Detection and localization of distal radius fractures: Deep learning system versus radiologists

Blüthgen, Christian; Becker, Anton S.; Martini, Isabella; Meier, Andreas; Martini, Katharina; Frauenfelder, Thomas

doi:10.1016/j.ejrad.2020.108925

Cited by 50 publications

(47 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we followed the recent works and trained a CNN-based pipeline for distal radius wrist fracture detection. Compared to recent studies on wrist fracture detection, on the general population dataset, our pipeline scored a better AUROC than others 13,[19][20][21] . The important aim of our study, was to bring up the general issues of safety and robustness of AI in medical imaging to the attention of the reader.…”

Section: Discussionmentioning

confidence: 69%

“…During recent years, Deep Learning (DL) has been widely applied in the realm of musculoskeletal radiology. In the domain of automatic fracture detection, DL has been used in application to radiographs on various body parts: ankle 14 , hip [15][16][17] , humerus 18 , and wrist 13,[19][20][21] . The wrist fracture detection performances in these studies were reported to be relatively high-the Area Under the Receiver Operator Characteristics curve (AUROC) was of above or equal to 0.80 on a test set.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Critical evaluation of deep neural networks for wrist fracture detection

Raisuddin

Vaattovaara

Nevalainen

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection—DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set—average precision of 0.99 (0.99–0.99) versus 0.64 (0.46–0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98–0.99) versus 0.84 (0.72–0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems.

show abstract

Section: Discussionmentioning

confidence: 69%

mentioning

confidence: 99%

Critical evaluation of deep neural networks for wrist fracture detection

Raisuddin

Vaattovaara

Nevalainen

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…However, studies using CNNs in the field of orthopedic surgery and traumatology are limited and the field is immature. So far, there are radiographic studies using CNNs for hip fractures (Adams et al 2019, Badgeley et al 2019, Cheng et al 2019, Urakawa et al 2019, distal radius fractures (Kim and MacKinnon 2018, Gan et al 2019, Yahalomi et al 2019, Blüthgen et al 2020, proximal humeral fractures (Chung et al 2018), ankle fractures (Kitamura et al 2019) and hand, wrist, and ankle fractures (Olczak et al 2017).…”

mentioning

confidence: 99%

Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy: ensemble decision-making with antero-posterior and lateral radiographs

et al. 2020

View full text Add to dashboard Cite

Background and purpose — Deep-learning approaches based on convolutional neural networks (CNNs) are gaining interest in the medical imaging field. We evaluated the diagnostic performance of a CNN to discriminate femoral neck fractures, trochanteric fractures, and non-fracture using antero-posterior (AP) and lateral hip radiographs. Patients and methods — 1,703 plain hip AP radiographs and 1,220 plain hip lateral radiographs were included in the total dataset. 150 images each of the AP and lateral views were separated out and the remainder of the dataset was used for training. The CNN made the diagnosis based on: (1) AP radiographs alone, (2) lateral radiographs alone, or (3) both AP and lateral radiographs combined. The diagnostic performance of the CNN was measured by the accuracy, recall, precision, and F1 score. We further compared the CNN’s performance with that of orthopedic surgeons. Results — The average accuracy, recall, precision, and F1 score of the CNN based on both anteroposterior and lateral radiographs were 0.98, 0.98, 0.98, and 0.98, respectively. The accuracy of the CNN was comparable to, or statistically significantly better than, that of the orthopedic surgeons regardless of radiographic view used. In the CNN model, the accuracy of the diagnosis based on both views was significantly better than the lateral view alone and tended to be better than the AP view alone. Interpretation — The CNN exhibited comparable or superior performance to that of orthopedic surgeons to discriminate femoral neck fractures, trochanteric fractures, and non-fracture using both AP and lateral hip radiographs.

show abstract

“…ViDi was originally developed as a quality control tool on assembly lines, is not approved for routine clinical use, but has shown promise in radiological studies with applications in mammography and radius fracture detection. [22][23][24] ViDi learns by example, sweeping the image with a circular feature window, creating a model of typical imaging features in the training set which is then used to estimate whether the validation set's features are within a tolerable range. 24 Computation was performed on a desktop personal computer with a dedicated graphical processing unit (Nvidia GeForce GTX 1080) ( Figure 1).…”

Section: Deep Learning and Statistical Analysismentioning

confidence: 99%

“…16,17 Previous deep learning publications focussing on DSA/aneurysms are specifically engineered for aneurysm segmentation, 18 use a two-stage technique to locate specific regions before aneurysm detection, 19 use a spatial information fusion method on 3D rotational angiography 20 or incorporate temporal information from multiple DSA frames. 21 The goal of our study was to determine if commercial-grade deep learning software with previously described applications in mammography 22,23 and radius fracture detection 24 could detect intracranial aneurysms using only standard, whole-brain anteroposterior and lateral projections of DSA.…”

Section: Introductionmentioning

confidence: 99%

Deep learning based detection of intracranial aneurysms on digital subtraction angiography: A feasibility study

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background Digital subtraction angiography is the gold standard for detecting and characterising aneurysms. Here, we assess the feasibility of commercial-grade deep learning software for the detection of intracranial aneurysms on whole-brain anteroposterior and lateral 2D digital subtraction angiography images. Material and methods Seven hundred and six digital subtraction angiography images were included from a cohort of 240 patients (157 female, mean age 59 years, range 20–92; 83 male, mean age 55 years, range 19–83). Three hundred and thirty-five (47%) single frame anteroposterior and lateral images of a digital subtraction angiography series of 187 aneurysms (41 ruptured, 146 unruptured; average size 7±5.3 mm, range 1–5 mm; total 372 depicted aneurysms) and 371 (53%) aneurysm-negative study images were retrospectively analysed regarding the presence of intracranial aneurysms. The 2D data was split into testing and training sets in a ratio of 4:1 with 3D rotational digital subtraction angiography as gold standard. Supervised deep learning was performed using commercial-grade machine learning software (Cognex, ViDi Suite 2.0). Monte Carlo cross validation was performed. Results Intracranial aneurysms were detected with a sensitivity of 79%, a specificity of 79%, a precision of 0.75, a F1 score of 0.77, and a mean area-under-the-curve of 0.76 (range 0.68–0.86) after Monte Carlo cross-validation, run 45 times. Conclusion The commercial-grade deep learning software allows for detection of intracranial aneurysms on whole-brain, 2D anteroposterior and lateral digital subtraction angiography images, with results being comparable to more specifically engineered deep learning techniques.

show abstract

Detection and localization of distal radius fractures: Deep learning system versus radiologists

Cited by 50 publications

References 22 publications

Critical evaluation of deep neural networks for wrist fracture detection

Critical evaluation of deep neural networks for wrist fracture detection

Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy: ensemble decision-making with antero-posterior and lateral radiographs

Deep learning based detection of intracranial aneurysms on digital subtraction angiography: A feasibility study

Contact Info

Product

Resources

About