Purpose: The molecular classification of breast cancer is crucial for effective treatment. The emergence of digital pathology has ushered in a new era in which weakly supervised learning leveraging whole-slide images has gained prominence in developing deep learning models because this approach alleviates the need for extensive manual annotation. Weakly supervised learning was employed to classify the molecular subtypes of breast cancer. Materials and Methods: Our approach capitalizes on two whole-slide image datasets: one consisting of breast cancer cases from the Korea University Guro Hospital (KG) and the other originating from The Cancer Genomic Atlas dataset (TCGA). Furthermore, we visualized the inferred results using an attention-based heat map and reviewed the histomorphological features of the most attentive patches. Results: The KG+TCGA-trained model achieved an area under the receiver operating characteristics value of 0.749. An inherent challenge lies in the imbalance among subtypes. Additionally, discrepancies between the two datasets resulted in different molecular subtype proportions. To mitigate this imbalance, we merged the two datasets, and the resulting model exhibited improved performance. The attentive patches correlated well with widely recognized histomorphologic features. The triple-negative subtype has a high incidence of high-grade nuclei, tumor necrosis, and intratumoral tumor-infiltrating lymphocytes. The luminal A subtype showed a high incidence of collagen fibers. Conclusion The artificial intelligence (AI) model based on weakly supervised learning showed promising performance. A review of the most attentive patches provided insights into the predictions of the AI model. AI models can become invaluable screening tools that reduce costs and workloads in practice.

This study analyzed dental treatments under general anesthesia at the Department of Pediatric Dentistry of Pusan National University Dental Hospital from 2014 to 2023. The study results indicated an increased use of general anesthesia, primarily for younger patients, highlighting the increasing need for specialized healthcare professionals in pediatric dentistry. The study population predominantly consisted of male patients and those residing in Gyeongsangnam-do province. The most common treatment for dental caries was restorative, followed by surgical procedures and orthodontic interventions. The number of surgical procedures abruptly increased after 2020. However, pulp treatments and restorations using stainless steel or zirconia crowns decreased over time, with increased resin restorations. Individuals with disabilities more frequently undergo repeat dental procedures under general anesthesia, indicating potential barriers to access for this population. This study emphasizes the need for comprehensive and equitable dental care for all individuals, particularly those with disabilities. Future research should focus on expanding the scope of the analysis to include multiple institutions and exploring long-term outcomes of patients receiving dental treatment under general anesthesia to inform policy development and best practices in pediatric dentistry.

This study examined the transverse relationship between the maxilla and mandible in children with mixed dentition. The study focused on the primary second molar and the permanent first molar in relation to the anteroposterior skeletal patterns using cone-beam computed tomography (CBCT). A total of 102 patients from the Pediatric Dentistry Department at Pusan Dental Hospital were classified into three skeletal groups (Class I, Ⅱ, Ⅲ) based on the ANB angle (angle formed by A-point-nasion-B-point). CBCT scans were analyzed to assess the transverse dimensions of basal bone and dento-alveolar measurements. The results showed that Class Ⅲ patients exhibited a significantly narrower maxillary basal bone compared with Class I and Ⅱ patients. The mandibular basal width was not significantly different between the classes. For primary second molars, Class Ⅲ patients showed significantly narrower maxillary alveolar bone width at the root bifurcation level (51.7 ± 2.5 mm, p < 0.05) compared with Class I and II patients. For permanent first molars, the maxillary occlusal fossa distance was smallest in Class II (45.4 ± 2.4 mm, p < 0.05), and was significantly different from Class I and Class Ⅲ. Maxillary first molar inclination was more lingually inclined in Class Ⅱ patients (99.0 ± 4.2°, p < 0.05) compared with Class Ⅲ patients, whereas Class Ⅲ patients exhibited more buccal inclination. This study highlights the correlation between transverse discrepancies and anteroposterior skeletal classifications, with Class Ⅲ showing a narrower maxillary base and Class Ⅱ patients presenting greater lingual compensation. These findings may aid pediatric dentists in diagnosing transverse relationships in mixed dentition.

