cancer.
Collapse
Affiliation(s)
- Xuanzhang Huang
- Department of Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, PR China
| | - Zhendong Yang
- Department of Radiation Oncology, The First Affiliated Hospital of Guangxi Medical University, Nanning, PR China
| | - Wanyue Qin
- Department of Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, PR China
| | - Xigui Li
- Department of Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, PR China
| | - Shitao Su
- Department of Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, PR China
| | - Jianyuan Huang
- Department of Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, PR China
| |
Collapse
|
2
|
Wu YL, Zhang QQ, Shen SH, Li DD, Zhu YL, Zhang HZ. [The risk factors for regional lymph node metastasis of mismatch repair deficient colorectal cancer]. Zhonghua Zhong Liu Za Zhi 2021; 43:1082-1087. [PMID: 34695899 DOI: 10.3760/cma.j.cn112152-20210109-00032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
Objective: To explore the risk factors for regional lymph node (RLN) metastasis in colorectal cancer patients with mismatch repair deficiency (dMMR). Methods: The data of 357 dMMR colorectal cancer patients who underwent surgery in National Cancer Center from January 2012 to December 2016 was retrospectively analyzed. Univariate and multivariate analysis were used to identify the risk factors for RLN metastasis. Results: Among the 357 patients, 204 were male and 153 were female, 61.6% (220/357) lesion located in right half colon, while the other 16.2% (58/357) located in rectum. Univariate analysis showed that tumor size, differentiation, lymphovascular invasion, tumor deposit, postoperative pathologic T stage (pT), the number of negative lymph nodes and the expression of the MSH6 protein were significantly associated with RLN metastasis (P<0.05). All of the patients with well differentiation tumors (15 patients) or staged pT1 (13 patients) had no RLN metastasis. Multivariate analysis showed that tumor differentiation (OR=2.582, 95%CI=1.567-4.274, P<0.001), pT (OR=3.778, 95%CI=1.448-12.960, P=0.015) and the expression of MSH6 protein (OR=2.188, 95%CI=1.159-4.401, P=0.021) were independent risk factors for RLN metastasis. Conclusions: The postoperative pT stage, tumor differentiation and the expression of MSH6 protein are independent risk factors for RLN metastasis of dMMR colorectal cancer. Preoperative assessment of these factors may further improve the accuracy of predicting the risk of RLN metastasis.
Collapse
Affiliation(s)
- Y L Wu
- Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Q Q Zhang
- Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - S H Shen
- Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - D D Li
- Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Y L Zhu
- Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - H Z Zhang
- Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| |
Collapse
|
3
|
Duan M, Zhang L, Wang Y, Fan Y, Liu S, Yu Q, Huang L, Zhou F. Computational pan-cancer characterization of model-based quantitative transcription regulations dysregulated in regional lymph node metastasis. Comput Biol Med 2021; 135:104571. [PMID: 34166881 DOI: 10.1016/j.compbiomed.2021.104571] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2021] [Revised: 06/09/2021] [Accepted: 06/09/2021] [Indexed: 10/21/2022]
Abstract
Cancer is one of the major causes of mortality worldwide. Regional lymph node metastasis is an important mechanism during the spread of human cancers, in which transcription regulation plays an essential role. This study formulated a regression-model-based quantitative transcription regulation (mqTrans) between one mRNA gene and multiple transcription factors (TFs). Computational pan-cancer screening was carried out to detect the quantitative dysregulation of transcription regulation in the regional lymph node metastasis of 18 cancer types. Only a few metastasis-dysregulated mqTrans models were shared among the cancer types. The mRNA genes of the metastasis-dysregulated mqTrans models were not differentially expressed in regional lymph node metastasis. The experimental data suggested that mqTrans technology provided a complementary approach to the evaluation of transcription regulation mechanisms and may facilitate its quantitative investigation in other phenotypes.
