Asma'A Abdurrahman Al-Ekrish
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Asma'A Abdurrahman Al-Ekrish has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Gerlig Widmann
Medical University of Innsbruck, Department of Radiology, Innsbruck, Austria
2 shared publications- Gerlig Widmann
Department of Radiology, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria
2 shared publications Romed Hörmann
Medical University of Innsbruck, Division of Clinical and Functional Anatomy, Innsbruck, Austria
2 shared publications- Romed Hörmann
Division Clinical and Functional Anatomy, Medical University of Innsbruck, Innsbruck, Austria
2 shared publications Wafa Alfaleh
King Saud University College of Dentistry, Riyadh, Saudi Arabia
2 shared publications- Adel Alzahrani
Department of Oral Medicine and Diagnostic Sciences, Oral & Maxillofacial Radiology, College of Dentistry, King Saud University, P.O. Box 60169, Riyadh 11545, Kingdom of Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 23 March 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (7) , 1220
Prediction of the as Low as Diagnostically Acceptable CT Dose for Identification of the Inferior Alveolar Canal Using 3D Convolutional Neural Networks with Multi-Balancing Strategies
Ionizing radiation is necessary for diagnostic imaging and deciding the right radiation dose is extremely critical to obtain a decent quality image. However, increasing the dosage to improve the image quality has risks due to the potential harm from ionizing radiation. Thus, finding the optimal as low as diagnostically acceptable (ALADA) dosage is an open research problem that has yet to be tackled using artificial intelligence (AI) methods. This paper proposes a new multi-balancing 3D convolutional neural network methodology to build 3D multidetector computed tomography (MDCT) datasets and develop a 3D classifier model that can work properly with 3D CT scan images and balance itself over the heavy unbalanced multi-classes. The proposed models were exhaustively investigated through eighteen empirical experiments and three re-runs for clinical expert examination. As a result, it was possible to confirm that the proposed models improved the performance by an accuracy of 5% to 10% when compared to the baseline method. Furthermore, the resulting models were found to be consistent, and thus possibly applicable to different MDCT examinations and reconstruction techniques. The outcome of this paper can help radiologists to predict the suitability of CT dosages across different CT hardware devices and reconstruction algorithms. Moreover, the developed model is suitable for clinical application where the right dose needs to be predicted from numerous MDCT examinations using a certain MDCT device and reconstruction technique.
- 23 March 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (7) , 1220
Open AccessPrediction of the as Low as Diagnostically Acceptable CT Dose for Identification of the Inferior Alveolar Canal Using 3D Convolutional Neural Networks with Multi-Balancing Strategies
Ionizing radiation is necessary for diagnostic imaging and deciding the right radiation dose is extremely critical to obtain a decent quality image. However, increasing the dosage to improve the image quality has risks due to the potential harm from ionizing radiation. Thus, finding the optimal as low as diagnostically acceptable (ALADA) dosage is an open research problem that has yet to be tackled using artificial intelligence (AI) methods. This paper proposes a new multi-balancing 3D convolutional neural network methodology to build 3D multidetector computed tomography (MDCT) datasets and develop a 3D classifier model that can work properly with 3D CT scan images and balance itself over the heavy unbalanced multi-classes. The proposed models were exhaustively investigated through eighteen empirical experiments and three re-runs for clinical expert examination. As a result, it was possible to confirm that the proposed models improved the performance by an accuracy of 5% to 10% when compared to the baseline method. Furthermore, the resulting models were found to be consistent, and thus possibly applicable to different MDCT examinations and reconstruction techniques. The outcome of this paper can help radiologists to predict the suitability of CT dosages across different CT hardware devices and reconstruction algorithms. Moreover, the developed model is suitable for clinical application where the right dose needs to be predicted from numerous MDCT examinations using a certain MDCT device and reconstruction technique.
