Search

Background: This paper reviews recent literature employing Artificial Intelligence/Machine Learning (AI/ML) methods for diagnostic evaluation of head and neck cancers (HNC) using automated image analysis.Methods: Electronic database searches using MEDLINE via OVID, EMBASE and Google Scholar were conducted to retrieve articles using AI/ML for diagnostic evaluation of HNC (2009-2020). No restrictions were placed on the AI/ML method or imaging modality used.Results: In total, 32 articles were identified. HNC sites included oral cavity (n = 16), nasopharynx (n = 3), oropharynx (n = 3), larynx (n = 2), salivary glands (n = 2), sinonasal (n = 1) and in five studies multiple sites were studied. Imaging modalities included histological (n = 9), radiological (n = 8), hyperspectral (n = 6), endoscopic/clinical (n = 5), infrared thermal (n = 1) and optical (n = 1). Clinicopathologic/genomic data were used in two studies. Traditional ML methods were employed in 22 studies (69%), deep learning (DL) in eight studies (25%) and a combination of these methods in two studies (6%).Conclusions: There is an increasing volume of studies exploring the role of AI/ML to aid HNC detection using a range of imaging modalities. These methods can achieve high degrees of accuracy that can exceed the abilities of human judgement in making data predictions. Large-scale multi-centric prospective studies are required to aid deployment into clinical practice. [ABSTRACT FROM AUTHOR]

Background: This paper investigates the difference in survival of melanoma patients across stage and sex by utilising net survival measures. Metrics are presented at both the individual and population level.Methods: Flexible parametric models were fitted to estimate life-expectancy metrics to be applied to a group of 104,938 subjects with a melanoma skin cancer diagnosis from 2000 to 2017. Period analysis was used for better predictions for newly diagnosed patients, and missing-stage information was imputed for 9918 patients. Female relative survival was assigned to male subjects to demonstrate the survival discrepancies experienced between sexes.Results: At the age of 60, males diagnosed at the regional stage lose an average of 4.99 years of life compared to the general population, and females lose 4.79 years, demonstrating the sex variation in expected mortality. In 2017, males contributed 3545 more life years lost than females, and a potential 1931 life years could be preserved if sex differences in survival were eliminated.Conclusions: This study demonstrates the survival differences across population subgroups as a result of a melanoma cancer diagnosis. Females experience better prognosis across age and stage at diagnosis; however, further investigation is necessary to better understand the mechanisms behind this difference. [ABSTRACT FROM AUTHOR]

Background: The increasing incidence of testicular germ cell tumour (TGCT) combined with its strong heritable basis suggests that stratified screening for the early detection of TGCT may be clinically useful. We modelled the efficiency of such a personalised screening approach, based on genetic risk profiling in combination with other diagnostic tools.Methods: We compared the number of cases potentially detectable in the population under a number of screening models. The polygenic risk scoring (PRS) model was assumed to have a log-normal relative risk distribution across the 19 currently known TGCT susceptibility variants. The diagnostic performance of testicular biopsy and non-invasive semen analysis was also assessed, within a simulated combined screening programme.Results: The area under the curve for the TGCT PRS model was 0.72 with individuals in the top 1% of the PRS having a nine-fold increased TGCT risk compared with the population median. Results from population-screening simulations only achieved a maximal positive predictive value (PPV) of 60%, highlighting broader clinical factors that challenge such strategies, not least the rare nature of TGCT. In terms of future improvements, heritability estimates suggest that a significant number of additional genetic risk factors for TGCT remain to be discovered, identification of which would potentially yield improvement of the PPV to 80-90%.Conclusions: While personalised screening models may offer enhanced TGCT risk discrimination, presently the case for population-level testing is not compelling. However, future advances, such as more routine generation of whole genome data is likely to alter the landscape. More targeted screening programs may plausibly then offer clinical benefit, particularly given the significant survivorship issues associated with the successful treatment of TGCT. [ABSTRACT FROM AUTHOR]

