Myositis ossificans mimicking bone surface osteosarcoma: case report with literature review.

Myositis ossificans, a benign tumor composed of spindle cells and osteoblasts, can clinically and radiologically mimic osteosarcoma. While recognition and accurate diagnosis of myositis ossificans can be a challenge, this is critical as it may allow a conservative surgical approach to maximize functional outcomes. Herein, we present a patient with surface myositis ossificans confirmed genetically by the presence of COL1A1::USP6 gene fusion, along with a literature review. Due to the enhanced visualization of the bone matrix, computed tomography (CT) imaging may be a superior imaging modality to magnetic resonance (MR) imaging. Staged biopsies with samples obtained from the periphery and center of the lesions may allow pathologists to discern the zonal distribution histologically. Furthermore, immunohistochemistry fluorescence in situ hybridization and molecular testing can aid in the distinction of myositis ossificans from mimics. Because of their resemblance to other bone tumors, these cases of myositis ossificans highlight the importance of a multidisciplinary approach integrating clinical, radiologic, and pathologic analysis and involving serial imaging, sampling, and judicious use of ancillary immunohistochemical and molecular testing.

Cemented and Press-fit Femoral Stems for the Management of Oncologic Femoral Tumors.

BACKGROUND: Stem fixation in reconstruction after resection of femoral tumors is debated. Cemented stems offer immediate stability but risk aseptic loosening, while press-fit stems allow bone ingrowth but risk stress shielding and subsidence. Our retrospective review aimed to determine implant failure rates and their associated factors, as well as the rates of infection, debridement, and mortality for both fixation groups (cemented or press-fit stems) used in patients undergoing resection of femoral tumor disease and subsequent arthroplasty. METHODS: We retrospectively studied 252 patients who underwent resection of femoral tumors and subsequent arthroplasty using cemented (n = 173; 69%) or press-fit (noncemented) (n = 79; 31%) stems between 1999 and 2020. Implant failure was the primary outcome, with secondary outcomes including rates of implant infection, debridement, and mortality. Multivariable regression was done to assess risk factors for implant failures. RESULTS: The study found implant failure rates of 11% and 18% for cemented stems and press-fit stems, respectively. Lower stem to diaphyseal ratios (P = 0.024) and younger patients (P = 0.008) were associated with a higher risk of implant failure in cemented stems. The infection rates were 14% and 10% for cemented and press-fit stems, respectively. Debridement rates were 16% and 13% for cemented and press-fit stems, respectively, while the 1-year mortality rate was 16% for cemented stems and 1.5% for press-fit stems. CONCLUSIONS: This study is the largest of its kind, providing patient characteristics and outcomes in both cemented and press-fit stems in the setting of reconstruction for femoral tumors. Both methods can be effective, with outcomes dependent on patient-specific factors, such as life expectancy, activity level, and body habitus, as well as proper implant fit. Additional studies of both implants and longer follow-up are required to elucidate the optimal fixation method for each individual patient. LEVEL OF EVIDENCE: Level III, retrospective noncomparative study.

Bone Density Screening Rates Among Medicare Beneficiaries: An Analysis with a focus on Asian Americans.

PURPOSE: To report osteoporosis screening utilization rates among Asian American (AsA) populations in the USA. METHODS: We retrospectively assessed the use of dual-energy X-ray absorptiometry (DXA) screening using the Medicare 5% Research Identifiable Files. Using Current Procedural Terminology (CPT) codes indicative of a DXA scan, we identified patients recommended for DXA screening according to the ACR-SPR-SSR Practice Parameters (females ≥ 65 years, males ≥ 70 years). Sociodemographic factors and their association with screening were evaluated using chi-square tests. RESULTS: There were 80,439 eligible AsA beneficiaries, and 12,102 (15.1%) received osteoporosis screening. DXA rate for women was approximately four times greater than the rate for men (19.8% vs. 5.0%; p < 0.001). AsA beneficiaries in zip codes with higher mean household income (MHI) were more likely to have DXA than those in lower MHI areas (17.6% vs. 14.3%, p < 0.001). AsA beneficiaries aged < 80 were more likely to receive DXA (15.5%) than those aged ≥ 80 (14.1%, p < 0.001). There were 2,979,801 eligible non-AsA beneficiaries, and 496,957 (16.7%) received osteoporosis screening during the study period. Non-Hispanic white beneficiaries had the highest overall screening rate (17.5%), followed by North American Native (13.0%), Black (11.8%), and Hispanic (11.1%) beneficiaries. Comparing AsA to non-AsA populations, there were significantly lower DXA rates among AsA beneficiaries when controlling for years of Medicare eligibility, patient age, sex, location, and mean income (p < 0.001). CONCLUSION: We found lower than expected DXA screening rates for AsA patients. A better understanding of the barriers and facilitators to AsA osteoporosis screening is needed to improve patient care.

