3D dento-maxillary osteolytic lesion and active contour segmentation pilot study in CBCT: semi-automatic<i>vs</i>manual methods

Vallaeys, Karen; Kacem, Afef; Legoux, H; Tenier, M Le; Hamitouche, Chafiaâ; Arbab-Chirani, Reza

doi:10.1259/dmfr.20150079

Cited by 48 publications

(46 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While numerous methods of measuring cystic lesions have been described [3,21,[24][25][26], the reduction of the defect after surgery is increasingly measured by segmentation of 3D data sets [13,21]. Some of these methods are time-consuming and rather complicated, although they are becoming faster and easier to use.…”

Section: Discussionmentioning

confidence: 99%

Calculation of postoperative bone healing of cystic lesions of the jaw—a retrospective study

et al. 2019

View full text Add to dashboard Cite

Objectives There is a long history of studies into cystic lesions of the jaws. However, there is little data on postoperative bone regeneration. The aim of the study was to calculate the size of the residual bone lesions after cystostomies and cystectomies to predict the postoperative bone healing. Material and methods This retrospective study focused on patients undergoing cystectomy (n = 114) or cystostomy (n = 86), who were treated for cystic lesions between 2010 and 2015. New formulas were developed to measure the decrease in lesion sizes using the craniocaudal and mesiodistal diameters from preoperative as well as postoperative radiographs (panoramic radiographs, CT scans, CBCT). With these predictive models (calculated by linear regression analyses), it is possible to calculate how the lesions would shrink using initial size of the cyst and time after surgery for both dimensions. Results After cystostomy, the mesiodistal size was initial size 6.0 + 0.7 × initial size − 9.4 × time. The craniocaudal size was 5.1 + 0.7 × initial size − 7.3 × time. After cystectomy, the mesiodistal size was 0.4 + 0.7 × initial size − 8.4 × time. The craniocaudal size was 0.4 + 0.5 × initial size − 6.4 × time (R 2 = 0.59 and 0.67, respectively). Conclusion These formulas are suggested to be used to calculate residual size of bone lesion after cystostomy and cystectomy to predict postoperative bone healing. Clinical relevance The formulas are based on deliberately simple measurement using only panoramic radiographs to encourage their application in daily clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Calculation of postoperative bone healing of cystic lesions of the jaw—a retrospective study

et al. 2019

View full text Add to dashboard Cite

show abstract

“…A leave‐2‐out scheme was used so that 16 of the 18 training CBCT scans were alternately used for training and 2 for testing. As a clinical benchmark, these 18 CBCT scans were also segmented using a snake evolution algorithm that is commonly used for various clinical segmentation purposes . This algorithm is available in the open‐source ITK‐SNAP software package and requires an initial segmentation using global thresholding, followed by selection of seed points in the region of interest (i.e., bone).…”

Section: Methodsmentioning

confidence: 99%

Segmentation of dental cone‐beam CT scans affected by metal artifacts using a mixed‐scale dense convolutional neural network

et al. 2019

View full text Add to dashboard Cite

Purpose: In order to attain anatomical models, surgical guides and implants for computer-assisted surgery, accurate segmentation of bony structures in cone-beam computed tomography (CBCT) scans is required. However, this image segmentation step is often impeded by metal artifacts. Therefore, this study aimed to develop a mixed-scale dense convolutional neural network (MS-D network) for bone segmentation in CBCT scans affected by metal artifacts. Method: Training data were acquired from 20 dental CBCT scans affected by metal artifacts. An experienced medical engineer segmented the bony structures in all CBCT scans using global thresholding and manually removed all remaining noise and metal artifacts. The resulting gold standard segmentations were used to train an MS-D network comprising 100 convolutional layers using far fewer trainable parameters than alternative convolutional neural network (CNN) architectures. The bone segmentation performance of the MS-D network was evaluated using a leave-2-out scheme and compared with a clinical snake evolution algorithm and two state-of-the-art CNN architectures (U-Net and ResNet). All segmented CBCT scans were subsequently converted into standard tessellation language (STL) models and geometrically compared with the gold standard. Results: CBCT scans segmented using the MS-D network, U-Net, ResNet and the snake evolution algorithm demonstrated mean Dice similarity coefficients of 0.87 AE 0.06, 0.87 AE 0.07, 0.86 AE 0.05, and 0.78 AE 0.07, respectively. The STL models acquired using the MS-D network, U-Net, ResNet and the snake evolution algorithm demonstrated mean absolute deviations of 0.44 mm AE 0.13 mm, 0.43 mm AE 0.16 mm, 0.40 mm AE 0.12 mm and 0.57 mm AE 0.22 mm, respectively. In contrast to the MS-D network, the ResNet introduced wave-like artifacts in the STL models, whereas the U-Net incorrectly labeled background voxels as bone around the vertebrae in 4 of the 9 CBCT scans containing vertebrae. Conclusion: The MS-D network was able to accurately segment bony structures in CBCT scans affected by metal artifacts.

show abstract

“…Many semiautomatic segmentation methods have been proposed in the literature. These methods essentially concentrate on the region of interest segmentation on every slice and few are superior to manual segmentation 19 in CBCT images without artifacts interference. It is reasonable to assume that the manual segmentation method will be more accurate than other semiautomatic methods in CBCT images affected by artifacts.…”

Section: Discussionmentioning

confidence: 99%

Accuracy assessment of a novel semiautomatic method evaluating bone grafts around the dental implant: an in vitro and ex vivo study

Shi

Liu

et al. 2020

Sci Rep

View full text Add to dashboard Cite

The present study aimed to evaluate the accuracy and repeatability of morphological contour interpolation (MCI)-based semiautomatic segmentation method for volumetric measurements of bone grafts around dental implants. Three in vitro (one with a cylinder and two with a geometrically complex form) and four ex vivo models (peri-implant cylinder-shaped bone defect) were created for imitating implant placement with simultaneous guided bone regeneration (GBR) procedure. Cone beam computerized tomography (CBCT) scans of all models were obtained with the same parameters. For volumetric measurements, the actual volumes of bone grafts in models were assessed by computer-aided calculation and both manual and MCI-based methods were utilized as test methods. The accuracy of the methods was evaluated by comparing the measured value and the actual volume. The repeatability was assessed by calculating the coefficients of variation of repeated measurements. For the accuracy of three dimensional (3D) reconstructions, the computer-designed corresponding models were set as the reference and the morphological deviation of 3D surface renderings created by two methods were evaluated by comparing with reference. Besides, measurement time was recorded and a comparison between the two methods was performed. High accuracy of the MCI-based segmentation method was found with a discrepancy between the measured value and actual value never exceeding − 7.5%. The excellent repeatability was shown with coefficients of variation never exceeding 1.2%. The MCI-based method showed less measurement time than the manual method and its 3D surface rendering showed a lower deviation from the reference.

show abstract

3D dento-maxillary osteolytic lesion and active contour segmentation pilot study in CBCT: semi-automaticvsmanual methods

Cited by 48 publications

References 33 publications

Calculation of postoperative bone healing of cystic lesions of the jaw—a retrospective study

Calculation of postoperative bone healing of cystic lesions of the jaw—a retrospective study

Segmentation of dental cone‐beam CT scans affected by metal artifacts using a mixed‐scale dense convolutional neural network

Accuracy assessment of a novel semiautomatic method evaluating bone grafts around the dental implant: an in vitro and ex vivo study

Contact Info

Product

Resources

About