Detection Of Recurrent Nasopharyngeal Carcinomas Research Articles

Deep learning-based recurrence detector on magnetic resonance scans in nasopharyngeal carcinoma: A multicenter study

ObjectivesAccuracy in the detection of recurrent nasopharyngeal carcinoma (NPC) on follow-up magnetic resonance (MR) scans needs to be improved. Material and methodsA total of 5 035 follow-up MR scans from 5 035 survivors with treated NPC between April 2007 and July 2020 were retrospectively collected from three cancer centers for developing and evaluating the deep learning (DL) model MODERN (MR-based Deep learning model for dEtecting Recurrent Nasopharyngeal carcinoma). In a reader study with 220 scans, the accuracy of two radiologists in detecting recurrence on scans with vs without MODERN was evaluated. The performance was measured using the area under the receiver operating characteristic curve (ROC-AUC) and accuracy with a 95% confidence interval (CI). ResultsMODERN exhibited sound performance in the validation cohort (internal: ROC-AUC, 0.88, 95% CI, 0.86–0.90; external 1: ROC-AUC, 0.88, 95% CI, 0.86–0.90; external 2: ROC-AUC, 0.85, 95% CI, 0.82–0.88). In a reader study, MODERN alone achieved reliable accuracy compared to that of radiologists (MODERN: 84.1%, 95% CI, 79.3%–88.9%; competent: 80.9%, 95% CI, 75.7%–86.1%, P < 0.001; expert: 85.9%, 95% CI, 81.3%–90.5%, P < 0.001). The accuracy of radiologists was boosted by the MODERN score (competent with MODERN score: 84.6%, 95% CI, 79.8%–89.3%, P < 0.001; expert with MODERN score: 87.7%, 95% CI, 83.4%–92.1%, P < 0.001). ConclusionWe developed a DL model for recurrence detection with reliable performance. Computer-human collaboration has the potential to refine the workflow in interpreting surveillant MR scans among patients with treated NPC.

Surveillance tools for detection of recurrent nasopharyngeal carcinoma: An evidence-based review and recommendations.

ObjectiveNasopharyngeal carcinomas (NPC) are tumors arising from epithelium of the nasopharynx. The 5‐year survival rate of primary NPC is 80% with significant risks of recurrence. The objective here is to provide an evidence‐based systemic review of the diagnostic value of different modalities in detecting local, regional, and distal recurrent NPC, as well as the associated costs with these modalities.MethodsMEDLINE, EMBASE, and the Cochrane review database were queried. Two hundred and twenty‐three abstracts were generated using the inclusion criteria: patients >18 years of age; histopathological reference standard; and modalities pertaining to imaging or microbiology.ResultsTwenty‐four manuscripts fulfilled the inclusion criteria and 5 surveillance tools identified: endoscopy, MR, FDG‐PET, Tc‐99m MIBI and 201TI SPECT, and EBV DNA.ConclusionsFor local surveillance, endoscopy is the gold standard recommendation, with increased efficacy if Narrow Band Imaging or contact endoscopy are utilized. MRI and FDG‐PET is also recommended to help with local to distal spread; however, Tc‐99m MIBI and 201TI SPECT are options as well. EBV DNA is recommended as a cheap and accessible adjunct surveillance tool if an available as an option.

Plasma Epstein‐Barr virus DNA screening followed by 18F‐fluoro‐2‐deoxy‐D‐glucose positron emission tomography in detecting posttreatment failures of nasopharyngeal carcinoma

The authors investigated the clinical implication of plasma Epstein-Barr virus (EBV) DNA assay and (18) F-fluoro-2-deoxy-D-glucose ((18) F-FDG) positron emission tomography (PET) in the detection of recurrent nasopharyngeal carcinoma (NPC). Two hundred forty-five patients with NPC who had previously received treatment and were in a state of remission were monitored prospectively using a plasma EBV DNA assay every 3 to 6 months. (18) F-FDG PET studies were obtained when abnormal EBV DNA or clinically suggestive signs of recurrence were noted. Thirty-six of 245 patients (14.7%) patients had abnormal EBV DNA tests and underwent PET scans. In the remaining 209 patients, 3658 blood tests were negative. PET scans also were obtained in 5 patients who had undetectable EBV DNA levels but signs that were clinically suggestive of disease recurrence. Subsequent analyses focused on 41 patients who had PET studies. In lesion-based analyses, the sensitivity, specificity, and accuracy of PET by visual interpretation were 81.8%, 77.1%, and 79.2%, respectively, for all 125 lesions. In patient-based analyses, the accuracy of PET by visual interpretation was 51.2%. All 36 patients who had detectable plasma levels of EBV DNA had demonstrable NPC recurrences, whereas no recurrences were noted in 5 patients who had undetectable EBV DNA levels but signs that clinically mimicked a recurrence. Compared with annual PET, the annual cost of blood tests every 3 to 6 months per patient saved approximately 77% ∼ 88% in expenses. The plasma EBV DNA assay correctly predicted all NPC recurrences, and PET had high capacity to localize potential lesion sites. The authors concluded that applying the strategy of EBV DNA screening followed by PET scanning may guide appropriate further treatment planning in a cost-effective manner.

Detection of Recurrent Nasopharyngeal Carcinomas After Radiotherapy with Technetium-99m Tetrofosmin Single Photon Emission Computed Tomography in Patients with Indeterminate Magnetic Resonance Imaging Findings

The aim of this study is to evaluate the effectiveness of technetium-99m tetrofosmin (Tc-99m TF) single photon emission computed tomography (SPECT) of head and neck for detecting suspected recurrence of nasopharyngeal carcinomas (NPCs) when magnetic resonance imaging (MRI) findings are indeterminate. MRI was performed 4 months after radiotherapy and 26 NPC patients with indeterminate MRI findings were included. MRI, Tc-99m TF SPECT, and biopsy were performed within 1 week. The final results were based on histopathologic findings and clinical follow-up for at least 6 months. For detecting recurrent NPC in indeterminate MRI findings, the sensitivity, specificity, and accuracy of Tc-99m TF SPECT were 92.3%, 100.0%, and 96.2%, respectively. Based on this result, we can suggest Tc-99m TF SPECT is effective to detect recurrent NPC when MRI findings are indeterminate. However, further studies including a larger NPC patient population are warranted to determine the exact role and clinical usefulness of Tc-99m TF SPECT to differentiate benign lesions and recurrent NPC when MRI findings are indeterminate.

Detection of recurrent nasopharyngeal carcinomas with positron emission tomography using 18-fluoro-2-deoxyglucose in patients with indeterminate magnetic resonance imaging findings after radiotherapy.

The aim of this study was to evaluate the effectiveness of positron emission tomography (PET) using 18-fluoro-2-deoxyglucose (FDG) to detect recurrent nasopharyngeal carcinomas (NPC) when magnetic resonance imaging (MRI) findings are indeterminate. After radiotherapy, 28 NPC patients with indeterminate MRI findings were included. MRI, FDG-PET, and biopsy were performed at least 4 months after radiotherapy and within 1 week. The final results were based on histopathologic findings and a clinical follow-up of at least 6 months. For detecting recurrent NPC in indeterminate MRI findings, the sensitivity, specificity and accuracy of FDG-PET were 100.0%, 92.9% and 96.4%, respectively. Based on these results, we can recommend FDG-PET for detecting recurrent NPC when MRI findings are indeterminate.