Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment

Chen, Chao; Chen, Zhihong; Jin, Xinyu; Li, Lanjuan; Speier, William; Arnold, Corey

doi:10.1109/jbhi.2021.3095128

Cited by 25 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these RoI-free methods can save a lot of manpower and materials for annotations. The method in [ 36 ] predicted bone age by using a two-stage network, which does not require ROI annotation yet achieves comparable performance as the ROI-based method. However, this method suffers some limitations because it cannot apply end-to-end training.…”

Section: Experiments and Resultsmentioning

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

Section: Experiments and Resultsmentioning

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

show abstract

“…The other category is the automatic BAA algorithm that combines local and global features and exhibits better performance. Cao et al (16) (18) proposed an attention-guided approach to obtain ROIs from whole-hand images and then aggregated these ROIs for BAA.…”

Section: Related Workmentioning

confidence: 99%

SMANet: multi-region ensemble of convolutional neural network model for skeletal maturity assessment

Zhang

Zhu

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Bone age assessment (BAA) is a crucial research topic in pediatric radiology. Interest in the development of automated methods for BAA is increasing. The current BAA algorithms based on deep learning have displayed the following deficiencies: (I) most methods involve end-to-end prediction, lacking integration with clinically interpretable methods; (II) BAA methods exhibit racial and geographical differences.Methods: A novel, automatic skeletal maturity assessment (SMA) method with clinically interpretable methods was proposed based on a multi-region ensemble of convolutional neural networks (CNNs). This method predicted skeletal maturity scores and thus assessed bone age by utilizing left-hand radiographs and key regional patches of clinical concern.Results: Experiments included 4,861 left-hand radiographs from the database of Beijing Jishuitan Hospital and revealed that the mean absolute error (MAE) was 31.4±0.19 points (skeletal maturity scores) and 0.45±0.13 years (bone age) for the carpal bones-series and 29.9±0.21 points and 0.43±0.17 years, respectively, for the radius, ulna, and short (RUS) bones series based on the Tanner-Whitehouse 3 (TW3) method. Conclusions:The proposed automatic SMA method, which was without racial and geographical influence, is a novel, automatic method for assessing childhood bone development by utilizing skeletal maturity.Furthermore, it provides a comparable performance to endocrinologists, with greater stability and efficiency.

show abstract

“…For example, the test sets in Refs. [12][13][14][15] are with sizes 307, 200, 500, and 200 respectively. In this work, without loss of generality, we use only a portion of the bone age data selected from the RSNA in order to show the effectiveness of the proposed unsupervised deep-learning method.…”

Section: The Dataset: the Data Selection And The Classificationmentioning

confidence: 99%

“…[12] reports the MAE of the bone age assessment 4.7 months with the whole hand, and 5.1 months with the index finger. In 2020, Chen Chao et al propose an attention-guided approach to automatically localize the discriminative regions for bone age assessment achieving the MAE 4.3 months [13]. In 2021, Zhang Y et al extracted skeletal features based on the inception V3 neural network, and use the adversarial regression learning network (ARLNet) to obtain an MAE of 3.01 months [14].…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Deep-Learning Method for Bone Age Assessment

Zhu¹,

Nie²,

Hou³

et al. 2022

Preprint

View full text Add to dashboard Cite

The bone age, reflecting the degree of development of the bones, can be used to predict the adult height and detect endocrine diseases of children. Both examinations of radiologists and variability of operators have a significant impact on bone age assessment. To decrease human intervention , machine learning algorithms are used to assess the bone age automatically. However, conventional supervised deep-learning methods need pre-labeled data. In this paper, based on the convolutional auto-encoder with constraints (CCAE), an unsupervised deep-learning model proposed in the classification of the fingerprint, we propose this model for the classification of the bone age and baptize it BA-CCAE. In the proposed BA-CCAE model, the key regions of the raw X-ray images of the bone age are encoded, yielding the latent vectors. The K-means clustering algorithm is used to obtain the final classifications by grouping the latent vectors of the bone images. A set of experiments on the Radiological Society of North America pediatric bone age dataset (RSNA) show that the accuracy of classifications at 48-month intervals is 76.15%. Although the accuracy now is lower than most of the existing supervised models, the proposed BA-CCAE model can establish the classification of bone age without any pre-labeled data, and to the best of our knowledge, the proposed BA-CCAE is one of the few trails using the unsupervised deep-learning method for the bone age assessment.

show abstract

Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment

Cited by 25 publications

References 37 publications

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

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

SMANet: multi-region ensemble of convolutional neural network model for skeletal maturity assessment

An Unsupervised Deep-Learning Method for Bone Age Assessment

Contact Info

Product

Resources

About