Chondrosarcoma evaluation using hematein-based x-ray staining and high-resolution 3D micro-CT: a feasibility study.

BACKGROUND: Chondrosarcomas are rare malignant bone tumors diagnosed by analyzing radiological images and histology of tissue biopsies and evaluating features such as matrix calcification, cortical destruction, trabecular penetration, and tumor cell entrapment. METHODS: We retrospectively analyzed 16 cartilaginous tumor tissue samples from three patients (51-, 54-, and 70-year-old) diagnosed with a dedifferentiated chondrosarcoma at the femur, a moderately differentiated chondrosarcoma in the pelvis, and a predominantly moderately differentiated chondrosarcoma at the scapula, respectively. We combined a hematein-based x-ray staining with high-resolution three-dimensional (3D) microscopic x-ray computed tomography (micro-CT) for nondestructive 3D tumor assessment and tumor margin evaluation. RESULTS: We detected trabecular entrapment on 3D micro-CT images and followed bone destruction throughout the volume. In addition to staining cell nuclei, hematein-based staining also improved the visualization of the tumor matrix, allowing for the distinction between the tumor and the bone marrow cavity. The hematein-based staining did not interfere with further conventional histology. There was a 5.97 ± 7.17% difference between the relative tumor area measured using micro-CT and histopathology (p = 0.806) (Pearson correlation coefficient r = 0.92, p = 0.009). Signal intensity in the tumor matrix (4.85 ± 2.94) was significantly higher in the stained samples compared to the unstained counterparts (1.92 ± 0.11, p = 0.002). CONCLUSIONS: Using nondestructive 3D micro-CT, the simultaneous visualization of radiological and histopathological features is feasible. RELEVANCE STATEMENT: 3D micro-CT data supports modern radiological and histopathological investigations of human bone tumor specimens. It has the potential for being an integrative part of clinical preoperative diagnostics. KEY POINTS: • Matrix calcifications are a relevant diagnostic feature of bone tumors. • Micro-CT detects all clinically diagnostic relevant features of x-ray-stained chondrosarcoma. • Micro-CT has the potential to be an integrative part of clinical diagnostics.

Development and benchmarking of a Deep Learning-based MRI-guided gross tumor segmentation algorithm for Radiomics analyses in extremity soft tissue sarcomas.

BACKGROUND: Volume of interest (VOI) segmentation is a crucial step for Radiomics analyses and radiotherapy (RT) treatment planning. Because it can be time-consuming and subject to inter-observer variability, we developed and tested a Deep Learning-based automatic segmentation (DLBAS) algorithm to reproducibly predict the primary gross tumor as VOI for Radiomics analyses in extremity soft tissue sarcomas (STS). METHODS: A DLBAS algorithm was trained on a cohort of 157 patients and externally tested on an independent cohort of 87 patients using contrast-enhanced MRI. Manual tumor delineations by a radiation oncologist served as ground truths (GTs). A benchmark study with 20 cases from the test cohort compared the DLBAS predictions against manual VOI segmentations of two residents (ERs) and clinical delineations of two radiation oncologists (ROs). The ROs rated DLBAS predictions regarding their direct applicability. RESULTS: The DLBAS achieved a median dice similarity coefficient (DSC) of 0.88 against the GTs in the entire test cohort (interquartile range (IQR): 0.11) and a median DSC of 0.89 (IQR 0.07) and 0.82 (IQR 0.10) in comparison to ERs and ROs, respectively. Radiomics feature stability was high with a median intraclass correlation coefficient of 0.97, 0.95 and 0.94 for GTs, ERs, and ROs, respectively. DLBAS predictions were deemed clinically suitable by the two ROs in 35% and 20% of cases, respectively. CONCLUSION: The results demonstrate that the DLBAS algorithm provides reproducible VOI predictions for radiomics feature extraction. Variability remains regarding direct clinical applicability of predictions for RT treatment planning.

Deep Learning to Differentiate Benign and Malignant Vertebral Fractures at Multidetector CT.