Background: This Phase I study evaluated continuous- and intermittent-dosing (every other week) of afatinib plus nintedanib in patients with advanced solid tumours.Methods: In the dose-escalation phase (n=45), maximum tolerated doses (MTDs) were determined for continuous/intermittent afatinib 10, 20, 30 or 40 mg once daily plus continuous nintedanib 150 or 200 mg twice daily. Secondary objectives included safety and efficacy. Clinical activity of continuous afatinib plus nintedanib at the MTD was further evaluated in an expansion phase (n=25).Results: The most frequent dose-limiting toxicities were diarrhoea (11%) and transaminase elevations (7%). Maximum tolerated doses were afatinib 30 mg continuously plus nintedanib 150 mg, and afatinib 40 mg intermittently plus nintedanib 150 mg. Treatment-related adverse events (mostly Grade⩽3) included diarrhoea (98%), asthenia (64%), nausea (62%) and vomiting (60%). In the dose-escalation phase, two patients had partial responses (PRs) and 27 (60%) had stable disease (SD). In the expansion phase, one complete response and three PRs were observed (all non-small cell lung cancer), with SD in 13 (52%) patients. No pharmacokinetic interactions were observed.Conclusions: MTDs of continuous or intermittent afatinib plus nintedanib demonstrated a manageable safety profile with proactive management of diarrhoea. Antitumour activity was observed in patients with solid tumours. [ABSTRACT FROM AUTHOR]

Background: Early detection of non-small-cell lung cancer (NSCLC) and accurate prognostic risk assessment could improve patient outcome. We examined the significance of urinary N(1), N(12)-diacetylspermine (DiAcSpm) in the detection and prognostic stratification of NSCLC patients.Methods: A DiAcSpm/cutoff ratio (DASr) was established for 260 NSCLC patients, 99 benign lung disease patients, and 140 healthy volunteers, using colloidal gold aggregation methods. The DASr was compared between patients and healthy controls, and the prognostic significance of DASr was examined.Results: The median urinary DASr of NSCLC patients was significantly higher than that of healthy controls (0.810 vs 0.534, P<0.001). The DASr was higher in squamous cell carcinoma (SqCC) patients than in adenocarcinoma patients (1.18 vs 0.756, respectively, P=0.039). An increased urinary DASr value was significantly associated with pathological stage, other histological invasive factors and unfavourable outcomes in patients with completely resected NSCLC. Multivariate Cox regression analysis showed that increased urinary DASr was an independent prognostic factor (hazard ratio=4.652, 95% confidence interval (CI), 2.092-10.35; P<0.001).Conclusions: Urinary DASr was significantly increased in NSCLC, especially in SqCC. Urinary DASr was an independent poor prognostic indicator in patients with completely resected NSCLC. The DASr could be a useful biomarker for detecting malignancies and predicting prognosis. [ABSTRACT FROM AUTHOR]

Background: The purpose of this study was to assess the impact of bevacizumab alone and in combination with cytotoxic therapy on tumour vasculature in osteosarcoma (OS) using DCE-MRI.Methods: Six DCE-MRI and three (18)F-FDG PET examinations were scheduled in 42 subjects with newly diagnosed OS to monitor the response to antiangiogenic therapy alone and in combination with cytotoxic therapy before definitive surgery (week 10). Serial DCE-MRI parameters (K(trans), v(p), and v(e)) were examined for correlation with FDG-PET (SUV(max)) and association with drug exposure, and evaluated with clinical outcome.Results: K(trans) (P=0.041) and v(p) (P=0.001) significantly dropped from baseline at 24 h after the first dose of bevacizumab alone, but returned to baseline by 72 h. Greater exposure to bevacizumab was correlated with larger decreases in v(p) at day 5 (P=0.04) and week 10 (P=0.02). A lower K(trans) at week 10 was associated with greater percent necrosis (P=0.024) and longer event-free survival (P=0.034).Conclusions: This is the first study to demonstrate significant changes of the plasma volume fraction and vascular leakage in OS with bevacizumab alone. The combination of demonstrated associations between drug exposure and imaging metrics, and imaging metrics and patient survival during neoadjuvant therapy, provides a compelling rationale for larger studies using DCE-MRI to assess vascular effects of therapy in OS. [ABSTRACT FROM AUTHOR]