Diagnostic strategy for elderly patients with isolated greater trochanter fractures on plain radiographs

Moon, Nam Hoon; Shin, Won Chul; Uk, Min; Woo, Seung Hun; Son, Seung Min; Suh, Kuen Tak

doi:10.1186/s12891-018-2193-5

Cited by 15 publications

(21 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although Occult ITF has PFN applied publications, it was seen that distal locking screws were used as a standard treatment. 21,22 In stable ITFs, DHS and PFN have proven not to be superior to each other. 30 DHS was preferred in our study because compression in DHS was more pronounced than PFN and it was a cheaper implant for the treatment.…”

Section: Discussionmentioning

confidence: 99%

“…20 Studies focused on the importance of MRI in the diagnosis of hip fractures that have not yet been diagnosed. 21,22 A study reported that the occult ITF can only be confirmed with MRI, and other radiological methods have failed in this regard. 9 Clinical history, physical examination, and radiographic evaluation are a classic approach in the diagnosis of proximal femur fractures.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Treatment strategy for elderly patients with the isolated greater trochanteric fracture

et al. 2020

View full text Add to dashboard Cite

Background: The objective of this study was to evaluate the risk of femur intertrochanteric fracture associated with femur trochanter major fractures in patients over 65 years of age with magnetic resonance examination for better diagnosis and treatment. Methods: Thirty-one patients who had incomplete femur intertrochanteric fracture diagnosed were included in the study. Patients were classified according to the length of the fracture line crossing the intertrochanteric border. Fracture patterns were described on magnetic resonance imaging coronal views. Group A, pattern 1, greater trochanteric fracture extends to intertrochanteric region with both cortices; Group B, pattern 2, fracture has characteristics of pattern 1 fracture including diametaphysis fracture line; Group C, pattern 3, greater trochanteric fracture only has extending superolateral cortex fracture line of intertrochanteric region; and Group D, pattern 4, fracture has characteristics of pattern 1 fracture and including superior extension to the baso-cervical line. Surgical treatment with dynamic hip screw was applied to all patients with intertrochanteric extension after magnetic resonance examination. Results: This study included 16 women (80.3 ± 6.7 years) and 15 men (76.9 ± 10.94 years). Group A had 11 patients, group B had 8 patients, group C had 6 patients, and group D had 6 patients. Ambulation was initially prescribed for these patients 1 day after the surgery. The average surgery durations of the A, B, C, and D patterns were 44.54 ± 7.56, 49.37 ± 12.65, 49.16 ± 3.76, and 44.16 ± 5.84 min, respectively. No statistically significant differences were observed among the four patterns (P = 0.404). Conclusion: Surgical treatment of the greater trochanteric fracture which is considered an indicator of occult intertrochanteric fracture is a good choice for the treatment because of the procedure safety and early mobilization after the surgery

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Treatment strategy for elderly patients with the isolated greater trochanteric fracture

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To classify the fracture type, we used the Garden classification (Garden classification stage I, II, III, IV: G/S I-IV) for femoral neck fractures [26] and the AO/OTA classification for femoral trochanteric fractures (AO/OTA 31-A1, A2, A3) [27]. We defined a great trochanteric fracture as one in which the fracture line did not extend to the medial cortex [28]. A total of 5024 cases (95.8%) were diagnosed from AP pelvic X-rays alone.…”

Section: Evaluation Of Fracturesmentioning

confidence: 99%

Artificial intelligence improves the accuracy of residents in the diagnosis of hip fractures: a multicenter study

