Prediction of multi-criteria optimization (MCO) parameter efficiency in volumetric modulated arc therapy (VMAT) treatment planning using machine learning (ML)

PurposeTo predict the impact of optimization parameter changes on dosimetric plan quality criteria in multi-criteria optimized volumetric-modulated-arc therapy (VMAT) planning prior to optimization using machine learning (ML).MethodsA data base comprising a total of 21,266 VMAT treatment plans for 44 cranial and 18 spinal patient geometries was generated. The underlying optimization algorithm is governed by three highly composite parameters which model a combination of important aspects of the solution. Patient geometries were parametrized via volume- and shape properties of the voxel objects and overlap-volume histograms (OVH) of the planning-target-volume (PTV) and a relevant organ-at-risk (OAR). The impact of changes in one of the three optimization parameters on the maximally achievable value range of five dosimetric properties of the resulting dose distributions was studied. To predict the extent of this impact based on patient geometry, treatment site, and current parameter settings prior to optimization, three different ML-models were trained and tested. Precision-recall curves, as well as the area-under-curve (AUC) of the resulting receiver-operator-characteristic (ROC) curves were analyzed for model assessment.ResultsSuccessful identification of parameter regions resulting in a high variability of dosimetric plan properties depended on the choice of geometry features, the treatment indication and the plan property under investigation. AUC values between 0.82 and 0.99 could be achieved. The best average-precision (AP) values obtained from the corresponding precision/recall curves ranged from 0.71 to 0.99.ConclusionsMachine learning models trained on a database of pre-optimized treatment plans can help finding relevant optimization parameter ranges prior to optimization.     

Comparison of the RayStation photon Monte Carlo dose calculation algorithm against measured data under homogeneous and heterogeneous irradiation geometries

PurposeThis work compares Monte Carlo dose calculations performed using the RayStation treatment planning system against data measured on a Varian Truebeam linear accelerator with 6 MV and 10 MV FFF photon beams.MethodsThe dosimetric performance of the RayStation Monte Carlo calculations was evaluated in a variety of irradiation geometries employing homogeneous and heterogeneous phantoms. Profile and depth dose comparisons against measurement were carried out in relative mode using the gamma index as a quantitative measure of similarity within the central high dose regions.ResultsThe results demonstrate that the treatment planning system dose calculation engine agrees with measurement to within 2%/1 mm for more than 95% of the data points in the high dose regions for all test cases. A systematic underestimation was observed at the tail of the profile penumbra and out of field, with mean differences generally <0.5 mm or 1% of curve dose maximum respectively. Out of field agreement varied between evaluated beam models.ConclusionsThe RayStation implementation of photon Monte Carlo dose calculations show good agreement with measured data for the range of scenarios considered in this work and is deemed sufficiently accurate for introduction into clinical use.     

Automatic VMAT technique to treat glioblastoma: A two years’ experience

PurposeThe present work aims to guide the physicist in order to start automated planning for the VMAT treatment of glioblastoma multiforme (GBM) by giving a recipe that was set up and tested during a long-term (two years) evaluation.MethodsAn automatic technique in AutoPlanning module of the Pinnacle3 (Philips Medical Systems, Fitchburg, WI) treatment planning system was created and validated by comparing dose distributions of automatic plans (APs) and manual plans (MPs) and by performing a blind AP-MP comparison on a cohort of 20 patients. Automatic technique was then applied to 145 patients and failures were recorded i.e. the number of times for which dose distributions produced by the automatic module were not suitable for treatment.ResultsEach of the 20 APs considered in the validation step was clinically acceptable and proved to be better (15 cases) or equal (5 cases) respect to MPs. A statistically significant improvement in brain stem, optic pathways, cochleae, pituitary gland and scalp sparing was observed for APs, while no statistically significant differences were recorded in target coverage or plan parameters. For only 5 cases out of the 145 plans the operator intervention was needed in order to obtain a clinical acceptable plan, while for the remaining 140 plans the automatic created solution was suitable.ConclusionsA straightforward automatic procedure has been created and tested in our clinic. The AutoPlanning technique proposed represents a reliable tool to improve treatment planning efficiency and the recipe, here presented, could be simply imported to every radiotherapy center.     

