Genomic progression for local invasion of cutaneous squamous cell carcinoma from the superficial to the deep portion.

Cutaneous squamous cell carcinoma (cSCC) is the second most common skin cancer. While many treatments exist, our understanding of its genomic progression, especially from the epidermis to the deep dermis, remains limited. This study aims to identify genetic mutations associated with the progression of cSCC into the deep dermis, providing insights into its aggressive behavior and high-risk features. We performed high-depth whole-exome sequencing on 12 cSCC tissues, along with paired normal tissues from six patients, using microdissection techniques. The mutational analysis focused on identifying alterations enriched during cSCC progression. Gene Ontology enrichment analysis, immunohistochemical assays, and external single-cell RNA data were utilized for validation. A total of 8863 non-synonymous somatic mutations were identified in 4092 genes across the superficial and deep portions of cSCCs. Analysis of deep portion mutations revealed a significant correlation with gene ontology biological processes, particularly cell junction organization, and cell-cell adhesion. Clonal mutations in these processes were more prevalent in the deep portions, indicating their impact on the cSCC mutation landscape. Genetic evolution analysis identified 29 causal genes associated with dermal invasion in cSCC. We highlight somatic mutations in cSCC, revealing heterogeneity between superficial and deep regions. Altered genes in cell junction organization and cell-cell adhesion emerged as pivotal in dermal invasion. We identified 29 causal genes primarily in deep tumor regions. Our findings emphasize analyzing multiple tumor regions to capture varied mutational landscapes. These insights advance our understanding of cSCC progression, emphasizing genetic and cellular changes during tumor evolution.

The Quality of Life and Psychosocial Impact on Female Pattern Hair Loss.

BACKGROUND: Alopecia, a benign dermatologic condition affecting both genders, particularly harms female patients due to psychosocial effects. Female pattern hair loss (FPHL), the primary cause of hair loss in women, lacks sufficient Korean epidemiological studies examining its psychosocial aspects. OBJECTIVE: This study aimed to explore FPHL's psychosocial impacts, including quality of life (QoL), depression, anxiety, medical consumption, and hair loss factors in Korean women. METHODS: A total of 202 patients with FPHL were interviewed using a validated questionnaire to assess the QoL, psychological impact, and pattern of medical consumption. The severity of hair loss was evaluated using the "basic and specific (BASP) classification" by dermatologists. The Hair-Specific Skindex-29 (HSS29) was used to assess the QoL and Beck depression inventory (BDI), Beck anxiety inventory (BAI) to evaluate psychological aspects, and medical expenses and the number of clinic visits to determine medical consumption. RESULTS: The global HSS29 score of FPHL was 40.97±18.92, indicating a notable impact on QoL. The mean BDI and BAI scores were 14.47 and 10.06, respectively. In multivariable regression analysis, HSS29, BDI, and BAI scores were most affected by the severity of hair loss (p<0.001). CONCLUSION: FPHL damages the psychosocial aspects of patients, such as QoL, depression, and medical consumption, according to the severity of hair loss.

A Case of Perineal Hemangioma, External Genitalia Malformations, Lipomyelomeningocele, Vesicorenal Abnormalities, Imperforate Anus, and Skin Tag (PELVIS) Syndrome with Extensive Perineal Infantile Hemangioma.

PELVIS syndrome describes the constellation of perineal hemangioma, external genitalia malformations, lipomyelomeningocele, vesicorenal abnormalities, imperforate anus, and skin tag. A 2-month-old girl presented with infantile hemangioma on her perineum and genitalia with imperforate anus, rectovaginal fistula and perineal skin tag at birth. Under the impression of PELVIS syndrome, consequential spinal sonography was conducted and revealed an intrasacral meningocele without clinical neurologic deficit. The anorectal malformation was surgically corrected, she was taking oral propranolol for the cutaneous lesion, and she showed improvement and no complications.

Valorization of leftover green tea residues through conversion to bioactive peptides using probiotics-aided anaerobic digestion.

