Ensemble Learning with Multiclassifiers on Pediatric Hand Radiograph Segmentation for Bone Age Assessment

Li, Rui; Jia, Yuanyuan; He, Xiufeng; Li, Zhe; Cai, Jun; Li, Hao; Xiao, Yang

doi:10.1155/2020/8866700

Cited by 3 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Pan et al [22] introduced a U-Net based model, which consists of image segmentation, feature extraction, and ensemble modules. More recently, Liu et al [23] proposed a bone age assessment model, which is trained on multiclassifiers based on ensemble learning, to predict the optimal segmentation threshold for hand mask segmentation. In [24], a region-based feature connected layer from the essential seg-mented region of a hand X-ray is introduced in order to predict bone age using deep learning models.…”

Section: Related Workmentioning

confidence: 99%

Ridge Regression Neural Network for Pediatric Bone Age Assessment

Salim¹,

Hamza²

2021

Preprint

View full text Add to dashboard Cite

Bone age is an important measure for assessing the skeletal and biological maturity of children. Delayed or increased bone age is a serious concern for pediatricians, and needs to be accurately assessed in a bid to determine whether bone maturity is occurring at a rate consistent with chronological age. In this paper, we introduce a unified deep learning framework for bone age assessment using instance segmentation and ridge regression. The proposed approach consists of two integrated stages. In the first stage, we employ an image annotation and segmentation model to annotate and segment the hand from the radiographic image, followed by background removal. In the second stage, we design a regression neural network architecture composed of a pre-trained convolutional neural network for learning salient features from the segmented pediatric hand radiographs and a ridge regression output layer for predicting the bone age. Experimental evaluation on a dataset of hand radiographs demonstrates the competitive performance of our approach in comparison with existing deep learning based methods for bone age assessment.

show abstract

Section: Related Workmentioning

confidence: 99%

Ridge Regression Neural Network for Pediatric Bone Age Assessment

Salim¹,

Hamza²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Ridge regression neural network for pediatric bone age assessment

Salim

Hamza

2021

Multimed Tools Appl

View full text Add to dashboard Cite

Ensemble Image Explainable AI (XAI) Algorithm for Severe Community-Acquired Pneumonia and COVID-19 Respiratory Infections

Zou

Goh

Liew

et al. 2023

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

Since the onset of the COVID-19 pandemic in 2019, many clinical prognostic scoring tools have been proposed or developed to aid clinicians in the disposition and severity assessment of pneumonia. However, there is limited work that focuses on explaining techniques that are best suiteds for clinicians in their decision making. In this paper, we present a new image explainability method named Ensemble XAI, which is based on the SHAP and Grad-CAM++ methods. It provides a visual explanation for a deep learning prognostic model that predicts the mortality risk of community-acquired pneumonia and COVID-19 respiratory infected patients. In addition, we surveyed the existing literature and compiled prevailing quantitative and qualitative metrics to systematically review the efficacy of Ensemble XAI, and to make comparisons with several state-of-the-art explainability methods (LIME, SHAP, Saliency Map, Grad-CAM, Grad-CAM++). Our quantitative experimental results have shown that Ensemble XAI has an comparable absence impact (decision impact: 0.72, confident impact: 0.24). Our qualitative experiment, in which a panel of 3 radiologists were involved to evaluate the degree of concordance and trust in the algorithms, has showed that Ensemble XAI has localization effectiveness (mean set accordance precision: 0.52, mean set accordance recall: 0.57, mean set 𝑭 𝟏 : 0.50, mean set IOU: 0.36) and is the most trusted method by the panel of radiologists (mean vote: 70.2%). Finally, the deep learning interpretation dashboard used for the radiologist panel voting will be made available to the community. Our code is available at https://github.com/IHIS-HealthInsights/Interpretation-Methods-Voting-dashboard. Impact Statement -Compared to other sectors that have deployed artificial intelligent (AI), the use of AI in healthcare understandably requires closer scrutiny due to the potential risks to patient safety, especially for clinical AI. As such, AI Explainability (XAI) is a key focus area in regard to the adoption of AI in healthcare. However, most of the current XAI methods for medical imaging revolve around quantitative assessment and there is a lack of systematic qualitative studies that seek to gain trust and concordance with clinicians. In this paper, we worked with a panel of clinicians to devise a comprehensive XAI evaluation framework combining quantitative and qualitative metrics to systematically review the efficacy of XAI techniques on deep learning models for pneumonia medical imaging. More importantly, we developed a new image explainability algorithm named Ensemble XAI, which gained the most trust by the panel of radiologists with a mean vote of 70.2%. It is envisioned that with the proposed XAI evaluation

show abstract

Ensemble Learning with Multiclassifiers on Pediatric Hand Radiograph Segmentation for Bone Age Assessment

Cited by 3 publications

References 32 publications

Ridge Regression Neural Network for Pediatric Bone Age Assessment

Ridge Regression Neural Network for Pediatric Bone Age Assessment

Ridge regression neural network for pediatric bone age assessment

Ensemble Image Explainable AI (XAI) Algorithm for Severe Community-Acquired Pneumonia and COVID-19 Respiratory Infections

Contact Info

Product

Resources

About