- Open Access
- 10 January 2022
- Published by Springer Nature in The Saudi Dental Journal
- Vol. 34 (3) , 220-225
Development of a deep learning model for automatic localization of radiographic markers of proposed dental implant site locations
To develop a Deep Learning Artificial Intelligence (AI) model that automatically localizes the position of radiographic stent gutta percha (GP) markers in cone beam computed tomography (CBCT) images to identify proposed implant sites within the images, and to test the performance of the newly developed AI model. Thirty-four CBCT datasets were used for initial model training, validation and testing. The CBCT datasets were those of patients who had a CBCT examination performed wearing a radiographic stent for implant treatment planning. The datasets were exported in Digital Imaging and Communications in Medicine (DICOM), then imported into the software Horos ®. Each GP marker was manually labelled for object detection and recognition by the deep learning model by drawing rectangles around the GP markers in all axial images, then the labelled images were split into training, validation, and test sets. The axial sections of 30 CBCT datasets were randomly divided into training and validation sets. four CBCT datasets were used for testing the performance of the deep learning model. Descriptive statistics were calculated for the number of GP markers present, number of correct and incorrect identifications of GP markers. The AI model had an 83% true positive rate for identification of the GP markers. Of the areas labelled by the AI model as GP markers, 28 % were not truly GP markers, but the overall false positive rate was 2.8 %. An AI model for localization of GP markers in CBCT images was able to identify most of the GP markers, but 2.8% of the results were false positive and 17% were missed GP markers. Using only axial images for training an AI program is not enough to give an accurate AI model performance.
- 10 January 2022
- Published by Springer Nature in The Saudi Dental Journal
- Vol. 34 (3) , 220-225
Open AccessDevelopment of a deep learning model for automatic localization of radiographic markers of proposed dental implant site locations
To develop a Deep Learning Artificial Intelligence (AI) model that automatically localizes the position of radiographic stent gutta percha (GP) markers in cone beam computed tomography (CBCT) images to identify proposed implant sites within the images, and to test the performance of the newly developed AI model. Thirty-four CBCT datasets were used for initial model training, validation and testing. The CBCT datasets were those of patients who had a CBCT examination performed wearing a radiographic stent for implant treatment planning. The datasets were exported in Digital Imaging and Communications in Medicine (DICOM), then imported into the software Horos ®. Each GP marker was manually labelled for object detection and recognition by the deep learning model by drawing rectangles around the GP markers in all axial images, then the labelled images were split into training, validation, and test sets. The axial sections of 30 CBCT datasets were randomly divided into training and validation sets. four CBCT datasets were used for testing the performance of the deep learning model. Descriptive statistics were calculated for the number of GP markers present, number of correct and incorrect identifications of GP markers. The AI model had an 83% true positive rate for identification of the GP markers. Of the areas labelled by the AI model as GP markers, 28 % were not truly GP markers, but the overall false positive rate was 2.8 %. An AI model for localization of GP markers in CBCT images was able to identify most of the GP markers, but 2.8% of the results were false positive and 17% were missed GP markers. Using only axial images for training an AI program is not enough to give an accurate AI model performance.
