Search

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) (PConclusions 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.

BackgroundThis study aims to develop artificial intelligence (AI) system to automatically classify patients with maxillary sinus fungal ball (MFB), chronic rhinosinusitis (CRS), and healthy controls (HCs).MethodsWe collected 512 coronal image sets from ostiomeatal unit computed tomography (OMU CT) performed on subjects who visited a single tertiary hospital. These data included 254 MFB, 128 CRS, and 130 HC subjects and were used for training the proposed AI system. The AI system takes these 1024 sets of half CT images as input and classifies these as MFB, CRS, or HC. To optimize the classification performance, we adopted a 3-D convolutional neural network of ResNet 18. We also collected 64 coronal OMU CT image sets for external validation, including 26 MFB, 18 CRS, and 20 HCs from subjects from another referral hospital. Finally, the performance of the developed AI system was compared with that of the otolaryngology resident physicians.ResultsClassification performance was evaluated using internal 5-fold cross-validation (818 training and 206 internal validation data) and external validation (128 data). The area under the receiver operating characteristic over the internal 5-fold cross-validation and the external validation was 0.96 ±0.006 and 0.97 ±0.006, respectively. The accuracy of the internal 5-fold cross-validation and the external validation was 87.5 ±2.3% and 88.4 ±3.1%, respectively. As a result of performing a classification test on external validation data from six otolaryngology resident physicians, the accuracy was obtained as 84.6 ±11.3%.ConclusionsThis AI system is the first study to classify MFB, CRS, and HC using deep neural networks to the best of our knowledge. The proposed system is fully automatic but performs similarly to or better than otolaryngology resident physicians. Therefore, we believe that in regions where otolaryngology specialists are scarce, the proposed AI will perform sufficiently effective diagnosis on behalf of doctors.

Dysarthria may present during the natural course of many degenerative neurological conditions. Hypokinetic and ataxic dysarthria are common in movement disorders and represent the underlying neuropathology. We developed an artificial intelligence (AI) model to distinguish ataxic dysarthria and hypokinetic dysarthria from normal speech and differentiate ataxic and hypokinetic speech in parkinsonian diseases and cerebellar ataxia. We screened 804 perceptual speech analyses performed in the Samsung Medical Center Neurology Department between January 2017 and December 2020. The data of patients diagnosed with parkinsonian disorders or cerebellar ataxia were included. Two speech tasks (numbering from 1 to 50 and reading nine sentences) were analyzed. We adopted convolutional neural networks and developed a patch-wise wave splitting and integrating AI system for audio classification (PWSI-AI-AC) to differentiate between ataxic and hypokinetic speech. Of the 395 speech recordings for the reading task, 76, 112, and 207 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. Of the 409 recordings of the numbering task, 82, 111, and 216 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. The reading and numbering task recordings were classified with 5-fold cross-validation using PWSI-AI-AC as follows: hypokinetic dysarthria vs. others (area under the curve: 0.92 ± 0.01 and 0.92 ± 0.02), ataxia vs. others (0.93 ± 0.04 and 0.89 ± 0.02), hypokinetic dysarthria vs. ataxia (0.96 ± 0.02 and 0.95 ± 0.01), hypokinetic dysarthria vs. none (0.86 ± 0.03 and 0.87 ± 0.05), and ataxia vs. none (0.87 ± 0.07 and 0.87 ± 0.09), respectively. PWSI-AI-AC showed reliable performance in differentiating ataxic and hypokinetic dysarthria and effectively augmented data to classify the types even with limited training samples. The proposed fully automatic AI system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases.

BackgroundRecently, we developed a chest compression device that can move the chest compression position without interruption during CPR and be remotely controlled to minimize rescuer exposure to infectious diseases. The purpose of this study was to compare its performance with conventional mechanical CPR device in a mannequin and a swine model of cardiac arrest.Materials and methodsA prototype of a remote-controlled automatic chest compression device (ROSCER) that can change the chest compression position without interruption during CPR was developed, and its performance was compared with LUCAS 3 in a mannequin and a swine model of cardiac arrest. In a swine model of cardiac arrest, 16 male pigs were randomly assigned into the two groups, ROSCER CPR (n = 8) and LUCAS 3 CPR (n = 8), respectively. During 5 minutes of CPR, hemodynamic parameters including aortic pressure, right atrial pressure, coronary perfusion pressure, common carotid blood flow, and end-tidal carbon dioxide partial pressure were measured.ResultsIn the compression performance test using a mannequin, compression depth, compression time, decompression time, and plateau time were almost equal between ROSCER and LUCAS 3. In a swine model of cardiac arrest, coronary perfusion pressure showed no difference between the two groups (p = 0.409). Systolic aortic pressure and carotid blood flow were higher in the LUCAS 3 group than in the ROSCER group during 5 minutes of CPR (p < 0.001, p = 0.008, respectively). End-tidal CO2 level of the ROSCER group was initially lower than that of the LUCAS 3 group, but was higher over time (p = 0.022). A Kaplan-Meier survival analysis for ROSC also showed no difference between the two groups (p = 0.46).ConclusionThe prototype of a remote-controlled automated chest compression device can move the chest compression position without interruption during CPR. In a mannequin and a swine model of cardiac arrest, the device showed no inferior performance to a conventional mechanical CPR device.

BACKGROUND:The aim of this study was to investigate whether 33% duty cycle increases end-tidal carbon dioxide (ETCO2) level, a surrogate measurement for cardiac output during cardiopulmonary resuscitation (CPR), compared with 50% duty cycle. METHODS:Six pigs were randomly assigned to the DC33 or DC50 group. After 3 min of induced ventricular fibrillation (VF), CPR was performed for 5 min with 33% duty cycle (DC33 group) or with 50% duty cycle (DC50 group) (phase I). Defibrillation was delivered until return of spontaneous circulation (ROSC) thereafter. After 30 min of stabilization, the animals were re-assigned to the opposite groups. VF was induced again, and CPR was performed (phase II). The primary outcome was ETCO2 during CPR, and the secondary outcomes were coronary perfusion pressure (CPP), systolic arterial pressure (SAP), diastolic arterial pressure (DAP), and right atrial pressure (RAP). RESULTS:Mean ETCO2 was higher in the DC33 group compared with the DC50 group (22.5 mmHg vs 21.5 mmHg, P = 0.018). In a linear mixed model, 33% duty cycle increased ETCO2 by 1.0 mmHg compared with 50% duty cycle (P < 0.001). ETCO2 increased over time in the DC33 group [0.6 mmHg/min] while ETCO2 decreased in the DC50 group [-0.6 mmHg/min] (P < 0.001). Duty cycle of 33% increased SAP (6.0 mmHg, P < 0.001), DAP (8.9 mmHg, P < 0.001) RAP (2.6 mmHg, P < 0.001) and CPP (4.7 mmHg, P < 0.001) compared with the duty cycle of 50%. CONCLUSION:Duty cycle of 33% increased ETCO2, a surrogate measurement for cardiac output during CPR, compared with duty cycle of 50%. Moreover, ETCO2 increased over time during CPR with 33% duty cycle while ETCO2 decreased with 50% duty cycle.