To evaluate an annotation-free deep learning (DL) approach for the image-level detection of periapical bone rarefactions (PBRs) on panoramic radiographs (PRs). A retrospective dataset of 2,527 PRs was classified at the image level based on expert consensus using internationally accepted radiographic criteria. Multiple pretrained convolutional neural network (CNN) and vision transformer (ViT) architectures were evaluated under different modeling strategies, including fine-tuning and attention mechanisms. Model performance was assessed using accuracy, recall, specificity, and F1 score. Inferential comparisons were performed using nonparametric statistical tests. CNN-based models consistently outperformed ViT architectures in binary classification of PBRs. The fine-tuned Xception model achieved the highest overall performance, with an F1-score of 64.7% and low variability across repeated runs. Analyses were restricted to Classes A and B due to class imbalance constraints, then multiclass evaluation was not performed at this stage. Annotation-free DL demonstrated feasibility for binary image-level detection of PBRs on PRs, reducing dependence on labor-intensive spatial annotations while maintaining clinically interpretable behavior. Multiclass classification remains a target for investigation with balanced datasets. The approach supports scalable image-level analysis under clinically realistic conditions, although external validation is still required to confirm generalizability.
Objective: Epidemiological and survival data on osteosarcoma of the jaws (OSJ) in Latin America remain scarce. We characterized the clinicopathological, radiographic, treatment‐related, and survival features of OSJ in Latin America. Methods: This multicenter case series involved 22 institutions from Brazil, Chile, Argentina, Colombia, Venezuela, Uruguay, and Mexico. Demographic, clinical, radiographic, histopathological, treatment, and survival data were analyzed using descriptive and inferential statistical methods. Survival outcomes were assessed using Kaplan–Meier analysis and Cox regression models. Results: A total of 119 OSJ cases were included. The median age was 33 years, with a female predominance (58%), and the mandible was the most commonly affected site (68.9%). A mixed radiographic appearance predominated and was frequently accompanied by cortical perforation and a sunburst periosteal reaction. Histologically, the osteoblastic subtype accounted for 63.5% of cases. Surgical resection was the main treatment modality (71.2%). Increasing age ( p = 0.034) and multimodal or nonsurgical management ( p = 0.023) were independently associated with poorer survival. The estimated overall survival rates were 67.5% at 12 months and 37.5% at 60 months. Conclusion: Data corroborate previous literature and demonstrate that OSJ in Latin America predominantly affects adults and exhibits aggressive patterns. Surgical management remains central to improving survival whenever it is technically feasible.
28 September 2026 in International Journal of Imaging Systems and Technology
This study aimed to compare an annotation‐free deep learning (DL) model with human evaluators for detecting periapical bone rarefactions (PBRs) on panoramic radiographs (PRs) and to assess the clinical acceptability of AI‐supported dental imaging. A mixed‐methods diagnostic validation was conducted using 238 PRs, equally distributed between images with ( n = 119) and without ( n = 119) PBRs. Model performance was compared with that of four calibrated dentists: two oral and maxillofacial radiologists and two endodontists. The reference standard was based on internationally accepted radiographic criteria applied by calibrated researchers under expert supervision, with final classifications verified by the principal investigator. Diagnostic performance was assessed using standard diagnostic metrics, chance‐corrected agreement statistics and receiver operating characteristic analysis, while clinical acceptability was explored through questionnaires and thematically analysed semi‐structured interviews. At the sensitivity‐oriented decision threshold of 0.27, the DL model achieved a sensitivity of 0.924, a specificity of 0.109, an accuracy of 0.517, a precision of 0.509 and an F 1‐score of 0.657. Threshold‐independent binary discrimination was moderate (ROC‐AUC = 0.726). Human evaluators showed more balanced profiles, with accuracy ranging from 0.655 to 0.752 and F 1‐scores from 0.654 to 0.779. Professional perception was generally favourable, although responses varied among evaluators. The annotation‐free DL model showed high sensitivity and moderate discrimination for PBR detection. Although low specificity limits autonomous use, the findings support annotation‐free learning as a potentially scalable strategy, warranting further training with larger and more heterogeneous datasets.