Phosphaturic mesenchymal tumor: management and outcomes of ten patients treated at a single institution.

BACKGROUND: Phosphaturic mesenchymal tumor (PMT) is a rare tumor that causes tumor-induced osteomalacia. Patients present with non-specific symptoms secondary to renal phosphate wasting and decreased bone mineralization. We sought to assess: (1) What are the common presenting features, laboratory and imaging findings, histologic findings of phosphaturic mesenchymal tumors? (2) What are the available treatment strategies for phosphaturic mesenchymal tumors and their long-term outcomes in terms of local recurrence and symptom control after treatment? METHODS: We retrospectively identified patients with a histologic diagnosis of PMT located in the axial or appendicular skeleton, or surrounding soft tissues. A total of 10 patients were finally included in our study. RESULTS: Median tumor size was 1.9 cm (range, 1.1 to 6.1) and median time from symptom onset to diagnosis was 3 years (range, 0.5 to 15 years). All patients but one presented with hypophosphatemia (median 1.9 mg/dL, range 1.2 to 3.2). Pre-operative FGF-23 was elevated in all cases (median 423.5 RU/mL, range 235 to 8950). Six patients underwent surgical resection, three were treated percutaneously (radiofrequency ablation or cryoablation), and one refused treatment. Only one patient developed local recurrence and no patients developed metastatic disease. At last follow-up, nine patients showed no evidence of disease and one was alive with disease. CONCLUSION: Phosphaturic mesenchymal tumor is a rare tumor presenting with non-specific symptoms. Surgery is the standard treatment when negative margins can be achieved without significant morbidity. In patients with small tumors in surgically-inaccessible areas, radiofrequency ablation or cryoablation can be performed successfully.

Biomarkers of Body Composition.

The importance and impact of imaging biomarkers has been increasing over the past few decades. We review the relevant clinical and imaging terminology needed to understand the clinical and research applications of body composition. Imaging biomarkers of bone, muscle, and fat tissues obtained with dual-energy X-ray absorptiometry, computed tomography, magnetic resonance imaging, and ultrasonography are described.

Can gas and infection coexist in the intervertebral disc? A retrospective analysis of percutaneously biopsied suspected discitis-osteomyelitis cases.

OBJECTIVES: To retrospectively evaluate the correlation between intradiscal gas and infection in patients percutaneously biopsied for suspected discitis-osteomyelitis. MATERIALS AND METHODS: We retrospectively reviewed all CT-guided discitis-osteomyelitis biopsies performed between 2002 and 2022. Two independent trained musculoskeletal radiologists evaluated for presence of gas on CT and/or MRI within 1 week of the biopsy. Disagreements were resolved by a third musculoskeletal radiologist. CT was considered the gold standard for the detection of intradiscal gas. Pathology, microbiology, and imaging and clinical follow-up were used as the gold standard for presence of infection. Interrater agreement on CT and MRI, sensitivity, and positive predictive value were calculated, using the presence of gas as an indicator (test positive) for "no infection." RESULTS: There were 284 biopsies in 275 subjects (mean age 58 ± 1.0 (range 4-99) years; 101 (37%) females and 174 (63%) males). Of the biopsies, 12 (4%) were cervical, 80 (28%) were thoracic, 192 (68%) were lumbar, and 200 (70%) were considered true discitis-osteomyelitis based on pathology, imaging, and clinical follow-up. Interrater agreement was excellent for CT (kappa = 0.83) and poor for MRI (kappa = - 0.021). The presence of gas had a 94% specificity and 76% negative predictive value for the absence of infection. CONCLUSION: CT is the preferred method for detecting intradiscal gas. The presence of gas means that discitis-osteomyelitis is unlikely. If intradiscal gas is present in the setting of discitis-osteomyelitis, the gas bubbles tend to be smaller and fewer in number.

Bone Marrow Biopsies: Is CT, Fluoroscopy, or no Imaging Guidance the Most Cost-Effective Strategy?

