Artificial intelligence-based classification of bone tumors in the proximal femur on plain radiographs: System development and validation

Park, Chanwoo; Oh, Seong Je; Kim, Kyung Soo; Jang, Min-Chang; Kim, Il Su; Lee, Young-Keun; Chung, Myung Jin; Cho, Baek Hwan; Seo, Sung-Wook

doi:10.1371/journal.pone.0264140

Cited by 31 publications

(29 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further patient demographics information is then combined together with the network outputs and given to a fully connected layer to obtain the final prediction. Another radiological-based DL analysis is conducted in [ 35 ], where samples of standard anteroposterior hip radiographs are exploited in order to classify autonomously the considered bone tumors. Several preprocessing steps are employed to stabilize and strengthen out the predictions of the evaluated architectures (ResNet, GoogleNet and EfficientNet).…”

Section: Related Workmentioning

confidence: 99%

Deep Learning for Chondrogenic Tumor Classification through Wavelet Transform of Raman Spectra

Conforti

D’Acunto

Russo

2022

Sensors

View full text Add to dashboard Cite

The grading of cancer tissues is still one of the main challenges for pathologists. The development of enhanced analysis strategies hence becomes crucial to accurately identify and further deal with each individual case. Raman spectroscopy (RS) is a promising tool for the classification of tumor tissues as it allows us to obtain the biochemical maps of the tissues under analysis and to observe their evolution in terms of biomolecules, proteins, lipid structures, DNA, vitamins, and so on. However, its potential could be further improved by providing a classification system which would be able to recognize the sample tumor category by taking as input the raw Raman spectroscopy signal; this could provide more reliable responses in shorter time scales and could reduce or eliminate false-positive or -negative diagnoses. Deep Learning techniques have become ubiquitous in recent years, with models able to perform classification with high accuracy in most diverse fields of research, e.g., natural language processing, computer vision, medical imaging. However, deep models often rely on huge labeled datasets to produce reasonable accuracy, otherwise occurring in overfitting issues when the training data is insufficient. In this paper, we propose a chondrogenic tumor CLAssification through wavelet transform of RAman spectra (CLARA), which is able to classify with high accuracy Raman spectra obtained from bone tissues. CLARA recognizes and grades the tumors in the evaluated dataset with 97% accuracy by exploiting a classification pipeline consisting of the division of the original task in two binary classification steps, where the first is performed on the original RS signals while the latter is accomplished through the use of a hybrid temporal-frequency 2D transform.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning for Chondrogenic Tumor Classification through Wavelet Transform of Raman Spectra

Conforti

D’Acunto

Russo

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Another report [30] on the detection of hip fracture using VGG16 with 3346 simple radiographs of 1773 fractured and 1573 nonfractured hips showed that the model and orthopaedic surgeons had accuracies of 95.5% and 92.2%, sensitivities of 93.9% and 88.3%, and specificities of 97.4% and 96.8%, respectively, indicating that the deep-learning model outperformed clinicians. Meanwhile, another study [24] reported the performances of CNN models and compared them against the performances of clinicians to classify proximal femoral bone tumors to determine the absence of tumor, benign tumors, and malignant tumors on plain radiographs. The diagnostic accuracy of the best-performing model, EfficientNet-bs, was higher than the mean accuracy of two general orthopaedic surgeons and two orthopaedic oncologists.…”

Section: Discussionmentioning

confidence: 99%

“…Although the number of cancers continues to rise [15, 25], improvements in diagnostic modalities, surgical techniques, radiotherapy, and systemic therapy have improved patient survival rates [19]. However, this improvement in survival in patients with advanced cancer has been accompanied by an increased probability of bone metastasis [8] and pathologic fractures, especially in the proximal femur [24].…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning, which is likened to an advanced neural network such as the human brain, can be used to solve complex problems that cannot be addressed by conventional artificial intelligence. A convolutional neural network (CNN) is a representative deep-learning model with high performance for analyzing radiologic data with complex details [24]. In interpreting two-dimensional images, deep learning performs similarly to expert radiologists [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and Validation of a Convolutional Neural Network Model to Predict a Pathologic Fracture in the Proximal Femur Using Abdomen and Pelvis CT Images of Patients With Advanced Cancer

