Utilizing a Digital Swarm Intelligence Platform to Improve Consensus Among Radiologists and Exploring Its Applications.

Radiologists today play a central role in making diagnostic decisions and labeling images for training and benchmarking artificial intelligence (AI) algorithms. A key concern is low inter-reader reliability (IRR) seen between experts when interpreting challenging cases. While team-based decisions are known to outperform individual decisions, inter-personal biases often creep up in group interactions which limit nondominant participants from expressing true opinions. To overcome the dual problems of low consensus and interpersonal bias, we explored a solution modeled on bee swarms. Two separate cohorts, three board-certified radiologists, (cohort 1), and five radiology residents (cohort 2) collaborated on a digital swarm platform in real time and in a blinded fashion, grading meniscal lesions on knee MR exams. These consensus votes were benchmarked against clinical (arthroscopy) and radiological (senior-most radiologist) standards of reference using Cohen's kappa. The IRR of the consensus votes was then compared to the IRR of the majority and most confident votes of the two cohorts. IRR was also calculated for predictions from a meniscal lesion detecting AI algorithm. The attending cohort saw an improvement of 23% in IRR of swarm votes (k = 0.34) over majority vote (k = 0.11). Similar improvement of 23% in IRR (k = 0.25) in 3-resident swarm votes over majority vote (k = 0.02) was observed. The 5-resident swarm had an even higher improvement of 30% in IRR (k = 0.37) over majority vote (k = 0.07). The swarm consensus votes outperformed individual and majority vote decision in both the radiologists and resident cohorts. The attending and resident swarms also outperformed predictions from a state-of-the-art AI algorithm.

Institution-wide shape analysis of 3D spinal curvature and global alignment parameters.

The spine is an articulated, 3D structure with 6 degrees of translational and rotational freedom. Clinical studies have shown spinal deformities are associated with pain and functional disability in both adult and pediatric populations. Clinical decision making relies on accurate characterization of the spinal deformity and monitoring of its progression over time. However, Cobb angle measurements are time-consuming, are limited by interobserver variability, and represent a simplified 2D view of a 3D structure. Instead, spine deformities can be described by 3D shape parameters, addressing the limitations of current measurement methods. To this end, we develop and validate a deep learning algorithm to automatically extract the vertebral midline (from the upper endplate of S1 to the lower endplate of C7) for frontal and lateral radiographs. Our results demonstrate robust performance across datasets and patient populations. Approximations of 3D spines are reconstructed from the unit normalized midline curves of 20,118 pairs of full spine radiographs belonging to 15,378 patients acquired at our institution between 2008 and 2020. The resulting 3D dataset is used to describe global imbalance parameters in the patient population and to build a statistical shape model to describe global spine shape variations in preoperative deformity patients via eight interpretable shape parameters. The developed method can identify patient subgroups with similar shape characteristics without relying on an existing shape classification system.

Automatic Deep Learning-assisted Detection and Grading of Abnormalities in Knee MRI Studies.

PURPOSE: To test the hypothesis that artificial intelligence (AI) techniques can aid in identifying and assessing lesion severity in the cartilage, bone marrow, meniscus, and anterior cruciate ligament (ACL) in the knee, improving overall MRI interreader agreement. MATERIALS AND METHODS: This retrospective study was conducted on 1435 knee MRI studies (n = 294 patients; mean age, 43 years ± 15 [standard deviation]; 153 women) collected within three previous studies (from 2011 to 2014). All MRI studies were acquired using high-spatial-resolution three-dimensional fast-spin-echo CUBE sequence. Three-dimensional convolutional neural networks were developed to detect the regions of interest within MRI studies and grade abnormalities of the cartilage, bone marrow, menisci, and ACL. Evaluation included sensitivity, specificity, and Cohen linear-weighted ĸ. The impact of AI-aided grading in intergrader agreement was assessed on an external dataset. RESULTS: Binary lesion sensitivity reported for all tissues was between 70% and 88%. Specificity ranged from 85% to 89%. The area under the receiver operating characteristic curve for all tissues ranged from 0.83 to 0.93. Deep learning-assisted intergrader Cohen ĸ agreement significantly improved in 10 of 16 comparisons among two attending physicians and two trainees for all tissues. CONCLUSION: The three-dimensional convolutional neural network had high sensitivity, specificity, and accuracy for knee-lesion-severity scoring and also increased intergrader agreement when used on an external dataset.Supplemental material is available for this article. Keywords: Bone Marrow, Cartilage, Computer Aided Diagnosis (CAD), Computer Applications-3D, Computer Applications-Detection/Diagnosis, Knee, Ligaments, MR-Imaging, Neural Networks, Observer Performance, Segmentation, Statistics © RSNA, 2021See also the commentary by Li and Chang in this issue.: An earlier incorrect version of this article appeared online. This article was corrected on April 16, 2021.

