Automatic segmentation of the liver and hepatic lesions is an important step towards deriving quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This paper presents a method to automatically segment liver and lesions in CT and MRI abdomen images using cascaded fully convolutional neural networks (CFCNs) enabling the segmentation of large-scale medical trials and quantitative image analyses. We train and cascade two FCNs for the combined segmentation of the liver and its lesions. As a first step, we train an FCN to segment the liver as ROI input for a second FCN. The second FCN solely segments lesions within the predicted liver ROIs of step 1. CFCN models were trained on an abdominal CT dataset comprising 100 hepatic tumor volumes. Validation results on further datasets show that CFCN-based semantic liver and lesion segmentation achieves Dice scores over 94% for the liver with computation times below 100s per volume. We further experimentally demonstrate the robustness of the proposed method on 38 MRI liver tumor volumes and the public 3DIRCAD dataset.
Background: The tyrosine kinase inhibitor (TKI) Lenvatinib represents one of the most effective therapeutic options in patients with advanced radioiodine refractory differentiated thyroid carcinoma (DTC). We aimed to assess the role of 2-deoxy-2-[18F] fluoro-D-glucose positron-emission-tomography/computed-tomography (18F-FDG-PET/CT) in the monitoring of functional tumor response compared to morphological response. Methods: In 22 patients, a modified Positron Emission Tomography Response Criteria In Solid Tumors (mPERCIST) evaluation before treatment with Lenvatinib and at 3 and 6 month follow up was performed. Further PET-parameters and morphologic tumor response using Response Evaluation Criteria in Solid Tumors (RECIST) 1.1 were assessed and their prediction of progression-free survival (PFS) and disease-specific survival (DSS) was evaluated. Results: Most patients were rated stable in morphological evaluation and progressive using a metabolic response. All patients who responded to therapy through RECIST showed a decline in nearly all Positron Emission Tomography (PET)-parameters. For both time-points, non-responders according to mPERCIST showed significantly lower median PFS and DSS, whereas according to RECIST, only DSS was significantly lower. Conclusion: Tumor response assessment by 18F-FDG-PET outperforms morphological response assessment by CT in patients with advanced radioiodine refractory DTC treated with Lenvatinib, which seems to be correlated with clinical outcomes.
Purpose There are controversial debates if patients with Hürthle cell carcinoma, also known as oxyphilic or oncocytic cell follicular thyroid carcinoma, have a poorer outcome. In this study, we systematically evaluated the clinical outcome in a large patient cohort following thyroidectomy and initial I-131 radioactive iodine therapy (RIT). Methods We retrospectively evaluated a total of 378 patients with diagnosed oncocytic follicular Hürthle cell carcinoma (OFTC) (N = 126) or with classical follicular thyroid carcinoma (FTC) (N = 252). Patients received thyroidectomy and complementary I-131 RIT. Clinical data regarding basic demographic characteristics, tumor grade, persistent disease and recurrence during followup, and disease-free, disease-specific, and overall survival were collected during follow-up of 6.9 years (interquartile range 3.7; 11.7 years). Univariate and multivariate analyses were used to identify factors associated with disease-related and overall survival. Results Before and after matching for risk factors, recurrence was significantly more frequently diagnosed in OFTC patients during follow-up (17% vs. 8%; p value 0.037). Likewise, OFTC patients presented with a reduced mean disease-free survival of 17.9 years (95% CI 16.0-19.8) vs. 20.1 years (95% CI 19.0-21.1) in FTC patients (p value 0.027). Multivariate analysis revealed OFTC (HR 0.502; 95% CI 0.309-0.816) as the only independent prognostic factor for disease-free survival. Distant metastases of OFTC patients were significantly less iodine-avid (p value 0.014). Mean disease-specific and overall survival did not differ significantly (p value 0.671 and 0.687) during follow-up of median 6.9 years (3.7; 11.7 years). Conclusions Our study suggests that recurrence is more often seen in OFTC patients. OFTC patients have a poorer prognosis for disease-free survival. Thus, OFTC and FTC behave differently and should be categorized separately. However, patients suffering from OFTC present with the same overall and disease-specific survival at the end of follow-up indifferent to FTC patients after initial RIT.
Background: Extrathyroidal extension of differentiated thyroid cancer is a poor outcome factor but seems to be less significant in minimal extrathyroidal extension (mETE). However, the impact of mETE on response rate after (adjuvant) initial radioactive iodine (RAI) therapy remains unclear. We therefore compared response rates of patients with classical and follicular variants of papillary thyroid cancer (PTC) according to the updated eighth tumor-node-metastasis (TNM) classification to a control group. Methods: 455 patients with T3 (primary tumor > 4 cm) PTC according to the seventh classification who underwent total thyroidectomy followed by RAI therapy were screened. Patients formerly classified as T3 PTC solely due to mETE were reclassified into patients with T1 (primary tumor ≤ 2 cm) or T2 (primary tumor > 2 cm but ≤ 4 cm) +mETE and compared to a control group of T1/T2 −mETE PTC patients. Results: 138/455 patients were reclassified as T1/2 +mETE and compared to 317/455 T1/T2 −mETE control patients. At initial presentation, +mETE patients showed significantly higher rates of cervical lymph node metastases (p-value 0.001). Response rates were comparable in both groups (p-value n.s.). N1a/N1b-stage (Hazard ratio, HR 0.716; 95% CI 0.536–0.956, p-value 0.024) was identified as an independent prognostic factor for lower response rates. Conclusion: Response rates after RAI therapy were comparable in PTC patients irrespective of mETE but with higher rates of lymph node metastases.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.