Collapse
Affiliation(s)
- Meiyu Duan
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China
| | - Lei Zhang
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China
| | - Yueying Wang
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; Department of Epidemiology and Biostatistics, School of Public Health, Jilin University, Changchun, Jilin Province, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China
| | - Yusi Fan
- College of Software, Jilin University, Changchun, Jilin, 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China
| | - Shuai Liu
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China
| | - Qiong Yu
- Department of Epidemiology and Biostatistics, School of Public Health, Jilin University, Changchun, Jilin Province, China
| | - Lan Huang
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China
| | - Fengfeng Zhou
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, 130012, China.
| |
Collapse
|
4
|
van der Kamp MF, Muntinghe FOW, Iepsma RS, Plaat BEC, van der Laan BFAM, Algassab A, Steenbakkers RJHM, Witjes MJH, van Dijk BAC, de Bock GH, Halmos GB. Predictors for distant metastasis in head and neck cancer, with emphasis on age. Eur Arch Otorhinolaryngol 2021; 278:181-90. [PMID: 32542417 DOI: 10.1007/s00405-020-06118-0] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2020] [Accepted: 06/08/2020] [Indexed: 12/16/2022]
Abstract
PURPOSE Distant metastasis (DM) in patients with head and neck squamous cell carcinoma (HNSCC) is uncommon, but strongly deteriorates prognosis. Controversy exists regarding age as a predictor for the presence and development of DM. The aim of this study was to investigate age and other predictors for DM in HNSCC patients. METHODS From 1413 patients diagnosed with a primary HNSCC between 1999 and 2010 in a tertiary referral centre, patient, disease and pathological characteristics were extracted from patient files. Uni- and multivariable Cox regression analyses were performed to identify risk factors for DM as primary outcome. RESULTS DM occurred in 131 (9.3%) patients, of which 27 (1.9%) were diagnosed simultaneously with the primary tumour, 27 (1.9%) were diagnosed synchronous, and 77 (5.4%) were diagnosed metachronous. The most common site of DM was lung (51.1%), followed by bone (19.1%) and liver (11.5%). Multivariable analysis identified male gender (HR = 1.95, 95% CI 1.23-3.10) hypopharyngeal tumours (HR = 3.28, 95% CI 1.75-6.14), advanced T-stage (HR = 1.61, 95% CI 1.09-2.38), poor differentiation grade (HR = 2.49, 95% CI 1.07-5.78), regional lymph node metastasis (HR = 5.35, 95% CI 3.25-8.79) and extranodal extension of regional lymph nodes metastasis (HR = 3.06, 95% CI 1.39-6.72) as independent prognostic factors for the presence or development of DM. No relation with age was found. CONCLUSION Age is not related to the presence or development of DM. This study emphasizes the importance of screening for DM, especially in males, patients with hypopharyngeal tumours, advanced T-stage, histopathological poor differentiation grade, regional lymph node metastasis and extranodal extension.
Collapse
|
5
|
WANG Q, CUI Y, REN L, WANG H, WANG Z, WANG H, FAN H. Suspected Regional Lymph Node Metastasis in Hepatic Alveolar Echinococcosis: A Case Report. Iran J Parasitol 2020; 15:138-141. [PMID: 32489386 PMCID: PMC7244840] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 10/31/2022]
Abstract
There is no direct evidence to support the existence of regional lymph node metastatic routes in hepatic alveolar echinococcosis, and only a few literature have been reported. There was a case of hepatic alveolar echinococcosis suspected of metastasis of regional lymph node in Clinical Center for Hydatidosis, Qinghai Province, China. The patient was a 24-yr-old male from pastoral area of Seda County, Sichuan Province, China in 2018. He was admitted to the hospital for physical examination and had no special discomfort. Preoperative examination showed liver occupancy and regional lymph node enlargement in the space between liver and stomach. Hepatectomy and lymph node resections were performed. Postoperative pathological results showed that both primary and metastatic lesion were of alveolar echinococcosis. Recovery of patient was good without complications and recurrence. In this case, metastasis was considered because the liver lesion was not directly connected to the lymph node. However, the case was still suspected due to the lack of pathological examination of other lymph nodes in the lymphatic return pathway. Regional lymph node metastasis may be one of the metastatic ways of alveolar echinococcosis.
