Search

Purpose: To evaluate nnU-net's performance in automatically segmenting and volumetrically measuring ocular adnexal lymphoma (OAL) on multi-sequence MRI., Methods: We collected T1-weighted (T1), T2-weighted and T1-weighted contrast-enhanced images with/without fat saturation (T2_FS/T2_nFS, T1c_FS/T1c_nFS) of OAL from four institutions. Two radiologists manually annotated lesions as the ground truth using ITK-SNAP. A deep learning framework, nnU-net, was developed and trained using two models. Model 1 was trained on T1, T2, and T1c, while Model 2 was trained exclusively on T1 and T2. A 5-fold cross-validation was utilized in the training process. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), sensitivity, and positive prediction value (PPV). Volumetric assessment was performed using Bland-Altman plots and Lin's concordance correlation coefficient (CCC)., Results: A total of 147 patients from one center were selected as training set and 33 patients from three centers were regarded as test set. For both Model 1 and 2, nnU-net demonstrated outstanding segmentation performance on T2_FS with DSC of 0.80-0.82, PPV of 84.5-86.1%, and sensitivity of 77.6-81.2%, respectively. Model 2 failed to detect 19 cases of T1c, whereas the DSC, PPV, and sensitivity for T1_nFS were 0.59, 91.2%, and 51.4%, respectively. Bland-Altman plots revealed minor tumor volume differences with 0.22-1.24 cm 3 between nnU-net prediction and ground truth on T2_FS. The CCC were 0.96 and 0.93 in Model 1 and 2 for T2_FS images, respectively., Conclusion: The nnU-net offered excellent performance in automated segmentation and volumetric assessment in MRI of OAL, particularly on T2_FS images., (© 2024. The Author(s).)

Purpose: To develop and validate an MRI-based radiomics model in differentiation between sinonasal primary lymphomas and squamous cell carcinomas (SCCs)., Materials and Methods: One-hundred-and-fifty-four patients were enrolled (74 individuals with SCCs and 80 with lymphomas). After feature analysis and feature selection with variance threshold and least absolute shrinkage and selection operator (LASSO) methods, an MRI-based radiomics model with the support vector machine (SVM) classifier was constructed in differentiation between lymphomas and SCCs. Areas under the receiver operating characteristic curves (AUCs) of the MRI-based radiomics model were compared with those of radiologists using Delong test., Results: Five features (T1 original shape Compactness2, T1 wavelet-HHH first-order Total Energy, T2 wavelet-HLH GLCM Informational Measure of Correlation1, T1 wavelet-LHL GLCM Inverse Variance and T1 square GLRLM Long Run Low Gray Level Emphasis) were finally selected in the radiomics model. The AUC values in differentiation between lymphomas and SCCs were 0.94 for the training dataset and 0.85 for the validation dataset, respectively. For all the patient datasets, the AUC values of radiomics model, readers 1, 2 and 3 were 0.92, 0.76, 0.77 and 0.80, respectively. For the validation datasets, no significant difference was found between the AUCs of the radiomics model and those of the three radiologist (P = 0.459, 0.469, 0.738 for radiologist 1, 2 and 3, respectively)., Conclusion: An MRI-based radiomics model can help to differentiate sinonasal lymphomas from SCCs with high accuracy., (© 2021. Japan Radiological Society.)

