The value of positron emission tomography in early detection of lung cancer in high-risk population: a systematic review

Identification of Tumor-Specific MRI Biomarkers Using Machine Learning (ML)

The identification of reliable and non-invasive oncology biomarkers remains a main priority in healthcare. There are only a few biomarkers that have been approved as diagnostic for cancer. The most frequently used cancer biomarkers are derived from either biological materials or imaging data. Most cancer biomarkers suffer from a lack of high specificity. However, the latest advancements in machine learning (ML) and artificial intelligence (AI) have enabled the identification of highly predictive, disease-specific biomarkers. Such biomarkers can be used to diagnose cancer patients, to predict cancer prognosis, or even to predict treatment efficacy. Herein, we provide a summary of the current status of developing and applying Magnetic resonance imaging (MRI) biomarkers in cancer care. We focus on all aspects of MRI biomarkers, starting from MRI data collection, preprocessing and machine learning methods, and ending with summarizing the types of existing biomarkers and their clinical applications in different cancer types.

Validated imaging biomarkers as decision-making tools in clinical trials and routine practice: current status and recommendations from the EIBALL* subcommittee of the European Society of Radiology (ESR)

Observer-driven pattern recognition is the standard for interpretation of medical images. To achieve global parity in interpretation, semi-quantitative scoring systems have been developed based on observer assessments; these are widely used in scoring coronary artery disease, the arthritides and neurological conditions and for indicating the likelihood of malignancy. However, in an era of machine learning and artificial intelligence, it is increasingly desirable that we extract quantitative biomarkers from medical images that inform on disease detection, characterisation, monitoring and assessment of response to treatment. Quantitation has the potential to provide objective decision-support tools in the management pathway of patients. Despite this, the quantitative potential of imaging remains under-exploited because of variability of the measurement, lack of harmonised systems for data acquisition and analysis, and crucially, a paucity of evidence on how such quantitation potentially affects clinical decision-making and patient outcome. This article reviews the current evidence for the use of semi-quantitative and quantitative biomarkers in clinical settings at various stages of the disease pathway including diagnosis, staging and prognosis, as well as predicting and detecting treatment response. It critically appraises current practice and sets out recommendations for using imaging objectively to drive patient management decisions.

Low-dose computed tomography for lung cancer screening in high-risk populations: a systematic review and economic evaluation

BACKGROUND

Diagnosis of lung cancer frequently occurs in its later stages. Low-dose computed tomography (LDCT) could detect lung cancer early.

OBJECTIVES

To estimate the clinical effectiveness and cost-effectiveness of LDCT lung cancer screening in high-risk populations.

DATA SOURCES

Bibliographic sources included MEDLINE, EMBASE, Web of Science and The Cochrane Library.

METHODS

Clinical effectiveness - a systematic review of randomised controlled trials (RCTs) comparing LDCT screening programmes with usual care (no screening) or other imaging screening programmes [such as chest X-ray (CXR)] was conducted. Bibliographic sources included MEDLINE, EMBASE, Web of Science and The Cochrane Library. Meta-analyses, including network meta-analyses, were performed. Cost-effectiveness - an independent economic model employing discrete event simulation and using a natural history model calibrated to results from a large RCT was developed. There were 12 different population eligibility criteria and four intervention frequencies [(1) single screen, (2) triple screen, (3) annual screening and (4) biennial screening] and a no-screening control arm.

RESULTS

Clinical effectiveness - 12 RCTs were included, four of which currently contribute evidence on mortality. Meta-analysis of these demonstrated that LDCT, with ≤ 9.80 years of follow-up, was associated with a non-statistically significant decrease in lung cancer mortality (pooled relative risk 0.94, 95% confidence interval 0.74 to 1.19). The findings also showed that LDCT screening demonstrated a non-statistically significant increase in all-cause mortality. Given the considerable heterogeneity detected between studies for both outcomes, the results should be treated with caution. Network meta-analysis, including six RCTs, was performed to assess the relative clinical effectiveness of LDCT, CXR and usual care. The results showed that LDCT was ranked as the best screening strategy in terms of lung cancer mortality reduction. CXR had a 99.7% probability of being the worst intervention and usual care was ranked second. Cost-effectiveness - screening programmes are predicted to be more effective than no screening, reduce lung cancer mortality and result in more lung cancer diagnoses. Screening programmes also increase costs. Screening for lung cancer is unlikely to be cost-effective at a threshold of £20,000/quality-adjusted life-year (QALY), but may be cost-effective at a threshold of £30,000/QALY. The incremental cost-effectiveness ratio for a single screen in smokers aged 60-75 years with at least a 3% risk of lung cancer is £28,169 per QALY. Sensitivity and scenario analyses were conducted. Screening was only cost-effective at a threshold of £20,000/QALY in only a minority of analyses.

