Automated weight-bearing foot measurements using an artificial intelligence-based software.

OBJECTIVE: To assess the accuracy of an artificial intelligence (AI) software (BoneMetrics, Gleamer) in performing automated measurements on weight-bearing forefoot and lateral foot radiographs. METHODS: Consecutive forefoot and lateral foot radiographs were retrospectively collected from three imaging institutions. Two senior musculoskeletal radiologists independently annotated key points to measure the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs and the talus-first metatarsal, medial arch, and calcaneus inclination angles on lateral foot radiographs. The ground truth was defined as the mean of their measurements. Statistical analysis included mean absolute error (MAE), bias assessed with Bland-Altman analysis between the ground truth and AI prediction, and intraclass coefficient (ICC) between the manual ratings. RESULTS: Eighty forefoot radiographs were included (53 ± 17 years, 50 women), and 26 were excluded. Ninety-seven lateral foot radiographs were included (51 ± 20 years, 46 women), and 21 were excluded. MAE for the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs were respectively 1.2° (95% CI [1; 1.4], bias = - 0.04°, ICC = 0.98), 0.7° (95% CI [0.6; 0.9], bias = - 0.19°, ICC = 0.91) and 0.9° (95% CI [0.7; 1.1], bias = 0.44°, ICC = 0.96). MAE for the talus-first, medial arch, and calcaneal inclination angles on the lateral foot radiographs were respectively 3.9° (95% CI [3.4; 4.5], bias = 0.61° ICC = 0.88), 1.5° (95% CI [1.2; 1.8], bias = - 0.18°, ICC = 0.95) and 1° (95% CI [0.8; 1.2], bias = 0.74°, ICC = 0.99). Bias and MAE between the ground truth and the AI prediction were low across all measurements. ICC between the two manual ratings was excellent, except for the talus-first metatarsal angle. CONCLUSION: AI demonstrated potential for accurate and automated measurements on weight-bearing forefoot and lateral foot radiographs.

Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs.

Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests. Results The study included 500 patients (mean age, 54 years ± 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule, pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (-0.2%; 95% CI: -0.36, -0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001). Conclusion AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels of expertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax. © RSNA, 2023 Supplemental material is available for this article.

Commercially-available AI algorithm improves radiologists' sensitivity for wrist and hand fracture detection on X-ray, compared to a CT-based ground truth.

OBJECTIVES: Algorithms for fracture detection are spreading in clinical practice, but the use of X-ray-only ground truth can induce bias in their evaluation. This study assessed radiologists' performances to detect wrist and hand fractures on radiographs, using a commercially-available algorithm, compared to a computerized tomography (CT) ground truth. METHODS: Post-traumatic hand and wrist CT and concomitant X-ray examinations were retrospectively gathered. Radiographs were labeled based on CT findings. The dataset was composed of 296 consecutive cases: 118 normal (39.9%), 178 pathological (60.1%) with a total of 267 fractures visible in CT. Twenty-three radiologists with various levels of experience reviewed all radiographs without AI, then using it, blinded towards CT results. RESULTS: Using AI improved radiologists' sensitivity (Se, 0.658 to 0.703, p < 0.0001) and negative predictive value (NPV, 0.585 to 0.618, p < 0.0001), without affecting their specificity (Sp, 0.885 vs 0.891, p = 0.91) or positive predictive value (PPV, 0.887 vs 0.899, p = 0.08). On the radiographic dataset, based on the CT ground truth, stand-alone AI performances were 0.771 (Se), 0.898 (Sp), 0.684 (NPV), 0.915 (PPV), and 0.764 (AUROC) which were lower than previously reported, suggesting a potential underestimation of the number of missed fractures in the AI literature. CONCLUSIONS: AI enabled radiologists to improve their sensitivity and negative predictive value for wrist and hand fracture detection on radiographs, without affecting their specificity or positive predictive value, compared to a CT-based ground truth. Using CT as gold standard for X-ray labels is innovative, leading to algorithm performance poorer than reported elsewhere, but probably closer to clinical reality. CLINICAL RELEVANCE STATEMENT: Using an AI algorithm significantly improved radiologists' sensitivity and negative predictive value in detecting wrist and hand fractures on radiographs, with ground truth labels based on CT findings. KEY POINTS: • Using CT as a ground truth for labeling X-rays is new in AI literature, and led to algorithm performance significantly poorer than reported elsewhere (AUROC: 0.764), but probably closer to clinical reality. • AI enabled radiologists to significantly improve their sensitivity (+ 4.5%) and negative predictive value (+ 3.3%) for the detection of wrist and hand fractures on X-rays. • There was no significant change in terms of specificity or positive predictive value.

