Background
Radiomics is a promising field in oncology imaging. However, the implementation of radiomics clinically has been limited because its robustness remains unclear. Previous CT and PET studies suggested that radiomic features were sensitive to variations in pixel size and slice thickness of the images. The purpose of this study was to assess robustness of magnetic resonance (MR) radiomic features to pixel size resampling and interpolation in patients with cervical cancer.
Methods
This retrospective study included 254 patients with a pathological diagnosis of cervical cancer stages IB to IVA who received definitive chemoradiation at our institution between January 2006 and June 2020. Pretreatment MR scans were analyzed. Each region of cervical cancer was segmented on the axial gadolinium-enhanced T1- and T2-weighted images; 107 radiomic features were extracted. MR scans were interpolated and resampled using various slice thicknesses and pixel spaces. Intraclass correlation coefficients (ICCs) were calculated between the original images and images that underwent pixel size resampling (OP), interpolation (OI), or pixel size resampling and interpolation (OP+I) as well as among processed image sets with various pixel spaces (P), various slice thicknesses (I), and both (P + I).
Results
After feature standardization, ≥86.0% of features showed good robustness when compared between the original and processed images (OP, OI, and OP+I) and ≥ 88.8% of features showed good robustness when processed images were compared (P, I, and P + I). Although most first-order, shape, and texture features showed good robustness, GLSZM small-area emphasis-related features and NGTDM strength were sensitive to variations in pixel size and slice thickness.
Conclusion
Most MR radiomic features in patients with cervical cancer were robust after pixel size resampling and interpolation following the feature standardization process. The understanding regarding the robustness of individual features after pixel size resampling and interpolation could help future radiomics research.
Background: Current chemoradiation regimens for locally advanced cervical cancer are fairly uniform despite a profound diversity of treatment response and recurrence patterns. The wide range of treatment responses and prognoses to standardized concurrent chemoradiation highlights the need for a reliable tool to predict treatment outcomes. We investigated pretreatment magnetic resonance (MR) imaging features of primary tumor and involved lymph node for predicting clinical outcome in cervical cancer patients. Methods: We included 93 node-positive cervical cancer patients treated with definitive chemoradiotherapy at our institution between 2006 and 2017. The median follow-up period was 38 months (range, 5-128). Primary tumor and involved lymph node were manually segmented on axial gadolinium-enhanced T1-weighted images as well as T2weighted images and saved as 3-dimensional regions of interest (ROI). After the segmentation, imaging features related to histogram, shape, and texture were extracted from each ROI. Using these features, random survival forest (RSF) models were built to predict local control (LC), regional control (RC), distant metastasis-free survival (DMFS), and overall survival (OS) in the training dataset (n = 62). The generated models were then tested in the validation dataset (n = 31). Results: For predicting LC, models generated from primary tumor imaging features showed better predictive performance (C-index, 0.72) than those from lymph node features (C-index, 0.62). In contrast, models from lymph nodes showed superior performance for predicting RC, DMFS, and OS compared to models of the primary tumor. According to the 3-year time-dependent receiver operating characteristic analysis of LC, RC, DMFS, and OS prediction, the respective area under the curve values for the predicted risk of the models generated from the training dataset were 0.634, 0.796, 0.733, and 0.749 in the validation dataset. Conclusions: Our results suggest that tumor and lymph node imaging features may play complementary roles for predicting clinical outcomes in node-positive cervical cancer.
We present a rare case of spindle cell oncocytoma (SCO) of the sella turcica with malignant histologic features and rapid progression. A 42-year-old woman experienced bilateral blurred vision and was preoperatively misdiagnosed as having a pituitary macroadenoma on magnetic resonance imaging. After surgery, SCO was diagnosed by the histopathologic features of interlacing fascicles of spindle tumor cells with finely granular, eosinophilic cytoplasm. Focal anaplastic changes and necrosis were present. Immunohistochemically, the tumor cells were positive for vimentin, epithelial membrane antigen, S-100, galectin-3, and thyroid transcription factor 1. Four months later, the tumor had progressed, and second surgery with adjuvant radiotherapy was performed; the patients remains under observation. In this report, we proposed distinctive radiologic features for differential diagnosis between SCO and other pituitary tumors.
This report describes a case of a 40-year-old female patient with concurrent invasive ductal carcinoma of the breast and malignant follicular lymphoma, initially suspected to be metastatic breast cancer. During the initial evaluation of invasive ductal carcinoma of right breast, multiple lymphadenopathies were noted throughout the body on ultrasonography and positron emission tomography/computed tomography images. Clinically, metastatic breast cancer was suggested, and the patient was administered chemotherapy, including hormonal therapy. The breast cancer improved slightly, but the lymphadenopathies progressed and excisional biopsy of a cervical lymph node revealed malignant follicular lymphoma.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.