Background Differentiating between benign and malignant vertebral fractures poses diagnostic challenges. Purpose To investigate the reliability of CT-based deep learning models to differentiate between benign and malignant vertebral fractures. Materials and Methods CT scans acquired in patients with benign or malignant vertebral fractures from June 2005 to December 2022 at two university hospitals were retrospectively identified based on a composite reference standard that included histopathologic and radiologic information. An internal test set was randomly selected, and an external test set was obtained from an additional hospital. Models used a three-dimensional U-Net encoder-classifier architecture and applied data augmentation during training. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) and compared with that of two residents and one fellowship-trained radiologist using the DeLong test. Results The training set included 381 patients (mean age, 69.9 years ± 11.4 [SD]; 193 male) with 1307 vertebrae (378 benign fractures, 447 malignant fractures, 482 malignant lesions). Internal and external test sets included 86 (mean age, 66.9 years ± 12; 45 male) and 65 (mean age, 68.8 years ± 12.5; 39 female) patients, respectively. The better-performing model of two training approaches achieved AUCs of 0.85 (95% CI: 0.77, 0.92) in the internal and 0.75 (95% CI: 0.64, 0.85) in the external test sets. Including an uncertainty category further improved performance to AUCs of 0.91 (95% CI: 0.83, 0.97) in the internal test set and 0.76 (95% CI: 0.64, 0.88) in the external test set. The AUC values of residents were lower than that of the best-performing model in the internal test set (AUC, 0.69 [95% CI: 0.59, 0.78] and 0.71 [95% CI: 0.61, 0.80]) and external test set (AUC, 0.70 [95% CI: 0.58, 0.80] and 0.71 [95% CI: 0.60, 0.82]), with significant differences only for the internal test set (P < .001). The AUCs of the fellowship-trained radiologist were similar to those of the best-performing model (internal test set, 0.86 [95% CI: 0.78, 0.93; P = .39]; external test set, 0.71 [95% CI: 0.60, 0.82; P = .46]). Conclusion Developed models showed a high discriminatory power to differentiate between benign and malignant vertebral fractures, surpassing or matching the performance of radiology residents and matching that of a fellowship-trained radiologist. © RSNA, 2024 See also the editorial by Booz and D'Angelo in this issue.

MR imaging after patellar MACI and MPFL reconstruction: a comparison of isolated versus combined procedures.

OBJECTIVE: To qualitatively and quantitatively evaluate the 2.5-year MRI outcome after Matrix-associated autologous chondrocyte implantation (MACI) at the patella, reconstruction of the medial patellofemoral ligament (MPFL), and combined procedures. METHODS: In 66 consecutive patients (age 22.8 ± 6.4years) with MACI at the patella (n = 16), MPFL reconstruction (MPFL; n = 31), or combined procedures (n = 19) 3T MRI was performed 2.5 years after surgery. For morphological MRI evaluation WORMS and MOCART scores were obtained. In addition quantitative cartilage T2 and T1rho relaxation times were acquired. Several clinical scores were obtained. Statistical analyses included descriptive statistics, Mann-Whitney-U-tests and Pearson correlations. RESULTS: WORMS scores at follow-up (FU) were significantly worse after combined procedures (8.7 ± 4.9) than after isolated MACI (4.3 ± 3.6, P = 0.005) and after isolated MPFL reconstruction (5.3 ± 5.7, P = 0.004). Bone marrow edema at the patella in the combined group was the only (non-significantly) worsening WORMS parameter from pre- to postoperatively. MOCART scores were significantly worse in the combined group than in the isolated MACI group (57 ± 3 vs 88 ± 9, P < 0.001). Perfect defect filling was achieved in 26% and 69% of cases in the combined and MACI group, respectively (P = 0.031). Global and patellar T2 values were higher in the combined group (Global T2: 34.0 ± 2.8ms) and MACI group (35.5 ± 3.1ms) as compared to the MPFL group (31.1 ± 3.2ms, P < 0.05). T2 values correlated significantly with clinical scores (P < 0.005). Clinical Cincinnati scores were significantly worse in the combined group (P < 0.05). CONCLUSION: After combined surgery with patellar MACI and MPFL reconstruction inferior MRI outcomes were observed than after isolated procedures. Therefore, patients with need for combined surgery may be at particular risk for osteoarthritis.

Longitudinal MR-based proton-density fat fraction (PDFF) and T2* for the assessment of associations between bone marrow changes and myelotoxic chemotherapy.

OBJECTIVES: MR imaging-based proton density fat fraction (PDFF) and T2* imaging has shown to be useful for the evaluation of degenerative changes in the spine. Therefore, the aim of this study was to investigate the influence of myelotoxic chemotherapy on the PDFF and T2* of the thoracolumbar spine in comparison to changes in bone mineral density (BMD). METHODS: In this study, 19 patients were included who had received myelotoxic chemotherapy (MC) and had received a MR imaging scan of the thoracolumbar vertebrates before and after the MC. Every patient was matched for age, sex, and time between the MRI scans to two controls without MC. All patients underwent 3-T MR imaging including the thoracolumbar spine comprising chemical shift encoding-based water-fat imaging to extract PDFF and T2* maps. Moreover, trabecular BMD values were determined before and after chemotherapy. Longitudinal changes in PDFF and T2* were evaluated and compared to changes in BMD. RESULTS: Absolute mean differences of PDFF values between scans before and after MC were at 8.7% (p = 0.01) and at -0.5% (p = 0.57) in the control group, resulting in significantly higher changes in PDFF in patients with MC (p = 0.008). BMD and T2* values neither showed significant changes in patients with nor in those without myelotoxic chemotherapy (p = 0.15 and p = 0.47). There was an inverse, yet non-significant correlation between changes in PDFF and BMD found in patients with myelotoxic chemotherapy (r = -0.41, p = 0.12). CONCLUSION: Therefore, PDFF could be a useful non-invasive biomarker in order to detect changes in the bone marrow in patients receiving myelotoxic therapy. CLINICAL RELEVANCE STATEMENT: Using PDFF as a non-invasive biomarker for early bone marrow changes in oncologic patients undergoing myelotoxic treatment may help enable more targeted countermeasures at commencing states of bone marrow degradation and reduce risks of possible fragility fractures. KEY POINTS: Quantifying changes in bone marrow fat fraction, as well as T2* caused by myelotoxic pharmaceuticals using proton density fat fraction, is feasible. Proton density fat fraction could potentially be established as a non-invasive biomarker for early bone marrow changes in oncologic patients undergoing myelotoxic treatment.

