Role of CT imaging in addressing resectability issues in differentiated thyroid cancer: imaging-based Mahajan grading system for TI and ETE.

Background and objective: Extrathyroidal extension (ETE) is the term used to describe the growth of the primary thyroid tumor beyond the thyroid capsule. ETE is a critical prognostic marker for thyroid tumors, necessitating accurate preoperative assessment. This study aims to evaluate the diagnostic performance of computed tomography (CT)-based grading for ETE and tracheal invasion (TI) for preoperative prediction in patients with differentiated papillary thyroid carcinoma (PTC) and compare the diagnostic accuracy with ultrasound (US). Materials and methods: This retrospective study was approved by our institutional review board. Preoperative US and CT were performed for 83 patients who underwent surgery for PTC between 1 January 2010 and 31 December 2020. The US and CT features of ETE and TI of each case were retrospectively and independently investigated by two radiologists. The diagnostic performances of US and CT, including their specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) for ETE, and their accuracy in predicting ETE and TI were analyzed. As per the grading for ETE on USG and CT, lesions were graded into three grades and Mahajan grading was also devised on CT to predict the TI and graded into four grades. Results: The accuracy and specificity of CT are relatively good for identifying tumor infiltration into the adjacent structures and range from 82% to 87% and 95% to 98%, respectively. It, however, has a low sensitivity, between 14.3% and 77.78%, when compared to US, which suggests that in case of any doubt regarding CT evidence of tumor infiltration into surrounding structures, additional clinical examination must be performed. CT showed better sensitivity (78%) and specificity (75%) in detecting TI compared to previous studies. The diagnostic accuracy of CT Mahajan grading was 91.5% with p <0.005 in the prediction of TI. Conclusion: Preoperative US should be regarded as a first-line imaging modality for predicting minimal ETE, and CT should be additionally performed for the evaluation of maximal ETE. The specificity and PPV of CT are higher than those of US in detecting overall ETE and TI of PTC. The US- and CT-based grading systems have the potential to optimize preoperative surgical planning.

Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging.

PURPOSE: The authors aimed to develop and validate deep-learning-based radiogenomic (DLR) models and radiomic signatures to predict the EGFR mutation in patients with NSCLC, and to assess the semantic and clinical features that can contribute to detecting EGFR mutations. METHODS: Using 990 patients from two NSCLC trials, we employed an end-to-end pipeline analyzing CT images without precise segmentation. Two 3D convolutional neural networks segmented lung masses and nodules. RESULTS: The combined radiomics and DLR model achieved an AUC of 0.88 ± 0.03 in predicting EGFR mutation status, outperforming individual models. Semantic features further improved the model's accuracy, with an AUC of 0.88 ± 0.05. CT semantic features that were found to be significantly associated with EGFR mutations were pure solid tumours with no associated ground glass component (p < 0.03), the absence of peripheral emphysema (p < 0.03), the presence of pleural retraction (p = 0.004), the presence of fissure attachment (p = 0.001), the presence of metastatic nodules in both the tumour-containing lobe (p = 0.001) and the non-tumour-containing lobe (p = 0.001), the presence of ipsilateral pleural effusion (p = 0.04), and average enhancement of the tumour mass above 54 HU (p < 0.001). CONCLUSIONS: This AI-based radiomics and DLR model demonstrated high accuracy in predicting EGFR mutation, serving as a non-invasive and user-friendly imaging biomarker for EGFR mutation status prediction.

The complementary role of MRI and FET PET in high-grade gliomas to differentiate recurrence from radionecrosis.

Introduction: Conventional magnetic resonance imaging (MRI) has limitations in differentiating tumor recurrence (TR) from radionecrosis (RN) in high-grade gliomas (HGG), which can present with morphologically similar appearances. Multiparametric advanced MR sequences and Positron Emission Tomography (PET) with amino acid tracers can aid in diagnosing tumor metabolism. The role of both modalities on an individual basis and combined performances were investigated in the current study. Materials and Methods: Patients with HGG with MRI and PET within three weeks were included in the retrospective analysis. The multiparametric MRI included T1-contrast, T2-weighted sequences, perfusion, diffusion, and spectroscopy. MRI was interpreted by a neuroradiologist without using information from PET imaging. 18F-Fluoroethyl-Tyrosine (FET) uptake was calculated from the areas of maximum enhancement/suspicion, which was assessed by a nuclear medicine physician (having access to MRI to determine tumor-to-white matter ratio over a specific region). A definitive diagnosis of TR or RN was made based on the combination of multidisciplinary joint clinic decisions, histopathological examination, and clinic-radiological follow-up as applicable. Results: 62 patients were included in the study between July 2018 and August 2021. The histology during initial diagnosis was glioblastoma, oligodendroglioma, and astrocytoma in 43, 7, and 6 patients, respectively, while in 6, no definitive histological characterization was available. The median time from radiation (RT) was 23 months. 46 and 16 patients had TR and RN recurrence, respectively. Sensitivity, specificity, and accuracy using MRI were 98, 77, and 94%, respectively. Using PET imaging with T/W cut-off of 2.65, sensitivity, specificity, and accuracy were 79, 84, and 80%, respectively. The best results were obtained using both imaging combined with sensitivity, specificity, and accuracy of 98, 100, and 98%, respectively. Conclusion: Combined imaging with MRI and FET-PET offers multiparametric assessment of glioma recurrence that is correlative and complimentary, with higher accuracy and clinical value.

Unleashing the Mystery of a Treated Case of Medulloblastoma.

Medulloblastoma (MB) is the most common malignant brain tumor in children. Despite advancement in treatment modalities, recurrence remains common, even among those treated with a combination of neurosurgery, craniospinal irradiation, and chemotherapy. The diagnosis of recurrence is usually not difficult in these cases. However, it may pose a challenge in cases with unusual clinical presentation and imaging. Imaging findings on magnetic resonance imaging, with application of perfusion, in conjunction with positron emission tomography-computed tomography can help in clinching the diagnosis in such cases. MB subgroups show consistent patterns even in cases of recurrence, and sonic hedgehog group MB may present as local recurrence showing enhancement with no diffusion restriction, as demonstrated in this case.