A hierarchical algorithm for phalangeal and epiphyseal/metaphyseal segmentation

Hsieh, Chia‐Wei; Liu, Hsian-Chuan; Jong, Tai-Lang; Chen, Chih-Yen

doi:10.1007/s11042-016-3278-5

Cited by 2 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is necessary to obtain the location of the five metacarpals in order to determine the orientation of each of the fingers. For this purpose, the geometric property used by (Hsieh et al, 2017), which determines the centre of the wrist as the reference point to draw a circle with a radius of one‐third of the distance from that point to the maximum of the middle finger, was used as reference. Figure 4a,b illustrates the bone image of the binarized hand and the bones of the metacarpals found on the circumference traced, as well as the centroids of the metacarpals.…”

Section: Methodsmentioning

confidence: 99%

“…For the step of angular cut of the PROI, the geometric property used in the study (Hsieh et al, 2017) was adapted to determine the lower limits of each of the fingers and also for removing the excess of wrist. Also, the idea of searching for the upper reference points based on the study (Castro et al, 2009) was used.…”

Section: Methodsmentioning

confidence: 99%

“…In 2012, Hsieh et al presented a technique for automatic segmentation of the phalanges and the epiphyseal/metaphyseal region (Hsieh et al, 2012). In 2017, F I G U R E 1 System architecture Hsieh et al developed a hierarchical algorithm for segmenting these regions (Hsieh et al, 2017). The bone age estimation accuracies when using the fully automated segmentation methods are not described.…”

Section: Related Workmentioning

confidence: 99%

“…A group of Taiwanese researchers have been studying computer‐aided bone estimation for 17 years (Fan, Hsieh, Jong, & Tiu, 2001; Hsieh, Chen, Jong, Liu, & Chiu, 2012; Hsieh, Jong, Chou, & Tiu, 2007; Hsieh, Liu, Jong, & Chen, 2017; Hsieh, Liu, Jong, & Tiu, 2010). In 2001, they proposed a method for automatic estimation of bone age based on the bones of the wrist region (Fan et al, 2001).…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Bone age estimation from carpal radiography images using deep learning

et al. 2020

View full text Add to dashboard Cite

Bone age estimation has been used in medicine to verify whether the bone structure development degree of a person corresponds to their chronological age. Such estimate is useful for prognosis about the development of children and adolescents, as well as for the diagnosis of endocrinological diseases. This work proposes a fully automated methodology for bone age estimation from carpal radiography images. The methodology comprises two steps, the preprocessing of the image and the classification using a convolutional neural network. The system accuracy for different types of preprocessing is evaluated. We compare the accuracy achieved using the full radiography image as input for the neural network and using only parts of the image corresponding to the Phalangeal region, the Epiphyseal region, and the concatenation of these parts with a crop around the wrist. Digital image processing techniques are employed to segment these regions. Experiments are performed using radiography images from the California University Database. The impact of using different pretrained neural networks for transfer learning is evaluated.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%