Application of deep learning to the diagnosis of cervical lymph node metastasis from thyroid cancer with CT: external validation and clinical utility for resident training

This study aimed to validate a deep learning model ’s diagnostic performance in using computed tomography (CT) to diagnose cervical lymph node metastasis (LNM) from thyroid cancer in a large clinical cohort and to evaluate the model’s clinical utility for resident training.MethodsThe performance of eight deep learning models was validated using 3838 axial CT images from 698 consecutive patients with thyroid cancer who underwent preoperative CT imaging between January and August 2018 (3606 and 232 images from benign and malignant lymph nodes, respectively). Six trainees viewed the same patient images (n = 242), and their diagnostic performance and confidence level (5-point scale) were assessed before and after computer-aided diagnosis (CAD) was included.ResultsThe overall area under the receiver operating characteristics (AUROC) of the eight deep learning algorithms was 0.846 (range 0.784 –0.884). The best performing model was Xception, with an AUROC of 0.884. The diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of Xception were 82.8%, 80.2%, 83.0%, 83.0%, and 80.2%, respectively. After introducing the CAD system, underperformi ng trainees received more help from artificial intelligence than the higher performing trainees (p = 0.046), and overall confidence levels significantly increased from 3.90 to 4.30 (p 
Source: European Radiology - Category: Radiology Source Type: research

Related Links:

This study enrolled 272 pathologically proven metastatic and benign LNs. Multiphasic CT was utilized by using nonenhanced, arterial (25-second delay), and venous (80-second delay) phases. Mean tissue attenuation values (MAVs) of metastatic and benign LNs were measured, and normalized MAV (common carotid artery and paraspinal muscle) and wash-in and wash-out percentages were also calculated. Results The arterial phase showed the highest diagnostic performance in differentiation (area under the curve ± standard error, 0.97 ± 0.02; 95% confidence interval, 0.94–1.0; P
Source: Journal of Computer Assisted Tomography - Category: Radiology Tags: Neuroradiology Source Type: research
CONCLUSION: Although we could not replace 18F FDG PET-CT, MRI might be used as an adjunct to 18F FDG PET-CT for the evaluation of recurrent or cervical and upper mediastinal metastatic thyroid cancers; however, MRI is inadequate for the detection of metastases in small lymph nodes. PMID: 32008523 [PubMed - in process]
Source: Current Medical Imaging Reviews - Category: Radiology Tags: Curr Med Imaging Rev Source Type: research
In conclusion, the present case is an extremely rare occurrence of simultaneous multiple RDMs from PTC as the initial presentation.
Source: Frontiers in Endocrinology - Category: Endocrinology Source Type: research
Conclusions The DECT quantitative parameters NIC and λHU can be an additional tool to diagnose cervical lymph node metastasis.
Source: Journal of Computer Assisted Tomography - Category: Radiology Tags: Neuro/Head and Neck Imaging Source Type: research
Conclusion: In papillary thyroid carcinoma I-131 post-ablation SPECT/CT scan detects cervical lymphadenopathy and predicts relapse by NM stage more accurately than WBS.
Source: In Vivo - Category: Research Authors: Tags: Clinical Studies Source Type: research
ConclusionsPhysicians should be aware of the possibility of the emergence of primary malignancies in patients with a history of papillary thyroid carcinoma, especially lung cancer as it is a common site of papillary thyroid carcinoma metastases. Using appropriate diagnostic evaluations in order to choose the best therapeutic option is of utmost importance.
Source: Journal of Medical Case Reports - Category: General Medicine Source Type: research
Authors: Kushchayev SV, Kushchayeva YS, Tella SH, Glushko T, Pacak K, Teytelboym OM Abstract Medullary thyroid carcinoma (MTC), arising from the parafollicular C cells of the thyroid, accounts for 1-2% of thyroid cancers. MTC is frequently aggressive and metastasizes to cervical and mediastinal lymph nodes, lungs, liver, and bones. Although a number of new imaging modalities for directing the management of oncologic patients evolved over the last two decades, the clinical application of these novel techniques is limited in MTC. In this article, we review the biology and molecular aspects of MTC as an important back...
Source: Journal of Thyroid Research - Category: Endocrinology Tags: J Thyroid Res Source Type: research
CONCLUSION: This case highlights the importance of defining the US characteristics of rare variants of thyroid neoplasms, since an early diagnosis is decisive in defining the patient's prognosis. PMID: 31140157 [PubMed - as supplied by publisher]
Source: Hormones - Category: Endocrinology Tags: Hormones (Athens) Source Type: research
Conclusion: Although encountered rarely, metastatic lesions in thyroid from nonthyroidal primaries need to be excluded while evaluating thyroid lesions.
Source: Journal of Cancer Research and Therapeutics - Category: Cancer & Oncology Authors: Source Type: research
Authors: Kim JH, Sharan A, Cho W, Emam M, Hagen M, Kim SY Abstract Study Design: Case control study. Purpose: To determine the prevalence and degree of asymptomatic cervical and lumbar facet joint arthritis. We retrospectively reviewed 500 computed tomography (CT) scans of cervical facet joints obtained from 50 subjects. Moreover, 500 lumbar facet joints obtained from an additional 50 subjects were reviewed. Overview of Literature: Numerous reports in the literature indicate that joint arthritis is a major source of axial neck and low back pain. However, the diagnostic value of this condition, based on dege...
Source: Asian Spine Journal - Category: Orthopaedics Tags: Asian Spine J Source Type: research
More News: Cancer | Cancer & Oncology | Cervical Cancer | Computers | CT Scan | Learning | Radiology | Study | Thyroid | Thyroid Cancer | Training | Universities & Medical Training