Computerized geometric features of carpal bone for bone age estimation

A fuzzy-based growth model with principle component analysis selection for carpal bone-age assessment

“…The above aspects are very important about the area ratio of the bone which has a higher discrimination power than the compactness factor in BA determination. The point of view coincides with most researchers' results [6,14,16]. The trend for Ratio-I of Capitate.…”

“…The method Fig. 1 The flow chat of the study was illustrated based on morphology produced a rectangular CROI with four points A, B, C, and D. The procedure of the details was proposed in the articles [6][7][8], and the CROI was presented as shown in Fig. 2.…”

“…In the wrist, carpals overlap each other gradually and the carpals look mixed when ossifying in children greater than 9 years old [4,17]; thus, it is difficult to assess the BA older than approximately 10 years only using the information of the carpals. However, the growth of carpals is most apparent from newborn up to approximately 10 years of age; therefore, carpals can be taken as a good indicator when constructing a BAA procedure for children [6,8,25]. In the past two decades, many studies were undertaken focusing on the development of computerized feature extraction or BAA methods by utilizing digitalized hand radiograph images.…”

Simplified radius, ulna, and short bone‐age assessment procedure using grouped‐Tanner‐Whitehouse method

“…However, these studies did not focus on simplifying the original structure of the TW3 method, so the need for further simplification still exists. Moreover, there is evidence that carpal growth order is slightly mismatched between Chinese and Western children 17 . That means that the TW2/TW3 methods should be modified to increase the accurate estimation of BA.…”

The age at death assessment in a multi-ethnic sample of pelvic bones using nature-inspired data mining methods

“…In this study, we tested a full portfolio of established data mining methods for model generation (e.g., decision trees, Bayesian networks, and nearest neighbours). The best results, however, were obtained through computational intelligence methods [53][54][55], which most likely explains the popularity of the use of similar methods in prior studies, e.g., for sex classification [56,57], age estimation of children [58], and adults [52]. In anthropology, such methods have been used for the classification of fossils using their teeth morphology [59,60].…”