Detecting pathological features and predicting fracture risk from dual-energy X-ray absorptiometry images using deep learning

Nissinen, Tomi; Suoranta, Sanna; Saavalainen, Taavi; Sund, Reijo; Hurskainen, Ossi; Rikkonen, Toni; Kröger, Heikki; Lähivaara, Timo; Väänänen, Sami P.

doi:10.1016/j.bonr.2021.101070

Cited by 12 publications

(24 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fracture identification was performed using imaging-related data in 54 studies, tabular data in nine studies, and imaging and tabular data in three. Of the 57 studies using imaging-related and combined data, 33 analyzed radiograph images [ 6 , 7 , 28 – 31 , 35 – 38 , 40 – 42 , 45 , 47 – 49 , 52 – 57 , 59 , 61 , 62 , 66 – 68 , 72 – 74 , 78 ], 12 analyzed computed tomography (CT) images [ 8 , 9 , 39 , 43 , 50 , 63 , 65 , 69 , 75 , 81 – 83 ], and the remaining studies analyzed other imaging modalities ( S1 Table , and S2 Table ). The most common fracture outcome was vertebral fracture (20 studies) [ 8 , 10 , 11 , 28 , 31 , 34 , 35 , 38 , 44 , 46 , 50 , 51 , 58 , 59 , 65 , 72 ,…”

Section: Resultsmentioning

confidence: 99%

“…Only 12 studies addressed the handling of imbalance outcomes during model development, using Synthetic Minority Over-sampling Technique (SMOTE) [ 86 ] or undersampling [ 35 ]. Data augmentation was frequently utilized in image studies, including horizontal and vertical rotation [ 45 , 50 , 58 , 67 , 69 , 72 ], adding Gaussian noise [ 67 ], random rescaling and flipping [ 30 , 53 ], mirroring, and lighting and contrast adjustments [ 56 ].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

Jung,

Dai,

Liu

et al. 2024

PLOS Digit Health

View full text Add to dashboard Cite

Artificial Intelligence (AI), encompassing Machine Learning and Deep Learning, has increasingly been applied to fracture detection using diverse imaging modalities and data types. This systematic review and meta-analysis aimed to assess the efficacy of AI in detecting fractures through various imaging modalities and data types (image, tabular, or both) and to synthesize the existing evidence related to AI-based fracture detection. Peer-reviewed studies developing and validating AI for fracture detection were identified through searches in multiple electronic databases without time limitations. A hierarchical meta-analysis model was used to calculate pooled sensitivity and specificity. A diagnostic accuracy quality assessment was performed to evaluate bias and applicability. Of the 66 eligible studies, 54 identified fractures using imaging-related data, nine using tabular data, and three using both. Vertebral fractures were the most common outcome (n = 20), followed by hip fractures (n = 18). Hip fractures exhibited the highest pooled sensitivity (92%; 95% CI: 87–96, p< 0.01) and specificity (90%; 95% CI: 85–93, p< 0.01). Pooled sensitivity and specificity using image data (92%; 95% CI: 90–94, p< 0.01; and 91%; 95% CI: 88–93, p < 0.01) were higher than those using tabular data (81%; 95% CI: 77–85, p< 0.01; and 83%; 95% CI: 76–88, p < 0.01), respectively. Radiographs demonstrated the highest pooled sensitivity (94%; 95% CI: 90–96, p < 0.01) and specificity (92%; 95% CI: 89–94, p< 0.01). Patient selection and reference standards were major concerns in assessing diagnostic accuracy for bias and applicability. AI displays high diagnostic accuracy for various fracture outcomes, indicating potential utility in healthcare systems for fracture diagnosis. However, enhanced transparency in reporting and adherence to standardized guidelines are necessary to improve the clinical applicability of AI. Review Registration: PROSPERO (CRD42021240359).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

Jung,

Dai,

Liu

et al. 2024

PLOS Digit Health

View full text Add to dashboard Cite

show abstract

“…We used two additional open-source datasets, the CMMD 3,[31][32][33] and the VTB from the Susan G. Komen Tissue Bank, consisting of 826 and 765 mammogram examinations, respectively. To assess feature representations learned by the proposed model, we transferred the feature representations to the OSTPRE cohort [34][35][36] with 750 mammogram examinations. From OSTPRE, we selected breast tumor stage, represented with sufficient labels, for unsupervised clustering.…”

Section: Datasetsmentioning

confidence: 99%

An evidential deep learning framework for assessment of mammograms

Gudhe,

Mazen,

Sund

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

In this study, we present an evidential deep learning framework called MV-DEFEAT, incorporating the strength of Dempster-Shafer evidential theory and subjective logic, for various mammogram assessment tasks, including mammogram density assessment, BIRADS scoring, and mammogram finding as normal/benign/malignant. The framework combines evidence from multiple mammogram’s views to mimic a radiologist’s decision-making process. We conducted experiments on two open-source digital mammogram datasets, VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography and the Digital Database for Screening Mammography (DDSM), which include 5,000 and 1,975 mammogram examinations, respectively. Our results showed that MV-DEFEAT achieves weighted macro-average area under the receiver operating characteristic curves (AUCs) of 98.92 ± 0.007 and 86.53 ± 0.051 for mammogram density assessment on the VinDr-Mammo and DDSM datasets, respectively, which are considerably better than a state-of-the-art multi-view deep learning method with AUCs of 86.38 ± 0.258 and 70.62 ± 0.261. In addition, MV-DEFEAT demonstrated strong generalization for mammogram density assessment on two independent and unseen datasets, the Chinese Mammography Database (CMMD) and Virtual Tissue Biobank (VTB). Furthermore, we demonstrated the efficient feature representation of the MV-DEFEAT that could be transferred to a breast cancer stage classification task using the unseen Kuopio Osteoporosis Risk Factor and Prevention study (OSTPRE) dataset. Our results enhance trust in using deep learning algorithms to assess mammograms in clinical settings.

show abstract

“…For example, Xiao et al (2020) trained a neural network to predict histomorphometric parameters from simulated DXA images. Moreover, Nissinen et al (2021) used DL to classify DXA images. DL has also been used for bone classification ( Shen et al, 2021 ; Tanzi et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Predicting the trabecular bone apparent stiffness tensor with spherical convolutional neural networks

et al. 2022

View full text Add to dashboard Cite

Detecting pathological features and predicting fracture risk from dual-energy X-ray absorptiometry images using deep learning

Cited by 12 publications

References 41 publications

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

An evidential deep learning framework for assessment of mammograms

Predicting the trabecular bone apparent stiffness tensor with spherical convolutional neural networks

Contact Info

Product

Resources

About