Intelligent analysis of coronal alignment in lower limbs based on radiographic image with convolutional neural network

Nguyen, Thong; Chae, Dong-Sik; Park, Sung-Jun; Kang, Kyung-Yil; Lee, Woo Suk; Yoon, Jonghun

doi:10.1016/j.compbiomed.2020.103732

Cited by 25 publications

(25 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nguyen et al reported that the MAE for mLDFA was 0.899° for the right limbs and 1.137°f or the left limbs. In our study, the predicted MAE for MPTA of the right and left limbs was 0.638° and 0.602°, respectively, which are also better than the ones reported by Nguyen et al [19] (the MAE for MPTA of right and left limbs was 1.146° and 1.032°, respectively). Additionally, Zheng et al [20] realized the mechanical axis of the lower limbs using the AI model with an MAE of 4.5 mm, and our corresponding MAE values for the right and left legs were 1.124 mm and 1.032 mm, respectively.…”

Section: Discussioncontrasting

confidence: 65%

Fully Automated Measurement on Coronal Alignment of Lower Limbs using Deep Convolutional Neural Networks on Radiographic Images

Meng

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Background A deep convolutional neural network (DCNN) system is proposed to measure the lower limb parameters of the mechanical lateral distal femur angle (mLDFA), medial proximal tibial angle (MPTA), lateral distal tibial angle (LDTA), joint line convergence angle (JLCA), and mechanical axis of the lower limbs. Methods Standing X-rays of 1000 patients’ lower limbs were examined for the DCNN and assigned to training, validation, and test sets. A coarse-to-fine network was employed to locate 20 key landmarks on both limbs that first recognized the regions of hip, knee, and ankle, and subsequently outputted the key points in each sub-region from a full-length X-ray. Finally, information from these key landmark locations was used to calculate the above five parameters. Results The DCNN system showed high consistency (ICC > 0.91) for all five lower limb parameters. Additionally, the mean absolute error (MAE) and root mean squared error (RMSE) of all angle predictions were lower than 3° for both the left and right limbs. The MAE of the mechanical axis of the lower limbs was 1.124 mm and 1.416 mm and the RMSE was 1.032 mm and 1.321 mm, for the right and left limbs, respectively. The measurement time of the DCNN system was 1.8 ± 1.3 s, which was significantly shorter than that of experienced radiologists (616.8 ± 48.2 s, t = -180.4, P༜0.001). Conclusions The proposed DCNN system can automatically measure mLDFA, MPTA, LDTA, JLCA, and the mechanical axis of the lower limbs, thus helping physicians manage lower limb alignment accurately and efficiently.

show abstract

Section: Discussioncontrasting

confidence: 65%

Fully Automated Measurement on Coronal Alignment of Lower Limbs using Deep Convolutional Neural Networks on Radiographic Images

Meng

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, the MAE of the predicted mLDFA was 0.642° for the right limbs and 0.656° for the left limbs, and the errors were much lower, similar to a previous report. Nguyen et al [ 20 ] reported that the MAE for mLDFA was 0.899° for the right limbs and 1.137° for the left limbs. In our study, the predicted MAE for MPTA of the right and left limbs was 0.638° and 0.602°, respectively, which are also better than the ones reported by Nguyen et al [ 20 ] (the MAE for MPTA of right and left limbs was 1.146° and 1.032°, respectively).…”

Section: Discussionmentioning

confidence: 99%

“…Nguyen et al [ 20 ] reported that the MAE for mLDFA was 0.899° for the right limbs and 1.137° for the left limbs. In our study, the predicted MAE for MPTA of the right and left limbs was 0.638° and 0.602°, respectively, which are also better than the ones reported by Nguyen et al [ 20 ] (the MAE for MPTA of right and left limbs was 1.146° and 1.032°, respectively). Additionally, Zheng et al [ 21 ] determined the mechanical axis of the lower limbs using the AI model with an MAE of 4.5 mm, and our corresponding MAE values for the right and left legs were 1.124 mm and 1.032 mm, respectively.…”

Section: Discussionmentioning

confidence: 99%

Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images

Meng

Wang

et al. 2022

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Background A deep convolutional neural network (DCNN) system is proposed to measure the lower limb parameters of the mechanical lateral distal femur angle (mLDFA), medial proximal tibial angle (MPTA), lateral distal tibial angle (LDTA), joint line convergence angle (JLCA), and mechanical axis of the lower limbs. Methods Standing X-rays of 1000 patients’ lower limbs were examined for the DCNN and assigned to training, validation, and test sets. A coarse-to-fine network was employed to locate 20 key landmarks on both limbs that first recognised the regions of hip, knee, and ankle, and subsequently outputted the key points in each sub-region from a full-length X-ray. Finally, information from these key landmark locations was used to calculate the above five parameters. Results The DCNN system showed high consistency (intraclass correlation coefficient > 0.91) for all five lower limb parameters. Additionally, the mean absolute error (MAE) and root mean squared error (RMSE) of all angle predictions were lower than 3° for both the left and right limbs. The MAE of the mechanical axis of the lower limbs was 1.124 mm and 1.416 mm and the RMSE was 1.032 mm and 1.321 mm, for the right and left limbs, respectively. The measurement time of the DCNN system was 1.8 ± 1.3 s, which was significantly shorter than that of experienced radiologists (616.8 ± 48.2 s, t = -180.4, P < 0.001). Conclusions The proposed DCNN system can automatically measure mLDFA, MPTA, LDTA, JLCA, and the mechanical axis of the lower limbs, thus helping physicians manage lower limb alignment accurately and efficiently. Supplementary Information The online version contains supplementary material available at 10.1186/s12891-022-05818-4.

show abstract

“…Therefore, we used a decentralized CNN model [17][18][19] previously proposed as a highaccuracy landmark detecting method for medical images. The advantage of this method is that it narrows the ROI after each order, which not only reduces the number of non-related features that can affect the results, but also increases the diversity of the training dataset.…”

Section: Decentralized Cnn To Evaluate Anterior Incisor Inclinationmentioning

confidence: 99%

Automated analysis of three-dimensional CBCT images taken in natural head position that combines facial profile processing and multiple deep-learning models

Ahn

Nguyen

Kim

et al. 2022

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

Intelligent analysis of coronal alignment in lower limbs based on radiographic image with convolutional neural network

Cited by 25 publications

References 25 publications

Fully Automated Measurement on Coronal Alignment of Lower Limbs using Deep Convolutional Neural Networks on Radiographic Images

Fully Automated Measurement on Coronal Alignment of Lower Limbs using Deep Convolutional Neural Networks on Radiographic Images

Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images

Automated analysis of three-dimensional CBCT images taken in natural head position that combines facial profile processing and multiple deep-learning models

Contact Info

Product

Resources

About