Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm
Introduction: The need of accurate three-dimensional data of anatomical structures is increasing in the surgical field. The development of convolutional neural networks (CNNs) has been helping to fill this gap by trying to provide efficient tools to clinicians. Nonetheless, the lack of a fully acces...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/5/3271 |
| _version_ | 1797615749045420032 |
|---|---|
| author | Mattia Di Bartolomeo Arrigo Pellacani Federico Bolelli Marco Cipriano Luca Lumetti Sara Negrello Stefano Allegretti Paolo Minafra Federico Pollastri Riccardo Nocini Giacomo Colletti Luigi Chiarini Costantino Grana Alexandre Anesi |
| author_facet | Mattia Di Bartolomeo Arrigo Pellacani Federico Bolelli Marco Cipriano Luca Lumetti Sara Negrello Stefano Allegretti Paolo Minafra Federico Pollastri Riccardo Nocini Giacomo Colletti Luigi Chiarini Costantino Grana Alexandre Anesi |
| author_sort | Mattia Di Bartolomeo |
| collection | DOAJ |
| description | Introduction: The need of accurate three-dimensional data of anatomical structures is increasing in the surgical field. The development of convolutional neural networks (CNNs) has been helping to fill this gap by trying to provide efficient tools to clinicians. Nonetheless, the lack of a fully accessible datasets and open-source algorithms is slowing the improvements in this field. In this paper, we focus on the fully automatic segmentation of the Inferior Alveolar Canal (IAC), which is of immense interest in the dental and maxillo-facial surgeries. Conventionally, only a bidimensional annotation of the IAC is used in common clinical practice. A reliable convolutional neural network (CNNs) might be timesaving in daily practice and improve the quality of assistance. Materials and methods: Cone Beam Computed Tomography (CBCT) volumes obtained from a single radiological center using the same machine were gathered and annotated. The course of the IAC was annotated on the CBCT volumes. A secondary dataset with sparse annotations and a primary dataset with both dense and sparse annotations were generated. Three separate experiments were conducted in order to evaluate the CNN. The IoU and Dice scores of every experiment were recorded as the primary endpoint, while the time needed to achieve the annotation was assessed as the secondary end-point. Results: A total of 347 CBCT volumes were collected, then divided into primary and secondary datasets. Among the three experiments, an IoU score of 0.64 and a Dice score of 0.79 were obtained thanks to the pre-training of the CNN on the secondary dataset and the creation of a novel deep label propagation model, followed by proper training on the primary dataset. To the best of our knowledge, these results are the best ever published in the segmentation of the IAC. The datasets is publicly available and algorithm is published as open-source software. On average, the CNN could produce a 3D annotation of the IAC in 6.33 s, compared to 87.3 s needed by the radiology technician to produce a bidimensional annotation. Conclusions: To resume, the following achievements have been reached. A new state of the art in terms of Dice score was achieved, overcoming the threshold commonly considered of 0.75 for the use in clinical practice. The CNN could fully automatically produce accurate three-dimensional segmentation of the IAC in a rapid setting, compared to the bidimensional annotations commonly used in the clinical practice and generated in a time-consuming manner. We introduced our innovative deep label propagation method to optimize the performance of the CNN in the segmentation of the IAC. For the first time in this field, the datasets and the source codes used were publicly released, granting reproducibility of the experiments and helping in the improvement of IAC segmentation. |
| first_indexed | 2024-03-11T07:30:07Z |
| format | Article |
| id | doaj.art-cb58f6ded2e443e0a9bf8b4b5d0af365 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T07:30:07Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cb58f6ded2e443e0a9bf8b4b5d0af3652023-11-17T07:21:34ZengMDPI AGApplied Sciences2076-34172023-03-01135327110.3390/app13053271Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and AlgorithmMattia Di Bartolomeo0Arrigo Pellacani1Federico Bolelli2Marco Cipriano3Luca Lumetti4Sara Negrello5Stefano Allegretti6Paolo Minafra7Federico Pollastri8Riccardo Nocini9Giacomo Colletti10Luigi Chiarini11Costantino Grana12Alexandre Anesi13Surgery, Dentistry, Maternity and Infant Department, Unit of Dentistry and Maxillo-Facial Surgery, University of Verona, 37129 Verona, ItalySurgery, Dentistry, Maternity and Infant Department, Unit of Dentistry and Maxillo-Facial Surgery, University of Verona, 37129 Verona, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, ItalyCranio-Maxillo-Facial Surgery Unit, University Hospital of Modena, 41124 Modena, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, ItalyAffidea Modena Medica Srl, 41100 Modena, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, ItalySection of Ear Nose and Throat (ENT), Department of Surgical Sciences, Dentistry, Gynecology and Pediatrics, University of Verona, 37124 Verona, ItalyDepartment of Medical and Surgical Sciences for Children and Adults, Cranio-Maxillo-Facial Surgery, University of Modena and Reggio Emilia, 41121 Modena, ItalyDepartment of Medical and Surgical Sciences for Children and