Integrating GIS and expert judgment in a multi-criteria analysis to map and develop a habitat suitability index: A case study of large mammals on the Malayan Peninsula

Many habitat patches in tropical landscapes have become less suitable for wildlife due to an increase in anthropogenic disturbances. An index of habitat suitability based on the ecological factors that collectively determine the suitability of an organism's habitat is important for conservation planning. However, a widely accepted and comprehensive multi-criteria habitat suitability index for umbrella species is still lacking, particularly in areas where information related to the biology and ecology of the species of interest is not available. Therefore we develop preliminary habitat maps and measure the degree of habitat suitability for large mammals, focusing on four umbrella species in the State of Selangor, Peninsular Malaysia: Panthera tigris jacksoni (Malayan tiger), Tapirus indicus (Malayan tapir), Helarctos malayanus malayanus (Malayan sun bear), and Rusa unicolor cambojensis (sambar deer). The former two are endangered and the latter two are vulnerable according to the IUCN Red List. The suitability of habitat patches for each species was measured across the entire study area as well as in nine wildlife protected areas by integrating GIS data and expert opinion. Expert opinions were used as the source of information regarding the stresses faced by the species because there was insufficient information available from ground surveys.We developed an index and maps of habitat suitability for each species, which were then integrated to represent a combined index (ranging from 0 to 27) and spatially explicit maps of the area's habitat suitability for large mammals. The average large mammal habitat suitability index value of the State of Selangor (9) indicates that many habitat patches have become unsuitable for such species. Of the nine wildlife protected areas, Fraser's Hill (22), Sungai Dusun (22), and Bukit Kutu (21) are very suitable; Klang Gate (20) and Templers Park (17) are suitable; and the remaining four are unsuitable for large mammals. We assume that this preliminary habitat suitability index and mapping are useful for conservation planning of wildlife habitats at both landscape and regional scales, as well as providing an initial foundation for revision by future research with significant new information.     

Functional imaging in radiation therapy planning for head and neck cancer

Functional imaging and its application to radiotherapy (RT) is a rapidly expanding field with new modalities and techniques constantly developing and evolving. As technologies improve, it will be important to pay attention to their implementation. This review describes the main achievements in the field of head and neck cancer (HNC) with particular remarks on the unsolved problems.     

Managing sun bears in a changing tropical landscape

Aim

Across the tropics, large‐bodied mammal species are threatened by rapid and widespread forest habitat conversion by either commercial logging or agricultural expansion. How such species use these habitats is an important area of research for guiding their future management. The tropical forest‐dwelling sun bear, Helarctos malayanus, is the least known of the eight bear species. Consequently, the IUCN/SSC Bear Specialist Group ranks research on this species as a top priority. This study aims to investigate landscape variables that influence sun bear habitat use in forests under varying levels of degradation and protection.

Location

A 20,998 km² Sumatra forest landscape covering Kerinci Seblat National Park (KSNP), Batang Hari Protection Forest (BHPF) and neighbouring logging and agricultural concessions.

Methods

An occupancy‐based sampling technique using detection/non‐detection data with 10 landscape covariates was applied in six study areas that operated a total of 125 camera traps. The potential differences between habitat use (ψ) of sun bears were first modelled with broad‐scale covariates of study area, land‐use types and forest type. Sun bear habitat use was then investigated with the finer‐scale landscape features associated within these areas.

Results

From 10,935 trap nights, sun bears were recorded at altitudes ranging from 365 to 1791 m. At a broad‐scale, habitat use increased with protection status, being highest in KSNP (0.688 ± 0.092, ± SE) and BHPF (0.621 ± 0.110) compared to production (0.418 ± 0.121) and convertible (0.286 ± 0.122) forests. Within these areas, sun bears showed a preference for forest that was further from public roads and villages and at a lower elevation.

Main conclusions

The habitat suitability model identified several high‐quality habitat patches outside of the priority conservation areas for immediate protection. Consequently, conservation management strategies should emphasize the importance of high conservation value forests and prohibit further conversion of threatened lowland forests.

     

Conservation implications of divergent global patterns of ant and vertebrate diversity

Aim

Global conservation planning is often oriented around vertebrates and plants, yet most organisms are invertebrates. To explore the potential conservation implications of this bias, we assessed how well patterns of diversity for an influential group of invertebrates, the ants, correspond with those of three vertebrate groups (birds, mammals and amphibians).

Location

Global.

Methods

We compiled data on the number of genera of ants and the three vertebrate groups for 370 political regions across the world. We then compared their correlations both for overall diversity and between subsets of genera likely to be of conservation concern. We also developed generalized additive models (GAM) to identify regions where vertebrates and ants diverged in their diversity patterns.

Results

While ant and vertebrate diversity do positively correlate, the correlations are substantially weaker for the ant lineages of the greatest conservation concern. Vertebrates also notably fail to predict ant diversity in specific geographic areas, including Australia and Southeast Asia, parts of Africa and Madagascar, and south‐western China. These failures may be genuine differences in diversity patterns, or they may indicate important gaps in our knowledge of ant and vertebrate diversity.