- 16 November 2020
- Published by Wiley in International Endodontic Journal
- Vol. 53 (12) , 1742-1743
To the Editor‐in‐Chief of the International Endodontic Journal
- 16 November 2020
- Published by Wiley in International Endodontic Journal
- Vol. 53 (12) , 1742-1743
To the Editor‐in‐Chief of the International Endodontic Journal
- Open Access
- 6 August 2020
- Published by Springer Nature in The Saudi Dental Journal
- Vol. 33 (6) , 355-361
Comparative study of the accuracy of CBCT implant site measurements using different software programs
To measure and compare the accuracy of the linear dimensions of implant sites recorded from cone beam computed tomography (CBCT) images using Blue Sky Plan, coDiagnostiX, and RadiAnt. Five human dry skulls were imaged with a CBCT device then sectioned to obtain sample transverse cross-sections of the edentulous ridges, and the height and width of the ridge were measured with a digital caliper to provide the gold standard measurements. The CBCT datasets were exported in DICOM format and imported into the three test software programs which were used to obtain reformatted sectional images corresponding to the sample transverse cross-sections, and the height and width of the edentulous ridge was recorded using the linear measurement tool. Reliability of the measurements were measured using the intraclass correlation coefficient. One-sample t-test (test value: zero) was used to test the statistical significance of the mean of the absolute errors for each software program. Analysis of Variance with Repeated Measures was used to test the statistical significance of the difference between the means of the absolute errors obtained by the different software programs. Statistical significance was set at a p-value of 0.05. The reliability of the gold standard and image measurements were excellent. All three software programs demonstrated a statistically significant mean absolute measurement error of between 0.43 and 0.56 mm (p-value < 0.01), but no significant difference in error values was found between any of the tested programs (p- value = 0.18). There was no statistically significant difference in accuracy of linear CBCT measurements of implant sites recorded using Blue Sky Plan, coDiagnostiX, and RadiAnt.
- 6 August 2020
- Published by Springer Nature in The Saudi Dental Journal
- Vol. 33 (6) , 355-361
Open AccessComparative study of the accuracy of CBCT implant site measurements using different software programs
To measure and compare the accuracy of the linear dimensions of implant sites recorded from cone beam computed tomography (CBCT) images using Blue Sky Plan, coDiagnostiX, and RadiAnt. Five human dry skulls were imaged with a CBCT device then sectioned to obtain sample transverse cross-sections of the edentulous ridges, and the height and width of the ridge were measured with a digital caliper to provide the gold standard measurements. The CBCT datasets were exported in DICOM format and imported into the three test software programs which were used to obtain reformatted sectional images corresponding to the sample transverse cross-sections, and the height and width of the edentulous ridge was recorded using the linear measurement tool. Reliability of the measurements were measured using the intraclass correlation coefficient. One-sample t-test (test value: zero) was used to test the statistical significance of the mean of the absolute errors for each software program. Analysis of Variance with Repeated Measures was used to test the statistical significance of the difference between the means of the absolute errors obtained by the different software programs. Statistical significance was set at a p-value of 0.05. The reliability of the gold standard and image measurements were excellent. All three software programs demonstrated a statistically significant mean absolute measurement error of between 0.43 and 0.56 mm (p-value < 0.01), but no significant difference in error values was found between any of the tested programs (p- value = 0.18). There was no statistically significant difference in accuracy of linear CBCT measurements of implant sites recorded using Blue Sky Plan, coDiagnostiX, and RadiAnt.
- 2 July 2020
- Published by Wiley in International Endodontic Journal
- Vol. 53 (10) , 1318-1326
Accuracy of mean grey density values obtained with small field of view cone beam computed tomography in differentiation between periapical cystic and solid lesions
Aim: To determine if small and medium field of view (FOV) cone beam computed tomography (CBCT) adjusted grey density values can be used to distinguish between periapical cystic and solid lesions.Methodology: Fifty‐seven patients with periapical lesions having retrievable small or medium FOV CBCT images and biopsy samples were included. Two oral and maxillofacial pathologists examined the biopsy samples to provide the gold standard diagnosis of cystic or solid lesion. From the CBCT images, two independent examiners recorded the minimum adjusted grey density value of each lesion twice. Intra‐examiner and inter‐examiner reliability of the measurements were analysed, and sensitivity, specificity and accuracy of the minimum grey values in distinguishing a solid from cystic lesion were calculated. A receiver operating curve for diagnostic ability of adjusted grey density values to differentiate between periapical cystic and solid lesions was obtained, and the area under the curve (AUC) was calculated.Results: The intra‐ and inter‐examiner reliability of the grey density values of the lesions and dentine were excellent. The AUC was 0.44 (P‐value = 0.45). The adjusted grey density value with the greatest accuracy for differentiating between cystic and solid lesions had an accuracy, sensitivity and specificity of 0.54, 1.00 and 0.075, respectively.Conclusions: Small FOV CBCT adjusted grey density values obtained by the device used in the study could not distinguish between periapical cystic and solid lesions. Further developments in CBCT devices are needed to improve the accuracy of grey density measurements.
