RESUMO
INTRODUCTION: Texture and radiomic analysis characterizes the tumor's phenotype and evaluates its microenvironment in quantitative terms. This study aims to investigate the role of textural and radiomic analysis parameters in predicting histopathological factors in breast cancer patients. MATERIALS AND METHODS: Two hundred and twelve primary breast cancer patients underwent 18F-FDG PET/computed tomography for staging. The images were processed in a commercially available textural analysis software. ROI was drawn over the primary tumor with a 40% threshold and was processed further to derive textural and radiomic parameters. These parameters were then compared with histopathological factors of tumor. Receiver-operating characteristic analysis was performed with a P-value <0.05 for statistical significance. The significant parameters were subsequently utilized in various machine learning models to assess their predictive accuracy. RESULTS: A retrospective study of 212 primary breast cancer patients was done. Among all the significant parameters, SUVmin, SUVmean, SUVstd, SUVmax, discretized HISTO_Entropy, and gray level co-occurrence matrix_Contrast were found to be significantly associated with ductal carcinoma type. Four parameters (SUVmin, SUVmean, SUVstd, and SUVmax) were significant in differentiating the luminal subtypes of the tumor. Five parameters (SUVmin, SUVmean, SUVstd, SUVmax, and SUV kurtosis) were significant in predicting the grade of the tumor. These parameters showcased robust capabilities in predicting multiple histopathological parameters when tested using machine learning algorithms. CONCLUSION: Though textural analysis could not predict hormonal receptor status, lymphovascular invasion status, perineural invasion status, microcalcification status of tumor, and all the molecular subtypes of the tumor, it could predict the tumor's histologic type, triple-negative subtype, and score of the tumor noninvasively.
RESUMO
Background: Lymphoma is a common malignant proliferative disease in which bone marrow infiltration will upstage the disease and thus affect prognosis of the disease. As of now bone marrow biopsy is considered as a reference standard to find out bone marrow involvement in lymphoma. Performing an invasive and painful intervention in all newly diagnosed lymphoma patients is controversial. PET-CT is a non-invasive technique that gives functional information about the cells using the glucose metabolism. It can detect early bone marrow and extra medullary organ involvement which can lead to restaging of the disease. These advantages make PET-CT a valuable adjunct in diagnosis of lymphoma. Aims and Objectives: Our study aims to evaluate the usefulness of 18 F-FDG PET-CT, a non-invasive, semi quantitative whole body imaging technique for detection of early bone marrow and extra medullary organ involvement in lymphoma patients which in turn can obviate the need for bone marrow study (BMS). The primary objective of study is to categorise FDG uptake in bone marrow as diffuse /unifocal /multifocal / no uptake and to correlate pattern of FDG uptake to bone marrow study. Our study also assesses the role of FDG PET/CT in staging of lymphoma. Materials and Methods: Thirty patients with newly diagnosed lymphoma in the age group 18 to 75 years of both sexes within 3 months of diagnosis and who have not been started on any treatment was included in the study. Marrow uptake on FDG PET/CT has been categorized as diffuse, unifocal, multifocal and no uptake. Agreement between bone marrow study and FDG PET/CT has been assessed by reliability analysis using Cohen's kappa. Sensitivity, specificity, PPV, NPV of PET/CT in detecting marrow involvement have been calculated. Results: The sensitivity, specificity, PPV, NPV and accuracy of 18 F-FDG PET-CT in detecting marrow involvement of lymphoma cases are 86.6%, 77.7%, 68.4%, 91.3% and 80.9% respectively. 18 F-FDG PET-CT detected bone marrow involvement in 86.6% (13 out of 15 total positive cases) cases of lymphoma which included both HL and NHL. Reliability analysis using Cohen's kappa is used to test the agreement between bone marrow study and 18F-FDG PET/CT. k value of 0.6 was obtained which showed a moderate agreement between bone marrow study and 18F-FDG PET/CT in marrow assessment. Conclusion: 18F-FDG PET/CT is a highly sensitive imaging modality which can pick up extra-nodal organ and BMI in patients with lymphoma and can upstage the disease and alter treatment strategies. PET-CT cannot completely replace the bone marrow study. However, being an invasive painful procedure, BMB can be avoided in cases with unifocal or multifocal marrow involvement on PET-CT.