Fully Automatic Model Based on SE-ResNet for Bone Age Assessment

He, Jin; Jiang, Dan

doi:10.1109/access.2021.3074713

Cited by 32 publications

(17 citation statements)

References 25 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking out the inception layer essentially created a ResNet based model with SE blocks added. Several studies have reported that adding SE blocks to the base ResNet increased performance (Xu and Zhang, 2020 ; He and Jiang, 2021 ). When tested on the ImageNet validation set, there was also a decrease in error by 0.86% which is in agreement with our results (Rodrigues et al, 2020 ).…”

Section: Discussionmentioning

confidence: 99%

Automatic Artifact Detection Algorithm in Fetal MRI

Lim

Wagner

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Fetal MR imaging is subject to artifacts including motion, chemical shift, and radiofrequency artifacts. Currently, such artifacts are detected by the MRI operator, a process which is subjective, time consuming, and prone to errors. We propose a novel algorithm, RISE-Net, that can consistently, automatically, and objectively detect artifacts in 3D fetal MRI. It makes use of a CNN ensemble approach where the first CNN aims to identify and classify any artifacts in the image, and the second CNN uses regression to determine the severity of the detected artifacts. The main mechanism in RISE-Net is the stacked Residual, Inception, Squeeze and Excitation (RISE) blocks. This classification network achieved an accuracy of 90.34% and a F1 score of 90.39% and outperformed other state-of-the-art architectures, such as VGG-16, Inception, ResNet-50, ReNet-Inception, SE-ResNet, and SE-Inception. The severity regression network had an MSE of 0.083 across all classes. The presented algorithm facilitates rapid and accurate fetal MRI quality assurance that can be implemented into clinical use.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Artifact Detection Algorithm in Fetal MRI

Lim

Wagner

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Both methods [19], [20] have compared the proposed networks' performance with pre-trained networks such as VGG, R-CNN, GoogLeNet, and OxfordNet, demonstrating the proposed methods' superiority. In [21], an unsupervised learning method has been used with convolution layers to extract the largest area as the hand region.…”

Section: Related Workmentioning

confidence: 95%

“…BAA studies based on the deep learning algorithm are explained in the following. In [19], a compression module with 15 convolution layers and 4 pooling layers for big data compression and combined SE (squeeze-and-excitation) and ResNet with over 16 feature extraction and classification layers has presented. [20] has introduced a 15-layer convolutional network called BoNet for bone age assessment.…”

Section: Related Workmentioning

confidence: 99%

A Bone Age Assessment based on a hybrid Knowledge Distillation Paradigm using single ROI

Mardanpour

Sepahvand

Abdali-Mohammadi

et al. 2022

Preprint

View full text Add to dashboard Cite

Bone age assessment (BAA) has been widely used in clinical area from pediatric endocrine diagnosis to estimating height of children for adulthood. Advancements in technology has accelerated the evolution of BAA methodologies, one of which is deep learning algorithms, which overcome the drawbacks of conventional approaches. In spite of excellent effectiveness of deep neural networks in detection of the correct class for bone age, they have a significant degree of complexity due to the numerous parameters they employ for each ROI. Therefore, they are not suitable for implementation in edge devices with limited resources. In this paper, we propose a BAA method using a hybrid knowledge distillation (KD) paradigm in order to conquer this difficulty by mapping different ROIs into a single ROI. In this regard, the student receives knowledge from a teacher network that has been pre-trained on six ROIs including bones of five fingers and the wrist, transfers the knowledge of its final response layer and internal layers to the student. Then, six student models each of which is constructed based on just one of these ROIs, while receiving the information of the teacher model by matching the feature maps of intermediate layers and last output of teacher with those of student in distillation modules. Empirical results on Digital Hand Atlas (DHA) report that our student model trained on one ROI obtains 95% accuracy on 19 classes of bone age makes it appropriate for medical IoT deployment. Also, it has competitive performance compared to the other state-of-the-art BAA studies, and performance analysis of our KD with three base KD models indicates superiority of our introduced method.

show abstract

“…Larson et al (14) trained models using CNNs that were compared by radiologists, exhibiting a mean difference of 0 years between the neural network models and the BAA of radiologists, with a mean effective value and mean absolute difference (MAD) of 0.63 and 0.50, respectively. He et al (15) proposed a novel, end-to-end BAA approach that was based on lossless image compression and compressionstimulated deep residual networks. However, these methods omitted the inclusion of specific bone parts as ROIs.…”

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

Fully Automatic Model Based on SE-ResNet for Bone Age Assessment

Cited by 32 publications

References 25 publications

Automatic Artifact Detection Algorithm in Fetal MRI

Automatic Artifact Detection Algorithm in Fetal MRI

A Bone Age Assessment based on a hybrid Knowledge Distillation Paradigm using single ROI

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

Contact Info

Product

Resources

About