RATIONALE AND OBJECTIVES: To determine the most cost-effective strategy for pelvic bone marrow biopsies. MATERIALS AND METHODS: A decision analytic model from the health care system perspective for patients with high clinical concern for multiple myeloma (MM) was used to evaluate the incremental cost-effectiveness of three bone marrow core biopsy techniques: computed tomography (CT) guided, and fluoroscopy guided, no-imaging (landmark-based). Model input data on utilities, costs, and probabilities were obtained from comprehensive literature review and expert opinion. Costs were estimated in 2023 U.S. dollars. Primary effectiveness outcome was quality adjusted life years (QALY). Willingness to pay threshold was $100,000 per QALY gained. RESULTS: No-imaging based biopsy was the most cost-effective strategy as it had the highest net monetary benefit ($4218) and lowest overall cost ($92.17). Fluoroscopy guided was excluded secondary to extended dominance. CT guided biopsies were less preferred as it had an incremental cost-effectiveness ratio ($334,043) greater than the willingness to pay threshold. Probabilistic sensitivity analysis found non-imaging based biopsy to be the most cost-effective in 100% of simulations and at all willingness to pay thresholds up to $200,000. CONCLUSION: No-imaging based biopsy appears to be the most cost-effective strategy for bone marrow core biopsy in patients suspected of MM. CLINICAL RELEVANCE: No imaging guidance is the preferred strategy, although image-guidance may be required for challenging anatomy. CT image interpretation may be helpful for planning biopsies. Establishing a non-imaging guided biopsy service with greater patient anxiety and pain support may be warranted.

[ 11 C]-PBR28 positron emission tomography signal as an imaging marker of joint inflammation in knee osteoarthritis.

ABSTRACT: Although inflammation is known to play a role in knee osteoarthritis (KOA), inflammation-specific imaging is not routinely performed. In this article, we evaluate the role of joint inflammation, measured using [ 11 C]-PBR28, a radioligand for the inflammatory marker 18-kDa translocator protein (TSPO), in KOA. Twenty-one KOA patients and 11 healthy controls (HC) underwent positron emission tomography/magnetic resonance imaging (PET/MRI) knee imaging with the TSPO ligand [ 11 C]-PBR28. Standardized uptake values were extracted from regions-of-interest (ROIs) semiautomatically segmented from MRI data, and compared across groups (HC, KOA) and subgroups (unilateral/bilateral KOA symptoms), across knees (most vs least painful), and against clinical variables (eg, pain and Kellgren-Lawrence [KL] grades). Overall, KOA patients demonstrated elevated [ 11 C]-PBR28 binding across all knee ROIs, compared with HC (all P 's < 0.005). Specifically, PET signal was significantly elevated in both knees in patients with bilateral KOA symptoms (both P 's < 0.01), and in the symptomatic knee ( P < 0.05), but not the asymptomatic knee ( P = 0.95) of patients with unilateral KOA symptoms. Positron emission tomography signal was higher in the most vs least painful knee ( P < 0.001), and the difference in pain ratings across knees was proportional to the difference in PET signal ( r = 0.74, P < 0.001). Kellgren-Lawrence grades neither correlated with PET signal (left knee r = 0.32, P = 0.19; right knee r = 0.18, P = 0.45) nor pain ( r = 0.39, P = 0.07). The current results support further exploration of [ 11 C]-PBR28 PET signal as an imaging marker candidate for KOA and a link between joint inflammation and osteoarthritis-related pain severity.

Anterior and posterior hip osteoarthritis: prevalence and potential value of CT compared to radiographs.

PURPOSE: To determine the added value of computed tomography (CT) to identify severe hip osteoarthritis (OA). MATERIALS AND METHODS: A retrospective query of all cases of hip or knee arthroplasty planning CTs between January 2018 and March 2022 was performed. Age, sex, and symptoms were collected from the medical record. CTs were evaluated for the degree of osteoarthritis and classified using an adapted Kellgren-Lawrence (KL) grading system in the anterior, posterior, superior, and superomedial hip. Frontal hip or pelvis radiographs within 1 year of the CT were also graded. RESULTS: There were 265 eligible hips in 178 subjects, age 66 ± 11 (range 31-93) years, with 85/178 (48%) males and 93/178 (52%) females, and 127/265 (48%) right and 138/265 (52%) left hips. The posterior hip joint was the most common location for grade 2/3 OA (20%), followed by superior hip joint (14%). Anterior or posterior grade 2/3 OA occurred concurrently with superior or superomedial grade 2/3 OA in 32/68 (47%) of hips. Grade 2/3 OA was detected on CT more commonly than on XR both in the superior (14 vs 8.6%, P = 0.0016) and superomedial (8.7 vs 4.8%, P = 0.016) hip joint. Of the 71 symptomatic hips, 22 (31%) hips demonstrated either anterior and/or posterior grade 2/3 OA on CT, and 9 (9/22, 41%) of these hips had superior or superomedial grade 0/1 OA. CONCLUSION: CT may be warranted when the patient has pain suggestive of osteoarthritis not detected on radiographs.

