Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network

Peng, Limei; Guo, Yucheng; Lee, Wan; Liu, Tai-Ang; Wang, Peng; Zhao, Hu; Wang, Yahui

doi:10.1007/s00414-021-02746-1

Cited by 11 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been used for the study of equipment, and machinery for biomedical applications such as ECG, EEG, EMG, etc. ANN and machine learning can be [23] 88.00 Two-stage CNN X-rays of the adolescent pelvis for forensic bone age estimation Almabdy et al [24] 94-100 CNN with multi-class SVM Face recognition from facial images Khan et al [26] 98.5 Deep CNN Facial Recognition from smart glass for authentication and security Diyasa et al [48] 87.00 Convolutional Neural Network Multi-face detection and identification of Prisoners in Jail Jadhav et al [30] 99.00 Recurrent Neural Network Classifier Fake news identification and classification Phisannupawong et al [32] 92. 53 Deep CNN Non-cooperative docking process for vision-based spacecraft and pose prediction Rai et al [25] 97.37 CNN Intelligent health assistant for Knowing symptoms of common diseases Khumprom et al [49] 90.00 Deep CNN Aircraft engine feature selection for a data-driven prognostic model Naïve Bayes, and Support vector machine Early detection of Parkinson's disease using multimodal features Shi et al [53] 80.00 Support vector machine Forecasting the power output of photovoltaic systems based on weather classification…”

Section: Resultsmentioning

confidence: 99%

“…In the healthcare industry, Convolutional neural networks (CNN) [22] are used for CT scans, MRI, X-ray detection, ECG, EEG, and ultrasound. The medical images and supporting data received from the aforesaid tests are evaluated and measured using neural network models, as CNN [23] is used in image processing. Recurrent neural networks (RNNs) have been widely adopted for learning and realizing voice recognition systems.…”

Section: Medical Diagnosis and Health Carementioning

confidence: 99%

“…The MLP uses several training methods such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Squared Error (MSE) to forecast social media trends (MSE). MLP considers a variety of parameters, including the user's favorite Instagram pages, bookmarked options, and so on [23]. These variables are used as inputs in the MLP model's training.…”

Section: Social Mediamentioning

confidence: 99%

See 2 more Smart Citations

The role of artificial neural network and machine learning in utilizing spatial information

Goel

Kumar

2022

Spat. Inf. Res.

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Medical Diagnosis and Health Carementioning

confidence: 99%

Section: Social Mediamentioning

confidence: 99%

See 1 more Smart Citation

The role of artificial neural network and machine learning in utilizing spatial information

Goel

Kumar

2022

Spat. Inf. Res.

View full text Add to dashboard Cite

show abstract

“…Looking ahead to the future of forensic age assessment, it becomes evident that the path leads toward fully automated procedures reliant on artificial intelligence [66][67][68][69][70][71][72][73][74][75]. This prompts a broader question about the relevance of the present research.…”

Section: Discussionmentioning

confidence: 96%

Third Molar Eruption in Dental Panoramic Radiographs as a Feature for Forensic Age Assessment—Presentation of a New Non-Staging Method Based on Measurements

Timme,

Bender,

Steffens

et al. 2023

Biology

View full text Add to dashboard Cite

The evaluation of third molar eruption in dental panoramic radiographs (DPRs) constitutes an evidence-based approach for forensic age assessment in living individuals. Existing methodologies involve staging morphological radiographic findings and comparing them to reference populations. Conversely, the existing literature presents an alternative method where the distance between third molars and the occlusal plane is measured on dental plaster models. The aim of this study was to adapt this measurement principle for DPRs and to determine correlation between eruption and chronological age. A total of 423 DPRs, encompassing 220 females and 203 males aged 15 to 25 years, were examined, including teeth 38 [FDI] and 48. Two independent examiners conducted the measurements, with one examiner providing dual assessments. Ultimately, a quotient was derived by comparing orthogonal distances from the mesial cementoenamel junctions of the second and third molars to a simplified radiological occlusal plane. This quotient was subsequently correlated with the individual’s age. We estimated correlations between age and quotients, as well as inter- and intra-rater reliability. Correlation coefficients (Spearman’s rho) between measurements and individuals’ ages ranged from 0.555 to 0.597, conditional on sex and tooth. Intra-rater agreement (Krippendorf’s alpha) ranged from 0.932 to 0.991, varying according to the tooth and sex. Inter-rater agreement ranged from 0.984 to 0.992, with distinctions drawn for different teeth and sex. Notably, all observer agreement values fell within the “very good” range. In summary, assessing the distance of third molars from a simplified occlusal plane in DPRs emerges as a new and promising method for evaluating eruption status in forensic age assessment. Subsequent reference studies should validate these findings.

show abstract

“…Recently, the segmentation of bones using computer-aided algorithms has been studied for use in clinical diagnosis and treatment planning [ 7 , 8 , 9 , 10 ]. Wrist bone segmentation also has been studied as a predecessor to wrist fracture classification [ 11 ], bone age assessment [ 12 , 13 ], and the diagnosis of rheumatoid arthritis [ 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Automatic Segmentation for Favourable Delineation of Ten Wrist Bones on Wrist Radiographs Using Convolutional Neural Network

Kang

Han

et al. 2022

JPM

View full text Add to dashboard Cite

Purpose: This study aimed to develop and validate an automatic segmentation algorithm for the boundary delineation of ten wrist bones, consisting of eight carpal and two distal forearm bones, using a convolutional neural network (CNN). Methods: We performed a retrospective study using adult wrist radiographs. We labeled the ground truth masking of wrist bones, and propose that the Fine Mask R-CNN consisted of wrist regions of interest (ROI) using a Single-Shot Multibox Detector (SSD) and segmentation via Mask R-CNN, plus the extended mask head. The primary outcome was an improvement in the prediction of delineation via the network combined with ground truth masking, and this was compared between two networks through five-fold validations. Results: In total, 702 images were labeled for the segmentation of ten wrist bones. The overall performance (mean (SD] of Dice coefficient) of the auto-segmentation of the ten wrist bones improved from 0.93 (0.01) using Mask R-CNN to 0.95 (0.01) using Fine Mask R-CNN (p < 0.001). The values of each wrist bone were higher when using the Fine Mask R-CNN than when using the alternative (all p < 0.001). The value derived for the distal radius was the highest, and that for the trapezoid was the lowest in both networks. Conclusion: Our proposed Fine Mask R-CNN model achieved good performance in the automatic segmentation of ten overlapping wrist bones derived from adult wrist radiographs.

show abstract

Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network

Cited by 11 publications

References 23 publications

The role of artificial neural network and machine learning in utilizing spatial information

The role of artificial neural network and machine learning in utilizing spatial information

Third Molar Eruption in Dental Panoramic Radiographs as a Feature for Forensic Age Assessment—Presentation of a New Non-Staging Method Based on Measurements

Automatic Segmentation for Favourable Delineation of Ten Wrist Bones on Wrist Radiographs Using Convolutional Neural Network

Contact Info

Product

Resources

About