• Journal of Periodontal and Implant Science
• /
• v.53 no.1
• /
• pp.38-53
• /
• 2023

Purpose: The current Classification of Periodontal and Peri-Implant Diseases and Conditions, published and disseminated in 2018, involves some difficulties and causes diagnostic conflicts due to its criteria, especially for inexperienced clinicians. The aim of this study was to design a decision system based on machine learning algorithms by using clinical measurements and radiographic images in order to determine and facilitate the staging and grading of periodontitis. Methods: In the first part of this study, machine learning models were created using the Python programming language based on clinical data from 144 individuals who presented to the Department of Periodontology, Faculty of Dentistry, Süleyman Demirel University. In the second part, panoramic radiographic images were processed and classification was carried out with deep learning algorithms. Results: Using clinical data, the accuracy of staging with the tree algorithm reached 97.2%, while the random forest and k-nearest neighbor algorithms reached 98.6% accuracy. The best staging accuracy for processing panoramic radiographic images was provided by a hybrid network model algorithm combining the proposed ResNet50 architecture and the support vector machine algorithm. For this, the images were preprocessed, and high success was obtained, with a classification accuracy of 88.2% for staging. However, in general, it was observed that the radiographic images provided a low level of success, in terms of accuracy, for modeling the grading of periodontitis. Conclusions: The machine learning-based decision system presented herein can facilitate periodontal diagnoses despite its current limitations. Further studies are planned to optimize the algorithm and improve the results.

• 대한두경부종양학회:학술대회논문집
• /
• 2001.11a
• /
• pp.278-281
• /
• 2001

• Journal of Gastric Cancer
• /
• v.21 no.1
• /
• pp.1-3
• /
• 2021

• Tuberculosis and Respiratory Diseases
• /
• v.47 no.3
• /
• pp.339-346
• /
• 1999

Background : Non-small cell lung carcinoma is a common tumor with a poor prognosis. Of all malignancies, it is the main cause of death for male and female patients in the Western world. Resection remains the most effective treatment when feasible. Accurate description and classification of the extent of cancer growth are important in planning treatment, estimating prognosis, evaluating end results of therapy, and exchanging information on human cancer research. Until effective systemic therapy is available for non-small cell lung cancer, development of new treatment strategies depends on knowledge of the end results achieved for carefully staged groups of patients in the lung cancer populations. For these reasons, we investigated the survival rate in radically resected non-small cell lung cancer patients by newly revised staging system adopted by the American Joint Committee on Cancer and the Union Internationale Contre le Cancer. Methods: Clinical, surgical-pathologic and follow-up informations on 84 consecutive, previously untreated, patients who received their primary treatment for non-small cell lung cancer were investigated. Staging definitions for the T(primary tumor), N(reginal lymph node), and M(distant metastasis) components were according to the International Staging System for Lung Cancer. Death from any causes was the primary target of the evaluation. Results: The median survival rates were as follows; stage I ;79.1 months, stage II ;47.3 months, stage IIIa; 22.7 months, stage IIIb; 16.1 months, and stage IV;15.2 months versus newly revised stage Ia;58.5 months, stage I b;76.0 months, stage IIa; not available, stage IIb;43.0 months, stage IIIa;22.5 months, stage IIIb; 16.1 months, and stage IV;15.2 months. The survival rates were not significantly different between old and newly revised staging system. Cumulative percent survival at 36months after treatment was 100% in stage Ia, 80% in stage Ib, not available in stage IIa, 26 % in stage IIb, and 21 % in stage m a respectively. Conclusions: Although these data were not significantly different statistically, the newly revised lung cancer staging system might be more promising for the accurate evaluation of the prognosis in the non-small cell lung caner patients.