Differentiation of benign and malignant vertebral fractures using a convolutional neural network to extract CT-based texture features.

PURPOSE: To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs). METHODS: A total of 409 patients who underwent routine thoracolumbar spine CT at two institutions were included. VFs were categorized as benign or malignant using either biopsy or imaging follow-up of at least three months as standard of reference. Automated detection, labelling, and segmentation of the vertebrae were performed using a CNN-based framework ( https://anduin.bonescreen.de ). Eight TFs were extracted: Varianceglobal, Skewnessglobal, energy, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP). Multivariate regression models adjusted for age and sex were used to compare TFs between benign and malignant VFs. RESULTS: Skewnessglobal showed a significant difference between the two groups when analyzing fractured vertebrae from T1 to L6 (benign fracture group: 0.70 [0.64-0.76]; malignant fracture group: 0.59 [0.56-0.63]; and p = 0.017), suggesting a higher skewness in benign VFs compared to malignant VFs. CONCLUSION: Three-dimensional CT-based global TF skewness assessed using a CNN-based framework showed significant difference between benign and malignant thoracolumbar VFs and may therefore contribute to the clinical diagnostic work-up of patients with VFs.

Development and Evaluation of MR-Based Radiogenomic Models to Differentiate Atypical Lipomatous Tumors from Lipomas.

BACKGROUND: The aim of this study was to develop and validate radiogenomic models to predict the MDM2 gene amplification status and differentiate between ALTs and lipomas on preoperative MR images. METHODS: MR images were obtained in 257 patients diagnosed with ALTs (n = 65) or lipomas (n = 192) using histology and the MDM2 gene analysis as a reference standard. The protocols included T2-, T1-, and fat-suppressed contrast-enhanced T1-weighted sequences. Additionally, 50 patients were obtained from a different hospital for external testing. Radiomic features were selected using mRMR. Using repeated nested cross-validation, the machine-learning models were trained on radiomic features and demographic information. For comparison, the external test set was evaluated by three radiology residents and one attending radiologist. RESULTS: A LASSO classifier trained on radiomic features from all sequences performed best, with an AUC of 0.88, 70% sensitivity, 81% specificity, and 76% accuracy. In comparison, the radiology residents achieved 60-70% accuracy, 55-80% sensitivity, and 63-77% specificity, while the attending radiologist achieved 90% accuracy, 96% sensitivity, and 87% specificity. CONCLUSION: A radiogenomic model combining features from multiple MR sequences showed the best performance in predicting the MDM2 gene amplification status. The model showed a higher accuracy compared to the radiology residents, though lower compared to the attending radiologist.

Associations of gestational diabetes and proton density fat fraction of vertebral bone marrow and paraspinal musculature in premenopausal women.

Background and objective: Fat content in bones and muscles, quantified by magnetic resonance imaging (MRI) as a proton density fat fraction (PDFF) value, is an emerging non-invasive biomarker. PDFF has been proposed to indicate bone and metabolic health among postmenopausal women. Premenopausal women with a history of gestational diabetes (GDM) carry an increased risk of developing type 2 diabetes and an increased risk of fractures. However, no studies have investigated the associations between a history of GDM and PDFF of bone or of paraspinal musculature (PSM), composed of autochthonous muscle (AM) and psoas muscle, which are responsible for moving and stabilizing the spine. This study aims to investigate whether PDFF of vertebral bone marrow and of PSM are associated with a history of GDM in premenopausal women. Methods: A total of 37 women (mean age 36.3 ± 3.8 years) who were 6 to 15 months postpartum with (n=19) and without (n=18) a history of GDM underwent whole-body 3T MRI, including a chemical shift encoding-based water-fat separation. The PDFF maps were calculated for the vertebral bodies and PSM. The cross-sectional area (CSA) of PSM was obtained. Associations between a history of GDM and PDFF were assessed using multivariable linear and logistic regression models. Results: The PDFF of the vertebral bodies was significantly higher in women with a history of GDM (GDM group) than in women without (thoracic: median 41.55 (interquartile range 32.21-49.48)% vs. 31.75 (30.03-34.97)%; p=0.02, lumbar: 47.84 (39.19-57.58)% vs. 36.93 (33.36-41.31)%; p=0.02). The results remained significant after adjustment for age and body mass index (BMI) (p=0.01-0.02). The receiver operating characteristic curves showed optimal thoracic and lumbar vertebral PDFF cutoffs at 38.10% and 44.18%, respectively, to differentiate GDM (AUC 0.72 and 0.73, respectively, sensitivity 0.58, specificity 0.89). The PDFF of the AM was significantly higher in the GDM group (12.99 (12.18-15.90)% vs. 10.83 (9.39-14.71)%; p=0.04) without adjustments, while the CSA was similar between the groups (p=0.34). Conclusion: A history of GDM is significantly associated with a higher PDFF of the vertebral bone marrow, independent of age and BMI. This statistical association between GDM and increased PDFF highlights vertebral bone marrow PDFF as a potential biomarker for the assessment of bone health in premenopausal women at risk of diabetes.