Erratum: Automatic Deep Learning-assisted Detection and Grading of Abnormalities in Knee MRI Studies.

[This corrects the article DOI: 10.1148/ryai.2021200165.].

Deep learning for large scale MRI-based morphological phenotyping of osteoarthritis.

Osteoarthritis (OA) develops through heterogenous pathophysiologic pathways. As a result, no regulatory agency approved disease modifying OA drugs are available to date. Stratifying knees into MRI-based morphological phenotypes may provide insight into predicting future OA incidence, leading to improved inclusion criteria and efficacy of therapeutics. We trained convolutional neural networks to classify bone, meniscus/cartilage, inflammatory, and hypertrophy phenotypes in knee MRIs from participants in the Osteoarthritis Initiative (n = 4791). We investigated cross-sectional association between baseline morphological phenotypes and baseline structural OA (Kellgren Lawrence grade > 1) and symptomatic OA. Among participants without baseline OA, we evaluated association of baseline phenotypes with 48-month incidence of structural OA and symptomatic OA. The area under the curve of bone, meniscus/cartilage, inflammatory, and hypertrophy phenotype neural network classifiers was 0.89 ± 0.01, 0.93 ± 0.03, 0.96 ± 0.02, and 0.93 ± 0.02, respectively (mean ± standard deviation). Among those with no baseline OA, bone phenotype (OR: 2.99 (95%CI: 1.59-5.62)) and hypertrophy phenotype (OR: 5.80 (95%CI: 1.82-18.5)) each respectively increased odds of developing incident structural OA and symptomatic OA at 48 months. All phenotypes except meniscus/cartilage increased odds of undergoing total knee replacement within 96 months. Artificial intelligence can rapidly stratify knees into structural phenotypes associated with incident OA and total knee replacement, which may aid in stratifying patients for clinical trials of targeted therapeutics.

Deep Learning for Hierarchical Severity Staging of Anterior Cruciate Ligament Injuries from MRI.

PURPOSE: To evaluate the diagnostic utility of two convolutional neural networks (CNNs) for severity staging of anterior cruciate ligament (ACL) injuries. MATERIALS AND METHODS: In this retrospective study, 1243 knee MR images (1008 intact, 18 partially torn, 77 fully torn, and 140 reconstructed ACLs) from 224 patients (mean age, 47 years ± 14 [standard deviation]; 54% women) were analyzed. The MRI examinations were performed between 2011 and 2014. A modified scoring metric was used. Classification of ACL injuries using deep learning involved use of two types of CNN, one with three-dimensional (3D) and the other with two-dimensional (2D) convolutional kernels. Performance metrics included sensitivity, specificity, weighted Cohen κ, and overall accuracy, and the McNemar test was used to compare the performance of the CNNs. RESULTS: The overall accuracies for ACL injury classification using the 3D CNN and 2D CNN were 89% (225 of 254) and 92% (233 of 254), respectively (P = .27), and both CNNs had a weighted Cohen κ of 0.83. The 2D CNN and 3D CNN performed similarly in classifying intact ACLs (2D CNN, sensitivity of 93% [188 of 203] and specificity of 90% [46 of 51] vs 3D CNN, sensitivity of 89% [180 of 203] and specificity of 88% [45 of 51]). Classification of full tears by both networks was also comparable (2D CNN, sensitivity of 82% [14 of 17] and specificity of 94% [222 of 237] vs 3D CNN, sensitivity of 76% [13 of 17] and specificity of 100% [236 of 237]). The 2D CNN classified all reconstructed ACLs correctly. CONCLUSION: Two-dimensional and 3D CNNs applied to ACL lesion classification had high sensitivity and specificity, suggesting that these networks could be used to help nonexperts grade ACL injuries. Supplemental material is available for this article. © RSNA, 2020.