This study aims to analyze anatomical and structural changes related to abnormal eruption of the maxillary first premolar in children, focusing on the correlation between maxillary sinus pneumatization volume and positional shifts in the premolar and canine. Twenty-nine children, with Hellman dental age IIIA, exhibiting unilateral abnormal eruption of the maxillary first premolar, were selected. Maxillary sinus morphology and the positions of tooth buds were assessed through CBCT images, and 3D-scanned diagnostic models were used to evaluate the upper arch form. The affected and control sides were compared in terms of sinus pneumatization and the positions of the first premolar and canine tooth buds. Maxillary sinus pneumatization on the affected side was significantly increased (p = 0.0202), while no significant difference was found in the total sinus volume (p = 0.9694). On the affected side, the apex of the first premolar was positioned more anteriorly (p = 0.0029) and more palatally (p = 0.0011) than that on the unaffected side. Additionally, the apex of the canine was positioned more posteriorly on the affected side compared to that on the unaffected side (p = 0.0039). Model analysis revealed that the anteroposterior total arch length on the affected side was longer than that on the control side (p < 0.0001), while the transverse width did not show any statistically significant difference. These findings suggest a potential relationship between maxillary sinus pneumatization and the abnormal eruption path of the first premolar, as well as possible effects on the eruption of canines.

Purpose: The molecular classification of breast cancer is crucial for effective treatment. The emergence of digital pathology has ushered in a new era in which weakly supervised learning leveraging whole-slide images has gained prominence in developing deep learning models because this approach alleviates the need for extensive manual annotation. Weakly supervised learning was employed to classify the molecular subtypes of breast cancer. Materials and Methods: Our approach capitalizes on two whole-slide image datasets: one consisting of breast cancer cases from the Korea University Guro Hospital (KG) and the other originating from The Cancer Genomic Atlas dataset (TCGA). Furthermore, we visualized the inferred results using an attention-based heat map and reviewed the histomorphological features of the most attentive patches. Results: The KG+TCGA-trained model achieved an area under the receiver operating characteristics value of 0.749. An inherent challenge lies in the imbalance among subtypes. Additionally, discrepancies between the two datasets resulted in different molecular subtype proportions. To mitigate this imbalance, we merged the two datasets, and the resulting model exhibited improved performance. The attentive patches correlated well with widely recognized histomorphologic features. The triple-negative subtype has a high incidence of high-grade nuclei, tumor necrosis, and intratumoral tumor-infiltrating lymphocytes. The luminal A subtype showed a high incidence of collagen fibers. Conclusion The artificial intelligence (AI) model based on weakly supervised learning showed promising performance. A review of the most attentive patches provided insights into the predictions of the AI model. AI models can become invaluable screening tools that reduce costs and workloads in practice.

This study analyzed dental treatments under general anesthesia at the Department of Pediatric Dentistry of Pusan National University Dental Hospital from 2014 to 2023. The study results indicated an increased use of general anesthesia, primarily for younger patients, highlighting the increasing need for specialized healthcare professionals in pediatric dentistry. The study population predominantly consisted of male patients and those residing in Gyeongsangnam-do province. The most common treatment for dental caries was restorative, followed by surgical procedures and orthodontic interventions. The number of surgical procedures abruptly increased after 2020. However, pulp treatments and restorations using stainless steel or zirconia crowns decreased over time, with increased resin restorations. Individuals with disabilities more frequently undergo repeat dental procedures under general anesthesia, indicating potential barriers to access for this population. This study emphasizes the need for comprehensive and equitable dental care for all individuals, particularly those with disabilities. Future research should focus on expanding the scope of the analysis to include multiple institutions and exploring long-term outcomes of patients receiving dental treatment under general anesthesia to inform policy development and best practices in pediatric dentistry.

This study examined the transverse relationship between the maxilla and mandible in children with mixed dentition. The study focused on the primary second molar and the permanent first molar in relation to the anteroposterior skeletal patterns using cone-beam computed tomography (CBCT). A total of 102 patients from the Pediatric Dentistry Department at Pusan Dental Hospital were classified into three skeletal groups (Class I, Ⅱ, Ⅲ) based on the ANB angle (angle formed by A-point-nasion-B-point). CBCT scans were analyzed to assess the transverse dimensions of basal bone and dento-alveolar measurements. The results showed that Class Ⅲ patients exhibited a significantly narrower maxillary basal bone compared with Class I and Ⅱ patients. The mandibular basal width was not significantly different between the classes. For primary second molars, Class Ⅲ patients showed significantly narrower maxillary alveolar bone width at the root bifurcation level (51.7 ± 2.5 mm, p < 0.05) compared with Class I and II patients. For permanent first molars, the maxillary occlusal fossa distance was smallest in Class II (45.4 ± 2.4 mm, p < 0.05), and was significantly different from Class I and Class Ⅲ. Maxillary first molar inclination was more lingually inclined in Class Ⅱ patients (99.0 ± 4.2°, p < 0.05) compared with Class Ⅲ patients, whereas Class Ⅲ patients exhibited more buccal inclination. This study highlights the correlation between transverse discrepancies and anteroposterior skeletal classifications, with Class Ⅲ showing a narrower maxillary base and Class Ⅱ patients presenting greater lingual compensation. These findings may aid pediatric dentists in diagnosing transverse relationships in mixed dentition.