LIMITATIONS

Clinical effectiveness - the largest of the included RCTs compared LDCT with CXR screening rather than no screening. Cost-effectiveness - a representative cost to the NHS of lung cancer has not been recently estimated according to key variables such as stage at diagnosis. Certain costs associated with running a screening programme have not been included.

CONCLUSIONS

LDCT screening may be clinically effective in reducing lung cancer mortality, but there is considerable uncertainty. There is evidence that a single round of screening could be considered cost-effective at conventional thresholds, but there is significant uncertainty about the effect on costs and the magnitude of benefits.

FUTURE WORK

Clinical effectiveness and cost-effectiveness estimates should be updated with the anticipated results from several ongoing RCTs [particularly the NEderlands Leuvens Longkanker Screenings ONderzoek (NELSON) screening trial].

STUDY REGISTRATION

This study is registered as PROSPERO CRD42016048530.

FUNDING

The National Institute for Health Research Health Technology Assessment programme.

[(18)F]Fluorodeoxyglucose-positron emission tomography screening for lung cancer: a systematic review and meta-analysis

Rationale and objectives: Although low-dose computed tomography (CT) is a recommended modality for lung cancer screening in high-risk populations, the role of other modalities, such as [¹⁸F]fluorodeoxyglucose-positron emission tomography (PET), is unclear. We conducted a systematic review to describe the role of PET in lung cancer screening. Materials and methods: A systematic review was conducted by reviewing primary studies focusing on PET screening for lung cancer until July 2012. Two independent reviewers identified studies that were compatible for inclusion/exclusion criteria. The analysis was restricted to English and included studies published since 2000. A descriptive analysis was used to summarize the results, and the pooled diagnostic performance of selective PET screening was calculated by weighted average using individual sample sizes. Results: Among the identified studies (n = 3497), 12 studies were included for analysis. None of the studies evaluated the efficacy of primary PET screening specific to lung cancer. Eight studies focused on primary PET screening for all types of cancer; the detection rates of lung cancer were low. Four studies reported evidence of lung cancer screening programs with selective PET, in which the estimated pooled sensitivity and specificity was 83% and 91%, respectively. Conclusions: The role of primary PET screening for lung cancer remains unknown. However, PET has high sensitivity and specificity as a selective screening modality. Further studies must be conducted to evaluate the use of PET or PET/computed tomography screening for high-risk populations, preferably using randomized trials or prospective registration. Advances in knowledge: Our meta-analysis indicates that PET has high sensitivity and specificity as a selective screening modality.

Simplified programming and control of automated radiosynthesizers through unit operations

Background

Many automated radiosynthesizers for producing positron emission tomography (PET) probes provide a means for the operator to create custom synthesis programs. The programming interfaces are typically designed with the engineer rather than the radiochemist in mind, requiring lengthy programs to be created from sequences of low-level, non-intuitive hardware operations. In some cases, the user is even responsible for adding steps to update the graphical representation of the system. In light of these unnecessarily complex approaches, we have created software to perform radiochemistry on the ELIXYS radiosynthesizer with the goal of being intuitive and easy to use.

Methods

Radiochemists were consulted, and a wide range of radiosyntheses were analyzed to determine a comprehensive set of basic chemistry unit operations. Based around these operations, we created a software control system with a client–server architecture. In an attempt to maximize flexibility, the client software was designed to run on a variety of portable multi-touch devices. The software was used to create programs for the synthesis of several ¹⁸F-labeled probes on the ELIXYS radiosynthesizer, with [¹⁸F]FDG detailed here. To gauge the user-friendliness of the software, program lengths were compared to those from other systems. A small sample group with no prior radiosynthesizer experience was tasked with creating and running a simple protocol.

Results

The software was successfully used to synthesize several ¹⁸F-labeled PET probes, including [¹⁸F]FDG, with synthesis times and yields comparable to literature reports. The resulting programs were significantly shorter and easier to debug than programs from other systems. The sample group of naive users created and ran a simple protocol within a couple of hours, revealing a very short learning curve. The client–server architecture provided reliability, enabling continuity of the synthesis run even if the computer running the client software failed. The architecture enabled a single user to control the hardware while others observed the run in progress or created programs for other probes.

Conclusions

We developed a novel unit operation-based software interface to control automated radiosynthesizers that reduced the program length and complexity and also exhibited a short learning curve. The client–server architecture provided robustness and flexibility.