Associations of incidental vertebral fractures and longitudinal changes of MR-based proton density fat fraction and T2* measurements of vertebral bone marrow.

Background: Quantitative magnetic resonance imaging (MRI) techniques such as chemical shift encoding-based water-fat separation techniques (CSE-MRI) are increasingly applied as noninvasive biomarkers to assess the biochemical composition of vertebrae. This study aims to investigate the longitudinal change of proton density fat fraction (PDFF) and T2* derived from CSE-MRI of the thoracolumbar vertebral bone marrow in patients that develop incidental vertebral compression fractures (VCFs), and whether PDFF and T2* enable the prediction of an incidental VCF. Methods: In this study we included 48 patients with CT-derived bone mineral density (BMD) measurements at baseline. Patients that presented an incidental VCF at follow up (N=12, mean age 70.5 ± 7.4 years, 5 female) were compared to controls without incidental VCF at follow up (N=36, mean age 71.1 ± 8.6 years, 15 females). All patients underwent 3T MRI, containing a significant part of the thoracolumbar spine (Th11-L4), at baseline, 6-month and 12 month follow up, including a gradient echo sequence for chemical shift encoding-based water-fat separation, from which PDFF and T2* maps were obtained. Associations between changes in PDFF, T2* and BMD measurements over 12 months and the group (incidental VCF vs. no VCF) were assessed using multivariable regression models. Mixed-effect regression models were used to test if there is a difference in the rate of change in PDFF, T2* and BMD between patients with and without incidental VCF. Results: Prior to the occurrence of an incidental VCF, PDFF in vertebrae increased in the VCF group (ΔPDFF=6.3 ± 3.1%) and was significantly higher than the change of PDFF in the group without VCF (ΔPDFF=2.1 ± 2.5%, P=0.03). There was no significant change in T2* (ΔT2*=1.7 ± 1.1ms vs. ΔT2*=1.1 ± 1.3ms, P=0.31) and BMD (ΔBMD=-1.2 ± 11.3mg/cm3 vs. ΔBMD=-11.4 ± 24.1mg/cm3, P= 0.37) between the two groups over 12 months. At baseline, no significant differences were detected in the average PDFF, T2* and BMD of all measured vertebrae (Th11-L4) between the VCF group and the group without VCF (P=0.66, P=0.35 and P= 0.21, respectively). When assessing the differences in rates of change, there was a significant change in slope for PDFF (2.32 per 6 months, 95% confidence interval (CI) 0.31-4.32; P=0.03) but not for T2* (0.02 per 6 months, CI -0.98-0.95; P=0.90) or BMD (-4.84 per 6 months, CI -23.4-13.7; P=0.60). Conclusions: In our study population, the average change of PDFF over 12 months is significantly higher in patients that develop incidental fractures at 12-month follow up compared to patients without incidental VCF, while T2* and BMD show no significant changes prior to the occurrence of the incidental vertebral fractures. Therefore, a longitudinal increase in bone marrow PDFF may be predictive for vertebral compression fractures.

Differentiating Enchondromas and Atypical Cartilaginous Tumors in Long Bones with Computed Tomography and Magnetic Resonance Imaging.

