Direct automated quantitative measurement of spine by cascade amplifier regression network with manifold regularization

Pang, Shumao; Su, Zhihai; Leung, Stephanie; Nachum, Ilanit Ben; Chen, Bin; Feng, Qianjin; Li, Shuo

doi:10.1016/j.media.2019.04.012

Cited by 46 publications

(29 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thirteen studies investigated bone properties such as vertebral fracture load, ( 23–25 ) microarchitecture parameters, ( 26,27 ) vertebral height, ( 28 ) or BMD ( 29–35 ) (Table 1). The main objective of these efforts was to improve the diagnosis of osteoporosis.…”

Section: Resultsmentioning

confidence: 99%

“…Of note, Pang and colleagues reported their methods in detail and shared the code used for their analysis. ( 28 )…”

Section: Resultsmentioning

confidence: 99%

“…External validation was performed in two studies from different local institutions in the same country with comparable results. ( 23,32 ) Feature selection, ( 23 ) data augmentation, (32 ) and transfer learning from pre‐trained models ( 28,30 ) were applied to control overfitting. However, critical limitations in the use of ML methods were present: the gold standard, BMD as estimated from DXA, was not used as the ground truth (BMD from DXA is the reference technique used in practice, whereas BMD as estimated from CT scans was used as the ground truth); (30–32,34 ) model parameter selection was not reported; (23–25,29,33,35 ) discussion of crucial limitations regarding generalization was absent; (24,25,27,28,32,35 ) and the inclusion of the training set in model evaluation ( 33 ) or the use of 25 times more input features than data, ( 35 ) both indicating an increased risk of overfitting.…”

Section: Resultsmentioning

confidence: 99%

“…( 29,51,60,72,92 ) Acknowledging potential biases or limitations is fundamental for the accurate interpretation and especially for claims related to clinical implication. Nevertheless, several studies showed a greater awareness of the potential existence of bias and made efforts to address this either directly by controlling for the risks of overfitting, ( 23,28,30,32,34,37–40,43–46,49,53,54,56,57,59,64,77–85,90,91,93–95 ) indirectly by visualizing decision‐making, ( 36,38,48,66,67,78,79,84,90,94,104 ) or by using gold standard strategies for comparison. ( 66,71,78–83,85,91,93,94,104,107 )…”

Section: Discussionmentioning

confidence: 99%

“…( 23,32,50,95 ) It is encouraging to note that some authors reported their methodology in great detail and/or freely shared their data or code, allowing for future replication. ( 28,37,42,56,67,75,77 ) Because the use of ML approaches to address uncertainties and issues in osteoporosis is relatively recent, we are still on time to avoid a replication crisis in the field. Besides transparency and high‐quality reporting, data and code sharing should be encouraged.…”

Section: Discussionmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning Solutions for Osteoporosis—A Review

Smets

Shevroja

Hügle

et al. 2020

Journal of Bone and Mineral Research

114

View full text Add to dashboard Cite

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high‐dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n = 13), osteoporosis classification (n = 34), fracture detection (n = 32), and risk prediction (n = 14). Reporting and methodological quality was determined by means of a 12‐point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML‐based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model‐based decision‐making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

show abstract

Section: Resultsmentioning

confidence: 99%

“…Of note, Pang and colleagues reported their methods in detail and shared the code used for their analysis. ( 28 )…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning Solutions for Osteoporosis—A Review

Smets

Shevroja

Hügle

et al. 2020

Journal of Bone and Mineral Research

114

View full text Add to dashboard Cite

show abstract

Automated measurement of spine indices on axial MR images for lumbar spinal stenosis diagnosis using segmentation‐guided regression network

Pang

Lin

et al. 2022

Medical Physics

Self Cite

View full text Add to dashboard Cite

Purpose Automated measurement of spine indices on axial magnetic resonance (MR) images plays a significant role in lumbar spinal stenosis diagnosis. Existing direct spine indices measurement approaches fail to explicitly focus on the task‐specific region or feature channel with the additional information for guiding. We aim to achieve accurate spine indices measurement by introducing the guidance of the segmentation task. Methods In this paper, we propose a segmentation‐guided regression network (SGRNet) to achieve automated spine indices measurement. SGRNet consists of a segmentation path for generating the spine segmentation prediction and a regression path for producing spine indices estimation. The segmentation path is a U‐Net‐like network which includes a segmentation encoder and a decoder which generates multilevel segmentation features and segmentation prediction. The proposed segmentation‐guided attention module (SGAM) in the regression encoder extracts the attention‐aware regression feature under the guidance of the segmentation feature. Based on the attention‐aware regression feature, a fully connected layer is utilized to output the accurate spine indices estimation. Results Experiments on the open‐access Lumbar Spine MRI data set show that SGRNet achieves state‐of‐the‐art performance with a mean absolute error of 0.49 mm and mean Pearson correlation coefficient of 0.956 for four indices estimation. Conclusions The proposed SGAM in SGRNet is capable of improving the performance of spine indices measurement by focusing on the task‐specific region and feature channel under the guidance of the segmentation task.

show abstract