Application of deep learning artificial intelligence technique to the classification of clinical orthodontic photos.

BACKGROUND: Taking facial and intraoral clinical photos is one of the essential parts of orthodontic diagnosis and treatment planning. Among the diagnostic procedures, classification of the shuffled clinical photos with their orientations will be the initial step while it was not easy for a machine to classify photos with a variety of facial and dental situations. This article presents a convolutional neural networks (CNNs) deep learning technique to classify orthodontic clinical photos according to their orientations. METHODS: To build an automated classification system, CNNs models of facial and intraoral categories were constructed, and the clinical photos that are routinely taken for orthodontic diagnosis were used to train the models with data augmentation. Prediction procedures were evaluated with separate photos whose purpose was only for prediction. RESULTS: Overall, a 98.0% valid prediction rate resulted for both facial and intraoral photo classification. The highest prediction rate was 100% for facial lateral profile, intraoral upper, and lower photos. CONCLUSION: An artificial intelligence system that utilizes deep learning with proper training models can successfully classify orthodontic facial and intraoral photos automatically. This technique can be used for the first step of a fully automated orthodontic diagnostic system in the future.

Dual-Blocking of PI3K and mTOR Improves Chemotherapeutic Effects on SW620 Human Colorectal Cancer Stem Cells by Inducing Differentiation.

Cancer stem cells (CSCs) have tumor initiation, self-renewal, metastasis and chemo-resistance properties in various tumors including colorectal cancer. Targeting of CSCs may be essential to prevent relapse of tumors after chemotherapy. Phosphatidylinositol-3-kinase (PI3K) and mammalian target of rapamycin (mTOR) signals are central regulators of cell growth, proliferation, differentiation, and apoptosis. These pathways are related to colorectal tumorigenesis. This study focused on PI3K and mTOR pathways by inhibition which initiate differentiation of SW620 derived CSCs and investigated its effect on tumor progression. By using rapamycin, LY294002, and NVP-BEZ235, respectively, PI3K and mTOR signals were blocked independently or dually in colorectal CSCs. Colorectal CSCs gained their differentiation property and lost their stemness properties most significantly in dual-blocked CSCs. After treated with anti-cancer drug (paclitaxel) on the differentiated CSCs cell viability, self-renewal ability and differentiation status were analyzed. As a result dual-blocking group has most enhanced sensitivity for anti-cancer drug. Xenograft tumorigenesis assay by using immunodeficiency mice also shows that dual-inhibited group more effectively increased drug sensitivity and suppressed tumor growth compared to single-inhibited groups. Therefore it could have potent anti-cancer effects that dual-blocking of PI3K and mTOR induces differentiation and improves chemotherapeutic effects on SW620 human colorectal CSCs.

Profilin 2 promotes migration, invasion, and stemness of HT29 human colorectal cancer stem cells.

We investigated the role of profilin 2 in the stemness, migration, and invasion of HT29 cancer stem cells (CSCs). Increased and decreased levels of profilin 2 significantly enhanced and suppressed the self-renewal, migration, and invasion ability of HT29 CSCs, respectively. Moreover, profilin 2 directly regulated the expression of stemness markers (CD133, SOX2, and ß-catenin) and epithelial mesenchymal transition (EMT) markers (E-cadherin and snail). CD133 and ß-catenin were up-regulated by overexpression of profilin 2 and down-regulated by depletion of profilin 2. SOX2 was decreased by profilin 2 depletion. E-cadherin was not influenced by profilin 2- overexpression but increased by profilin 2- knockdown. The expression of snail was suppressed by profilin 2- knockdown. We speculated that stemness and the EMT are closely linked through profilin 2-related pathways. Therefore, this study indicates that profilin 2 affects the metastatic potential and stemness of colorectal CSCs by regulating EMT- and stemness-related proteins.

Outcome of reclassification of World Health Organization (WHO) class III under International Society of Nephrology-Renal Pathology Society (ISN-RPS) classification: retrospective observational study.

The outcome of systemic lupus erythematosus (SLE) is largely influenced by the existence of lupus nephritis (LN), and its histologic classification guides the treatment and prognosis of SLE. International Society of Nephrology-Renal Pathology Society (ISN-RPS) announced a revised classification of LN in 2004. The present study investigated the differential outcome of World Health Organization (WHO) class III LN when reclassified according to ISN-RPS classification. Forty-three patients with biopsy-proven WHO class III LN at a single tertiary hospital were included in the study. Baseline characteristics at the time of renal biopsy and clinical data during follow-up were obtained from medical records. Renal response to treatment at one-year follow-up was analyzed in three ways; complete response (CR), partial response (PR), and no response (NR). Of 43 patients with previous WHO class III LN, 12 cases were reclassified into ISN-RPS class IV (9 cases of class IV-S and 3 cases of IV-G). Baseline characteristics at the time of renal biopsy were not different between the reclassified class IV and remaining class III LN group except activity index on renal histology, which was significantly elevated in the reclassified class IV group (4.90 vs. 6.75; P = 0.02). Significantly higher number of patients with remaining class III LN achieved CR to treatment than those with reclassified class IV LN at one-year follow-up since initial biopsy (CR: PR: NR; 16:7:7 vs. 3:1:8; P = 0.032). Our study suggests that the ISN-RPS classification is more advantageous in predicting renal outcome and guiding treatment when evaluating previously classified WHO class III LN.

Comparative Analysis of the Differences in Dentofacial Morphology According to the Tongue and Lip Pressure.

The aim of this study was to evaluate the effects of the tongue and lip pressure on dentofacial morphology. The subjects comprised 194 patients with malocclusion. Anterior and posterior tongue elevation and lip pressures were evaluated using the Iowa Oral Performance Instrument (IOPI) device. The lateral cephalograms of each subject were traced and digitized to perform the analysis. Statistical analysis was used to investigate the relationship between perioral muscle force and the cephalometric variables. Anterior and posterior tongue pressure was both higher in males than in females. No sex difference in lip pressure was observed. The group with a low posterior tongue pressure showed a short ramus height, short posterior facial height, and clockwise-rotated mandible. On the other hand, lip pressure had a significant influence on maxillary incisor angulation. Skeletal pattern was not found to be significantly related with lip pressure. The anterior tongue pressure appeared as a mixed pattern of the two results. Tongue pressure was related to skeletal measurements, such as short posterior facial height, and lip pressure was related to the angulation of the anterior teeth. This study suggests that there may be differences in dentofacial morphology according to the differences in perioral muscle force.