eprintid: 5663 rev_number: 8 eprint_status: archive userid: 2 dir: disk0/00/00/56/63 datestamp: 2023-02-01 23:30:13 lastmod: 2023-02-01 23:30:13 status_changed: 2023-02-01 23:30:13 type: article metadata_visibility: show creators_name: Fatima, Anum creators_name: Shafi, Imran creators_name: Afzal, Hammad creators_name: Mahmood, Khawar creators_name: Díez, Isabel de la Torre creators_name: Lipari, Vivian creators_name: Brito Ballester, Julién creators_name: Ashraf, Imran creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: vivian.lipari@uneatlantico.es creators_id: julien.brito@uneatlantico.es creators_id: title: Deep Learning-Based Multiclass Instance Segmentation for Dental Lesion Detection ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: unincol_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uninipr_produccion_cientifica divisions: unic_produccion_cientifica full_text_status: public keywords: Mask-RCNN; MobileNet; deep learning; dental disease detection abstract: Automated dental imaging interpretation is one of the most prolific areas of research using artificial intelligence. X-ray imaging systems have enabled dental clinicians to identify dental diseases. However, the manual process of dental disease assessment is tedious and error-prone when diagnosed by inexperienced dentists. Thus, researchers have employed different advanced computer vision techniques, as well as machine and deep learning models for dental disease diagnoses using X-ray imagery. In this regard, a lightweight Mask-RCNN model is proposed for periapical disease detection. The proposed model is constructed in two parts: a lightweight modified MobileNet-v2 backbone and region-based network (RPN) are proposed for periapical disease localization on a small dataset. To measure the effectiveness of the proposed model, the lightweight Mask-RCNN is evaluated on a custom annotated dataset comprising images of five different types of periapical lesions. The results reveal that the model can detect and localize periapical lesions with an overall accuracy of 94%, a mean average precision of 85%, and a mean insection over a union of 71.0%. The proposed model improves the detection, classification, and localization accuracy significantly using a smaller number of images compared to existing methods and outperforms state-of-the-art approaches date: 2023 publication: Healthcare volume: 11 number: 3 pagerange: 347 id_number: doi:10.3390/healthcare11030347 refereed: TRUE issn: 2227-9032 official_url: http://doi.org/10.3390/healthcare11030347 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Fundación Universitaria Internacional de Colombia > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Abierto Inglés Automated dental imaging interpretation is one of the most prolific areas of research using artificial intelligence. X-ray imaging systems have enabled dental clinicians to identify dental diseases. However, the manual process of dental disease assessment is tedious and error-prone when diagnosed by inexperienced dentists. Thus, researchers have employed different advanced computer vision techniques, as well as machine and deep learning models for dental disease diagnoses using X-ray imagery. In this regard, a lightweight Mask-RCNN model is proposed for periapical disease detection. The proposed model is constructed in two parts: a lightweight modified MobileNet-v2 backbone and region-based network (RPN) are proposed for periapical disease localization on a small dataset. To measure the effectiveness of the proposed model, the lightweight Mask-RCNN is evaluated on a custom annotated dataset comprising images of five different types of periapical lesions. The results reveal that the model can detect and localize periapical lesions with an overall accuracy of 94%, a mean average precision of 85%, and a mean insection over a union of 71.0%. The proposed model improves the detection, classification, and localization accuracy significantly using a smaller number of images compared to existing methods and outperforms state-of-the-art approaches metadata Fatima, Anum; Shafi, Imran; Afzal, Hammad; Mahmood, Khawar; Díez, Isabel de la Torre; Lipari, Vivian; Brito Ballester, Julién y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, vivian.lipari@uneatlantico.es, julien.brito@uneatlantico.es, SIN ESPECIFICAR (2023) Deep Learning-Based Multiclass Instance Segmentation for Dental Lesion Detection. Healthcare, 11 (3). p. 347. ISSN 2227-9032 document_url: http://repositorio.unini.edu.mx/id/eprint/5663/1/healthcare-11-00347.pdf