Joo,

Ko,

Kim

et al. 2023

Clin Orthop Relat Res

View full text Add to dashboard Cite

Background Improvement in survival in patients with advanced cancer is accompanied by an increased probability of bone metastasis and related pathologic fractures (especially in the proximal femur). The few systems proposed and used to diagnose impending fractures owing to metastasis and to ultimately prevent future fractures have practical limitations; thus, novel screening tools are essential. A CT scan of the abdomen and pelvis is a standard modality for staging and follow-up in patients with cancer, and radiologic assessments of the proximal femur are possible with CT-based digitally reconstructed radiographs. Deep-learning models, such as convolutional neural networks (CNNs), may be able to predict pathologic fractures from digitally reconstructed radiographs, but to our knowledge, they have not been tested for this application. Questions/purposes (1) How accurate is a CNN model for predicting a pathologic fracture in a proximal femur with metastasis using digitally reconstructed radiographs of the abdomen and pelvis CT images in patients with advanced cancer? (2) Do CNN models perform better than clinicians with varying backgrounds and experience levels in predicting a pathologic fracture on abdomen and pelvis CT images without any knowledge of the patients’ histories, except for metastasis in the proximal femur? Methods A total of 392 patients received radiation treatment of the proximal femur at three hospitals from January 2011 to December 2021. The patients had 2945 CT scans of the abdomen and pelvis for systemic evaluation and follow-up in relation to their primary cancer. In 33% of the CT scans (974), it was impossible to identify whether a pathologic fracture developed within 3 months after each CT image was acquired, and these were excluded. Finally, 1971 cases with a mean age of 59 ± 12 years were included in this study. Pathologic fractures developed within 3 months after CT in 3% (60 of 1971) of cases. A total of 47% (936 of 1971) were women. Sixty cases had an established pathologic fracture within 3 months after each CT scan, and another group of 1911 cases had no established pathologic fracture within 3 months after CT scan. The mean age of the cases in the former and latter groups was 64 ± 11 years and 59 ± 12 years, respectively, and 32% (19 of 60) and 53% (1016 of 1911) of cases, respectively, were female. Digitally reconstructed radiographs were generated with perspective projections of three-dimensional CT volumes onto two-dimensional planes. Then, 1557 images from one hospital were used for a training set. To verify that the deep-learning models could consistently operate even in hospitals with a different medical environment, 414 images from other hospitals were used for external validation. The number of images in the groups with and without a pathologic fracture within 3 months after each CT scan increased from 1911 to 22,932 and from 60 to 720, respectively, using data augmentation methods that are known to be an effective way to boost the performance of deep-learning models. Three CNNs (VGG16, ResNet50, and DenseNet121) were fine-tuned using digitally reconstructed radiographs. For performance measures, the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, precision, and F1 score were determined. The area under the receiver operating characteristic curve was used to evaluate three CNN models mainly, and the optimal accuracy, sensitivity, and specificity were calculated using the Youden J statistic. Accuracy refers to the proportion of fractures in the groups with and without a pathologic fracture within 3 months after each CT scan that were accurately predicted by the CNN model. Sensitivity and specificity represent the proportion of accurately predicted fractures among those with and without a pathologic fracture within 3 months after each CT scan, respectively. Precision is a measure of how few false-positives the model produces. The F1 score is a harmonic mean of sensitivity and precision, which have a tradeoff relationship. Gradient-weighted class activation mapping images were created to check whether the CNN model correctly focused on potential pathologic fracture regions. The CNN model with the best performance was compared with the performance of clinicians. Results DenseNet121 showed the best performance in identifying pathologic fractures; the area under the receiver operating characteristic curve for DenseNet121 was larger than those for VGG16 (0.77 ± 0.07 [95% CI 0.75 to 0.79] versus 0.71 ± 0.08 [95% CI 0.69 to 0.73]; p = 0.001) and ResNet50 (0.77 ± 0.07 [95% CI 0.75 to 0.79] versus 0.72 ± 0.09 [95% CI 0.69 to 0.74]; p = 0.001). Specifically, DenseNet121 scored the highest in sensitivity (0.22 ± 0.07 [95% CI 0.20 to 0.24]), precision (0.72 ± 0.19 [95% CI 0.67 to 0.77]), and F1 score (0.34 ± 0.10 [95% CI 0.31 to 0.37]), and it focused accurately on the region with the expected pathologic fracture. Further, DenseNet121 was less likely than clinicians to mispredict cases in which there was no pathologic fracture than cases in which there was a fracture; the performance of DenseNet121 was better than clinician performance in terms of specificity (0.98 ± 0.01 [95% CI 0.98 to 0.99] versus 0.86 ± 0.09 [95% CI 0.81 to 0.91]; p = 0.01), precision (0.72 ± 0.19 [95% CI 0.67 to 0.77] versus 0.11 ± 0.10 [95% CI 0.05 to 0.17]; p = 0.0001), and F1 score (0.34 ± 0.10 [95% CI 0.31 to 0.37] versus 0.17 ± 0.15 [95% CI 0.08 to 0.26]; p = 0.0001). Conclusion CNN models may be able to accurately predict impending pathologic fractures from digitally reconstructed radiographs of the abdomen and pelvis CT images that clinicians may not anticipate; this can assist medical, radiation, and orthopaedic oncologists clinically. To achieve better performance, ensemble-learning models using knowledge of the patients’ histories should be developed and validated. The code for our model is publicly available online at https://github.com/taehoonko/CNN_path_fx_prediction. Level of Evidence Level III, diagnostic study.