Learning from the machine: AI assistance is not an effective learning tool for resident education in chest x-ray interpretation.

OBJECTIVES: To assess whether a computer-aided detection (CADe) system could serve as a learning tool for radiology residents in chest X-ray (CXR) interpretation. METHODS: Eight radiology residents were asked to interpret 500 CXRs for the detection of five abnormalities, namely pneumothorax, pleural effusion, alveolar syndrome, lung nodule, and mediastinal mass. After interpreting 150 CXRs, the residents were divided into 2 groups of equivalent performance and experience. Subsequently, group 1 interpreted 200 CXRs from the "intervention dataset" using a CADe as a second reader, while group 2 served as a control by interpreting the same CXRs without the use of CADe. Finally, the 2 groups interpreted another 150 CXRs without the use of CADe. The sensitivity, specificity, and accuracy before, during, and after the intervention were compared. RESULTS: Before the intervention, the median individual sensitivity, specificity, and accuracy of the eight radiology residents were 43% (range: 35-57%), 90% (range: 82-96%), and 81% (range: 76-84%), respectively. With the use of CADe, residents from group 1 had a significantly higher overall sensitivity (53% [n = 431/816] vs 43% [n = 349/816], p < 0.001), specificity (94% [i = 3206/3428] vs 90% [n = 3127/3477], p < 0.001), and accuracy (86% [n = 3637/4244] vs 81% [n = 3476/4293], p < 0.001), compared to the control group. After the intervention, there were no significant differences between group 1 and group 2 regarding the overall sensitivity (44% [n = 309/696] vs 46% [n = 317/696], p = 0.666), specificity (90% [n = 2294/2541] vs 90% [n = 2285/2542], p = 0.642), or accuracy (80% [n = 2603/3237] vs 80% [n = 2602/3238], p = 0.955). CONCLUSIONS: Although it improves radiology residents' performances for interpreting CXRs, a CADe system alone did not appear to be an effective learning tool and should not replace teaching. CLINICAL RELEVANCE STATEMENT: Although the use of artificial intelligence improves radiology residents' performance in chest X-rays interpretation, artificial intelligence cannot be used alone as a learning tool and should not replace dedicated teaching. KEY POINTS: • With CADe as a second reader, residents had a significantly higher sensitivity (53% vs 43%, p < 0.001), specificity (94% vs 90%, p < 0.001), and accuracy (86% vs 81%, p < 0.001), compared to residents without CADe. • After removing access to the CADe system, residents' sensitivity (44% vs 46%, p = 0.666), specificity (90% vs 90%, p = 0.642), and accuracy (80% vs 80%, p = 0.955) returned to that of the level for the group without CADe.

Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning.