Bioactive peptides (BPs) are protein fragments that benefit human health. To assess whether leftover green tea residues (GTRs) can serve as a resource for new BPs, we performed in silico proteolysis of GTRs using the BIOPEP database, revealing a wide range of BPs embedded in GTRs. Comparative genomics and the percentage of conserved protein analyses enabled us to select a few probiotic strains for GTR hydrolysis. The selected probiotics digested GTRs anaerobically to yield GTR-derived peptide fractions. To examine whether green tea (GT) peptide fractions could be potential mediators of host-microbe interactions, we comprehensively screened agonistic and antagonistic activities of 168 human G protein-coupled receptors (GPCRs). NanoLC-MS/MS analysis and thin-layer chromatography allowed the identification of peptide sequences and the composition of glycan moieties in the GTRs. Remarkably, GT peptide fractions produced by Lactiplantibacillus plantarum APsulloc 331261, a strain isolated from GT, showed a potent-binding activity for P2RY6, a GPCR involved in intestinal homeostasis. Therefore, this study suggests the potential use of probiotics-aided GTR hydrolysates as postbiotic BPs, providing a biological process for recycling GTRs from agro-waste into renewable resources as health-promoting BPs.

Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method.

OBJECTIVES: To develop a facial growth prediction model incorporating individual skeletal and soft tissue characteristics. MATERIALS AND METHODS: Serial longitudinal lateral cephalograms were collected from 303 children (166 girls and 137 boys), who had never undergone orthodontic treatment. A growth prediction model was devised by applying the multivariate partial least squares (PLS) algorithm, with 161 predictor variables. Response variables comprised 78 lateral cephalogram landmarks. Multiple linear regression analysis was performed to investigate factors influencing growth prediction errors. RESULTS: Using the leave-one-out cross-validation method, a PLS model with 30 components was developed. Younger age at prediction resulted in greater prediction error (0.03 mm/y). Further, prediction error increased in proportion to the growth prediction interval (0.24 mm/y). Girls, subjects with Class II malocclusion, growth in the vertical direction, skeletal landmarks, and landmarks on the maxilla were associated with more accurate prediction results than boys, subjects with Class I or III malocclusion, growth in the anteroposterior direction, soft tissue landmarks, and landmarks on the mandible, respectively. CONCLUSIONS: The prediction error of the prediction model was proportional to the remaining growth potential. PLS growth prediction seems to be a versatile approach that can incorporate large numbers of predictor variables to predict numerous landmarks for an individual subject.

A Genomics-Based Semirational Approach for Expanding the Postbiotic Potential of Collagen Peptides Using Lactobacillaceae.

Food-derived bioactive peptides (BPs) have received considerable attention as postbiotics for human gut health. Here we used a genomics-based semirational approach to expand the postbiotic potential of collagen peptides (CPs) produced from probiotic fermentation. In silico digestion revealed distinct BPs embedded in fish collagen in a protease-dependent manner. Anaerobic digestion of collagen by representative Lactobacillaceae species revealed differential substrate utilization and collagen degradation patterns. Nanoliquid chromatography-mass spectrometry analysis of CPs showed that each species exhibited different cleavage patterns and unique peptide profiles. Remarkably, the 1-10 kDa CPs produced by Lacticaseibacillus paracasei showed agonistic activities toward G protein-coupled receptor 35 (GPR35). These CPs could repair intestinal epithelium through the GPR35-mediated extracellular signal-regulated protein kinase (ERK) 1/2 signaling pathway, suggesting that probiotic-aided collagen hydrolysates can serve as postbiotics for host-microbe interactions. Therefore, this study provides an effective strategy for the rapid screening of CPs for gut health in the gastrointestinal tract.

Histologic analysis according to HER2 gene status in HER2 2 + invasive breast cancer: a study of 280 cases comparing ASCO/CAP 2013 and 2018 guideline recommendations.

The American Society of Clinical Oncology and College of American Pathologists guidelines for HER2 testing in breast cancer (BC) have been updated with more stringent criteria regarding immunohistochemistry (IHC) 2 + interpretation. The aim of our study was to determine HER2 status in IHC 2 + cases based on 2013 and 2018 guidelines and to investigate specific histologic characteristics that might predict HER2 status in tumors with equivocal IHC staining. Two hundred eighty BC cases reported as IHC 2 + and 24 cases reported as non-IHC 2 + were reviewed with 12 histologic characteristics. Of the IHC 2 + cases based on 2013 guideline, 21% were reclassified to IHC 1 + when applying the 2018 guidelines. Consequently, it led to an 8% increase of HER2 amplification rate in 2018 IHC 2 + group. Seven characteristics were significantly associated with prediction of HER2 amplification in IHC 2 + BCs, including high tumor-infiltrating lymphocytes (TILs), distinct cellular membrane, no apical snout, large nuclear size, nuclear size variation, high nuclear grade, and tubule formation < 10%. Using these criteria, the presence of four or more characteristics significantly indicates HER2 amplification. Moreover, four characteristics among them, including high TILs, distinct cellular membrane, nuclear size variation, and high nuclear grade, were also associated with HER2 amplification in non-IHC 2 + cases, demonstrating their predictive value as complements to IHC. In conclusion, we provide specific morphologic features that will improve pathologist performance in identifying more HER2-positive BCs. We further suggest an algorithm for trastuzumab therapy decisions using a combination of histomorphologic evaluation and the updated 2018 guidelines.

