Lymphoproliferative Disease of the Orbit

A deep learning model combining multimodal radiomics, clinical and imaging features for differentiating ocular adnexal lymphoma from idiopathic orbital inflammation

OBJECTIVES

To evaluate the value of deep learning (DL) combining multimodal radiomics and clinical and imaging features for differentiating ocular adnexal lymphoma (OAL) from idiopathic orbital inflammation (IOI).

METHODS

Eighty-nine patients with histopathologically confirmed OAL (n = 39) and IOI (n = 50) were divided into training and validation groups. Convolutional neural networks and multimodal fusion layers were used to extract multimodal radiomics features from the T1-weighted image (T1WI), T2-weighted image, and contrast-enhanced T1WI. These multimodal radiomics features were then combined with clinical and imaging features and used together to differentiate between OAL and IOI. The area under the curve (AUC) was used to evaluate DL models with different features under five-fold cross-validation. The Student t-test, chi-squared, or Fisher exact test was used for comparison of different groups.

RESULTS

In the validation group, the diagnostic AUC of the DL model using combined features was 0.953 (95% CI, 0.895-1.000), higher than that of the DL model using multimodal radiomics features (0.843, 95% CI, 0.786-0.898, p < 0.01) or clinical and imaging features only (0.882, 95% CI, 0.782-0.982, p = 0.13). The DL model built on multimodal radiomics features outperformed those built on most bimodalities and unimodalities (p < 0.05). In addition, the DL-based analysis with the orbital cone area (covering both the orbital mass and surrounding tissues) was superior to that with the region of interest (ROI) covering only the mass area, although the difference was not significant (p = 0.33).

CONCLUSIONS

DL-based analysis that combines multimodal radiomics features with clinical and imaging features may help to differentiate between OAL and IOI.

KEY POINTS

• It is difficult to differentiate OAL from IOI due to the overlap in clinical and imaging manifestations. • Radiomics has shown potential for noninvasive diagnosis of different orbital lymphoproliferative disorders. • DL-based analysis combining radiomics and imaging and clinical features may help the differentiation between OAL and IOI.

Atypical lymphoid proliferation of the orbit

Objective: Lymphoproliferative disorders are a group of lesions characterized by abnormal proliferation of lymphocytes. In the orbit, they can occur in the ocular adnexae. These neoplasms have defined clinical and pathologic characteristics and account for more than 20% of all orbital tumors. Several types of lymphoproliferative lesions have been described in the orbit. One example is lymphoid hyperplasia, which commonly involves the lacrimal gland. A benign lesion like lymphoid hyperplasia will show a general normal archetype of the tissues-involved lacrimal gland. We expect a polyclonal group of cells with more or less normal architecture of a follicle. On the other hand, lymphoma will show less organized arrangement of cells, and we expect them to be of monoclonal lineage. Methods: This is a case report of a 55-year-old Filipino female who came in for blurring of vision of both eyes. During her assessment, there was an incidental finding of bilateral upper eyelid swelling, and a 30x15 mm palpable firm mass under the right superior orbital rim and a 30x10 mm mass under the left were noted. The right globe was displaced inferiorly, but no proptosis was seen on exophthalmometry. On plain CT scan, we noted a homogenous mass with molding or contouring around the orbital structures. On coronal view, we noted homogenous masses that mold around the globe and recti, and this also confirmed on axial cuts. A section biopsy was done via anterior orbitotomy. Results: Our patient's histopath had features of both. On scanning magnification, we noted a very cellular round cell tumor. The round cell lesion seemed to be reminiscent of a germinal center of a lymph node. Around it we noticed the glandular structures, which were expected, since this specimen was from the lacrimal gland. A closer view of the lesion on high power showed these lymphocytes within a germinal center. These are large macrophages that actively phagocytose apoptotic lymphoid cells in germinal centers. We expect to see a lot of them in benign hyperplasia, but only a few will be present in malignancies. In summary, our patient had both benign and malignant features, resulting in a histopath result of atypical lymphoid proliferation. Conclusion: Atypical lymphoid proliferation is a rare orbital tumor with benign and malignant features. There is no standard protocol for treatment, and proper multi-specialty coordination is important. External beam radiation therapy with linear accelerator (LINAC) appears to be an effective treatment, with no recurrence in our patient after 5 months.