show abstract

“…Artificial intelligence (AI) applications are popular in orthopedics for diagnosis and classification from radiography images. 1 ,2 Based on the results of these studies, the algorithms developed achieve near-perfect results. 3 It is important to conduct human comparison studies in order to translate this theoretical success into real-life medical practice.…”

Section: Introductionmentioning

confidence: 96%

Comparison of artificial intelligence algorithm for the diagnosis of hip fracture on plain radiography with decision-making physicians: a validation study

Beyaz,

Yayli,

Kılıç

et al. 2024

Acta Orthopaedica et Traumatologica Turcica

View full text Add to dashboard Cite

Objective: This study aimed to compare an algorithm developed for diagnosing hip fractures on plain radiographs with the physicians involved in diagnosing hip fractures. Methods: Radiographs labeled as fractured (n = 182) and non-fractured (n = 542) by an expert on proximal femur fractures were included in the study. General practitioners in the emergency department (n = 3), emergency medicine (n = 3), radiologists (n = 3), orthopedic residents (n = 3), and orthopedic surgeons (n = 3) were included in the study as the labelers, who labeled the presence of fractures on the right and left sides of the proximal femoral region on each anteroposterior (AP) plain pelvis radiograph as fractured or non-fractured. In addition, all the radiographs were evaluated using an artificial intelligence (AI) algorithm consisting of 3 AI models and a majority voting technique. Each AI model evaluated each graph separately, and majority voting determined the final decision as the majority of the outputs of the 3 AI models. The results of the AI algorithm and labelling physicians included in the study were compared with the reference evaluation. Results: Based on F-1 scores, here are the average scores of the group: majority voting (0.942) > orthopedic surgeon (0.938) > AI models (0.917) > orthopedic resident (0.858) > emergency medicine (0.758) > general practitioner (0.689) > radiologist (0.677). Conclusion: The AI algorithm developed in our previous study may help recognize fractures in AP pelvis in plain radiography in the emergency department for non-orthopedist physicians. Level of Evidence: Level IV, Diagnostic Study.

show abstract

Artificial intelligence-based classification of bone tumors in the proximal femur on plain radiographs: System development and validation

Cited by 31 publications

References 26 publications

Deep Learning for Chondrogenic Tumor Classification through Wavelet Transform of Raman Spectra

Deep Learning for Chondrogenic Tumor Classification through Wavelet Transform of Raman Spectra

Development and Validation of a Convolutional Neural Network Model to Predict a Pathologic Fracture in the Proximal Femur Using Abdomen and Pelvis CT Images of Patients With Advanced Cancer

Comparison of artificial intelligence algorithm for the diagnosis of hip fracture on plain radiography with decision-making physicians: a validation study

Contact Info

Product

Resources

About