Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms

Şenol, Deniz; BODUR, Furkan; Seçgin, Yusuf; Bakıcı, Rukiye Sümeyye; Şahin, Nihat Ege; Toy, Serkan; Öner, Serkan; Öner, Zübeyde

doi:10.5603/fm.a2022.0052

Cited by 9 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is often employed for assessing the physiological condition of animal organisms [16][17][18][19]. In addition, many phenotypic traits of most organisms can also be measured or analyzed from X-ray images [20][21][22]. However, the level of automation in the aforementioned studies remains relatively low, as they still require human intervention for image analysis.…”

Section: Introductionmentioning

confidence: 99%

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Zhu,

Li,

Yang

et al. 2024

Animals

View full text Add to dashboard Cite

Accurately estimating the breast muscle weight of broilers is important for poultry production. However, existing related methods are plagued by cumbersome processes and limited automation. To address these issues, this study proposed an efficient method for predicting the breast muscle weight of broilers. First, because existing deep learning models struggle to strike a balance between accuracy and memory consumption, this study designed a multistage attention enhancement fusion segmentation network (MAEFNet) to automatically acquire pectoral muscle mask images from X-ray images. MAEFNet employs the pruned MobileNetV3 as the encoder to efficiently capture features and adopts a novel decoder to enhance and fuse the effective features at various stages. Next, the selected shape features were automatically extracted from the mask images. Finally, these features, including live weight, were input to the SVR (Support Vector Regression) model to predict breast muscle weight. MAEFNet achieved the highest intersection over union (96.35%) with the lowest parameter count (1.51 M) compared to the other segmentation models. The SVR model performed best (R2 = 0.8810) compared to the other prediction models in the five-fold cross-validation. The research findings can be applied to broiler production and breeding, reducing measurement costs, and enhancing breeding efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Zhu,

Li,

Yang

et al. 2024

Animals

View full text Add to dashboard Cite

show abstract

Anthropometric measurements of the foot cannot predict the screw diameter for fifth metatarsal fractures intramedullary fixation

Symeonidis,

Totlis,

Dermitzakis

et al. 2023

Surg Radiol Anat

View full text Add to dashboard Cite

Purpose The present study aimed to evaluate the accuracy of anthropometric foot measurements in predicting the diameter of the intramedullary screw for fifth metatarsal fracture fixation. Secondary aim was to identify whether the fifth metatarsal intramedullary canal diameter is correlated to the fifth metatarsal length and the foot dimensions. Methods In 29 cadaveric feet, the maximum length of the plantar surface of the foot (PL) and the perimeter of the foot at the level of the fifth metatarsal base (PBFM) were measured using a measuring tape. Subsequently, the fifth metatarsal was excised. Using Computed Tomography scan, the metatarsal length (FML), and the horizontal (HDI) and vertical diameter (VDI) at the isthmus level were measured. The HDI values were grouped in 5 mm increments to correspond to the recommended screw diameter (RSD) for intramedullary fixation. A univariate linear regression analysis considered RSD and HDI as the dependent variables and FML, PL, PBFM as the independent variables. A multivariate regression analysis was performed to examine the predictive value of the two anthropometric measurements. A p-value < 0.05 was considered statistically significant. Results All six univariate analyses revealed that the dependent variable was significantly correlated with the independent variable. However, the multivariate regression models showed that the anthropometric measurements were not significantly correlated with the RSD and HDI. Conclusion The current study found an association between the fifth metatarsal intramedullary canal diameter and the fifth metatarsal length and foot anthropometric dimensions. However, the anthropometric measurements of the foot presented a low predictive value for the decision of an intramedullary screw diameter in the treatment of fractures of the base of the fifth metatarsal.

show abstract

Sex estimation from Thai hand radiographs using convolutional neural networks

Nonthasaen

Mahikul

Chobpenthai

et al. 2023

Forensic Science International: Reports

View full text Add to dashboard Cite

Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms

Cited by 9 publications

References 32 publications

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning

Anthropometric measurements of the foot cannot predict the screw diameter for fifth metatarsal fractures intramedullary fixation

Sex estimation from Thai hand radiographs using convolutional neural networks

Contact Info

Product

Resources

About