• Journal of Gastric Cancer
• /
• v.1 no.1
• /
• pp.32-37
• /
• 2001

Purpose: Three subgroups of stage II stomach cancer (T1N2M0, T2N1M0, T3N0M0) by UICC-TNM staging system show obvious survival difference to each other, which becomes the pitfall of the current staging system. We analyzed the survival and relapse pattern of stage II stomach cancer patients in three subgroups retrospectively to prove the need for change in staging system. Materials and Methods: From July 1989 to December 1995, curative gastric resection was performed in 1,037 patients with gastric adenocarcinoma, and among them 268 patients ($26\%$) were in stage II. The number in each of subgroups (T1N2M0, T2N1M0, and T3N0M0) were 17, 139 and 112 respectively. Survival and relapse pattern were analyzed and median follow up period was 46 months. Results: The 3-year cumulative survival rates of T1N2M0, T2N1M0, and T3N0M0 were $50\%,\;80\%,\;and\;76\%$ respectively (p=0.001). And the 3-year cumulative survival rates of T1N2M0 was comparable to those of 2 subgroups of stage IIIa (T2N2M0, T3N1M0), $47\%\;and\;45\%$ (p>0.05). Peritoneal recurrence was the most frequent in T3N0M0. And hematogenous spread was more frequent in T2N1M0 while nodal spread was more frequent in T1N2M0. Ten out of 17 cases of T1N2M0 died of recurrence. Most of them showed submucosal tumor with depressed lesion and mean tumor size was 3.3 cm. Conclusions: Up-staging of T1N2M0 should be considered because it has the lowest survival rate and the worst prognosis among the three subgroups of Stage II stomach cancer patients. In early gastric cancer patients with high-risk factors (large tumor size, invasion into the submucosal layer, and lymphatic vessel involvement), lymph node dissection and postoperative adjuvant therapy is recommended in an attempt to prevent recurrence in the form of lymph node metastasis.

• Journal of Gastric Cancer
• /
• v.3 no.3
• /
• pp.134-138
• /
• 2003

Purpose: The lymph node (N) classification in the International Union Against Cancer (UICC) TNM staging system for gastric adenocarcinomas has been revised from the anatomic sites of metastatic lymph nodes to the number of metastatic lymph nodes. The purpose of this study was to investigate the proper number of retrieved lymph nodes for applying the new TNM staging system. Materials and Methods: We retrospectively studied 267 patients who had undergone a curative resection performed by one surgeon for gastric adenocarcinomas from March 1993 to December 1996 at Korea University Guro Hospital. We compared the old staging system to the new one and analyzed the number of retrieved and metastatic lymph nodes. We also analyzed the number of retrieved and metastatic lymph nodes according to the operative procedure and the extent of the lymphadenectomy, as well as the correlation of lymph-node metastasis to the number of retrieved lymph nodes. Results: The mean number of retrieved lymph nodes was $34.27\pm14.18$, of those $6.85\pm6.24$ were metastatic. According to the extent of the lymphadenectomy, these numbers were $17.8\pm9.3\;and\;7.0\pm5.3$ in D1, $33.1\pm14.6\;and\;3.0\pm3.0$ in $D1+\alpha$, $33.9\pm13.8\;and\;7.5\pm6.2$ in D2, and $40.6\pm13.3\;and\;7.9\pm7.5$ in $D2+\alpha$. There was no correlation between the percentage of the specimen with positive lymph nodes and the number of retrieved lymph nodes, but a logistic regres sion analysis showed that the probability of lymph-node metastasis increased as the number of retrieved lymph nodes increased. Conclusion: The mean number of retrieved lymph nodes was about 34. Although by logistic regression analysis, the probability of lymph-node metastasis increased as the number of retrieved lymph nodes increased, we failed to determine the minimum number of nodes retrieved during a lymphadenectomy needed for accurate staging in a gastric adenocarcinoma. Further study is required to identify the optimum number of lymph nodes that need to be retrieved.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.3
• /
• pp.1429-1434
• /
• 2014

