Hand Pose Estimation for Pediatric Bone Age Assessment

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

doi:10.1007/978-3-030-32226-7_59

Cited by 37 publications

(46 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 1, our DI outperforms BoNet on the RSNA and RHPE with various percentages (10%, 20%, 40%, 100%) of the training samples available. Comparing to the public implemented version of BoNet [1], the bone age prediction part of DI is over 12× smaller in model size than the bone age prediction part of BoNet. Also, evaluated on the number of floating-point multiplication-adds (FLOPs) on our GPU, DI outperforms BoNet by a clear margin.…”

Section: Methodsmentioning

confidence: 99%

“…We evaluate Doctor Imitator (DI) on the RSNA-BAA dataset [1,3] and RHPE dateset [1]. RSNA-BAA contains 12,611 hand radiographs in the training set, 1,425 radiographs in the validation set, and 200 radiographs in the test set.…”

Section: Methodsmentioning

confidence: 99%

“…We compare DI with the state-of-the-art BoNet [1] on the MAD and model complexity. As the ground truth annotations of the RHPE test set are not available and the evaluation server [1] is not stable, we compare DI and BoNet on the validation set of RHPE. The performances of BoNet reported on the RHPE validation set are obtained by running the open source codes .…”

Section: Methodsmentioning

confidence: 99%

“…A relation computing module was introduced in [6] to better deal with the important parts of the hands. A new annotation for the Central Positions of Anatomical ROIs (CPAR) to the Radiological Society of North America BAA (RSNA-BAA) dataset was published [1], which provided the ground truth central positions of the anatomical region of interests (ROIs). Using the CPAR annotations, BoNet [1] promoted the performance of the challenge champion methods.…”

Section: Introductionmentioning

confidence: 99%

“…A new annotation for the Central Positions of Anatomical ROIs (CPAR) to the Radiological Society of North America BAA (RSNA-BAA) dataset was published [1], which provided the ground truth central positions of the anatomical region of interests (ROIs). Using the CPAR annotations, BoNet [1] promoted the performance of the challenge champion methods. Although these methods could obtain good performance in BAA, they used features of the entire hands and incurred poor interpretability.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Doctor Imitator: A Graph-Based Bone Age Assessment Framework Using Hand Radiographs

Chen¹,

Yu²,

Lei³

et al. 2020

Medical Image Computing and Computer Assisted Intervention – MICCAI 2020

View full text Add to dashboard Cite

Bone age assessment is challenging in clinical practice due to the complicated bone age assessment process. Current automatic bone age assessment methods were designed with rare consideration of the diagnostic logistics and thus may yield certain uninterpretable hidden states and outputs. Consequently, doctors can find it hard to cooperate with such models harmoniously because it is difficult to check the correctness of the model predictions. In this work, we propose a new graph-based deep learning framework for bone age assessment with hand radiographs, called Doctor Imitator (DI). The architecture of DI is designed to learn the diagnostic logistics of doctors using the scoring methods (e.g., the Tanner-Whitehouse method) for bone age assessment. Specifically, the convolutions of DI capture the local features of the anatomical regions of interest (ROIs) on hand radiographs and predict the ROI scores by our proposed Anatomy-based Group Convolution, summing up for bone age prediction. Besides, we develop a novel Dual Graph-based Attention module to compute patient-specific attention for ROI features and context attention for ROI scores. As far as we know, DI is the first automatic bone age assessment framework following the scoring methods without fully supervised hand radiographs. Experiments on hand radiographs with only bone age supervision verify that DI can achieve excellent performance with sparse parameters and provide more interpretability.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Doctor Imitator: A Graph-Based Bone Age Assessment Framework Using Hand Radiographs

Chen¹,

Yu²,

Lei³

et al. 2020

Medical Image Computing and Computer Assisted Intervention – MICCAI 2020

View full text Add to dashboard Cite

show abstract

SVTNet: Automatic bone age assessment network based on TW3 method 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