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.

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.