Posterior capsule edema in adhesive capsulitis: comparison with established non-contrast MRI findings and multivariable analysis.

OBJECTIVES: To evaluate posterior glenohumeral capsule edema compared to other MRI findings in adhesive capsulitis (AC). METHODS: This study was approved by the local Institutional Review Board and it is HIPAA compliant. A retrospective search identified subjects who received fluoroscopically guided intra-articular corticosteroid injections for AC and had an MRI within 6 months prior to injection. The study group was compared with an age-, sex-, and side-matched control group who underwent the same procedures but did not have AC. MRIs were evaluated for edema of posterior capsule, anterior capsule, axillary pouch, coracohumeral ligament (CHL) and rotator interval (RI), thickness of axillary pouch and CHL, thickness of anterior capsule, RI and subcoracoid fat replacement, and teres minor atrophy and edema. Multivariable analysis was performed. RESULTS: A total of 57 subjects with AC and 57 matched controls were studied: mean age 52 ± 7 (range 31-71) years, 37 female and 20 male, 22 right and 35 left. Posterior capsule edema was more common in the AC group vs. control group (66.7 vs 17.5%, p < 0.001). Multivariable analysis showed posterior capsule edema, CHL edema, and axillary pouch (glenoid) thickness (optimum cutoff = 4 mm) were significant independent predictors of AC. Simplified analysis using these three variables had an area under the curve of 0.860 (95%CI: 0.792-0.928). With all three variables present, the sensitivity and specificity for AC were 32% and 98%, respectively. CONCLUSIONS: Posterior joint capsule edema may be helpful to confirm AC. Posterior capsule edema, CHL edema, and axillary pouch (glenoid) thickness produce a strong model for distinguishing AC from controls. CLINICAL RELEVANCE STATEMENT: Edema involving the posterior shoulder joint capsule is an imaging marker of capsulitis and is useful in differentiating patients with adhesive capsulitis from those without in conjunction with other proven MRI findings. KEY POINTS: • Posterior capsule edema has a sensitivity of 66.7% and a specificity of 82.5% for the detection of adhesive capsulitis. • Posterior capsule edema, coracohumeral ligament (CHL) edema, and axillary pouch (glenoid) thickness were significant independent predictors of adhesive capsulitis, and combining these variables together produces a very strong model for distinguishing cases from controls (AUC = 0.860). • Optimal cutoff values for CHL, axillary pouch (humeral), axillary pouch (glenoid), and axillary pouch (total) thickness were 2.5, 2.6, 4, and 6.3 mm, respectively.

Intraosseous pressure measurement during iliac bone marrow biopsy: its feasibility and difference of IOP in diseased marrow and non-diseased marrow.

OBJECTIVE: The purposes of this study were (1) to establish the feasibility and safety of an imaging-guided technique for intraosseous pressure (IOP) measurement in a large cohort of patients, and (2) to compare IOP values between normal and diseased bone marrow. METHODS: Adult patients undergoing CT-guided marrow biopsy were prospectively and consecutively enrolled from November 2020 to February 2022. IOP measurements were obtained connecting the biopsy needle to a monitoring device using a standard arterial line setup. Clinical data including sex, age and pathology results were obtained. Student t test and Pearson correlation were used for continuous variables comparisons. Univariable analyses were performed using Fisher's exact test. A P value of .05 was considered statistically significant. RESULTS: A total of 139 participants were initially enrolled, and four were excluded during technique optimization. There were no complications related to the measurement technique. Ninety participants (90/135, 67%) had histology confirming marrow pathology. The participants in the diseased marrow group were older than those in the normal marrow group (63 ± 14 vs. 55 ± 14 years; P < .01). There was no difference in mean IOP between both groups (66 ± 23 vs. 64 ± 28 mmHg; P = .69). There was no correlation between mean arterial blood pressure and mean IOP (P = .08). CONCLUSION: There was no difference in IOP measurements between patients with normal and diseased marrow undergoing CT-guided biopsy. IOP does not appear to be influenced by systemic blood pressure. No complication occurred during the procedures.

