Head and neck squamous cell carcinoma (HNSC) patients are at risk of suffering from both pulmonary metastases or a second squamous cell carcinoma of the lung (LUSC). Differentiating pulmonary metastases from primary lung cancers is of high clinical importance, but not possible in most cases with current diagnostics. To address this, we performed DNA methylation profiling of primary tumors and trained three different machine learning methods to distinguish metastatic HNSC from primary LUSC. We developed an artificial neural network that correctly classified 96.4% of the cases in a validation cohort of 279 patients with HNSC and LUSC as well as normal lung controls, outperforming support vector machines (95.7%) and random forests (87.8%). Prediction accuracies of more than 99% were achieved for 92.1% (neural network), 90% (support vector machine), and 43% (random forest) of these cases by applying thresholds to the resulting probability scores and excluding samples with low confidence. As independent clinical validation of the approach, we analyzed a series of 51 patients with a history of HNSC and a second lung tumor, demonstrating the correct classifications based on clinicopathological properties. In summary, our approach may facilitate the reliable diagnostic differentiation of pulmonary metastases of HNSC from primary LUSC to guide therapeutic decisions.
BackgroundAlready in the late 1960s and early 1970s, targeting of the “posterior subthalamic area (PSA)” was explored by different functional neurosurgical groups applying the radiofrequency (RF) technique to treat patients suffering from essential tremor (ET). Recent advances in magnetic resonance (MR)-guided focused ultrasound (MRgFUS) technology offer the possibility to perform thermocoagulation of the cerebellothalamic fiber tract in the PSA without brain penetration, allowing a strong reduction of the procedure-related risks and increased accuracy. We describe here the first results of the MRgFUS cerebellothalamic tractotomy (CTT).MethodsTwenty-one consecutive patients suffering from chronic (mean disease duration 29.9 years), therapy-resistant ET were treated with MRgFUS CTT. Three patients received bilateral treatment with a 1-year interval. Primary relief assessment indicators were the Essential Tremor Rating Scale (Fahn, Tolosa, and Marin) (ETRS) taken at follow-up (3 months to 2 years) with accent on the hand function subscores (HF16 for treated hand and HF32 for both hands) and handwriting. The evolution of seven patients with HF32 above 28 points over 32 (group 1) differentiated itself from the others’ (group 2) and was analyzed separately. Global tremor relief estimations were provided by the patients. Lesion reconstruction and measurement of targeting accuracy were done on 2-day post-treatment MR pictures for each CTT lesion.ResultsThe mean ETRS score for all patients was 57.6 ± 13.2 at baseline and 25.8 ± 17.6 at 1 year (n = 10). The HF16 score reduction was 92 % in group 2 at 3 months and stayed stable at 1 year (90 %). Group 1 showed only an improvement of 41 % at 3 months and 40 % at 1 year. Nevertheless, two patients of group 1 treated bilaterally had an HF16 score reduction of 75 and 88 % for the dominant hand at 1 year after the second side. The mean patient estimation of global tremor relief after CTT was 92 % at 2 days and 77 % at 1-year follow-up.ConclusionsCTT with MRgFUS was shown to be an effective and safe approach for patients with therapy-refractory essential tremor, combining neurological function sparing with precise targeting and the possibility to treat patients bilaterally.
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.