Sato

Takegami

Asamoto³

et al. 2021

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Background Less experienced clinicians sometimes make misdiagnosis of hip fractures. We developed computer-aided diagnosis (CAD) system for hip fractures on plain X-rays using a deep learning model trained on a large dataset. In this study, we examined whether the accuracy of the diagnosis of hip fracture of the residents could be improved by using this system. Methods A deep convolutional neural network approach was used for machine learning. Pytorch 1.3 and Fast.ai 1.0 were applied as frameworks, and an EfficientNet-B4 model (a pre-trained ImageNet model) was used. We handled the 5295 X-rays from the patients with femoral neck fracture or femoral trochanteric fracture from 2009 to 2019. We excluded cases in which the bilateral hips were not included within an image range, and cases of femoral shaft fracture and periprosthetic fracture. Finally, we included 5242 AP pelvic X-rays from 4851 cases. We divided these 5242 images into two images per image, and prepared 5242 images including fracture site and 5242 images without fracture site. Thus, a total of 10,484 images were used for machine learning. The accuracy, sensitivity, specificity, F-value, and area under the curve (AUC) were assessed. Gradient-weighted class activation mapping (Grad-CAM) was used to conceptualize the basis for the diagnosis of the fracture by the deep learning algorithm. Secondly, we conducted a controlled experiment with clinicians. Thirty-one residents;young doctors within 2 years of graduation from medical school who rotate through various specialties, were tested using 300 hip fracture images that were randomly extracted from the dataset. We evaluated the diagnostic accuracy with and without the use of the CAD system for each of the 300 images. Results The accuracy, sensitivity, specificity, F-value, and AUC were 96.1, 95.2, 96.9%, 0.961, and 0.99, respectively, with the correct diagnostic basis generated by Grad-CAM. In the controlled experiment, the diagnostic accuracy of the residents significantly improved when they used the CAD system. Conclusions We developed a newly CAD system with a deep learning algorithm from a relatively large dataset from multiple institutions. Our system achieved high diagnostic performance. Our system improved the diagnostic accuracy of residents for hip fractures. Level of evidence Level III, Foundational evidence, before-after study. Clinical relevance: high

show abstract

“…To classify the fracture type, we used the Garden classi cation (Garden classi cation stage I, II, III, IV: G/S I-IV) for femoral neck fractures [22] and the AO/OTA classi cation for femoral trochanteric fractures (AO/OTA 31-A1, A2, A3) [23]. We de ned a great trochanteric fracture as one in which the fracture line did not extend to the medial cortex [24]. A total of 5024 cases (95.8%) were diagnosed from AP pelvic X-rays alone.…”

Section: Evaluation Of Fracturesmentioning

confidence: 99%

Artificial Intelligence Improves the Accuracy of Residents in the Diagnosis of Hip Fractures –A Multicenter Study

Sato

Takegami

ASAMOTO³

et al. 2020

Preprint

View full text Add to dashboard Cite

BackgroundLess experienced clinicians sometimes make misdiagnosis of hip fractures. We developed computer-aided diagnosis (CAD) system for hip fractures on plain X-rays using a deep learning model trained on a large dataset. In this study, we examined whether the accuracy of the diagnosis of hip fracture of the residents could be improved by using this system.MethodsA deep convolutional neural network approach was used for machine learning. Pytorch 1.3 and Fast.ai 1.0 were applied as frameworks, and an EfficientNet-B4 model (a pre-trained ImageNet model) was used. We handled the 5295 X-rays from the patients with femoral neck fracture or femoral trochanteric fracture from 2009 to 2019. We excluded cases in which the bilateral hips were not included within an image range, and cases of femoral shaft fracture and periprosthetic fracture. Finally, we included 5242 AP pelvic X-rays from 4,851 cases. These images were divided into 5242 images that included the fracture site and 5242 images that did not. Thus, a total of 10484 images were used for machine learning. The accuracy, sensitivity, specificity, F-value, and area under the curve (AUC) were assessed. Gradient-weighted class activation mapping (Grad-CAM) was used to conceptualize the basis for the diagnosis of the fracture by the deep learning algorithm. Secondly, we conducted a controlled experiment with clinicians. Thirty-one residents and four orthopedic surgery fellows were tested using 300 hip fracture images that were randomly extracted from the dataset. We evaluated the diagnostic accuracy with and without the use of the CAD system for each of the 300 images.ResultsThe accuracy, sensitivity, specificity, F-value, and AUC were 96.1%, 95.2%, 96.9%, 0.961, and 0.99, respectively, with the correct diagnostic basis generated by Grad-CAM. In the controlled experiment, the diagnostic accuracy of the residents significantly improved when they used the CAD system.ConclusionsWe developed a newly CAD system with a deep learning algorithm from a relatively large dataset from multiple institutions. Our system achieved high diagnostic performance. Our system improved the diagnostic accuracy of residents for hip fractures.Level of EvidenceLevel Ⅲ, Foundational evidence, before-after study. Clinical relevance: high

show abstract

Diagnostic strategy for elderly patients with isolated greater trochanter fractures on plain radiographs

Cited by 15 publications

References 28 publications

Treatment strategy for elderly patients with the isolated greater trochanteric fracture

Treatment strategy for elderly patients with the isolated greater trochanteric fracture

Artificial intelligence improves the accuracy of residents in the diagnosis of hip fractures: a multicenter study

Artificial Intelligence Improves the Accuracy of Residents in the Diagnosis of Hip Fractures –A Multicenter Study

Contact Info

Product

Resources

About