ABSTRACT
Purpose To develop an artificial intelligence (AI) system for humeral tumor detection on chest radiographs (CRs) and evaluate the impact on reader performance. Materials and Methods In this retrospective study, 14 709 CRs (January 2000 to December 2021) were collected from 13 468 patients, including CT-proven normal (n = 13 116) and humeral tumor (n = 1593) cases. The data were divided into training and test groups. A novel training method called false-positive activation area reduction (FPAR) was introduced to enhance the diagnostic performance by focusing on the humeral region. The AI program and 10 radiologists were assessed using holdout test set 1, wherein the radiologists were tested twice (with and without AI test results). The performance of the AI system was evaluated using holdout test set 2, comprising 10 497 normal images. Receiver operating characteristic analyses were conducted for evaluating model performance. Results FPAR application in the AI program improved its performance compared with a conventional model based on the area under the receiver operating characteristic curve (0.87 vs 0.82, P = .04). The proposed AI system also demonstrated improved tumor localization accuracy (80% vs 57%, P < .001). In holdout test set 2, the proposed AI system exhibited a false-positive rate of 2%. AI assistance improved the radiologists' sensitivity, specificity, and accuracy by 8.9%, 1.2%, and 3.5%, respectively (P < .05 for all). Conclusion The proposed AI tool incorporating FPAR improved humeral tumor detection on CRs and reduced false-positive results in tumor visualization. It may serve as a supportive diagnostic tool to alert radiologists about humeral abnormalities. Keywords: Artificial Intelligence, Conventional Radiography, Humerus, Machine Learning, Shoulder, Tumor Supplemental material is available for this article. © RSNA, 2024.
Subject(s)
Artificial Intelligence , Neoplasms , Humans , Retrospective Studies , Humerus/diagnostic imaging , Radiography , RadiopharmaceuticalsABSTRACT
OBJECTIVES: Diseases of the middle ear can interfere with normal sound transmission, which results in conductive hearing loss. Since video pneumatic otoscopy (VPO) findings reveal not only the presence of middle ear effusions but also dynamic movements of the tympanic membrane and part of the ossicles, analyzing VPO images was expected to be useful in predicting the presence of middle ear transmission problems. Using a convolutional neural network (CNN), a deep neural network implementing computer vision, this preliminary study aimed to create a deep learning model that detects the presence of an air-bone gap, conductive component of hearing loss, by analyzing VPO findings. DESIGN: The medical records of adult patients who underwent VPO tests and pure-tone audiometry (PTA) on the same day were reviewed for enrollment. Conductive hearing loss was defined as an average air-bone gap of more than 10 dB at 0.5, 1, 2, and 4 kHz on PTA. Two significant images from the original VPO videos, at the most medial position on positive pressure and the most laterally displaced position on negative pressure, were used for the analysis. Applying multi-column CNN architectures with individual backbones of pretrained CNN versions, the performance of each model was evaluated and compared for Inception-v3, VGG-16 or ResNet-50. The diagnostic accuracy predicting the presence of conductive component of hearing loss of the selected deep learning algorithm used was compared with experienced otologists. RESULTS: The conductive hearing loss group consisted of 57 cases (mean air-bone gap = 25 ± 8 dB): 21 ears with effusion, 14 ears with malleus-incus fixation, 15 ears with stapes fixation including otosclerosis, one ear with a loose incus-stapes joint, 3 cases with adhesive otitis media, and 3 ears with middle ear masses including congenital cholesteatoma. The control group consisted of 76 cases with normal hearing thresholds without air-bone gaps. A total of 1130 original images including repeated measurements were obtained for the analysis. Of the various network architectures designed, the best was to feed each of the images into the individual backbones of Inception-v3 (three-column architecture) and concatenate the feature maps after the last convolutional layer from each column. In the selected model, the average performance of 10-fold cross-validation in predicting conductive hearing loss was 0.972 mean areas under the curve (mAUC), 91.6% sensitivity, 96.0% specificity, 94.4% positive predictive value, 93.9% negative predictive value, and 94.1% accuracy, which was superior to that of experienced otologists, whose performance had 0.773 mAUC and 79.0% accuracy on average. The algorithm detected over 85% of cases with stapes fixations or ossicular chain problems other than malleus-incus fixations. Visualization of the region of interest in the deep learning model revealed that the algorithm made decisions generally based on findings in the malleus and nearby tympanic membrane. CONCLUSIONS: In this preliminary study, the deep learning algorithm created to analyze VPO images successfully detected the presence of conductive hearing losses caused by middle ear effusion, ossicular fixation, otosclerosis, and adhesive otitis media. Interpretation of VPO using the deep learning algorithm showed promise as a diagnostic tool to differentiate conductive hearing loss from sensorineural hearing loss, which would be especially useful for patients with poor cooperation.
Subject(s)
Deep Learning , Otitis Media with Effusion , Otitis Media , Otosclerosis , Adult , Audiometry, Pure-Tone/methods , Hearing Loss, Conductive/diagnosis , Hearing Loss, Conductive/etiology , Humans , Otitis Media/complications , Otitis Media with Effusion/complications , Otosclerosis/complications , Otoscopy , Retrospective StudiesABSTRACT
PURPOSE: Early detection and classification of bone tumors in the proximal femur is crucial for their successful treatment. This study aimed to develop an artificial intelligence (AI) model to classify bone tumors in the proximal femur on plain radiographs. METHODS: Standard anteroposterior hip radiographs were obtained from a single tertiary referral center. A total of 538 femoral images were set for the AI model training, including 94 with malignant, 120 with benign, and 324 without tumors. The image data were pre-processed to be optimized for training of the deep learning model. The state-of-the-art convolutional neural network (CNN) algorithms were applied to pre-processed images to perform three-label classification (benign, malignant, or no tumor) on each femur. The performance of the CNN model was verified using fivefold cross-validation and was compared against that of four human doctors. RESULTS: The area under the receiver operating characteristic (AUROC) of the best performing CNN model for the three-label classification was 0.953 (95% confidence interval, 0.926-0.980). The diagnostic accuracy of the model (0.853) was significantly higher than that of the four doctors (0.794) (P = 0.001) and also that of each doctor individually (0.811, 0.796, 0.757, and 0.814, respectively) (P<0.05). The mean sensitivity, specificity, precision, and F1 score of the CNN models were 0.822, 0.912, 0.829, and 0.822, respectively, whereas the mean values of four doctors were 0.751, 0.889, 0.762, and 0.797, respectively. CONCLUSIONS: The AI-based model demonstrated high performance in classifying the presence of bone tumors in the proximal femur on plain radiographs. Our findings suggest that AI-based technology can potentially reduce the misdiagnosis of doctors who are not specialists in musculoskeletal oncology.