Decreased rotator cuff muscle cross-sectional areas in subjects with adhesive capsulitis: a study comparing male and female subjects.

OBJECTIVE: To compare rotator cuff (RC) muscle cross-sectional areas (CSA) in subjects with adhesive capsulitis (AC) to age- and sex-matched controls. MATERIALS AND METHODS: We retrospectively analyzed 97 shoulder MRIs or MR arthrography studies, of which 42 were clinically diagnosed with AC (27 female, 15 male) and 55 were age- and sex-matched controls (38 female, 17 male). All AC subjects underwent imaging ≥ 6 months after symptom onset. All imaging was examined to exclude RC full-thickness tears and prior surgery. A standardized T1 sagittal MR image was segmented in each subject to obtain the CSA of subscapularis (SSC), supraspinatus (SSP), and infraspinatus (ISP) muscles. Differences in CSAs between AC and control subjects were analyzed by sex (females and males separately) and all subjects combined. RESULTS: AC females had significantly decreased SSC (P = 0.002) and total (P = 0.006) CSAs compared to controls. Male AC subjects showed decreased SSC (P = 0.044), SSP (P = 0.001), and total (P = 0.005) CSAs. Across all subjects, male and female, the AC cohort had significantly decreased SSC (P = 0.019) and total (P = 0.029) CSAs compared to controls. CONCLUSION: Decreased RC muscle CSAs were present in AC subjects with ≥ 6 months of symptom duration, with decreased SSC and total CSAs in male and female subjects, and decreased SSP CSA in males.

Five Years of the Musculoskeletal Radiology Fellowship Match: Trends and Perspectives.

RATIONALE AND OBJECTIVES: The 2023 Match marks 5 years since the Musculoskeletal (MSK) Radiology Fellowship Match first took place in June 2019. The objective of this study is to analyze trends in the MSK Match over its 5-year course. MATERIALS AND METHODS: Data from the National Resident Matching Program were evaluated for the number of applicants, medical school type of matched applicants, number of programs, and number of positions. Programs were grouped according to geographic region, program size, and ACGME accreditation status. These data were plotted to look for trends over time and by program characteristics. RESULTS: There has been little variation in the number of eligible programs registering for the Match (range 80-83). The number of available positions has had a wider variation (range 204-218), and the number of applicants preferring MSK has varied from 156 to 178. The gap between positions and applicants has resulted in a percentage of positions filled that has ranged from 70.9% to 82.4%. Program size is positively correlated with Match rates, with 100% of programs with five or more positions filling ≥ 50% in 4 out of 5 years. CONCLUSION: The variable numbers of fellowship positions and applicants have resulted in variable success of the Match by all metrics. Maintaining or increasing the number of applicants is the most critical factor for ongoing Match success.

CT-guided lumbar facet cyst rupture and corticosteroid injection: technique, approach, and procedural and clinical success rates.

PURPOSE: To evaluate success rates of computed tomography (CT)-guided lumbar facet synovial cyst (LFC) rupture. MATERIALS AND METHODS: We retrospectively reviewed all LFC ruptures performed by a single musculoskeletal radiologist with > 10 years of experience, using posterior facet approach and/or direct puncture by ipsilateral/contralateral interlaminar, or transforaminal approach. All patients also received a corticosteroid injection. Rupture rates were calculated, and clinical success rate was determined through medical record review. Pre-procedure magnetic resonance imaging (MRI) images and CT procedure images were also reviewed for LFC and facet joint imaging features that may predict rupture. RESULTS: There were 37 patients, 17 (46%) female and 20 (54%) male, ages 62 ± 12 (range 39-87) years. Thirty-four (92%) of LFC were successfully ruptured, 17 (50%) by facet approach and 17 (50%) by direct cyst puncture. At least one direct puncture approach was possible in 35 (95%) patients. No MRI or CT LFC or facet joint features predicted cyst rupture. Thirty-one (91%) of patients reported immediate pain relief, and 19 (53%) did not have further intervention for LFC-related pain. Sixteen (84%) of these patients remained pain-free for an average follow-up time period of 28 months. Fourteen (39%) of patients required surgical intervention. There were no complications. CONCLUSION: Our systematic approach to CT-guided LFC rupture is safe and has high technical and clinical success rates similar to prior studies. Since there are no definitive imaging features that determine rupture success, this procedure can almost always be attempted as a first-line treatment for LFC.