The differentiation between the atypical cartilaginous tumor (ACT) and the enchondromas is crucial as ACTs require a curettage and clinical as well as imaging follow-ups, whereas in the majority of cases enchondromas require neither a treatment nor follow-ups. Differentiating enchondromas from ACTs radiologically remains challenging. Therefore, this study evaluated imaging criteria in a combination of computed tomography (CT) and magnetic resonance (MR) imaging for the differentiation between enchondromas and ACTs in long bones. A total of 82 patients who presented consecutively at our institution with either an ACT (23, age 52.7 ±18.8 years; 14 women) or an enchondroma (59, age 46.0 ± 11.1 years; 37 women) over a period of 10 years, who had undergone preoperative MR and CT imaging and subsequent biopsy or/and surgical removal, were included in this study. A histopathological diagnosis was available in all cases. Two experienced radiologists evaluated several imaging criteria on CT and MR images. Likelihood of an ACT was significantly increased if either edema within the bone (p = 0.049), within the adjacent soft tissue (p = 0.006) or continuous growth pattern (p = 0.077) were present or if the fat entrapment (p = 0.027) was absent on MR images. Analyzing imaging features on CT, the likelihood of the diagnosis of an ACT was significantly increased if endosteal scalloping >2/3 (p < 0.001), cortical penetration (p < 0.001) and expansion of bone (p = 0.002) were present and if matrix calcifications were observed in less than 1/3 of the tumor (p = 0.013). All other imaging criteria evaluated showed no significant influence on likelihood of ACT or enchondroma (p > 0.05). In conclusion, both CT and MR imaging show suggestive signs which can help to adequately differentiate enchondromas from ACTs in long bones and therefore can improve diagnostics and consequently patient management. Nevertheless, these features are rare and a combination of CT and MR imaging features did not improve the diagnostic performance substantially.

The Predictive Value of Early Postoperative MRI-Based Bone Marrow Parameters for Mid-Term Outcome after MACI with Autologous Bone Grafting at the Knee.

OBJECTIVE: The aim of this study was to longitudinally determine the prognostic value of early postoperative quantitative 3T-MRI (magnetic resonance imaging) parameters of subchondral bone marrow for 2-year clinical and MRI outcome after matrix-associated autologous chondrocyte implantation (MACI) with autologous bone grafting (ABG) at the knee. DESIGN: Consecutive subjects who received MACI with ABG for treatment of focal osteochondral defects received MRI follow-up 3, 6, 12, and 24 months postoperatively. Quantitative MRI included bone marrow edema-like lesion (BMEL) volume measurements and single-voxel magnetic resonance spectroscopy (MRS; n = 9) of the subchondral bone marrow. At 2-year follow-up, morphological MRI outcome included MOCART (magnetic resonance observation of cartilage repair tissue) 2.0 scores. Clinical outcomes were assessed using Lysholm scores. RESULTS: Among a total of 18 subjects (mean age: 28.7 ± 8.4 years, n = 14 males) with defects at the medial or lateral (n = 15 and n = 3, respectively) condyle, mean BMEL volume decreased from 4.9 cm3 at 3 months to 2.0 cm3 at 2-year follow-up (P = 0.040). MRS-based bone marrow water T2 showed a decrease from 20.7 ms at 1-year follow-up to 16.8 ms at 2-year follow-up (P = 0.040). Higher BMEL volume at 6 months correlated with lower 2-year Lysholm (R = -0.616, P = 0.015) and MOCART 2.0 scores (R = -0.567, P = 0.027). Larger early postoperative BMEL volumes at 3 months (R = -0.850, P = 0.007) and 6 months (R = -0.811, P = 0.008) correlated with lower MRS-based unsaturated lipid fractions at 2-year follow-up. Furthermore, patients with early postoperative bony defects showed worse MOCART 2.0 (P = 0.044) and Lysholm scores (P = 0.017) after 24 months. CONCLUSION: Low subchondral BMEL volume and optimal restoration of the subchondral bone at early postoperative time points predict better 2-year clinical and MRI outcomes after MACI with ABG.

Development and evaluation of machine learning models based on X-ray radiomics for the classification and differentiation of malignant and benign bone tumors.

OBJECTIVES: To develop and validate machine learning models to distinguish between benign and malignant bone lesions and compare the performance to radiologists. METHODS: In 880 patients (age 33.1 ± 19.4 years, 395 women) diagnosed with malignant (n = 213, 24.2%) or benign (n = 667, 75.8%) primary bone tumors, preoperative radiographs were obtained, and the diagnosis was established using histopathology. Data was split 70%/15%/15% for training, validation, and internal testing. Additionally, 96 patients from another institution were obtained for external testing. Machine learning models were developed and validated using radiomic features and demographic information. The performance of each model was evaluated on the test sets for accuracy, area under the curve (AUC) from receiver operating characteristics, sensitivity, and specificity. For comparison, the external test set was evaluated by two radiology residents and two radiologists who specialized in musculoskeletal tumor imaging. RESULTS: The best machine learning model was based on an artificial neural network (ANN) combining both radiomic and demographic information achieving 80% and 75% accuracy at 75% and 90% sensitivity with 0.79 and 0.90 AUC on the internal and external test set, respectively. In comparison, the radiology residents achieved 71% and 65% accuracy at 61% and 35% sensitivity while the radiologists specialized in musculoskeletal tumor imaging achieved an 84% and 83% accuracy at 90% and 81% sensitivity, respectively. CONCLUSIONS: An ANN combining radiomic features and demographic information showed the best performance in distinguishing between benign and malignant bone lesions. The model showed lower accuracy compared to specialized radiologists, while accuracy was higher or similar compared to residents. KEY POINTS: • The developed machine learning model could differentiate benign from malignant bone tumors using radiography with an AUC of 0.90 on the external test set. • Machine learning models that used radiomic features or demographic information alone performed worse than those that used both radiomic features and demographic information as input, highlighting the importance of building comprehensive machine learning models. • An artificial neural network that combined both radiomic and demographic information achieved the best performance and its performance was compared to radiology readers on an external test set.