Collapse
Affiliation(s)
- Qiang WANG
- Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai 810001, P.R.China
| | - Yu CUI
- Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai 810001, P.R.China
| | - Li REN
- Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai 810001, P.R.China, Qinghai Province Key Laboratory of Hydatid Disease Research, Xining, Qinghai 810001, P.R.China
| | - Haijiu WANG
- Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai 810001, P.R.China, Qinghai Province Key Laboratory of Hydatid Disease Research, Xining, Qinghai 810001, P.R.China
| | - Zhixin WANG
- Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai 810001, P.R.China, Qinghai Province Key Laboratory of Hydatid Disease Research, Xining, Qinghai 810001, P.R.China
| | - Hu WANG
- Health Commission of Qinghai Province, Xining, Qinghai 810001, P.R.China
| | - Haining FAN
- Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai 810001, P.R.China, Qinghai Province Key Laboratory of Hydatid Disease Research, Xining, Qinghai 810001, P.R.China,Correspondence
| |
Collapse
|
6
|
Yang Z, Liu Z. The efficacy of 18F-FDG PET/CT-based diagnostic model in the diagnosis of colorectal cancer regional lymph node metastasis. Saudi J Biol Sci 2019; 27:805-811. [PMID: 32127755 PMCID: PMC7042675 DOI: 10.1016/j.sjbs.2019.12.017] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2019] [Revised: 11/16/2019] [Accepted: 12/09/2019] [Indexed: 02/08/2023] Open
Abstract
In order to assess the efficacy of 18F-FDG PET/CT-based diagnostic model in diagnosing colorectal cancer (CRC) lymph node metastasis (LNM), the 18F-FDG PET/CT medical records of CRC patients were acquired, and the CRC regional LNM diagnostic model was constructed through the combination of image and grain factors of 18F-FDG PET/CT. The specific analysis methods include univariate analysis, multivariate analysis, ROC curve analysis, and statistical analysis. The research results showed statistical differences in TNM staging, intestinal obstructions, tumor infiltration, regional lymph node (LN) SUVmax, regional LN minimum dimension, and remote metastasis between the CRC patients in the LNM positive group and the LNM negative group. Through the comparisons between the diagnostic model proposed in the research and other diagnostic methods, it was found that the AUC (95%CI) and sensitivity of the proposed diagnostic model were the highest, the comprehensive diagnostic efficacy of the diagnostic model was optimal. Therefore, it was concluded that the diagnostic model was of significant application values, which provided the basis for subsequent clinical diagnosis of CRC.
Collapse
Affiliation(s)
- Zhiguang Yang
- Nuclear Medicine Department, Shengjing Hospital Affiliated to China Medical University, Shenyang 110000, China
| | - Zhaoyu Liu
- Radiology Department, Shengjing Hospital Affiliated to China Medical University, Shenyang 110000, China
| |
Collapse
|
7
|
Ulmer A, Kofler L. [Sentinel node biopsy and lymph node dissection in the era of new systemic therapies for malignant melanoma]. Hautarzt 2019; 70:864-9. [PMID: 31605168 DOI: 10.1007/s00105-019-04491-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Abstract
BACKGROUND Recently, adjuvant therapies with checkpoint inhibitors and BRAF/MEK inhibitors have become available for patients with malignant melanoma and microscopic nodal disease. Meanwhile the number of complete nodal dissections for a melanoma-positive sentinel node (SN) have decreased significantly. OBJECTIVE The authors discuss the significance of sentinel node biopsy (SNB) and early lymph node dissection in the era of adjuvant systemic therapy for stage III melanoma. MATERIALS AND METHODS Current publications and recommendations were evaluated. RESULTS Complete nodal dissection for a positive SN significantly reduces the risk of regional nodal relapse. However, neither SNB nor complete nodal dissection following a positive SN are associated with a benefit in survival. With the availability of novel adjuvant systemic treatment strategies for stage III melanoma, SNB has become an even more important part of modern staging diagnostics. Thus, detection of early dissemination of melanoma cells into the SN as well as the quantification of the tumor load are decisive for further therapy planning. CONCLUSION Accurate assessment of the regional lymph node status by SNB is becoming even more important in the era of novel effective adjuvant therapies for microscopic nodal disease. Whether complete lymph node dissection is performed in patients with a positive SN needs to be assessed individually. In the case of "active nodal surveillance" instead of surgery, long-term close follow-up in specialized centers, including ultrasonographic controls, is required.
Collapse
|