Extract Bone Parts Without Human Prior: End-to-end Convolutional Neural Network for Pediatric Bone Age Assessment

Liu, Chuanbin; Xie, Hongtao; Liu, Yizhi; Zha, Zheng-Jun; Lin, Fanchao; Zhang, Yongdong

doi:10.1007/978-3-030-32226-7_74

Cited by 18 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human [10] 7.32 Larson [10] 6.24 Ren [14] 5.20 Iglovikov [7] 4.97 PRSNet [8] 4.49 AR-CNN [11] 4.38 BoNet [2] 4.14 ALA-Net(Our)…”

Section: Methods Global Local Maementioning

confidence: 99%

“…PRSNet [8] uses a part selection module to select the most helpful hand parts for BAA and uses part relation module to model the multi-scale context information. Liu et al [11] propose to use the attention agent to discover the discriminative bone parts and extract features from these parts. Although the importance of bone part information is emphasized in their methods, there are also certain limitations.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

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

“…Human [10] 7.32 Larson [10] 6.24 Ren [14] 5.20 Iglovikov [7] 4.97 PRSNet [8] 4.49 AR-CNN [11] 4.38 BoNet [2] 4.14 ALA-Net(Our)…”

Section: Methods Global Local Maementioning

confidence: 99%

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

show abstract

“…Since discriminative local region details play an important role for FGVC, learning to propose the discriminative regions possesses high importance in recent researches (Xie et al 2019) (Liu et al 2019a). A series of methods have been proposed by utilizing filter response to detect the corresponding discriminative region.…”

Section: Discriminative Region Proposingmentioning

confidence: 99%

Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization

Liu

Xie

Zha

et al. 2020

AAAI

Self Cite

125

View full text Add to dashboard Cite

Delicate attention of the discriminative regions plays a critical role in Fine-Grained Visual Categorization (FGVC). Unfortunately, most of the existing attention models perform poorly in FGVC, due to the pivotal limitations in discriminative regions proposing and region-based feature learning. 1) The discriminative regions are predominantly located based on the filter responses over the images, which can not be directly optimized with a performance metric. 2) Existing methods train the region-based feature extractor as a one-hot classification task individually, while neglecting the knowledge from the entire object. To address the above issues, in this paper, we propose a novel “Filtration and Distillation Learning” (FDL) model to enhance the region attention of discriminate parts for FGVC. Firstly, a Filtration Learning (FL) method is put forward for discriminative part regions proposing based on the matchability between proposing and predicting. Specifically, we utilize the proposing-predicting matchability as the performance metric of Region Proposal Network (RPN), thus enable a direct optimization of RPN to filtrate most discriminative regions. Go in detail, the object-based feature learning and region-based feature learning are formulated as “teacher” and “student”, which can furnish better supervision for region-based feature learning. Accordingly, our FDL can enhance the region attention effectively, and the overall framework can be trained end-to-end without neither object nor parts annotations. Extensive experiments verify that FDL yields state-of-the-art performance under the same backbone with the most competitive approaches on several FGVC tasks.

show abstract

“…Wang et al [17] followed the structure of Faster-RCNN to predict bone ages. Besides, attention methods were utilized in [2,10] to highlight the essential parts of the hands. A relation computing module was introduced in [6] to better deal with the important parts of the hands.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, various automatic BAA methods were proposed [1,2,10,19]. Similar to the processing of the GP method, most of these models predicted bone ages by capturing the features of the entire hand, which benefited from the capability of deep learning models.…”

Section: Introductionmentioning

confidence: 99%

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

Extract Bone Parts Without Human Prior: End-to-end Convolutional Neural Network for Pediatric Bone Age Assessment

Cited by 18 publications

References 12 publications

Improve bone age assessment by learning from anatomical local regions

Improve bone age assessment by learning from anatomical local regions

Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization

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

Contact Info

Product

Resources

About