Diagnosis of joint invasion in patients with malignant bone tumors: value and reproducibility of direct and indirect signs on MR imaging.

OBJECTIVES: To evaluate the performance and reproducibility of MR imaging features in the diagnosis of joint invasion (JI) by malignant bone tumors. METHODS: MR images of patients with and without JI (n = 24 each), who underwent surgical resection at our institution, were read by three radiologists. Direct (intrasynovial tumor tissue (ITT), intraarticular destruction of cartilage/bone, invasion of capsular/ligamentous insertions) and indirect (tumor size, signal alterations of epiphyseal/transarticular bone (bone marrow replacement/edema-like), synovial contrast enhancement, joint effusion) signs of JI were assessed. Odds ratios, sensitivity, specificity, PPV, NPV, and reproducibilities (Cohen's and Fleiss' κ) were calculated for each feature. Moreover, the diagnostic performance of combinations of direct features was assessed. RESULTS: Forty-eight patients (28.7 ± 21.4 years, 26 men) were evaluated. All readers reliably assessed the presence of JI (sensitivity = 92-100 %; specificity = 88-100%, respectively). Best predictors for JI were direct visualization of ITT (OR = 186-229, p < 0.001) and destruction of intraarticular bone (69-324, p < 0.001). Direct visualization of ITT was also highly reliable in assessing JI (sensitivity, specificity, PPV, NPV = 92-100 %), with excellent reproducibility (κ = 0.83). Epiphyseal bone marrow replacement and synovial contrast enhancement were the most sensitive indirect signs, but lacked specificity (29-54%). By combining direct signs with high specificity, sensitivity was increased (96 %) and specificity (100 %) was maintained. CONCLUSION: JI by malignant bone tumors can reliably be assessed on preoperative MR images with high sensitivity, specificity, and reproducibility. Particularly direct visualization of ITT, destruction of intraarticular bone, and a combination of highly specific direct signs were valuable, while indirect signs were less predictive and specific. KEY POINTS: • Direct visualization of intrasynovial tumor was the single most sensitive and specific (92-100%) MR imaging sign of joint invasion. • Indirect signs of joint invasion, such as joint effusion or synovial enhancement, were less sensitive and specific compared to direct signs. • A combination of the most specific direct signs of joint invasion showed best results with perfect specificity and PPV (both 100%) and excellent sensitivity and NPV (both 96 %).

Evaluation of MR-derived simulated CT-like images and simulated radiographs compared to conventional radiography in patients with shoulder pain: a proof-of-concept study.

BACKGROUND: To evaluate the diagnostic value of MR-derived CT-like images and simulated radiographs compared with conventional radiographs in patients with suspected shoulder pathology. METHODS: 3 T MRI of the shoulder including a 3D T1-weighted gradient echo sequence was performed in 25 patients (mean age 52.4 ± 18 years, 13 women) with suspected shoulder pathology. Subsequently a cone-beam forward projection algorithm was used to obtain intensity-inverted CT-like images and simulated radiographs. Two radiologists evaluated the simulated images separately and independently using the conventional radiographs as the standard of reference, including measurements of the image quality, acromiohumeral distance, critical shoulder angle, degenerative joint changes and the acromial type. Additionally, the CT-like MR images were evaluated for glenoid defects, subcortical cysts and calcifications. Agreement between the MR-derived simulated radiographs and conventional radiographs was calculated using Cohen's Kappa. RESULTS: Measurements on simulated radiographs and conventional radiographs overall showed a substantial to almost perfect inter- and intra-rater agreement (κ = 0.69-1.00 and κ = 0.65-0.85, respectively). Image quality of the simulated radiographs was rated good to excellent (1.6 ± 0.7 and 1.8 ± 0.6, respectively) by the radiologists. A substantial agreement was found regarding diagnostically relevant features, assessed on Y- and anteroposterior projections (κ = 0.84 and κ = 0.69 for the measurement of the CSA; κ = 0.95 and κ = 0.60 for the measurement of the AHD; κ = 0.77 and κ = 0.77 for grading of the Samilson-Prieto classification; κ = 0.83 and κ = 0.67 for the grading of the Bigliani classification, respectively). CONCLUSION: In this proof-of-concept study, clinically relevant features of the shoulder joint were assessed reliably using MR-derived CT-like images and simulated radiographs with an image quality equivalent to conventional radiographs. MR-derived CT-like images and simulated radiographs may provide useful diagnostic information while reducing the amount of radiation exposure.