Purpose: To investigate the utility of intravoxel incoherent motion diffusion-weighted MRI (IVIM-DWI) derived diffusion and perfusion parameters in differentiating ocular adnexal lymphoma (OAL) from idiopathic orbital inflammation (IOI), and to assess whether IVIM-DWI provides improved diagnostic performance for the distinction., Method: Twenty-one patients with OAL and 24 patients with IOI underwent IVIM-DWI. Apparent diffusion coefficient (ADC) and IVIM-DWI parameters including true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f) were measured in lesions by two independent radiologists. The MRI parameter differences between OAL and IOI were tested using two-sample t-test. The receiver operating characteristic (ROC) analysis curves were used to determine the diagnostic performance of significant parameters for differentiation between OAL and IOI., Results: The ADC, D, and f were lower in OAL than those in IOI (ADC = 0.78 ± 0.12 vs. 0.99 ± 0.16 × 10 -3 mm 2 /s, P < 0.001; D = 0.34 ± 0.15 vs. 0.76 ± 0.25 × 10 -3 mm 2 /s, P < 0.001; f = 0.31 ± 0.06 vs. 0.41 ± 0.08 × 100 %, P < 0.001). There was no significant difference in D* between OAL and IOI (P = 0.235). The optimal cut-off values of ADC, D, and f in differentiating OAL from IOI were 0.83 × 10 -3 mm 2 /s, 0.56 × 10 -3 mm 2 /s, and 0.36 × 100 %, respectively. No significant differences were found in areas under the curve (AUCs) among ADC, D and f (all P > 0.05). The combination of D and f provided significantly higher AUC than ADC (AUC = 0.984 vs. 0.838, Z = 2.128, P = 0.033), and had higher sensitivity of 95.24 %, specificity of 95.83 %, and accuracy of 95.56 %., Conclusions: IVIM-DWI is valuable in differentiating OAL from IOI, and D combined f can improve the performance of differential diagnosis., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Purpose: To investigate the diagnostic performance of diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI), and the combination of both in the differential diagnosis of lymphoma and inflammation in the orbit., Materials and Methods: This retrospective study was approved by the Institutional Review Board and the informed consent requirement was waived. A total of 53 patients underwent preoperative 3T MRI. Parameters of DWI and DCE MRI were evaluated in these 30 patients with orbital lymphoma and 23 patients with orbital inflammation. The diagnostic performance was evaluated using receiver operating characteristic curve analysis., Results: Apparent diffusion coefficient (ADC) values and parameters derived from DCE MRI of orbital lymphoma and orbital inflammation differed significantly (ADC, T max , contrast index [CI], enhancement ratio [ER], and washout ratio [WR]: P < 0.001, P = 0.008, P < 0.001, P < 0.001, and P = 0.005 for reviewer 1, respectively; P < 0.001, P = 0.004, P < 0.001, P < 0.001, and P < 0.001 for reviewer 2, respectively). Sensitivity, specificity, and accuracy values of DWI were 76.67%, 100%, and 86.79% for reviewer 1; 70%, 95.65%, and 81.13% for reviewer 2, respectively. The combination of both were 90%, 86.96%, and 88.68% for reviewer 1; 93.33%, 78.26%, and 86.79% for reviewer 2, respectively. The combination of both was significantly superior to DWI for differentiation of orbital lymphoma from orbital inflammation (P = 0.016 for reviewer 1; P = 0.001 for reviewer 2)., Conclusion: The combination of DWI and DCE MRI can improve diagnostic performance in differentiating lymphoma from inflammation in the orbit compared with DWI alone., Level of Evidence: 3 J. MAGN. RESON. IMAGING 2017;45:1438-1445., (© 2016 International Society for Magnetic Resonance in Medicine.)

Objective: To explore the distribution and magnetic resonance imaging or computed tomography (MRI/CT) of lymphoma in orbit., Methods: Retrospective analyses were conducted for 73 cases with ocular complaints at Beijing Tong'ren Hospital from June 2006 to September 2012. They were confirmed pathologically as lymphoma with complete MRI/CT records., Results: Ocular adnexal lymphoma occurred predominantly in adults. There were 47 males and 26 females with a median age of (60 ± 12.0) years. The lesions were bilateral (n = 24), right side (n = 23) and left side (n = 26) respectively. The pathological types included mucosa-associated lymphoid tissue (MALT) lymphoma (n = 59), diffuse large B-cell lymphoma (DLBCL, n = 7), mantle cell lymphoma (MCL, n = 3), lymphoplasmacytic lymphoma (LPL, n = 2) and follicular lymphoma and natural killer/T-cell lymphoma (FL and NKT, n = 1) respectively. They had well-defined margins in 64 sides, less well-defined margins in 17 sides and ill-defined margins in 16 sides. And 29 sides of lesions presented as a regional mass within conjunctiva in 16/97 sides (16.5%), lacrimal gland in 5/97 sides (5.2%), eyelids in 3/97 sides (3.1%), ocular muscle in 2/97 sides (2.1%) and lacrimal sac in 3/97 sides (3.1%). Moreover, 68 sides of lesion were diffusely distributed. The invaded sites included preseptal region in 38/97 sides (39.2%), extraconal compartment in 69/97 sides (71.1%), intraconal compartment in 54/97 sides (55.7%), eyeball region in 45/97 sides (46.4%), subperiosteum in 14/97 sides (14.4%), cone compartment in 73/97 sides (75.3%), lacrimal gland in 38/97 sides (39.2%) and sheath of optic nerve in 33/97 sides (34.0%). And, on MRI scan, 70 cases (94 sides) had isointensity in 88/94 sides, hypointensity in 6/94 sides on T1WI and isointensity in 52/94 sides, mild hypointensity in 40/94 sides or mixed signal in 2/94 sides on T2WI. In addition, the signals were homogeneous in 67/94 sides and heterogeneous in 27/94 sides. After contrasting, these lesions showed mild contrast-enhancement (CE) in 27/94 sides, moderate CE in 67/94 sides with homogeneous CE in 52/94 sides and heterogeneous CE in 42/94 sides. On CT scan, 21 cases (24 sides) had isodensity in 18/24 sides and mild hyperdensity in 6/24 sides with homogeneous in 7/24 sides and heterogeneous in 17/24 sides. Moreover, most adjacent bone show no change (16/24 sides). Only 16/24 sides and 2/24 sides showed reformation or destruction respectively. At the same time, the lesions also involved other para-orbit structures, such as orbital apex (27/97 sides, 27.8%), fissure orbitalis inferior (14/97 sides, 14.4%), fossa pterygopalatina (10/97 sides, 10.3%), supraorbital nerve (8/97 sides, 8.2%), cavernous sinus (8/97 sides, 8.2%) and facial soft tissue (6/97 sides, 6.2%), et al., Conclusion: Ocular adnexal lymphoma occurs predominantly in male adults. And multiple strictures and sites are often involved. There is iso-/mild hyperintensity with mild-to-moderate homo-/heterogeneous CE and little change of adjacent bone on T1WI and T2WI.