Computer-Aided Detection AI Reduces Interreader Variability in Grading Hip Abnormalities With MRI.

BACKGROUND: Accurate interpretation of hip MRI is time-intensive and difficult, prone to inter- and intrareviewer variability, and lacks a universally accepted grading scale to evaluate morphological abnormalities. PURPOSE: To 1) develop and evaluate a deep-learning-based model for binary classification of hip osteoarthritis (OA) morphological abnormalities on MR images, and 2) develop an artificial intelligence (AI)-based assist tool to find if using the model predictions improves interreader agreement in hip grading. STUDY TYPE: Retrospective study aimed to evaluate a technical development. POPULATION: A total of 764 MRI volumes (364 patients) obtained from two studies (242 patients from LASEM [FORCe] and 122 patients from UCSF), split into a 65-25-10% train, validation, test set for network training. FIELD STRENGTH/SEQUENCE: 3T MRI, 2D T2 FSE, PD SPAIR. ASSESSMENT: Automatic binary classification of cartilage lesions, bone marrow edema-like lesions, and subchondral cyst-like lesions using the MRNet, interreader agreement before and after using network predictions. STATISTICAL TESTS: Receiver operating characteristic (ROC) curve, area under curve (AUC), specificity and sensitivity, and balanced accuracy. RESULTS: For cartilage lesions, bone marrow edema-like lesions and subchondral cyst-like lesions the AUCs were: 0.80 (95% confidence interval [CI] 0.65, 0.95), 0.84 (95% CI 0.67, 1.00), and 0.77 (95% CI 0.66, 0.85), respectively. The sensitivity and specificity of the radiologist for binary classification were: 0.79 (95% CI 0.65, 0.93) and 0.80 (95% CI 0.59, 1.02), 0.40 (95% CI -0.02, 0.83) and 0.72 (95% CI 0.59, 0.86), 0.75 (95% CI 0.45, 1.05) and 0.88 (95% CI 0.77, 0.98). The interreader balanced accuracy increased from 53%, 71% and 56% to 60%, 73% and 68% after using the network predictions and saliency maps. DATA CONCLUSION: We have shown that a deep-learning approach achieved high performance in clinical classification tasks on hip MR images, and that using the predictions from the deep-learning model improved the interreader agreement in all pathologies. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 1 J. Magn. Reson. Imaging 2020;52:1163-1172.

Learning osteoarthritis imaging biomarkers from bone surface spherical encoding.

PURPOSE: To learn bone shape features from spherical bone map of knee MRI images using established convolutional neural networks (CNN) and use these features to diagnose and predict osteoarthritis (OA). METHODS: A bone segmentation model was trained on 25 manually annotated 3D MRI volumes to segment the femur, tibia, and patella from 47 078 3D MRI volumes. Each bone segmentation was converted to a 3D point cloud and transformed into spherical coordinates. Different fusion strategies were performed to merge spherical maps obtained by each bone. A total of 41 822 merged spherical maps with corresponding Kellgren-Lawrence grades for radiographic OA were used to train a CNN classifier model to diagnose OA using bone shape learned features. Several OA Diagnosis models were tested and the weights for each trained model were transferred to the OA Incidence models. The OA incidence task consisted of predicting OA from a healthy scan within a range of eight time points, from 1 y to 8 y. The validation performance was compared and the test set performance was reported. RESULTS: The OA Diagnosis model had an area-under-the-curve (AUC) of 0.905 on the test set with a sensitivity and specificity of 0.815 and 0.839. The OA Incidence models had an AUC ranging from 0.841 to 0.646 on the test set for the range from 1 y to 8 y. CONCLUSION: Bone shape was successfully used as a predictive imaging biomarker for OA. This approach is novel in the field of deep learning applications for musculoskeletal imaging and can be expanded to other OA biomarkers.

Factors Predicting Positive Culture in CT-Guided Bone Biopsy Performed for Suspected Osteomyelitis.