MRI-based delta-radiomics predicts pathologic complete response in high-grade soft-tissue sarcoma patients treated with neoadjuvant therapy.

PURPOSE: In high-grade soft-tissue sarcomas (STS) the standard of care encompasses multimodal therapy regimens. While there is a growing body of evidence for prognostic pretreatment radiomic models, we hypothesized that temporal changes in radiomic features following neoadjuvant treatment ("delta-radiomics") may be able to predict the pathological complete response (pCR). METHODS: MRI scans (T1-weighted with fat-saturation and contrast-enhancement (T1FSGd) and T2-weighted with fat-saturation (T2FS)) of patients with STS of the extremities and trunk treated with neoadjuvant therapy were gathered from two independent institutions (training: 103, external testing: 53 patients). pCR was defined as <5% viable cells. After segmentation and preprocessing, 105 radiomic features were extracted. Delta-radiomic features were calculated by subtraction of features derived from MRI scans obtained before and after neoadjuvant therapy. After feature reduction, machine learning modeling was performed in 100 iterations of 3-fold nested cross-validation. Delta-radiomic models were compared with single timepoint models in the testing cohort. RESULTS: The combined delta-radiomic models achieved the best area under the receiver operating characteristic curve (AUC) of 0.75. Pre-therapeutic tumor volume was the best conventional predictor (AUC 0.70). The T2FS-based delta-radiomic model had the most balanced classification performance with a balanced accuracy of 0.69. Delta-radiomic models achieved better reproducibility than single timepoint radiomic models, RECIST or the peri-therapeutic volume change. Delta-radiomic models were significantly associated with survival in multivariate Cox regression. CONCLUSION: This exploratory analysis demonstrated that MRI-based delta-radiomics improves prediction of pCR over tumor volume and RECIST. Delta-radiomics may one day function as a biomarker for personalized treatment adaptations.

Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs.

Background An artificial intelligence model that assesses primary bone tumors on radiographs may assist in the diagnostic workflow. Purpose To develop a multitask deep learning (DL) model for simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. Materials and Methods This retrospective study analyzed bone tumors on radiographs acquired prior to treatment and obtained from patient data from January 2000 to June 2020. Benign or malignant bone tumors were diagnosed in all patients by using the histopathologic findings as the reference standard. By using split-sample validation, 70% of the patients were assigned to the training set, 15% were assigned to the validation set, and 15% were assigned to the test set. The final performance was evaluated on an external test set by using geographic validation, with accuracy, sensitivity, specificity, and 95% CIs being used for classification, the intersection over union (IoU) being used for bounding box placements, and the Dice score being used for segmentations. Results Radiographs from 934 patients (mean age, 33 years ± 19 [standard deviation]; 419 women) were evaluated in the internal data set, which included 667 benign bone tumors and 267 malignant bone tumors. Six hundred fifty-four patients were in the training set, 140 were in the validation set, and 140 were in the test set. One hundred eleven patients were in the external test set. The multitask DL model achieved 80.2% (89 of 111; 95% CI: 72.8, 87.6) accuracy, 62.9% (22 of 35; 95% CI: 47, 79) sensitivity, and 88.2% (67 of 76; CI: 81, 96) specificity in the classification of bone tumors as malignant or benign. The model achieved an IoU of 0.52 ± 0.34 for bounding box placements and a mean Dice score of 0.60 ± 0.37 for segmentations. The model accuracy was higher than that of two radiologic residents (71.2% and 64.9%; P = .002 and P < .001, respectively) and was comparable with that of two musculoskeletal fellowship-trained radiologists (83.8% and 82.9%; P = .13 and P = .25, respectively) in classifying a tumor as malignant or benign. Conclusion The developed multitask deep learning model allowed for accurate and simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Carrino in this issue.

Vertebral bone marrow T2* mapping using chemical shift encoding-based water-fat separation in the quantitative analysis of lumbar osteoporosis and osteoporotic fractures.