Evaluation of an automated superimposition method based on multiple landmarks for growing patients.

OBJECTIVES: To determine if an automated superimposition method using six landmarks (Sella, Nasion, Porion, Orbitale, Basion, and Pterygoid) would be more suitable than the traditional Sella-Nasion (SN) method to evaluate growth changes. MATERIALS AND METHODS: Serial lateral cephalograms at an average interval of 2.7 years were taken on 268 growing children who had not undergone orthodontic treatment. The T1 and T2 lateral images were manually traced. Three different superimposition methods: Björk's structural method, conventional SN, and the multiple landmark (ML) superimposition methods were applied. Bjork's structural method was used as the gold standard. Comparisons among the superimposition methods were carried out by measuring the linear distances between Anterior Nasal Spine, point A, point B, and Pogonion using each superimposition method. Multiple linear regression analysis was performed to identify factors that could affect the accuracy of the superimpositions. RESULTS: The ML superimposition method demonstrated smaller differences from Björk's method than the conventional SN method did. Greater differences among the cephalometric landmarks tested resulted when: the designated point was farther from the cranial base, the T1 age was older, and the more time elapsed between T1 and T2. CONCLUSIONS: From the results of this study in growing patients, the ML superimposition method seems to be more similar to Björk's structural method than the SN superimposition method. A major advantage of the ML method is likely to be that it can be applied automatically and may be just as reliable as manual superimposition methods.

The Prognostic Value of Sex-Determining Region Y-Box 2 and CD8+ Tumor-Infiltrating Lymphocytes in Limited-Stage Small-Cell Lung Cancer.

BACKGROUND: Sex-determining region Y-box 2 (SOX2) is a transcriptional factor that drives embryonic stem cells to neuroendocrine cells in lung development and is highly expressed in small-cell lung cancer (SCLC). However, the prognostic role of SOX2 and its relationship with tumor-infiltrating lymphocytes (TILs) has not been determined in SCLC. Herein, we assessed the expression of SOX2 and CD8+ TILs to obtain insights into the prognostic role of SOX2 and CD8+ TILs in limited-stage (LS)-SCLC. METHODS: A total of 75 patients with LS-SCLC was enrolled. The SOX2 expression and CD8+ TILs were evaluated by immunohistochemistry. RESULTS: High SOX2 and CD8+ TIL levels were identified in 52 (69.3%) and 40 (53.3%) patients, respectively. High SOX2 expression was correlated with increased density of CD8+ TILs (p = 0.041). Unlike SOX2, high CD8+ TIL numbers were associated with significantly longer progression-free survival (PFS; 13.9 vs. 8.0 months, p = 0.014). Patients with both high SOX2 expression and CD8+ TIL numbers (n = 29, 38.7%) had significantly longer PFS and overall survival (OS) compared to those from the other groups (median PFS 19.3 vs. 8.4 months; p = 0.002 and median OS 35.7 vs. 17.4 months; p = 0.004, respectively). Multivariate Cox regression analysis showed that the combination of high SOX2 expression and CD8+ TIL levels was an independent good prognostic factor for OS (HR = 0.471, 95% CI, 0.250-0.887, p = 0.02) and PFS (HR = 0.447, 95% CI, 0.250-0.801, p = 0.007) in SCLC. CONCLUSIONS: Evaluation of the combination of SOX2 and CD8+ TIL levels may be of a prognostic value in LS-SCLC.

Prognostic value of noggin protein expression in patients with resected gastric cancer.