Magnetic resonance imaging of the orbit, Part 2: Characterization of orbital pathologies

In this article we focus on a systematic approach to assess common orbital lesions on magnetic resonance imaging (MRI). The identification of the probable compartment or structure of origin helps narrow the differential diagnosis of a lesion. Analyzing the morphology, appearance, and signal intensity on various sequences, the pattern, and degree of contrast enhancement are key to characterize lesions on MRI. Imaging features suggesting cellularity and vascularity can also be determined to help plan for biopsy or surgery of these lesions. MRI can also distinguish active from chronic disease in certain pathologies and aids in selecting appropriate medical management. MRI may thus serve as a diagnostic tool and help in guiding therapeutic strategies and posttreatment follow-up.

Primary Orbital Lymphoma – A Challenging Diagnosis

Background and purpose: The occurrence of primary orbital lymphoma comprises approximately 1% of non-Hodgkin’s lymphoma and 8% of extranodal lymphoma. The vast majority of orbital lymphomas are of B-cell origin, of which extranodal marginal zone B-cell lymphoma is the most common subtype. The purpose of this paper was to present the diagnostic challenges in a case of orbital lymphoma. Case presentation: An 84-year -old woman with orbital tumour was operated on after a long period of inappropriate treatment. It was later diagnosed as B-cell lymphoma.

Conclusion: Orbital lymphoma can be easily mistaken for another ocular disease due to the slowly progressing non-specific complaints of the patients. We should be alert to the possibility of this ocular diagnosis when we are presented with an elderly patient with proptosis.

Immunoglobulin G4 (IgG4)-Positive Ocular Adnexal Mucosa-Associated Lymphoid Tissue Lymphoma and Idiopathic Orbital Inflammation

PURPOSE

To report clinical and pathological characteristics of idiopathic orbital inflammation and ocular adnexal mucosa-associated lymphoid tissue (MALT) lymphoma with immunoglobulin G4 (IgG4)-positive plasma cells.

METHODS

A retrospective histopathological review and clinical case series. A total of 51 biopsy samples from January 2005 to December 2015 were used in this study, including 21 cases of biopsy-confirmed idiopathic orbital inflammation and 30 cases of biopsy-confirmed ocular adnexal MALT lymphoma. Most cases of ocular adnexal lymphoma were conjunctival tissue. Retrospective immunohistochemical studies were performed to estimate the IgG4 and IgG4/IgG ratios. Histopathologic features, demographic and clinical data, radiologic findings, treatment, and follow-up information for each patient were analyzed.

RESULTS

Among idiopathic orbital inflammation, 6 (28.6%) of the 21 patients were diagnosed as "probable" ocular adnexal IgG4-related diseases and 13 (43.3%) of the 30 patients were diagnosed as MALT lymphoma with IgG4-positive plasma cells. Six cases of 13 IgG4-positive MALT lymphoma group had contralateral chronic inflammatory lesions infiltrated by IgG4-positive plasma cells, which was significantly (p = 0.007) higher than that in the IgG4-negative group. Conjunctival involvement was 69% of the IgG4-positive MALT lymphoma cases. Bilateral involvement of the ocular adnexa was significantly (p = 0.02) more frequent among IgG4-positive MALT lymphoma patients than that in IgG4-positive idiopathic orbital inflammation patients. Recurrence rate in the IgG4-positive group was higher (p = 0.05) than that in the IgG4-negative group but not significantly.