BACKGROUND: Chemical shift encoding-based water-fat separation techniques have been used for fat quantification [proton density fat fraction (PDFF)], but they also enable the assessment of bone marrow T2*, which has previously been reported to be a potential biomarker for osteoporosis and may give insight into the cause of vertebral fractures (i.e., osteoporotic vs. traumatic) and the microstructure of the bone when applied to vertebral bone marrow. METHODS: The 32 patients (78.1% with low-energy osteopenic/osteoporotic fractures, mean age 72.3±9.8 years, 76% women; 21.9% with high-energy traumatic fractures, 47.3±12.8 years, no women) were frequency-matched for age and sex to subjects without vertebral fractures (n=20). All study patients underwent 3T-MRI of the lumbar spine including sagittally acquired spoiled gradient echo sequences for chemical shift encoding-based water-fat separation, from which T2* values were obtained. Volumetric trabecular bone mineral density (BMD) and trabecular bone parameters describing the three-dimensional structural integrity of trabecular bone were derived from quantitative CT. Associations between T2* measurements, fracture status and trabecular bone parameters were assessed using multivariable linear regression models. RESULTS: Mean T2* values of non fractured vertebrae in all patients showed a significant correlation with BMD (r=-0.65, P<0.001), trabecular number (TbN) (r=-0.56, P<0.001) and trabecular spacing (TbSp) (r=0.61, P<0.001); patients with low-energy osteoporotic vertebral fractures showed significantly higher mean T2* values than those with traumatic fractures (13.6±4.3 vs. 8.4±2.2 ms, P=0.01) as well as a significantly lower TbN (0.69±0.08 vs. 0.93±0.03 mm-1, P<0.01) and a significantly larger trabecular spacing (1.06±0.16 vs. 0.56±0.08 mm, P<0.01). Mean T2* values of osteoporotic patients with and without vertebral fracture showed no significant difference (13.5±3.4 vs. 15.6±3.5 ms, P=0.40). When comparing the mean T2* of the fractured vertebrae, no significant difference could be detected between low-energy osteoporotic fractures and high-energy traumatic fractures (12.6±5.4 vs. 8.1±2.4 ms, P=0.10). CONCLUSIONS: T2* mapping of vertebral bone marrow using using chemical shift encoding-based water-fat separation allows for assessing osteoporosis as well as the trabecular microstructure and enables a radiation-free differentiation between patients with low-energy osteoporotic and high-energy traumatic vertebral fractures, suggesting its potential as a biomarker for bone fragility.

Development and External Validation of Deep-Learning-Based Tumor Grading Models in Soft-Tissue Sarcoma Patients Using MR Imaging.

BACKGROUND: In patients with soft-tissue sarcomas, tumor grading constitutes a decisive factor to determine the best treatment decision. Tumor grading is obtained by pathological work-up after focal biopsies. Deep learning (DL)-based imaging analysis may pose an alternative way to characterize STS tissue. In this work, we sought to non-invasively differentiate tumor grading into low-grade (G1) and high-grade (G2/G3) STS using DL techniques based on MR-imaging. METHODS: Contrast-enhanced T1-weighted fat-saturated (T1FSGd) MRI sequences and fat-saturated T2-weighted (T2FS) sequences were collected from two independent retrospective cohorts (training: 148 patients, testing: 158 patients). Tumor grading was determined following the French Federation of Cancer Centers Sarcoma Group in pre-therapeutic biopsies. DL models were developed using transfer learning based on the DenseNet 161 architecture. RESULTS: The T1FSGd and T2FS-based DL models achieved area under the receiver operator characteristic curve (AUC) values of 0.75 and 0.76 on the test cohort, respectively. T1FSGd achieved the best F1-score of all models (0.90). The T2FS-based DL model was able to significantly risk-stratify for overall survival. Attention maps revealed relevant features within the tumor volume and in border regions. CONCLUSIONS: MRI-based DL models are capable of predicting tumor grading with good reproducibility in external validation.

Detection of Bone Marrow Edema in Patients with Osteoid Osteoma Using Three-Material Decomposition with Dual-Layer Spectral CT.

The aim of this study is to assess whether perifocal bone marrow edema (BME) in patients with osteoid osteoma (OO) can be accurately detected on dual-layer spectral CT (DLCT) with three-material decomposition. To that end, 18 patients with OO (25.33 ± 12.44 years; 7 females) were pairwise-matched with 18 patients (26.72 ± 9.65 years; 9 females) admitted for suspected pathologies other than OO in the same anatomic location but negative imaging findings. All patients were examined with DLCT and MRI. DLCT data was decomposed into hydroxyapatite and water- and fat-equivalent volume fraction maps. Two radiologists assessed DLCT-based volume fraction maps for the presence of perifocal BME, using a Likert scale (1 = no edema; 2 = likely no edema; 3 = likely edema; 4 = edema). Accuracy, sensitivity, and specificity for the detection of BME on DLCT were analyzed using MR findings as standard of reference. For the detection of BME in patients with OO, DLCT showed a sensitivity of 0.92, a specificity of 0.94, and an accuracy of 0.92 for both radiologists. Interreader agreement for the assessment of BME with DLCT was substantial (weighted κ = 0.78; 95% CI, 0.59, 0.94). DLCT with material-specific volume fraction maps allowed accurate detection of BME in patients with OO. This may spare patients additional examinations and facilitate the diagnosis of OO.

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics.

BACKGROUND: In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS). METHODS: Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS. RESULTS: ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification. CONCLUSIONS: T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.