Ability of ¹⁸F-FDG PET/CT Radiomic Features to Distinguish Breast Carcinoma from Breast Lymphoma

Abstract

Purpose. To investigate the value of SUV metrics and radiomic features based on the ability of 18F-FDG PET/CT in differentiating between breast lymphoma and breast carcinoma. Methods. A total of 67 breast nodules from 44 patients who underwent 18F-FDG PET/CT pretreatment were retrospectively analyzed. Radiomic parameters and SUV metrics were extracted using the LIFEx package on PET and CT images. All texture parameters were divided into six groups: histogram (HISTO), SHAPE, gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), neighborhood gray-level different matrix (NGLDM), and gray-level zone-length matrix (GLZLM). Receiver operating characteristics (ROC) curves were generated to evaluate the discriminative ability of each parameter, and the optimal parameter in each group was selected to generate a new predictive variable by using binary logistic regression. PET predictive variable, CT predictive variable, the combination of PET and CT predictive variables, and SUVmax were compared in terms of areas under the curve (AUCs), sensitivity, specificity, and accuracy. Results. Except for SUVmin (p=0.971), the averages of FDG uptake metrics of lymphoma were significantly higher than those of carcinoma (p≤0.001), with the following median values: SUVmean, 4.75 versus 2.38 g/ml (P<0.001); SUVstd, 2.04 versus 0.88 g/ml (P=0.001); SUVmax, 10.69 versus 4.76 g/ml (P=0.001); SUVpeak, 9.15 versus 2.78 g/ml (P<0.001); TLG, 42.24 versus 9.90 (P<0.001). In the ROC curves analysis based on radiomic features and SUVmax, the AUC for SUVmax was 0.747, for CT texture parameters was 0.729, for PET texture parameters was 0.751, and for the combination of CT and PET texture parameters was 0.771. Conclusion. The SUV metrics in 18FDG PET/CT images showed a potential ability in the differentiation between breast lymphoma and carcinoma. The combination of SUVmax and PET/CT texture analysis may be promising to provide an effectively discriminant modality for the differential diagnosis of breast lymphoma and carcinoma, even for the differentiation of subtypes of lymphoma.

Distinguishing Lymphomatous and Cancerous Lymph Nodes in 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography by Radiomics Analysis

“…In the process of delineation, the tumors in each slice are carefully assigned to the VOI, and the surrounding tissues are excluded. Intensity discretization was performed automatically by the software: for PET images, intensity discretization was performed with the number of gray levels of 64 bins and the intensity rescaling was defined with absolute scale bounds between 0 and 20; for CT images, intensity discretization was performed with the number of gray levels of 400 bins and absolute scale bounds between −1000 and 3000 Hounsfield units (HUs) [33]. ereafter, extractionbased algorithms (fixed thresholding at 40% of maximum intensity cutoff) [39] were used to extract the radiomic parameters for both the PET and CT slices, including standardized uptake values (SUV) or CT-value parameters, PET parameters, and radiological parameters.…”

“…Moreover, it has been used to evaluate the prognosis of esophageal [28], lung [29], and hypopharyngeal [30] cancers. e results of the abovementioned studies have been mainly limited to the differentiation between benign and malignant lesions; studies reporting on the differentiation of tumor types are rare [31][32][33]. We previously identified the benefits of applying radiomics analysis to PET/CT images to distinguish between renal cell carcinoma and renal lymphoma [34] and between breast carcinoma and breast lymphoma [33].…”

“…e results of the abovementioned studies have been mainly limited to the differentiation between benign and malignant lesions; studies reporting on the differentiation of tumor types are rare [31][32][33]. We previously identified the benefits of applying radiomics analysis to PET/CT images to distinguish between renal cell carcinoma and renal lymphoma [34] and between breast carcinoma and breast lymphoma [33]. In this study, we focused on the usefulness of 18F-fluorodeoxyglucose (FDG) PET/CT-based radiomics analysis for distinguishing between LLN and CLN, and, moreover, used this method to classify the different subtypes of LLN in patients with lymphomas.…”

TLR5 is a new reporter for triple‐negative breast cancer indicated by radioimmunoimaging and fluorescent staining

“…Nuclear medicine molecular imaging is a kind of non‐invasive whole‐body scanning modality based on metabolism and function abnormal, more suitable for the detection and quantification of tumour target molecular, compared with traditional imaging CT (computed tomography) and MRI (magnetic resonance imaging) in diagnosis and tumour staging . Nowadays, 18 F‐FDG (F‐18‐deoxyglucose) PET/CT (positron emission tomography/computed tomography) was widely used in clinic for evaluation tumour metabolisms . However, 18 F‐FDG is a non‐specific agent, which made diagnosis sometimes not accurate.…”

“…6 Nowadays, 18 F-FDG (F-18-deoxyglucose) PET/CT (positron emission tomography/computed tomography) was widely used in clinic for evaluation tumour metabolisms. 7 However, 18 F-FDG is a non-specific agent, which made diagnosis sometimes not accurate. Searching the better molecular target for tumour diagnosis and therapy is critical for clinic.…”