Adults, Cranio-Maxillo-Facial Surgery, University of Modena and Reggio Emilia, 41121 Modena, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, ItalyDepartment of Medical and Surgical Sciences for Children and Adults, Cranio-Maxillo-Facial Surgery, University of Modena and Reggio Emilia, 41121 Modena, ItalyIntroduction: The need of accurate three-dimensional data of anatomical structures is increasing in the surgical field. The development of convolutional neural networks (CNNs) has been helping to fill this gap by trying to provide efficient tools to clinicians. Nonetheless, the lack of a fully accessible datasets and open-source algorithms is slowing the improvements in this field. In this paper, we focus on the fully automatic segmentation of the Inferior Alveolar Canal (IAC), which is of immense interest in the dental and maxillo-facial surgeries. Conventionally, only a bidimensional annotation of the IAC is used in common clinical practice. A reliable convolutional neural network (CNNs) might be timesaving in daily practice and improve the quality of assistance. Materials and methods: Cone Beam Computed Tomography (CBCT) volumes obtained from a single radiological center using the same machine were gathered and annotated. The course of the IAC was annotated on the CBCT volumes. A secondary dataset with sparse annotations and a primary dataset with both dense and sparse annotations were generated. Three separate experiments were conducted in order to evaluate the CNN. The IoU and Dice scores of every experiment were recorded as the primary endpoint, while the time needed to achieve the annotation was assessed as the secondary end-point. Results: A total of 347 CBCT volumes were collected, then divided into primary and secondary datasets. Among the three experiments, an IoU score of 0.64 and a Dice score of 0.79 were obtained thanks to the pre-training of the CNN on the secondary dataset and the creation of a novel deep label propagation model, followed by proper training on the primary dataset. To the best of our knowledge, these results are the best ever published in the segmentation of the IAC. The datasets is publicly available and algorithm is published as open-source software. On average, the CNN could produce a 3D annotation of the IAC in 6.33 s, compared to 87.3 s needed by the radiology technician to produce a bidimensional annotation. Conclusions: To resume, the following achievements have been reached. A new state of the art in terms of Dice score was achieved, overcoming the threshold commonly considered of 0.75 for the use in clinical practice. The CNN could fully automatically produce accurate three-dimensional segmentation of the IAC in a rapid setting, compared to the bidimensional annotations commonly used in the clinical practice and generated in a time-consuming manner. We introduced our innovative deep label propagation method to optimize the performance of the CNN in the segmentation of the IAC. For the first time in this field, the datasets and the source codes used were publicly released, granting reproducibility of the experiments and helping in the improvement of IAC segmentation.https://www.mdpi.com/2076-3417/13/5/3271inferior alveolarmandibularcanaldeep learning3Dcone beam computed tomography (CBCT) |
| spellingShingle | Mattia Di Bartolomeo Arrigo Pellacani Federico Bolelli Marco Cipriano Luca Lumetti Sara Negrello Stefano Allegretti Paolo Minafra Federico Pollastri Riccardo Nocini Giacomo Colletti Luigi Chiarini Costantino Grana Alexandre Anesi Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm Applied Sciences inferior alveolar mandibular canal deep learning 3D cone beam computed tomography (CBCT) |
| title | Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm |
| title_full | Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm |
| title_fullStr | Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm |
| title_full_unstemmed | Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm |
| title_short | Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm |
| title_sort | inferior alveolar canal automatic detection with deep learning cnns on cbcts development of a novel model and release of open source dataset and algorithm |
| topic | inferior alveolar mandibular canal deep learning 3D cone beam computed tomography (CBCT) |
| url | https://www.mdpi.com/2076-3417/13/5/3271 |
| work_keys_str_mv | AT mattiadibartolomeo inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT arrigopellacani inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT federicobolelli inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT marcocipriano inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT lucalumetti inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT saranegrello inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT stefanoallegretti inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT paolominafra inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT federicopollastri inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT riccardonocini inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT giacomocolletti inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT luigichiarini inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT costantinograna inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm AT alexandreanesi inferioralveolarcanalautomaticdetectionwithdeeplearningcnnsoncbctsdevelopmentofanovelmodelandreleaseofopensourcedatasetandalgorithm |