CONCLUSIONS

This study presented an unusual framework of ocular adnexal IgG4-related inflammation, in conjunctiva. It is important to understand contralateral chronic inflammatory lesions and their relationship with IgG4-positive MALT lymphoma. Tissue biopsy and IgG4 immunostaining are required for all cases because IgG4-positive MALT lymphoma can arise from a pre-existing IgG4-positive chronic inflammatory lesions. This is the first study that performs IgG4 immunostaining for tissue from a relatively large number of conjunctival MALT lymphomas in a single center. Therefore, it will help to diagnose conjunctival lymphoproliferative disease.

Differentiation of orbital lymphoma and idiopathic orbital inflammatory pseudotumor: combined diagnostic value of conventional MRI and histogram analysis of ADC maps

Background

The overlap of morphological feature and mean ADC value restricted clinical application of MRI in the differential diagnosis of orbital lymphoma and idiopathic orbital inflammatory pseudotumor (IOIP). In this paper, we aimed to retrospectively evaluate the combined diagnostic value of conventional magnetic resonance imaging (MRI) and whole-tumor histogram analysis of apparent diffusion coefficient (ADC) maps in the differentiation of the two lesions.

Methods

In total, 18 patients with orbital lymphoma and 22 patients with IOIP were included, who underwent both conventional MRI and diffusion weighted imaging before treatment. Conventional MRI features and histogram parameters derived from ADC maps, including mean ADC (ADC_mean), median ADC (ADC_median), skewness, kurtosis, 10th, 25th, 75th and 90th percentiles of ADC (ADC₁₀, ADC₂₅, ADC₇₅, ADC₉₀) were evaluated and compared between orbital lymphoma and IOIP. Multivariate logistic regression analysis was used to identify the most valuable variables for discriminating. Differential model was built upon the selected variables and receiver operating characteristic (ROC) analysis was also performed to determine the differential ability of the model.

Results

Multivariate logistic regression showed ADC₁₀ (P = 0.023) and involvement of orbit preseptal space (P = 0.029) were the most promising indexes in the discrimination of orbital lymphoma and IOIP. The logistic model defined by ADC₁₀ and involvement of orbit preseptal space was built, which achieved an AUC of 0.939, with sensitivity of 77.30% and specificity of 94.40%.

Conclusions

Conventional MRI feature of involvement of orbit preseptal space and ADC histogram parameter of ADC₁₀ are valuable in differential diagnosis of orbital lymphoma and IOIP.

Establishment of a combination scoring method for diagnosis of ocular adnexal lymphoproliferative disease

Lymphoproliferative diseases (LPDs) of the ocular adnexa encompass the majority of orbital diseases and include reactive follicular hyperplasia (RFH), atypical lymphoid hyperplasia (ALH), and mucosa-associated lymphoid tissue lymphoma (MALToma). Lymphoid follicles (LFs) are usually observed during the histological examination of LPDs. Currently, because there is a lack of specific clinical signs and diagnostic immunohistochemical biomarkers, it is difficult for pathologists to distinguish MALToma from ocular RFH and ALH, which makes the clinical management of these conditions difficult. Here, we analyzed the clinical features of patients with ocular adnexal LPDs (n = 125) and investigated the structure of LFs in paraffin-embedded tissue samples using anti-CD23 and anti-IgD immunochemistry. We found that some clinical features including age, sex, and laterality were different among RFH, LFH, and MALToma. Additionally, immunohistochemistry revealed that the expression of IgD and CD23 was higher in RFH patients and decreased in patients with ALH and MALToma. Moreover, LFs in RFH were intact, whereas the structures of most LFs were disrupted in ALH. In MALToma specimens, few intact LFs were observed. In a further investigation, we combined the results for CD23/IgD immunohistochemistry and the structure of LFs to establish a scoring method for the differential diagnosis of LPDs. According to the BIOMED-2 protocol, we further detected IgH gene monoclonal rearrangement in 73 cases (35 RFH, 17 ALH, and 21 MALToma cases). The sensitivity of our scoring method, based on a comparison with the results of IgH gene monoclonal rearrangement detection, was 85.7% (18/21) for MALToma and 35.3% (6/17) for ALH. Our study provides a method that may be useful for the differential diagnosis of RFH, ALH, and MALToma.