Current state of musculoskeletal fellowship program directors and future directions.

OBJECTIVE: To better understand the current state of musculoskeletal fellowship program directors and identify opportunities for formal training that could increase job satisfaction, provide a broader knowledge base for mentoring/advising trainees and increase diversity in musculoskeletal radiology. MATERIALS AND METHODS: Eighty-one fellowship program directors who signed the Fellowship Match Memorandum of Understanding with the Society of Skeletal Radiology were sent a survey with questions about demographics, career, background, and training both for musculoskeletal radiology and for the fellowship director role. RESULTS: A 57/81 (70%) of program directors responded, representing 27 different states with a range of 1-9 fellowship positions. Nearly half are in their forties (48%) with most identifying as White (67%) followed by Asian (30%). The majority are male (72%) with over half (60%) remaining at the institution where they completed prior training. Over half plan to change roles within 5 years and do not feel adequately compensated. Top qualities/skills identified as important for the role include effective communication, being approachable, and clinical excellence. Other than clinical excellence, most do not report formal training in skills identified as important for the role. CONCLUSIONS: Given the high amount of interaction with trainees, program directors play a key role in the future of our subspecialty. The low diversity among this group, the lack of formal training, and the fact that most do not feel adequately compensated could limit mentorship and recruitment. Program directors identified effective communication, organizational/planning skills, and conflict resolution as the top skills they would benefit from formal training.

Bone Tumor Risk Stratification and Management System: A Consensus Guideline from the ACR Bone Reporting and Data System Committee.

The assessment and subsequent management of a potentially neoplastic bone lesion seen at diagnostic radiography is often complicated by diagnostic uncertainty and inconsistent management recommendations. Appropriate clinical management should be directed by risk of malignancy. Herein, the ACR-sponsored Bone Reporting and Data System (Bone-RADS) Committee, consisting of academic leaders in the fields of musculoskeletal oncology imaging and orthopedic oncology, presents the novel Bone-RADS scoring system to aid in risk assignment and provide risk-aligned management suggestions. When viewed in the proper clinical context, a newly identified bone lesion can be risk stratified as having very low, low, intermediate, or high risk of malignancy. Radiographic features predictive of risk are reviewed include margination, pattern of periosteal reaction, depth of endosteal erosion, pathological fracture, and extra-osseous soft tissue mass. Other radiographic features predictive of histopathology are also briefly discussed. To apply the Bone-RADS scoring system to a potentially neoplastic bone lesion, radiographic features predictive of risk are each given a point value. Point values are summed to yield a point total, which can be translated to a Bone-RADS score (1-4) with corresponding risk assignment (very low, low, intermediate, high). For each score, evidence-based and best practice consensus management suggestions are outlined. Examples of each Bone-RADS scores are presented, and a standardized diagnostic radiography report template is provided.

Original research: utilization of a convolutional neural network for automated detection of lytic spinal lesions on body CTs.

OBJECTIVE: To develop, train, and test a convolutional neural network (CNN) for detection of spinal lytic lesions in chest, abdomen, and pelvis CT scans. MATERIALS AND METHODS: Cases of malignant spinal lytic lesions in CT scans were identified. Images were manually segmented for the following classes: (i) lesion, (ii) normal bone, (iii) background. If more than one lesion was on a single slice, all lesions were segmented. Images were stored as 128×128 pixel grayscale, with 10% segregated for testing. The training pipeline of the dataset included histogram equalization and data augmentation. A model was trained on Keras/Tensorflow using an 80/20 training/validation split, based on U-Net architecture. Additional testing of the model was performed on 1106 images of healthy controls. Global sensitivity measured detection of any lesion on a single image. Local sensitivity and positive predictive value (PPV) measured detection of all lesions on an image. Global specificity measured false positive rate in non-pathologic bone. RESULTS: Six hundred images were obtained for model creation. The training set consisted of 540 images, which was augmented to 20,000. The test set consisted of 60 images. Model training was performed in triplicate. Mean Dice scores were 0.61 for lytic lesion, 0.95 for normal bone, and 0.99 for background. Mean global sensitivity was 90.6%, local sensitivity was 74.0%, local PPV was 78.3%, and global specificity was 63.3%. At least one false positive lesion was noted in 28.8-44.9% of control images. CONCLUSION: A task-trained CNN showed good sensitivity in detecting spinal lytic lesions in axial CT images.