BACKGROUND: Noggin and RNA-binding protein for multiple splicing 2 (RBPMS2) are known to regulate the expression of smooth muscle cells, endothelial cells, and osteoblasts. However, the prognostic role of combined Noggin and RBPMS2 expression in resected gastric cancer (GC) is unclear. METHODS: A total of 163 patients with GC who underwent gastrectomy were included in this study. The expression of Noggin and RBPMS2 proteins in tumor cells at the tumor center and invasive front of resected GC was evaluated by immunohistochemistry, and in conjunction with clinicopathological parameters the patient survival was analyzed. RESULTS: RBPMS2 protein expression was high at the tumor center (n = 86, 52.8%) and low at the invasive front (n = 69, 42.3%), while Noggin protein expression was high in both tumor center (n = 91, 55.8%) and the invasive front (n = 90, 55.2%). Noggin expression at the invasive front and tumor center was significantly decreased in advanced T stage, non-intestinal-type (invasive front, P = 0.008 and P <  0.001; tumor center lesion, P = 0.013 and P = 0.001). RBPMS2 expression at the invasive front was significantly decreased in non-intestinal-type and positive lymphatic invasion (P <  0.001 and P = 0.013). Multivariate analysis revealed that high Noggin protein expression of the invasive front was an independent prognostic factor for overall survival (hazard ratio [HR], 0.58; 95% confidence interval [CI]; 0.35-0.97, P <  0.036), but not at the tumor center (HR, 1.35; 95% CI; 0.81-2.26, P = 0.251). CONCLUSIONS: Our study indicates that high Noggin expression is a crucial prognostic factor for favorable outcomes in patients with resected GC.

Evaluation of automated cephalometric analysis based on the latest deep learning method.

OBJECTIVES: To compare an automated cephalometric analysis based on the latest deep learning method of automatically identifying cephalometric landmarks (AI) with previously published AI according to the test style of the worldwide AI challenges at the International Symposium on Biomedical Imaging conferences held by the Institute of Electrical and Electronics Engineers (IEEE ISBI). MATERIALS AND METHODS: This latest AI was developed by using a total of 1983 cephalograms as training data. In the training procedures, a modification of a contemporary deep learning method, YOLO version 3 algorithm, was applied. Test data consisted of 200 cephalograms. To follow the same test style of the AI challenges at IEEE ISBI, a human examiner manually identified the IEEE ISBI-designated 19 cephalometric landmarks, both in training and test data sets, which were used as references for comparison. Then, the latest AI and another human examiner independently detected the same landmarks in the test data set. The test results were compared by the measures that appeared at IEEE ISBI: the success detection rate (SDR) and the success classification rates (SCR). RESULTS: SDR of the latest AI in the 2-mm range was 75.5% and SCR was 81.5%. These were greater than any other previous AIs. Compared to the human examiners, AI showed a superior success classification rate in some cephalometric analysis measures. CONCLUSIONS: This latest AI seems to have superior performance compared to previous AI methods. It also seems to demonstrate cephalometric analysis comparable to human examiners.

A Fibroma of Tendon Sheath Causing Carpal Tunnel Syndrome: A Case Report of an Atypical Clinical Presentation.

Fibroma of the tendon sheath is a benign slow-growing fibrous tumor. Although rare, cases occurring in the upper extremities usually involve the fingers. It appears as a well-defined, roundor oval-shaped mass originating from the flexor tendon. Abundant fibrous stroma makes fibromas appear as a low intensity mass in all MRI sequences. Most of the fibromas manifest as painless soft tissue masses. Herein, we report a case of fibroma of the tendon sheath with an unusual clinical presentation, triggering carpal tunnel syndrome during wrist movement.

Heterotopic pancreas: the added value of endoscopic ultrasound with Computed Tomography for diagnosis.

AIMS: To investigate the added value of endoscopic ultrasound (EUS) with computed tomography (CT) in distinguishing heterotopic pancreas (HP) from other pathologies, when gastroduodenal subepithelial tumors (SETs) are suspected on an upper endoscopic examination. MATERIAL AND METHODS: We retrospectively included 54 consecutive patients with gastroduodenal SETs who had undergone both abdominal CT and EUS within a 3-month interval. All EUS, endoscopy, and CT images were reviewed and evaluated in a blinded manner by an endoscopist and a radiologist, respectively. Univariate and multivariate analyses were performed to identify EUS/CT findings related to HP. Diagnostic performance of CT only and CT combined with EUS was compared for distinguishing HP from other SETs. RESULTS: We included patients with HP (n=17; pathologically confirmed, n=6), gastrointestinal stromal tumor (GIST, n=24), and other pathologies (n=13). Multivariate logistic regression analyses revealed that irregular margin, origin from submucosal layer, internal microcystic-tubular structure, and oval shape were independent factors in diagnosing HP by EUS, whereas a micro-lobulating contour was the only significantly independent factor in CT. In assessments of diagnostic performance, CT combined with EUS showed significantly superior diagnostic performance in comparison with CT only (area under the curve, 0.961 vs. 0.833, p=0.028) in the consensus interpretation of an endoscopist and a radiologist. CONCLUSIONS: CT combined with EUS with a comprehensive and complementary interpretation showed significant added value compared to CT only in diagnosing gastroduodenal HP.