This study aims to analyze anatomical and structural changes related to abnormal eruption of the maxillary first premolar in children, focusing on the correlation between maxillary sinus pneumatization volume and positional shifts in the premolar and canine. Twenty-nine children, with Hellman dental age IIIA, exhibiting unilateral abnormal eruption of the maxillary first premolar, were selected. Maxillary sinus morphology and the positions of tooth buds were assessed through CBCT images, and 3D-scanned diagnostic models were used to evaluate the upper arch form. The affected and control sides were compared in terms of sinus pneumatization and the positions of the first premolar and canine tooth buds. Maxillary sinus pneumatization on the affected side was significantly increased (p = 0.0202), while no significant difference was found in the total sinus volume (p = 0.9694). On the affected side, the apex of the first premolar was positioned more anteriorly (p = 0.0029) and more palatally (p = 0.0011) than that on the unaffected side. Additionally, the apex of the canine was positioned more posteriorly on the affected side compared to that on the unaffected side (p = 0.0039). Model analysis revealed that the anteroposterior total arch length on the affected side was longer than that on the control side (p < 0.0001), while the transverse width did not show any statistically significant difference. These findings suggest a potential relationship between maxillary sinus pneumatization and the abnormal eruption path of the first premolar, as well as possible effects on the eruption of canines.

Purpose: The molecular classification of breast cancer is crucial for effective treatment. The emergence of digital pathology has ushered in a new era in which weakly supervised learning leveraging whole-slide images has gained prominence in developing deep learning models because this approach alleviates the need for extensive manual annotation. Weakly supervised learning was employed to classify the molecular subtypes of breast cancer. Materials and Methods: Our approach capitalizes on two whole-slide image datasets: one consisting of breast cancer cases from the Korea University Guro Hospital (KG) and the other originating from The Cancer Genomic Atlas dataset (TCGA). Furthermore, we visualized the inferred results using an attention-based heat map and reviewed the histomorphological features of the most attentive patches. Results: The KG+TCGA-trained model achieved an area under the receiver operating characteristics value of 0.749. An inherent challenge lies in the imbalance among subtypes. Additionally, discrepancies between the two datasets resulted in different molecular subtype proportions. To mitigate this imbalance, we merged the two datasets, and the resulting model exhibited improved performance. The attentive patches correlated well with widely recognized histomorphologic features. The triple-negative subtype has a high incidence of high-grade nuclei, tumor necrosis, and intratumoral tumor-infiltrating lymphocytes. The luminal A subtype showed a high incidence of collagen fibers. Conclusion The artificial intelligence (AI) model based on weakly supervised learning showed promising performance. A review of the most attentive patches provided insights into the predictions of the AI model. AI models can become invaluable screening tools that reduce costs and workloads in practice.

This study analyzed dental treatments under general anesthesia at the Department of Pediatric Dentistry of Pusan National University Dental Hospital from 2014 to 2023. The study results indicated an increased use of general anesthesia, primarily for younger patients, highlighting the increasing need for specialized healthcare professionals in pediatric dentistry. The study population predominantly consisted of male patients and those residing in Gyeongsangnam-do province. The most common treatment for dental caries was restorative, followed by surgical procedures and orthodontic interventions. The number of surgical procedures abruptly increased after 2020. However, pulp treatments and restorations using stainless steel or zirconia crowns decreased over time, with increased resin restorations. Individuals with disabilities more frequently undergo repeat dental procedures under general anesthesia, indicating potential barriers to access for this population. This study emphasizes the need for comprehensive and equitable dental care for all individuals, particularly those with disabilities. Future research should focus on expanding the scope of the analysis to include multiple institutions and exploring long-term outcomes of patients receiving dental treatment under general anesthesia to inform policy development and best practices in pediatric dentistry.