OBJECTIVE: The goal of this study was to identify clinical factors and radiographic characteristics associated with positive culture results from bone biopsy in cases of suspected osteomyelitis. MATERIALS AND METHODS: A total of 997 CT-guided bone biopsies were reviewed. We reviewed the images and medical records of 29 cases of suspected osteomyelitis to determine if any of the following factors affected culture results: age, sex, history of diabetes, collection of fluid aspirate at the time of biopsy, recent antibiotic therapy, elevated WBC count, and mean attenuation. RESULTS: Of the 29 CT-guided bone biopsies, 21% yielded positive culture results. We found no significant difference in age, sex, history of diabetes, collection of fluid aspirate at the time of biopsy, recent antibiotic therapy, or elevated WBC count between positive culture and negative culture cases. We did, however, find a significant difference in the mean CT attenuation values of the sampled bone between the two groups: 72.0 ± 41.5 HU (95% CI, 28.4-115.6 HU) among the positive culture group compared with 227.5 ± 198.8 HU (95% CI, 141.4-313.6 HU) among the negative culture group (p = 0.03). CONCLUSION: The rate of positive culture from image-guided core biopsy of suspected osteomyelitis is low. In this study, lower CT attenuation values were associated with a significantly higher rate of positive culture. An attenuation value of 150 HU may serve as a threshold above which biopsy would be expected to have lower utility for obtaining specific microbial culture data.

Effect of gantry rotation speed and scan mode on peristalsis motion artifact frequency and severity at abdominal CT.

PURPOSE: The purpose of the study was to understand the effect of CT gantry speed and axial vs. helical scan mode on the frequency and severity of bowel peristalsis artifacts. METHOD: We retrospectively identified 150 oncologic abdominopelvic CT scans obtained on a 256 slice CT scanner: 50 scans obtained with Axial mode and 0.5-s gantry rotation time (Slow-Axial); 50 with Axial mode and 0.28-s gantry rotation time (Fast-Axial); and 50 scans with Helical mode and 0.28-s gantry rotation time (Fast-Helical). The patients included 74 women and 76 men with a mean age of 61 years (range 22-85 years). Two readers viewed all CT scans to record the presence and severity of bowel peristalsis artifact, location of artifact (stomach, duodenum/jejunum, ileum, and colon) and artifact location relative to bowel interface (gas-bowel, fluid-bowel, and gas-fluid). The severity of artifacts was recorded subjectively on a 3-point scale, and objectively based on maximum length of the artifact. RESULTS: Peristalsis artifact was more commonly seen with Slow-Axial scan acquisition (37 of 50 patient scans, or 74%) than Fast-Axial (15 in 50 patient scans, or 30%, p < 0.001) and Fast-Helical (22 of 50 patient scans, or 44%, p < 0.005). The bowel segment distribution and severity of peristalsis artifacts were not significantly different between scan techniques. CONCLUSION: Peristalsis artifacts are common at abdominopelvic CT scans. Fast gantry rotation speed significantly reduces the frequency of bowel peristalsis artifacts and should be a consideration when imaging of bowel and structures near bowel is critical.

Effect of Sonication Duration and Power on Ablation Depth During MR-Guided Focused Ultrasound of Bone.

PURPOSE: To evaluate the effect of differences in sonication duration and power on the size of postcontrast ablation zone following magnetic resonance-guided focused ultrasound (MRgFUS) of bone in a swine femoral bone model. MATERIALS AND METHODS: Experimental procedures received approval from the Institutional Committee on Animal Research. MRgFUS was used to create two thermal lesions in the left femur of six pigs. Each target was subjected to six sonications. 400J of energy was used for each sonication. However, the distal target received the standard sonication duration of 20 seconds (20W), while the proximal target received a longer sonication duration of 40 seconds (10W). MRgFUS lesions were imaged with fat-saturated spoiled gradient echo sequence at 3.0T MRI 10 minutes following the administration of contrast. Maximum three-plane dimensions of the hypoenhanced ablation area were measured. RESULTS: Postcontrast MR images demonstrated ovoid regions of hypoenhancement at each target. The average depth of ablation was significantly greater for the shorter high-power sonications (7.3 mm), compared to the longer lower-power sonications (4.5 mm), P = 0.026. The craniocaudal dimension was also greater for the shorter ablations 26.7 mm compared to the longer sonications 21.0 mm, P = 0.006. CONCLUSION: Contrary to anecdotal clinical experience, this preclinical model suggests that during MRgFUS of bone, standard duration, higher-power sonications resulted in deeper ablation volumes compared to long duration, lower-power sonications. These results suggest that to achieve deeper ablations, if longer sonications are used, then the power should be relatively maintained, for a net energy increase. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2017;46:1418-1422.