OBJECTIVE: We aimed to perform an external validation of an existing commercial AI software program (BoneView™) for the detection of acute appendicular fractures in pediatric patients. MATERIALS AND METHODS: In our retrospective study, anonymized radiographic exams of extremities, with or without fractures, from pediatric patients (aged 2-21) were included. Three hundred exams (150 with fractures and 150 without fractures) were included, comprising 60 exams per body part (hand/wrist, elbow/upper arm, shoulder/clavicle, foot/ankle, leg/knee). The Ground Truth was defined by experienced radiologists. A deep learning algorithm interpreted the radiographs for fracture detection, and its diagnostic performance was compared against the Ground Truth, and receiver operating characteristic analysis was done. Statistical analyses included sensitivity per patient (the proportion of patients for whom all fractures were identified) and sensitivity per fracture (the proportion of fractures identified by the AI among all fractures), specificity per patient, and false-positive rate per patient. RESULTS: There were 167 boys and 133 girls with a mean age of 10.8 years. For all fractures, sensitivity per patient (average [95% confidence interval]) was 91.3% [85.6, 95.3], specificity per patient was 90.0% [84.0,94.3], sensitivity per fracture was 92.5% [87.0, 96.2], and false-positive rate per patient in patients who had no fracture was 0.11. The patient-wise area under the curve was 0.93 for all fractures. AI diagnostic performance was consistently high across all anatomical locations and different types of fractures except for avulsion fractures (sensitivity per fracture 72.7% [39.0, 94.0]). CONCLUSION: The BoneView™ deep learning algorithm provides high overall diagnostic performance for appendicular fracture detection in pediatric patients.

Distribution of Flow in an Arteriovenous Fistula Using Reduced-Order Models.

The creation of a communication between an artery and a vein (arteriovenous fistula or AVF), to speed up the blood purification during hemodialysis of patients with renal insufficiency, induces significant rheological and mechanical modifications of the vascular network. In this study, we investigated the impact of the creation of an AVF with a zero-dimensional network model of the vascular system of an upper limb and a one-dimensional model around the anastomosis. We compared the simulated distribution of flow rate in this vascular system with Doppler ultrasound measurements. We studied three configurations: before the creation of the AVF, after the creation of the AVF, and after a focal reduction due to a hyper flow rate. The zero-dimensional model predicted the bounds of the diameter of the superficial vein that respects the flow constraints, assuming a high capillary resistance. We indeed highlighted the importance of knowing the capillary resistance as it is a decisive parameter in the models. We also found that the model reproduced the Doppler measurements of flow rate in every configuration and predicted the distribution of flow in cases where the Doppler was not available. The one-dimensional model allowed studying the impact of a venous constriction on the flow distribution, and the capillary resistance was still a crucial parameter.

Effects of Cross-Clamping on Vascular Mechanics: Comparing Waveform Analysis With a Numerical Model.

BACKGROUND: Immediate changes in vascular mechanics during aortic cross-clamping remain widely unknown. By using a numerical model of the arterial network, vascular compliance and resistance can be estimated and the time constant of pressure waves can be calculated and compared with results from the classic arterial waveform analysis. METHODS: Experimental data were registered from continuous invasive radial artery pressure measurements from 11 patients undergoing vascular surgery. A stable set of beats were chosen immediately before and after each clamping event. Through the arterial waveform analysis, the time constant was calculated for each individual beat and for a mean beat of each condition as to compare with numerical simulations. Overall proportional changes in resistance and compliance during clamping and unclamping were calculated using the numerical model. RESULTS: Arterial waveform analysis of individual beats indicated a significant 10% median reduction in the time constant after clamping, and a significant 17% median increase in the time constant after unclamping. There was a positive correlation between waveform analysis and numerical values of the time constant, which was moderate (ρ = 0.51; P = 0.01486) during clamping and strong (ρ = 0.77; P ≤ 0.0001) during unclamping. After clamping, there was a significant 16% increase in the mean resistance and a significant 23% decrease in the mean compliance. After unclamping, there was a significant 19% decrease in the mean resistance and a significant 56% increase in the mean compliance. CONCLUSIONS: There are significant hemodynamic changes in vascular compliance and resistance during aortic clamping and unclamping. Numerical computer models can add information on the mechanisms of injury due to aortic clamping.

High performance for bone age estimation with an artificial intelligence solution.

