Search

Purpose: Differentiating pulmonary lymphoma from lung infections using CT images is challenging. Existing deep neural network-based lung CT classification models rely on 2D slices, lacking comprehensive information and requiring manual selection. 3D models that involve chunking compromise image information and struggle with parameter reduction, limiting performance. These limitations must be addressed to improve accuracy and practicality. Methods: We propose a transformer sequential feature encoding structure to integrate multi-level information from complete CT images, inspired by the clinical practice of using a sequence of cross-sectional slices for diagnosis. We incorporate position encoding and cross-level long-range information fusion modules into the feature extraction CNN network for cross-sectional slices, ensuring high-precision feature extraction. Results: We conducted comprehensive experiments on a dataset of 124 patients, with respective sizes of 64, 20 and 40 for training, validation and testing. The results of ablation experiments and comparative experiments demonstrated the effectiveness of our approach. Our method outperforms existing state-of-the-art methods in the 3D CT image classification problem of distinguishing between lung infections and pulmonary lymphoma, achieving an accuracy of 0.875, AUC of 0.953 and F1 score of 0.889. Conclusion: The experiments verified that our proposed position-enhanced transformer-based sequential feature encoding model is capable of effectively performing high-precision feature extraction and contextual feature fusion in the lungs. It enhances the ability of a standalone CNN network or transformer to extract features, thereby improving the classification performance. The source code is accessible at https://github.com/imchuyu/PTSFE. [ABSTRACT FROM AUTHOR]

Abstract We report on a 70-year old woman with dyspnea, systemic lymphadenopathy and abnormal chest computed tomography (CT) findings. A complete laboratory testing as well as mediastinal tissue sampling via Endobronchial Ultrasound (EBUS)-guided Transbronchial Needle Biopsy (TBNB) did not reveal a definite diagnosis. After experiencing acute respiratory failure which led to intensive care unit, the patient underwent a cervical lymph node biopsy which revealed peripheral T-cell lymphoma not otherwise specified (PTCL-NOS). A CT-guided trans -thoracic lung biopsy was performed that showed involvement of the lung parenchyma in the context of PTCL-NOS. Lung involvement is a rare extra-nodal manifestation of PTCL. The imaging patterns of this lymphoma have not been well described. We conclude that the finding of crazy paving pattern is a rare manifestation of this disease. In patients with pre-existing lymphoma, lung involvement should be included in the differential due to high pre-test probability. [ABSTRACT FROM AUTHOR]

Bronchial-associated lymphoid tissue (BALT) lymphoma is an extranodal primary pulmonary lymphoma. The optimal therapy for this rare disease is still debated, and few heterogeneous data are available in literature. The aim of our study was to critically review data of patients with BALT lymphoma treated in first-line therapy with fludarabine and mitoxantrone-containing regimens (with or without rituximab) to investigate the effectiveness and the safety of this approach and patients' survival. An observational retrospective study was performed on homogenous clinical data from 17 patients with biopsy-proven diagnosis of BALT. All the patients were treated with fludarabine and mitoxantrone-containing regimen therapy. Radiological findings were also reviewed to assess the role of 18fluoro-deoxyglucose positron emission tomography in the initial assessment and in the monitoring of this extranodal lymphoma. A high percentage of response was observed: 82.3% of patients achieved a complete response, 11.8% a partial response. Furthermore, a very remarkable progression-free survival (71%) and overall survival (100%) were estimated at 14 years. No relevant toxicities were registered. Our results support the use of fludarabine and mitoxantrone-containing regimens as first-line therapy in the treatment of BALT lymphoma even if further data are necessary to consolidate our findings. Positron emission tomography scanning may provide additional valuable information in the assessment of BALT lymphoma. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Primary lung lymphoma is one of the rarest forms of lymphoma and pulmonary space-occupying lesions. This case report represents the F-18 fluorodeoxyglucose positron emission tomography/computed tomography images of the most severe form of the primary pulmonary lymphoma reported in the literature. [ABSTRACT FROM AUTHOR]