METHODOLOGY: We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC.
RESULTS: We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods.
CONCLUSION: We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to other reported FS methods.
Aim: This study is aimed at evaluating and comparing the remineralisation of early enamel caries on the occlusal surface of permanent posterior teeth using ICDAS II caries scoring system and DIAGNOdent Pen (DDPen) after remineralisation with Colgate Duraphat® and GC Tooth Mousse Plus®.
Materials and Methods: Extracted posterior teeth (N = 120) with incipient occlusal caries were included in this study. The occlusal surface of each tooth was scored using DDPen and ICDAS II scoring before remineralisation. Then, remineralisation of the teeth of the experimental group was carried out using either CPP-ACP-F or fluoride varnish. After the remineralisation procedures, the occlusal surface of each tooth was again scored using DDPen and ICDAS II scoring. The teeth were then fixed in dental stone blocks and sectioned longitudinally for histological examination using a stereomicroscope. Statistical analysis was performed to calculate the sensitivity and specificity of DDPen and ICDAS II to detect remineralisation and compare with the gold standard histological examination.
Results: According to ICDAS-II scores, a significant difference was noted in GC Tooth Mousse Plus® and Duraphat® study samples, whereas the difference between the pre-and post-remineralisation of the control group was not significant. According to the DDPen score criteria, a statistically significant difference was noted among all study groups; however, a greater significance level was noted in the GC Tooth Mousse Plus® and Duraphat® study samples compared with the control group. The Spearman's rank correlation of ICDAS-II and DDPen with Downer's histological score (gold standard) revealed a higher association of DDPen score (.738) as compared to ICDAS-II scores (.430).
Conclusion: The study concluded that both ICDAS II and DDPen could detect remineralisation of early enamel occlusal caries. DDPen was more sensitive than ICDAS-II to detect remineralisation compared with the Downers histological scores.