Background: Lymphoma of the lacrimal sac is rare, often misdiagnosed clinically. This study aimed to investigate the imaging features of these tumors and provide suggestions to aid the diagnosis., Methods: In this retrospective study, five cases were assessed according to magnetic resonance imaging (MRI), computed tomography (CT), and pathological findings. All five patients underwent MRI and contrast-enhanced T1-weighted imaging (CE-T1WI), of which four patients underwent dynamic contrast-enhanced (DCE) MRI and three patients underwent CT., Results: Four cases and one case had a lymphoma in left and right medial canthus, respectively. Soft tissue surrounding the eyelids, subcutaneous tissue in the nasal dorsum, and involvement of the entire nasolacrimal canal were demonstrated in all five lesions. In two cases, the mass invaded the extraconal space. In one case, the mass invaded the adjacent medial rectus muscle and nasal area. Well-defined margins were observed in three cases and ill-defined margins in two cases. All cases showed homogeneous isointense lesions on T1WI. Four cases showed homogeneous isointensity and one case demonstrated heterogeneous isointensity on T2WI. After contrast injection, the lesion showed slight homogeneous isointensity and moderate enhancement in four cases and heterogeneous isointensity and moderate enhancement in one case. In the four patients who underwent DCE-MRI, a plateau pattern was revealed in three cases and washout pattern in one case. In the three cases who underwent CT, two cases had isointense and one case had hyperintense lesions. The lacrimal duct was remodeled and the surrounding bone compressed., Conclusions: Tumors of the lacrimal sac showed homogeneous and isointense patterns on T1WI and T2WI with mildto- moderate enhancement and a plateau pattern on DCE-MRI. CT showed remodeling of the lacrimal duct with bone compression.

Background There are no established biomarkers predictive of the efficacy of treatment for ocular adnexal lymphoma (OAL). Purpose To evaluate the effectiveness of pretreatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) in predicting the response of OAL to chemotherapy. Material and Methods Twenty-one patients, who were pathologically diagnosed with OAL, were retrospectively analyzed. According to the National Comprehensive Cancer Network (NCCN) response evaluation criteria for non-Hodgkin's lymphoma, patients were divided into responders (n = 14) and non-responders (n = 7). The volume transfer constant (Ktrans), rate constant (Kep), extracellular extravascular volume fraction (Ve), and apparent diffusion coefficient (ADC) were computed. Two independent-sample tests were applied for statistical analysis. For significantly different parameters, receiver-operator characteristics curve analysis was performed. Results The Ktrans value (min-1), Kep value (min-1), and ADC value (10-3 mm2/s) were 0.76 ± 0.36 vs. 0.47 ± 0.18 (mean ± SD), 4.43 ± 1.29 vs. 3.14 ± 1.37, and 0.51 ± 0.12 vs. 0.66 ± 0.15, respectively, in the responders and non-responders groups. Significant differences were found between the two groups regarding these parameters ( P < 0.05). However, no significant difference was observed in Ve (min-1) between the groups ( P > 0.05). Ktrans, Kep, and ADC had a moderately predictive sensitivity or specificity. When Ktrans and ADC or the three parameters were combined, a considerably higher sensitivity (85.7%) and specificity (85.7%) with a significant discriminative accuracy (area under the curve = 0.929; P = 0.002) was found. Conclusion Ktrans, Kep, and ADC could potentially predict OAL response to chemotherapy. A combination of these DWI and DCE-MRI quantitative parameters might increase sensitivity and specificity. [ABSTRACT FROM AUTHOR]