- 2 July 2020
- Published by Wiley in International Endodontic Journal
- Vol. 53 (10) , 1318-1326
Accuracy of mean grey density values obtained with small field of view cone beam computed tomography in differentiation between periapical cystic and solid lesions
Aim: To determine if small and medium field of view (FOV) cone beam computed tomography (CBCT) adjusted grey density values can be used to distinguish between periapical cystic and solid lesions.Methodology: Fifty‐seven patients with periapical lesions having retrievable small or medium FOV CBCT images and biopsy samples were included. Two oral and maxillofacial pathologists examined the biopsy samples to provide the gold standard diagnosis of cystic or solid lesion. From the CBCT images, two independent examiners recorded the minimum adjusted grey density value of each lesion twice. Intra‐examiner and inter‐examiner reliability of the measurements were analysed, and sensitivity, specificity and accuracy of the minimum grey values in distinguishing a solid from cystic lesion were calculated. A receiver operating curve for diagnostic ability of adjusted grey density values to differentiate between periapical cystic and solid lesions was obtained, and the area under the curve (AUC) was calculated.Results: The intra‐ and inter‐examiner reliability of the grey density values of the lesions and dentine were excellent. The AUC was 0.44 (P‐value = 0.45). The adjusted grey density value with the greatest accuracy for differentiating between cystic and solid lesions had an accuracy, sensitivity and specificity of 0.54, 1.00 and 0.075, respectively.Conclusions: Small FOV CBCT adjusted grey density values obtained by the device used in the study could not distinguish between periapical cystic and solid lesions. Further developments in CBCT devices are needed to improve the accuracy of grey density measurements.
- Open Access
- 13 October 2018
- Published by Springer Nature in Oral Radiology
- Vol. 35 (3) , 280-286
Comparability of dental implant site ridge measurements using ultra-low-dose multidetector row computed tomography combined with filtered back-projection, adaptive statistical iterative reconstruction, and model-based iterative reconstruction
Objective To assess the linear measurements of edentulous ridges recorded from multidetector row computed tomography (MDCT) images obtained by a previously untested ultra-low dose in combination with filtered back-projection (FBP), adaptive statistical iterative reconstruction (ASIR), and model-based iterative reconstruction (MBIR). Methods Three cadavers were imaged using a reference protocol with a standard dose and FBP (volume CT dose index (CTDIvol): 29.4 mGy) and two ultra-low-dose protocols, LD1 and LD2 (CTDIvol: 0.53 and 0.29 mGy). All test examinations were reconstructed with FBP, ASIR 50, ASIR 100, and MBIR. Linear measurements from the images of the edentulous ridges recorded from the test protocols were compared with those from the reference using a one-sample t test, Bland–Altman plots, and linear regression. Statistical significance was set at a p value of 0.05. Results The one-sample t test demonstrated a statistically significant difference between the measurements from the reference protocol and all test protocols. The difference was not clinically significant for the following three test protocols: LD1/FBP, LD1/ASIR 50, and LD2/FBP. Bland–Altman plots with linear regression showed no systematic variation between the measurements obtained with the reference protocol and these three test protocols. Conclusions The lowest-dose protocol to demonstrate comparable measurements with a standard MDCT dose was CTDIvol 0.29 mGy with FBP. These results must be considered with caution for areas of the jaws with thin cortication. The results in areas of thin cortication should be verified by studies with larger sample sizes at such areas and comparison with true gold standard measurements.
