Self-Supervised Attention Mechanism for Pediatric Bone Age Assessment With Efficient Weak Annotation

Liu, Chuanbin; Xie, Hongtao; Zhang, Yongdong

doi:10.1109/tmi.2020.3046672

Cited by 16 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Essentially, the visualized heat maps confirm that the proposed neural network is attending to the critical locations, aligning with conventional clinical approaches that focus on carpals, metacarpals, and phalanx. In comparison, the ResNet50 method, a ROI-free approach, concentrate activation on the metacarpal areas, which may limit recognition learning and make it tendentious (Liu et al, 2020). Thus, the feature activation from the proposed deep network is explainable.…”

Section: Resultsmentioning

confidence: 99%

Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction

Chen

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

Bone age assessment (BAA) from hand radiographs is crucial for diagnosing endocrinology disorders in adolescents and supplying therapeutic investigation. In practice, due to the conventional clinical assessment being a subjective estimation, the accuracy of BAA relies highly on the pediatrician's professionalism and experience. Recently, many deep learning methods have been proposed for the automatic estimation of bone age and had good results. However, these methods do not exploit sufficient discriminative information or require additional manual annotations of critical bone regions that are important biological identifiers in skeletal maturity, which may restrict the clinical application of these approaches. In this research, we propose a novel two-stage deep learning method for BAA without any manual region annotation, which consists of a cascaded critical bone region extraction network and a gender-assisted bone age estimation network. First, the cascaded critical bone region extraction network automatically and sequentially locates two discriminative bone regions via the visual heat maps. Second, in order to obtain an accurate BAA, the extracted critical bone regions are fed into the gender-assisted bone age estimation network. The results showed that the proposed method achieved a mean absolute error (MAE) of 5.45 months on the public dataset Radiological Society of North America (RSNA) and 3.34 months on our private dataset.

show abstract

Section: Resultsmentioning

confidence: 99%

Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction

Chen

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Visualization experiments based on gradient-weighted class activation mapping (Grad-CAM) have been previously conducted to locate and identify the activation area over the input images to explain the feature learning and classification results of the DL models ( Panwar et al, 2020 ; Liu C. et al, 2021 ). In addition, Grad-CAM technology uses gradient information flowing into the last convolution layer to assess the weight of each neuron in the final decision of the fresh VCFs ( Mu et al, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

Deep learning-based automated high-accuracy location and identification of fresh vertebral compression fractures from spinal radiographs: a multicenter cohort study

Zhang,

Xu,

Guo

et al. 2024

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

BackgroundDigital radiography (DR) is a common and widely available examination. However, spinal DR cannot detect bone marrow edema, therefore, determining vertebral compression fractures (VCFs), especially fresh VCFs, remains challenging for clinicians.MethodsWe trained, validated, and externally tested the deep residual network (DRN) model that automated the detection and identification of fresh VCFs from spinal DR images. A total of 1,747 participants from five institutions were enrolled in this study and divided into the training cohort, validation cohort and external test cohorts (YHDH and BMUH cohorts). We evaluated the performance of DRN model based on the area under the receiver operating characteristic curve (AUC), feature attention maps, sensitivity, specificity, and accuracy. We compared it with five other deep learning models and validated and tested the model internally and externally and explored whether it remains highly accurate for an external test cohort. In addition, the influence of old VCFs on the performance of the DRN model was assessed.ResultsThe AUC was 0.99, 0.89, and 0.88 in the validation, YHDH, and BMUH cohorts, respectively, for the DRN model for detecting and discriminating fresh VCFs. The accuracies were 81.45% and 72.90%, sensitivities were 84.75% and 91.43%, and specificities were 80.25% and 63.89% in the YHDH and BMUH cohorts, respectively. The DRN model generated correct activation on the fresh VCFs and accurate peak responses on the area of the target vertebral body parts and demonstrated better feature representation learning and classification performance. The AUC was 0.90 (95% confidence interval [CI] 0.84–0.95) and 0.84 (95% CI 0.72–0.93) in the non-old VCFs and old VCFs groups, respectively, in the YHDH cohort (p = 0.067). The AUC was 0.89 (95% CI 0.84–0.94) and 0.85 (95% CI 0.72–0.95) in the non-old VCFs and old VCFs groups, respectively, in the BMUH cohort (p = 0.051).ConclusionIn present study, we developed the DRN model for automated diagnosis and identification of fresh VCFs from spinal DR images. The DRN model can provide interpretable attention maps to support the excellent prediction results, which is the key that most clinicians care about when using the model to assist decision-making.

show abstract

“…Deep learning performed on radiographs using convolutional and regression networks has been used for bone age assessments as bone age is an important measure of skeletal growth and biological maturity, indicating possible disorders in children [21][22][23][24]. Chest X-ray radiographs are considered the best, but they are a very challenging imaging modality for early and optimal pneumonia diagnosis in children.…”

Section: Deductive Content Analysis Of the Most Prolific Machine Lear...mentioning

confidence: 99%

Artificial Intelligence and Pediatrics: Synthetic Knowledge Synthesis

Završnik,

Kokol,

Žlahtič

et al. 2024

Electronics

View full text Add to dashboard Cite

The first publication on the use of artificial intelligence (AI) in pediatrics dates back to 1984. Since then, research on AI in pediatrics has become much more popular, and the number of publications has largely increased. Consequently, a need for a holistic research landscape enabling researchers and other interested parties to gain insights into the use of AI in pediatrics has arisen. To fill this gap, a novel methodology, synthetic knowledge synthesis (SKS), was applied. Using SKS, we identified the most prolific countries, institutions, source titles, funding agencies, and research themes and the most frequently used AI algorithms and their applications in pediatrics. The corpus was extracted from the Scopus (Elsevier, The Netherlands) bibliographic database and analyzed using VOSViewer, version 1.6.20. Done An exponential growth in the literature was observed in the last decade. The United States, China, and Canada were the most productive countries. Deep learning was the most used machine learning algorithm and classification, and natural language processing was the most popular AI approach. Pneumonia, epilepsy, and asthma were the most targeted pediatric diagnoses, and prediction and clinical decision making were the most frequent applications.

show abstract

Self-Supervised Attention Mechanism for Pediatric Bone Age Assessment With Efficient Weak Annotation

Cited by 16 publications

References 47 publications

Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction

Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction

Deep learning-based automated high-accuracy location and identification of fresh vertebral compression fractures from spinal radiographs: a multicenter cohort study

Artificial Intelligence and Pediatrics: Synthetic Knowledge Synthesis

Contact Info

Product

Resources

About