SIMBA: Specific Identity Markers for Bone Age Assessment

González, Cristina; Escobar, María; Daza, Laura; Torres, Fidel; Triana, Gustavo

doi:10.1007/978-3-030-59725-2_73

Cited by 12 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We included gender and bone age information for each individual in the annotation file of the Sekisui database. In addition, because the conversion of skeletal maturity scores to bone age is supported by the bone age scale, we used the Sekisui database to train and test the BoNet, 37 SIMBA, 38 Yitu‐AICARE, 39 and SMANet 40 models. The models that performed best on the validation set were used for comparison experiments.…”

Section: Comparison and Discussionmentioning

confidence: 99%

SVTNet: Automatic bone age assessment network based onTW3method and vision transformer

Wu,

Mi,

Zhang

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

This study aims to develop a proficient and clinically applicable algorithm that can accurately assess bone age. This algorithm is based on the principles of the Tanner‐Whitehouse 3 (TW3) integral approach, and aims to achieve efficiency, scalability, and interpretability. We developed a model for bone age prediction in children. The model was tested on a pediatric dataset from a tertiary care hospital consisting of left‐hand radiographs of children between the age of 0 and 18. Our model consists of removing the arm portion using a pre‐trained YOLO network, localizing 37 key points in the hand bone portion using a spatial configuration network, and segmenting the original image through 20 of these points to obtain 20 fixed‐size patches. Finally, each of the 20 bone images is classified by training a visual transformer (ViT) model. In this study, a hybrid network, SVTNet, was developed that incorporates visual transformers to obtain estimates of bone age in the carpal (C series) and metacarpal (RUS series) bones. The sum of the clinical TW3 scoring region scores and bone maturity scores were utilized to determine the bone age for each corresponding region. The performance of the algorithm was evaluated in terms of both training and testing by evaluating 3871 left hand X‐ray micrographs obtained from a tertiary hospital in China. The results showed that the average absolute error of bone age estimation was 0.50 years for the RUS series of bones and 0.47 years for the C series of bones. The main contribution of this study is to propose, for the first time, a ViT‐based bone age assessment method that automates the entire process of the TW3 algorithm and is clinically interpretable, with predictive accuracy comparable to that of an experienced orthopedic surgeon.

show abstract

Section: Comparison and Discussionmentioning

confidence: 99%

SVTNet: Automatic bone age assessment network based onTW3method and vision transformer

Wu,

Mi,

Zhang

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…A mean error of six months was achieved in the RSNA testing set. González et al [37] fused information from identity markers with visual features from raw hand bone X-rays and used this representation to estimate the relative bone age with an MAE of 5.47 months. Liu et al [38] applied ranked learning for the BAA and used VGG-U-Net to segment the hand and wrist.…”

Section: Discussionmentioning

confidence: 99%

“…Larson [36] Improved ResNet-50 6.0 González [37] Identity label + Inception-V3 5.47 Liu [38] Ranked learning + VGG-U-Net + GAN 6.05 Halabi [39] Sex + Inception v3 + Dense 4.2, 4.4, 4.5 (top3) Iglovikov [14] U-Net + key point detection 4.97 Koitka [40] Faster-RCNN + sex regression network 4.56 Liu [41] One-stage attention + age recognition network 4.38 Chen [42] Attention + joint age distribution learning 4.4 Ours Two-stage + alignment + sex token 4.586…”

Section: Methods Mae (Months)mentioning

confidence: 99%

Automated Skeletal Bone Age Assessment with Two-Stage Convolutional Transformer Network Based on X-ray Images

Mao

Hui

Zhu³

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Human skeletal development is continuous and staged, and different stages have various morphological characteristics. Therefore, bone age assessment (BAA) can accurately reflect the individual’s growth and development level and maturity. Clinical BAA is time consuming, highly subjective, and lacks consistency. Deep learning has made considerable progress in BAA in recent years by effectively extracting deep features. Most studies use neural networks to extract global information from input images. However, clinical radiologists are highly concerned about the ossification degree in some specific regions of the hand bones. This paper proposes a two-stage convolutional transformer network to improve the accuracy of BAA. Combined with object detection and transformer, the first stage mimics the bone age reading process of the pediatrician, extracts the hand bone region of interest (ROI) in real time using YOLOv5, and proposes hand bone posture alignment. In addition, the previous information encoding of biological sex is integrated into the feature map to replace the position token in the transformer. The second stage extracts features within the ROI by window attention, interacts between different ROIs by shifting the window attention to extract hidden feature information, and penalizes the evaluation results using a hybrid loss function to ensure its stability and accuracy. The proposed method is evaluated on the data from the Pediatric Bone Age Challenge organized by the Radiological Society of North America (RSNA). The experimental results show that the proposed method achieves a mean absolute error (MAE) of 6.22 and 4.585 months on the validation and testing sets, respectively, and the cumulative accuracy within 6 and 12 months reach 71% and 96%, respectively, which is comparable to the state of the art, markedly reducing the clinical workload and realizing rapid, automatic, and high-precision assessment.

show abstract

“…Results demonstrated an average variation between automated and manual assessments of approximately 0.8 years. Recently, Cristina et al [ 20 ] proposed a specific identity labels-based bone age assessment (SIMBA) model, which involved the gender as well as the age of patients. Different from the other bone age assessment methods, this model calculates the relative bone age according to the difference between practical age and bone age.…”

Section: Related Workmentioning

confidence: 99%

“…Results demonstrated an average variation between automated and manual assessments of approximately 0.8 years. Recently, Cristina et al [20] The third category adopts a ROI-based method with the multi-stage structure to predict bone age, which extracts local information and ultimately predicts bone age by introducing prior knowledge for image segmentation or hand bone ROIs detection. For instance, Escobar et al [21] proposed the Bonet which introduced a hand detection module and pose estimation module to the BBA system.…”

Section: Related Workmentioning

confidence: 99%

Multi-Branch Attention Learning for Bone Age Assessment with Ambiguous Label

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Bone age assessment (BAA) is a typical clinical technique for diagnosing endocrine and metabolic diseases in children’s development. Existing deep learning-based automatic BAA models are trained on the Radiological Society of North America dataset (RSNA) from Western populations. However, due to the difference in developmental process and BAA standards between Eastern and Western children, these models cannot be applied to bone age prediction in Eastern populations. To address this issue, this paper collects a bone age dataset based on the East Asian populations for model training. Nevertheless, it is laborious and difficult to obtain enough X-ray images with accurate labels. In this paper, we employ ambiguous labels from radiology reports and transform them into Gaussian distribution labels of different amplitudes. Furthermore, we propose multi-branch attention learning with ambiguous labels network (MAAL-Net). MAAL-Net consists of a hand object location module and an attention part extraction module to discover the informative regions of interest (ROIs) based only on image-level labels. Extensive experiments on both the RSNA dataset and the China Bone Age (CNBA) dataset demonstrate that our method achieves competitive results with the state-of-the-arts, and performs on par with experienced physicians in children’s BAA tasks.

show abstract

SIMBA: Specific Identity Markers for Bone Age Assessment

Cited by 12 publications

References 19 publications

SVTNet: Automatic bone age assessment network based onTW3method and vision transformer

SVTNet: Automatic bone age assessment network based onTW3method and vision transformer

Automated Skeletal Bone Age Assessment with Two-Stage Convolutional Transformer Network Based on X-ray Images

Multi-Branch Attention Learning for Bone Age Assessment with Ambiguous Label

Contact Info

Product

Resources

About