- 13 October 2018
- Published by Springer Nature in Oral Radiology
- Vol. 35 (3) , 280-286
Open AccessComparability of dental implant site ridge measurements using ultra-low-dose multidetector row computed tomography combined with filtered back-projection, adaptive statistical iterative reconstruction, and model-based iterative reconstruction
Objective To assess the linear measurements of edentulous ridges recorded from multidetector row computed tomography (MDCT) images obtained by a previously untested ultra-low dose in combination with filtered back-projection (FBP), adaptive statistical iterative reconstruction (ASIR), and model-based iterative reconstruction (MBIR). Methods Three cadavers were imaged using a reference protocol with a standard dose and FBP (volume CT dose index (CTDIvol): 29.4 mGy) and two ultra-low-dose protocols, LD1 and LD2 (CTDIvol: 0.53 and 0.29 mGy). All test examinations were reconstructed with FBP, ASIR 50, ASIR 100, and MBIR. Linear measurements from the images of the edentulous ridges recorded from the test protocols were compared with those from the reference using a one-sample t test, Bland–Altman plots, and linear regression. Statistical significance was set at a p value of 0.05. Results The one-sample t test demonstrated a statistically significant difference between the measurements from the reference protocol and all test protocols. The difference was not clinically significant for the following three test protocols: LD1/FBP, LD1/ASIR 50, and LD2/FBP. Bland–Altman plots with linear regression showed no systematic variation between the measurements obtained with the reference protocol and these three test protocols. Conclusions The lowest-dose protocol to demonstrate comparable measurements with a standard MDCT dose was CTDIvol 0.29 mGy with FBP. These results must be considered with caution for areas of the jaws with thin cortication. The results in areas of thin cortication should be verified by studies with larger sample sizes at such areas and comparison with true gold standard measurements.
- Open Access
- 16 June 2018
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 13 (11) , 1853-1860
Accuracy of computer-aided design models of the jaws produced using ultra-low MDCT doses and ASIR and MBIR
To compare the surface of computer-aided design (CAD) models of the maxilla produced using ultra-low MDCT doses combined with filtered backprojection (FBP), adaptive statistical iterative reconstruction (ASIR) and model-based iterative reconstruction (MBIR) reconstruction techniques with that produced from a standard dose/FBP protocol.
- 16 June 2018
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 13 (11) , 1853-1860
Open AccessAccuracy of computer-aided design models of the jaws produced using ultra-low MDCT doses and ASIR and MBIR
To compare the surface of computer-aided design (CAD) models of the maxilla produced using ultra-low MDCT doses combined with filtered backprojection (FBP), adaptive statistical iterative reconstruction (ASIR) and model-based iterative reconstruction (MBIR) reconstruction techniques with that produced from a standard dose/FBP protocol.
- 1 October 2015
- Published by Elsevier in Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
- Vol. 120 (4) , 534-6
Comparative study of the prevalence of temporomandibular joint (TMJ) osteoarthritic changes in cone beam computed tomograms of temporomandibular disorder (TMD) and non-TMD patients: Authors' reply.
- 1 October 2015
- Published by Elsevier in Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology
- Vol. 120 (4) , 534-6
Comparative study of the prevalence of temporomandibular joint (TMJ) osteoarthritic changes in cone beam computed tomograms of temporomandibular disorder (TMD) and non-TMD patients: Authors' reply.
- Open Access
- 1 July 2013
- Published by Elsevier in King Saud University Journal of Dental Sciences
- Vol. 4 (2) , 81-85
A retrospective study of the prevalence and reliability of the diagnosis of soft tissue calcification of the temporomandibular joint in cone beam computed tomography images
- 1 July 2013
- Published by Elsevier in King Saud University Journal of Dental Sciences
- Vol. 4 (2) , 81-85
Open AccessA retrospective study of the prevalence and reliability of the diagnosis of soft tissue calcification of the temporomandibular joint in cone beam computed tomography images