Recent glycemic control can predict the progressive motor deficits of acute subcortical infarction with diabetes or prediabetes.

BACKGROUND AND PURPOSE: The predictors of progressive motor deficits in acute subcortical infarctions are still controversial. It is not known whether glycemic control influences on stroke progression. METHODS: A total of 268 consecutive patients with diabetes or prediabetes who had acute (< 24 h) subcortical infarction were enrolled. (1) All patients were divided into 4 groups by quartile of glycated hemoglobin (HbA1c). (2) Only the patients with diabetes were divided by effective glycemic control. Progressive motor deficits were prospectively captured and defined as an increase of motor score ≥ 1 on the upper or lower limb items of the National Institute of Health Stroke Scale within 72 h from stroke onset. RESULTS: Progressive motor deficits occur in 8/78 (10.3%) for ≤ 5.9, 15/61 (24.6%) for 6.0-6.4, 16/62 (25.8%) for 6.5-7.4, and 30/67 (44.8%) for ≥ 7.5. In diabetic patients alone, those occur in 5/37 (13.5%) for ≤ 6.5, 10/42 (23.8%) for 6.6-7.0, 12/42 (28.6%) for 7.1-8.0, and 24/50 (48.0%) for ≥ 8.1. An adjusted OR of progressive motor deficits was 2.61 (95% confidence interval [CI] 0.98-7.00, P = .056) for 6.0-6.4, 3.42 (95% CI 1.27-9.18, P = .015) for 6.5-7.4, and 6.65 (95% CI 2.38-18.62, P < .001) for ≥ 7.5. In diabetic patients alone, those were 3.15 (95% CI 0.89-11.15, P = .075) for 6.6-7.0, 2.90 (95% CI 0.79-10.61, P = .107) for 7.1-8.0, and 4.17 (95% CI 1.07-16.25, P = .038) for ≥ 8.1. The optimal cutoff value of HbA1c was 6.65% in discriminating progressive motor deficits. CONCLUSION: Increased HbA1c was associated with higher incidence of progressive motor deficits in acute subcortical infarction with diabetes and prediabetes.

Evaluation of an automated superimposition method for computer-aided cephalometrics.

OBJECTIVES: To evaluate a new superimposition method compatible with computer-aided cephalometrics and to compare superimposition error to that of the conventional Sella-Nasion (SN) superimposition method. MATERIALS AND METHODS: A total of 283 lateral cephalometric radiographs were collected and cephalometric landmark identification was performed twice by the same examiner at a 3-month interval. The second tracing was superimposed on the first tracing by both the SN superimposition method and the new, proposed method. The proposed method not only relied on SN landmarks but also minimized the differences between four additional landmarks: Porion, Orbitale, Basion, and Pterygoid. The errors between the landmarks of the duplicate tracings oriented by the two superimposition methods were calculated at Anterior Nasal Spine, Point A, Point B, Pogonion, and Gonion. The paired t-test was used to find any statistical difference in the superimposition errors by the two superimposition methods and to investigate whether there existed clinically significant differences between the two methods. RESULTS: The proposed method demonstrated smaller superimposition errors than did the conventional SN superimposition method. When comparisons between the two superimposition methods were made with a 1-mm error range, there were clinically significant differences between them. CONCLUSIONS: The proposed method that was compatible with computer-aided cephalometrics might be a reliable superimposition method for superimposing serial cephalometric images.

How much deep learning is enough for automatic identification to be reliable?

OBJECTIVES: To determine the optimal quantity of learning data needed to develop artificial intelligence (AI) that can automatically identify cephalometric landmarks. MATERIALS AND METHODS: A total of 2400 cephalograms were collected, and 80 landmarks were manually identified by a human examiner. Of these, 2200 images were chosen as the learning data to train AI. The remaining 200 images were used as the test data. A total of 24 combinations of the quantity of learning data (50, 100, 200, 400, 800, 1600, and 2000) were selected by the random sampling method without replacement, and the number of detecting targets per image (19, 40, and 80) were used in the AI training procedures. The training procedures were repeated four times. A total of 96 different AIs were produced. The accuracy of each AI was evaluated in terms of radial error. RESULTS: The accuracy of AI increased linearly with the increasing number of learning data sets on a logarithmic scale. It decreased with increasing numbers of detection targets. To estimate the optimal quantity of learning data, a prediction model was built. At least 2300 sets of learning data appeared to be necessary to develop AI as accurate as human examiners. CONCLUSIONS: A considerably large quantity of learning data was necessary to develop accurate AI. The present study might provide a basis to determine how much learning data would be necessary in developing AI.