PURPOSE: The purpose of this study was to compare the performance of an artificial intelligence (AI) solution to that of a senior general radiologist for bone age assessment. MATERIAL AND METHODS: Anteroposterior hand radiographs of eight boys and eight girls from each age interval between five and 17 year-old from four different radiology departments were retrospectively collected. Two board-certified pediatric radiologists with knowledge of the sex and chronological age of the patients independently estimated the Greulich and Pyle bone age to determine the standard of reference. A senior general radiologist not specialized in pediatric radiology (further referred to as "the reader") then determined the bone age with knowledge of the sex and chronological age. The results of the reader were then compared to those of the AI solution using mean absolute error (MAE) in age estimation. RESULTS: The study dataset included a total of 206 patients (102 boys of mean chronological age of 10.9 ± 3.7 [SD] years, 104 girls of mean chronological age of 11 ± 3.7 [SD] years). For both sexes, the AI algorithm showed a significantly lower MAE than the reader (P < 0.007). In boys, the MAE was 0.488 years (95% confidence interval [CI]: 0.28-0.44; r2 = 0.978) for the AI algorithm and 0.771 years (95% CI: 0.64-0.90; r2 = 0.94) for the reader. In girls, the MAE was 0.494 years (95% CI: 0.41-0.56; r2 = 0.973) for the AI algorithm and 0.673 years (95% CI: 0.54-0.81; r2 = 0.934) for the reader. CONCLUSION: The AI solution better estimates the Greulich and Pyle bone age than a general radiologist does.

Assessment of performances of a deep learning algorithm for the detection of limbs and pelvic fractures, dislocations, focal bone lesions, and elbow effusions on trauma X-rays.

PURPOSE: To appraise the performances of an AI trained to detect and localize skeletal lesions and compare them to the routine radiological interpretation. METHODS: We retrospectively collected all radiographic examinations with the associated radiologists' reports performed after a traumatic injury of the limbs and pelvis during 3 consecutive months (January to March 2017) in a private imaging group of 14 centers. Each examination was analyzed by an AI (BoneView, Gleamer) and its results were compared to those of the radiologists' reports. In case of discrepancy, the examination was reviewed by a senior skeletal radiologist to settle on the presence of fractures, dislocations, elbow effusions, and focal bone lesions (FBL). The lesion-wise sensitivity of the AI and the radiologists' reports was compared for each lesion type. This study received IRB approval (CRM-2106-177). RESULTS: A total of 4774 exams were included in the study. Lesion-wise sensitivity was 73.7% for the radiologists' reports vs. 98.1% for the AI (+24.4 points) for fracture detection, 63.3% vs. 89.9% (+26.6 points) for dislocation detection, 84.7% vs. 91.5% (+6.8 points) for elbow effusion detection, and 16.1% vs. 98.1% (+82 points) for FBL detection. The specificity of the radiologists' reports was always 100% whereas AI specificity was 88%, 99.1%, 99.8%, 95.6% for fractures, dislocations, elbow effusions, and FBL respectively. The NPV was measured at 99.5% for fractures, 99.8% for dislocations, and 99.9% for elbow effusions and FBL. CONCLUSION: AI has the potential to prevent diagnosis errors by detecting lesions that were initially missed in the radiologists' reports.

Parameter estimation to study the immediate impact of aortic cross-clamping using reduced order models.

Aortic cross-clamping is a common strategy during vascular surgery, however, its instantaneous impact on hemodynamics is unknown. We, therefore, developed two numerical models to estimate the immediate impact of aortic clamping on the vascular properties. To assess the validity of the models, we recorded continuous invasive pressure signals during abdominal aneurysm repair surgery, immediately before and after clamping. The first model is a zero-dimensional (0D) three-element Windkessel model, which we coupled to a gradient-based parameter estimation algorithm to identify patient-specific parameters such as vascular resistance and compliance. We found a 10% increase in the total resistance and a 20% decrease in the total compliance after clamping. The second model is a nine-artery network corresponding to an average human body in which we solved the one-dimensional (1D) blood flow equations. With a similar parameter estimation method and using the results from the 0D model, we identified the resistance boundary conditions of the 1D network. Determining the patient-specific total resistance and the distribution of peripheral resistances through the parameter estimation process was sufficient for the 1D model to accurately reproduce the impact of clamping on the pressure waveform. Both models gave an accurate description of the pressure wave and had a high correlation (R2 > .95) with experimental blood pressure data.