An empirical study on global bone age assessment

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

doi:10.1117/12.2542431

Cited by 6 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We employ EfficientNets [33] as backbone feature extractors. In comparison to previously proposed end-to-end learning methods [14, 34], our applied average pooling reduces the dimensionality of the learned features and, thus, decreases the model size. For example, the largest of our BA models has a feature dimensionality of 1, 792 resulting in a total network size of 23 * 10 6 parameters, while the configuration proposed by [34] uses a feature dimensionality of 33, 712 and 82 * 10 6 parameters.…”

Section: Methodsmentioning

confidence: 99%

“…In comparison to previously proposed end-to-end learning methods [14, 34], our applied average pooling reduces the dimensionality of the learned features and, thus, decreases the model size. For example, the largest of our BA models has a feature dimensionality of 1, 792 resulting in a total network size of 23 * 10 6 parameters, while the configuration proposed by [34] uses a feature dimensionality of 33, 712 and 82 * 10 6 parameters. All the details of our model training are described in Appendix B, and the code for training the BA models is available at github.com/aimi-bonn/Deeplasia.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias

Rassmann

Keller

Skaf

et al. 2023

Preprint

View full text Add to dashboard Cite

Skeletal dysplasias collectively affect a large number of patients worldwide. The majority of these disorders cause growth anomalies. Hence, assessing skeletal maturity via determining the bone age (BA) is one of the most valuable tools for their diagnoses. Moreover, consecutive BA assessments are crucial for monitoring the pediatric growth of patients with such disorders, especially for timing hormone treatments or orthopedic interventions. However, manual BA assessment is time-consuming and suffers from high intra-and inter-rater variability. This is further exacerbated by genetic disorders causing severe skeletal malformations. While numerous approaches to automatize BA assessment were proposed, few were validated for BA assessment on children with abnormal development. In this work, we present Deeplasia, an open-source prior-free deep-learning ensemble approach. After training on the public RSNA BA dataset, we achieve state-of-the-art performance with a mean absolute difference (MAD) of 3.87 months based on the average of six different reference ratings. Next, we demonstrate that Deeplasia generalizes to an unseen dataset of 568 X-ray images from 189 patients with molecularly confirmed diagnoses of seven different genetic bone disorders (including Achondroplasia and Hypochondroplasia) achieving a MAD of 5.84 months w.r.t. to the average of two references. Further, using longitudinal data from a subset of the cohort (149 images), we estimate the test-retest precision of our model ensemble to be at least at the human expert level (2.74 months). We conclude that Deeplasia suits assessing and monitoring the BA in patients with skeletal dysplasias.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias

Rassmann

Keller

Skaf

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Spampinato et al [15] validate the effectiveness of deep CNNs pre-trained on general imagery in the bone age regression model. Torres et al [19] introduce a carefully tuned architecture called GPNet for BAA. Even though achieving promising results, these models do not consider the local information of different bones.…”

Section: Related Workmentioning

confidence: 99%

Improve bone age assessment by learning from anatomical local regions

Wang

Zhang

Ding

et al. 2020

Preprint

View full text Add to dashboard Cite

Skeletal bone age assessment (BAA), as an essential imaging examination, aims at evaluating the biological and structural maturation of human bones. In the clinical practice, Tanner and Whitehouse (TW2) method is a widely-used method for radiologists to perform BAA. The TW2 method splits the hands into Region Of Interests (ROI) and analyzes each of the anatomical ROI separately to estimate the bone age. Because of considering the analysis of local information, the TW2 method shows accurate results in practice. Following the spirit of TW2, we propose a novel model called Anatomical Local-Aware Network (ALA-Net) for automatic bone age assessment. In ALA-Net, anatomical local extraction module is introduced to learn the hand structure and extract local information. Moreover, we design an anatomical patch training strategy to provide extra regularization during the training process. Our model can detect the anatomical ROIs and estimate bone age jointly in an end-to-end manner. The experimental results show that our ALA-Net achieves a new state-of-the-art single model performance of 3.91 mean absolute error (MAE) on the public available RSNA dataset. Since the design of our model is well consistent with the well recognized TW2 method, it is interpretable and reliable for clinical usage.

show abstract

“…In our previous work [3], we created the Radiological Hand Pose Estimation (RHPE) dataset, which includes information of bone age, gender, anatomical RoIs, and chronological age for a cohort with a different ethnicity than the previously available dataset. There have been several automated methods for BAA that focus on a global approach [8,13,17,21], like what physicians do in G & P, and other approaches that exploit the local information [1,3,10,11,14], in a way inspired by TW2, to predict the bone age of the child.…”

Section: Introductionmentioning

confidence: 99%

SIMBA: Specific Identity Markers for Bone Age Assessment

González¹,

Escobar²,

Daza³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Bone Age Assessment (BAA) is a task performed by radiologists to diagnose abnormal growth in a child. In manual approaches, radiologists take into account different identity markers when calculating bone age, i.e., chronological age and gender. However, the current automated Bone Age Assessment methods do not completely exploit the information present in the patient's metadata. With this lack of available methods as motivation, we present SIMBA: Specific Identity Markers for Bone Age Assessment. SIMBA is a novel approach for the task of BAA based on the use of identity markers. For this purpose, we build upon the state-of-the-art model, fusing the information present in the identity markers with the visual features created from the original hand radiograph. We then use this robust representation to estimate the patient's relative bone age: the difference between chronological age and bone age. We validate SIMBA on the Radiological Hand Pose Estimation dataset and find that it outperforms previous state-of-the-art methods. SIMBA sets a trend of a new wave of Computer-aided Diagnosis methods that incorporate all of the data that is available regarding a patient. To promote further research in this area and ensure reproducibility we will provide the source code as well as the pre-trained models of SIMBA.

show abstract

An empirical study on global bone age assessment

Cited by 6 publications

References 20 publications

Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias

Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias

Improve bone age assessment by learning from anatomical local regions

SIMBA: Specific Identity Markers for Bone Age Assessment

Contact Info

Product

Resources

About