High Endothelial Venule with Concomitant High CD8+ Tumor-Infiltrating Lymphocytes Is Associated with a Favorable Prognosis in Resected Gastric Cancer.

CD8+ tumor-infiltrating lymphocytes (TILs) play a major role in antitumor immunity. High endothelial venules (HEVs) are related to diverse immune cells in solid tumors. We analyzed CD8+ and Foxp3+ TILs in combination with HEVs to determine their prognostic role in advanced gastric cancer (AGC). We enrolled 157 patients with AGC in this study. The densities of CD8+ TILs and Foxp3+ TILs were calculated using immunohistochemical staining. HEVs were evaluated by MECA-79 expression. HEVs were identified in 60 (38.2%) cases and was significantly associated with an increased number of CD8+ TILs (p = 0.027) but not of Foxp3+ TILs (p = 0.455) and CD20+ TILs (p = 0.163). A high CD8+/HEV+ level was significantly associated with nodal metastasis (p = 0.048). In survival analysis, patients with high CD8+/HEV+ levels demonstrated the longest overall survival (OS) (p = 0.015). Furthermore, a high CD8+/HEV+ level was an independent prognostic factor in AGC (p = 0.011; hazard ratio (HR) = 0.435; 95% confidence interval (CI) = 0.245-0.837). HEVs were found to play an important role in antitumor immunity associated with CD8+ TILs in AGC. This analysis of HEVs and CD8+ TILs helps stratify patients with AGC and sheds light on tumor immunity.

Risk of metachronous gastric neoplasm occurrence during intermediate-term follow-up period after endoscopic submucosal dissection for gastric dysplasia.

After endoscopic resection (ER) of gastric dysplasia, metachronous gastric neoplasm (MGN) appears to have an incidence rate similar to that detected after ER of early gastric cancer (EGC). We investigated whether the risk of MGN after ER for gastric dysplasia is different between patients with low-grade dysplasia (LGD) and high-grade dysplasia (HGD). Between March 2011 and December 2016, 198 patients with LGD (LGD group) and 46 patients with HGD (HGD group) who underwent ER were included in the study. During a median follow-up of 2.5 years, MGNs developed in 21 patients (10.6%) in the LGD group and in 6 patients (13.0%) in the HGD group. Hazard ratios (HRs) for MGNs (HR, 1.45; P = 0.425) and for metachronous HGD or gastric cancer (HR, 2.41; P = 0.214) in the HGD group were not different than those of the LGD group. However, considering patients without Helicobacter pylori infection, those in the HGD group had a significantly increased risk of metachronous HGD or gastric cancer compared to those in the LGD group (HR in HGD-group, 5.23; P = 0.044). These results indicate that meticulous surveillance endoscopy is needed to detect MGNs after ER of gastric dysplasia, especially in patients with HGD, including those without H. pylori infection.

Automated identification of cephalometric landmarks: Part 2-Might it be better than human?

OBJECTIVES: To compare detection patterns of 80 cephalometric landmarks identified by an automated identification system (AI) based on a recently proposed deep-learning method, the You-Only-Look-Once version 3 (YOLOv3), with those identified by human examiners. MATERIALS AND METHODS: The YOLOv3 algorithm was implemented with custom modifications and trained on 1028 cephalograms. A total of 80 landmarks comprising two vertical reference points and 46 hard tissue and 32 soft tissue landmarks were identified. On the 283 test images, the same 80 landmarks were identified by AI and human examiners twice. Statistical analyses were conducted to detect whether any significant differences between AI and human examiners existed. Influence of image factors on those differences was also investigated. RESULTS: Upon repeated trials, AI always detected identical positions on each landmark, while the human intraexaminer variability of repeated manual detections demonstrated a detection error of 0.97 ± 1.03 mm. The mean detection error between AI and human was 1.46 ± 2.97 mm. The mean difference between human examiners was 1.50 ± 1.48 mm. In general, comparisons in the detection errors between AI and human examiners were less than 0.9 mm, which did not seem to be clinically significant. CONCLUSIONS: AI showed as accurate an identification of cephalometric landmarks as did human examiners. AI might be a viable option for repeatedly identifying multiple cephalometric landmarks.