Sarcoidosis mimicking lymphoma on FDG-PET imaging

Deep convolutional neural network for differentiating between sarcoidosis and lymphoma based on [18F]FDG maximum-intensity projection images

OBJECTIVES

To compare the [18F]FDG PET/CT findings of untreated sarcoidosis and malignant lymphoma (ML) and develop convolutional neural network (CNN) models to differentiate between these diseases using maximum intensity projection (MIP) [18F]FDG PET images.

METHODS

We retrospectively collected data on consecutive patients newly diagnosed with sarcoidosis and ML who underwent [18F]FDG PET/CT before treatment. Two nuclear radiologists reviewed the images. CNN models were created using MIP PET images and evaluated with k-fold cross-validation. The points of interest were visualized using gradient-weighted class activation mapping (Grad-CAM).

RESULTS

A total of 56 patients with sarcoidosis and 62 patients with ML were included. Patients with sarcoidosis had more prominent FDG accumulation in the mediastinal lymph nodes and lung lesions, while those with ML had more prominent accumulation in the cervical lymph nodes (all p < 0.001). For the mediastinal lymph nodes, sarcoidosis patients had significant FDG accumulation in the level 2, 4, 7, and 10 lymph nodes (all p < 0.01). Otherwise, the accumulation in ML patients tended to be in the level 1 lymph nodes (p = 0.08). The CNN model using frontal and lateral MIP images achieved an average accuracy of 0.890 (95% CI: 0.804-0.977), a sensitivity of 0.898 (95% CI: 0.782-1.000), a specificity of 0.907 (95% CI: 0.799-1.000), and an area under the curve of 0.963 (95% CI: 0.899-1.000). Grad-CAM showed that the model focused on the sites of abnormal FDG accumulation.

CONCLUSIONS

CNN models based on differences in FDG accumulation sites archive high performance in differentiating between sarcoidosis and ML.

CLINICAL RELEVANCE STATEMENT

We developed a CNN model using MIP images of [18F]FDG PET/CT to distinguish between sarcoidosis and malignant lymphoma. It achieved high performance and could be useful in diagnosing diseases with involvement across organs and lymph nodes.

KEY POINTS

• There are differences in FDG distribution when comparing whole-body [18F]FDG PET/CT findings in patients with sarcoidosis and malignant lymphoma before treatment. • Convolutional neural networks, a type of deep learning technique, trained with maximum-intensity projection PET images from two angles showed high performance. • A deep learning model that utilizes differences in FDG distribution may be helpful in differentiating between diseases with lesions that are characteristically widespread among organs and lymph nodes.

Mediastinal lymphadenopathy in sarcoidosis: Can diffusion MRI play a role in its evaluation?

Background

Sarcoidosis is a multisystem disease defined by non-caseous epithelioid cell granulomas that can affect virtually all organs. Lung, mediastinal and hilar lymph node involvement is prevalent, occurring in around 90% of the patients, and is responsible for the majority of the morbidity and mortality related to the disorder. Sarcoidosis is one of the differential diagnoses of the benign mediastinal lymphadenopathy. This research aimed to detect the diagnostic value of magnetic resonance imaging (MRI) diffusion in evaluation of mediastinal lymphadenopathy in sarcoid patients.

Results

This cross study involved a total of 30 patients known to have sarcoidosis: 6 males and 24 females aged between 18 and 50 years (with a mean age 38.97 ± 8.67); all of them presented with mediastinal lymphadenopathy. For all patients, each lymph node group was evaluated for the average size and average ADC value. The mean ADC measured was (1.76 ± 0.28) × 10−3 mm2/s. Eight patients showed concurrent activity with poor response to the treatment, and they showed different ADC values with one of them showing low ADC with pattern of diffusion restriction displaying mean ADC value of 1.28 × 10−3 mm2/s.

Conclusions

Diffusion-weighted MRI is an established imaging technique that could be utilized to evaluate mediastinal lymphadenopathy in sarcoidosis as the benign counterpart of mediastinal lymphadenopathy.

18F-FDG PET/CT helps in unmasking the great mimicker: A case of neurosarcoidosis with isolated involvement of the spinal cord

A 36 year-old male with no significant past medical history presented with lower extremity numbness, gait instability, and urinary and bowel retention of 4 weeks onset. Spine MRI revealed diffuse oedema of cervicothoracic spinal cord with several solid enhancing intramedullary lesions, suggestive of metastases. The ¹⁸F-FDG PET/CT performed to identify the primary malignancy demonstrated mild hypermetabolic foci within the cervicothoracic cord, as well as a mildly hypermetabolic bilateral hilar lymphadenopathy and a mildly hypermetabolic pulmonary nodule, suggestive of sarcoidosis versus metastasis. The diagnosis of sarcoidosis was supported by identifying non-caseating granuloma in the biopsy of the pulmonary nodule. The patient responded well to steroid-therapy, with the symptoms being resolved within 3 weeks.

Fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography imaging in response monitoring of extra-pulmonary tuberculosis

Positron emission tomography/computed tomography (PET/CT) using 2-deoxy-2-(fluorine-18) fluoro-D-glucose (¹⁸F-FDG) has become a standard diagnostic modality in oncological practice. F18-FDG PET/CT is sensitive in detecting malignancy; however, specificity is low in differentiating infections or inflammatory diseases from tumor. In the present case study, we report a patient with postoperative carcinoma of tongue presenting with cervical lymphadenopathy and fever. The PET/CT scan showed metabolically active generalized lymphadenopathy, and a possibility of lymphoma was suggested. Fine needle aspiration cytology showed the Ziehl–Neelsen staining to be strongly positive for acid-fast bacilli and first line of antitubercular drug was administrated. Six months later after the initiation of therapy, a follow-up PET/CT showed remarkable improvement of the disease status. This case study illustrates that tubercular infection can be a pitfall in F18-FDG PET/CT imaging. PET positive lesions do not always indicate malignancy, and histological confirmation of lesions with biopsy should always be performed. Once diagnosed to be tubercular, FDG PET/CT is a powerful imaging tool in monitoring the therapy.

Sarcoidosis mimicking metastatic papillary thyroid cancer

•

Sarcoidosis is a multisystemic, idiopathic disease.

•

Thyroid cancer is rarely reported in the literature.

•

We present a case with sarcoidosis mimicking metastatic papillary thyroid cancer.

Introduction

Sarcoidosis is a multisystemic, idiopathic disease. It has a highly variable clinical course. It has been reported to present in association with malignancy. Coexistence of sarcoidosis and thyroid cancer is rarely reported in the literature.

Presentatioin of the case

We present a case with neck swelling for 3 months, and symmetrical painless thyroid enlargement without fixation to deep tissues of the neck. Multiple nodules on the both thyroid lobes, hard irregular, grade two goiter with lymphadenopathy all over anterior neck compartments. Fine needle aspiration cytology was done under ultrasound guide from right thyroid nodule and showed papillary thyroid carcinoma. Excisional biopsy of the neck lymphnode showed picture typical for sarcoidosis.

Discussion

Most researchers believe that patients with pulmonary sarcoidosis are predisposed to develop malignancies, less than a dozen of cases are reported in the literature to be associated with PTC with a very wide range of presentations and clincal coarses. An interesting finding of our case is that in contrast to what is reported, both diseases were not known by the physician until the time of presentation.

Conclusion

Cervical lymphadenopathy in association with goiter could be metastasis, sarcoidosis or mixed, therefore should be seperately biopsied.