Background: Owing to the variability of histopathological features and biological behaviour in gastric carcinoma, a great number of categorisation methods such as classical histopathologic grading, Lauren classification, the TNM staging system and the newly presented Goseki grading method are used by pathologists and other scientists. In our study, we aimed to investigate whether Goseki grade and tumour location have an effects on survival of gastric cancer cases. Materials and Methods: Eighty-four patients with gastric adenocarcinoma were covered in the investigation. The importance of Goseki grading system and tumour location were analysed in addition to the TNM staging and other conventional prognostic parameters. Results: The median survival time in our patients was 35 months (minimum: 5, maximum: 116). According to our findings, there was no relation between survival and tumour size (p=0.192) or classical histological type (p=0.270). In contrast, the Goseki grade and tumour location significantly correlated with survival (p=0.007 and p<0.001, respectively). Additionally, tumours of the intestinal type had a longer median survival time (60.0 months) than diffuse tumours (24.0 months). Conclusions: In addition to the TNM staging system, tumour location and the Goseki grading system may be used as significant prognostic parameters in patients with gastric cancer.

• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.570-570
• /
• 2022

• Tuberculosis and Respiratory Diseases
• /
• v.43 no.3
• /
• pp.331-338
• /
• 1996

Background : Lung cancer continues to be the leading cause of cancer death in the United States and it's incidence has been rapidly increasing in Korea, too. The overall cure rate for non-small cell lung cancer(NSCLC) is approximately 10%, and the cure is generally achieved by surgery. Unfortunately, however, less than 15% of all patients and less than 25% of those who present with localized disease are candidates for curative surgical resection. So preoperative staging evaluation followed by curative resection has a major role in determining the long tenn prognosis of NSCLC patients. Therefore, we have conducted this study to compare pre-operative and post-operative staging and the long-tenn relapse-free survival rates in NSCLC patients according to its stage. Methods : We analyzed the medical records of 217 NSCLC patients who were operated on for curative resection in Seoul National University Hospital, retrospectively. Among them, 170 patients who were completely resected were selected to determine the long term relapse-free survival rates. Results : Among 217 NSCLC patients, men were 157 and women were 30. The median age was 58 and the difference between men and women was not found. The discrepancy rate between preoperative and postoperative staging was 40.1%. Its major cause was due to the difference of nodal staging. The 3-year relapse-free survival rates were 73%, 53% and 48% in stage I, II and IIIa, respectively. There was no difference of relapse-free duration in recurred patients according to the stage or histologic types. Conclusion : The postoperative pathologic staging determines the long tenn prognosis of patients with NSCLC after surgery, but current preoperative clinical staging can not predict the postoperative pathologic staging correctly. So the improved modality of staging system is required to predict the pathologic staging more correctly.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.21
• /
• pp.9529-9534
• /
• 2014

Background: Cancer staging enables planning for the best treatments, evaluation of prognosis, and predictions for survival. The Collaborative Stage (CS) system makes it possible to significantly reduce the proportion of patients labeled at an "unknown" stage as well as discrepancies among different staging systems. This study aims to analyze the factors that influence the accuracy and validity of CS data. Materials and Methods: Data were randomly selected (233 cases) from stomach cancer cases enrolled for CS survey at the Korea Central Cancer Registry. Two questionnaires were used to assess CS values for each case and to review the cancer registration environment for each hospital. Data were analyzed in terms of the relationships between the time spent for acquisition and registration of CS information, environments relating to cancer registration in the hospitals, and document sources of CS information for each item. Results: The time for extracting and registering data was found to be shorter when the hospitals had prior experience gained from participating in a CS pilot study and when they were equipped with full-time cancer registrars. Evaluation of the CS information according to medical record sources found that the percentage of items missing for Site Specific Factor (SSF) was 30% higher than for other CS variables. Errors in CS coding were found in variables such as "CS Extension," "CS Lymph Nodes," "CS Metastasis at Diagnosis," and "SSF25 Involvement of Cardia and Distance from Esophagogastric Junction (EGJ)." Conclusions: To build CS system data that are reliable for cancer registration and clinical research, the following components are required: 1) training programs for medical records administrators; 2) supporting materials to promote active participation; and 3) format development to improve registration validity.