Main conclusions

We conclude that it is currently unwise to assume that global conservation priorities based on vertebrates will conserve ants as well. We suspect that this also applies to other invertebrates.

     

Core concepts of spatial prioritisation in systematic conservation planning

Systematic conservation planning (SCP) is a field of conservation biology concerned with delivering on‐the‐ground actions that achieve conservation goals. It describes a set of operational models that cover both design and implementation of conservation, with a strong focus on mobilising the collective action typically required to implement conservation. SCP, as it was originally described, was composed of six different stages: collection of data, identification of conservation goals, evaluation of the existing protected area network, design of expansions, implementation of conservation action, and long‐term maintenance of biodiversity in the network. Since then, the operational model has been expanded into several different variants. Conservation actions applied inside SCP include establishment and expansion of reserve networks and allocation of habitat restoration and management. Within the broader context of SCP, there is a fundamental biogeographic‐economic analysis frequently called spatial conservation prioritisation or conservation assessment, which is used for identifying where important areas for biodiversity are and how conservation goals might be achieved efficiently. Here, we review the usage and meaning of the 12 biogeographic‐economic core concepts of SCP: adequacy, complementarity, comprehensiveness, effectiveness, efficiency, flexibility, irreplaceability, replacement cost, representation, representativeness, threat, and vulnerability. Some of the concepts have clear definitions whereas others may have alternative and possibly conflicting definitions. With a comprehensive literature review literature, we elucidate the historical backgrounds of these concepts, the first definitions and usages, alternative later definitions, key applications, and prior reviews. This review reduces linguistic uncertainty in the application of SCP. Since SCP is a global activity with a multitude of different stakeholders involved, it is vital that those involved can speak the same language. Through these concepts, this review serves as a source of information about the historical development of SCP. It provides a comprehensive review for anyone wishing to understand the key concepts of spatial prioritisation within SCP.     

Wildlife conservation planning under the United States Forest Service's 2012 planning rule

In 2012, the United States Forest Service (USFS) promulgated new planning regulations in accordance with the National Forest Management Act (NFMA). These regulations represent the most significant change in federal forest policy in decades and have sweeping implications for wildlife populations. We provide a brief overview of the history of the NFMA planning regulations and their wildlife provisions and review the current science on planning for effective wildlife conservation at the landscape scale. We then discuss the approach to wildlife conservation planning in the 2012 rule and compare it to alternatives that were not selected and previous iterations of the planning rule. The new planning rule is of concern because of its highly discretionary nature and the inconsistency between its intent on the one hand and operational requirements on the other. Therefore, we recommend that the USFS include in the Directives for implementing the rule commitments to directly monitor populations of selected species of conservation concern and focal species and to maintain the viability of both categories of species. Additional guidance must be included to ensure the effective selection of species of conservation concern and focal species, and these categories should overlap when possible. If the USFS determines that the planning unit is not inherently capable of maintaining viable populations of a species, this finding should be made available for scientific review and public comment, and in such cases the USFS should commit to doing nothing that would further impair the viability of such species. In cases where extrinsic factors decrease the viability of species, the USFS has an increased, not lessened, responsibility to protect those species. Monitoring plans must include trigger points that will initiate a review of management actions, and plans must include provisions to ensure monitoring takes place as planned. If wildlife provisions in forest plans are implemented so that they are enforceable and ensure consistency between intent and operational requirements, this will help to prevent the need for additional listings under the Endangered Species Act and facilitate delisting. Although the discretionary nature of the wildlife provisions in the planning rule gives cause for concern, forward-thinking USFS officials have the opportunity under the 2012 rule to create a robust and effective framework for wildlife conservation planning. © 2013 The Wildlife Society.     

Short-term disturbance by a commercial two-dimensional seismic survey does not lead to long-term displacement of harbour porpoises

Assessments of the impact of offshore energy developments are constrained because it is not known whether fine-scale behavioural responses to noise lead to broader-scale displacement of protected small cetaceans. We used passive acoustic monitoring and digital aerial surveys to study changes in the occurrence of harbour porpoises across a 2000 km² study area during a commercial two-dimensional seismic survey in the North Sea. Acoustic and visual data provided evidence of group responses to airgun noise from the 470 cu inch array over ranges of 5–10 km, at received peak-to-peak sound pressure levels of 165–172 dB re 1 µPa and sound exposure levels (SELs) of 145–151 dB re 1 µPa² s⁻¹. However, animals were typically detected again at affected sites within a few hours, and the level of response declined through the 10 day survey. Overall, acoustic detections decreased significantly during the survey period in the impact area compared with a control area, but this effect was small in relation to natural variation. These results demonstrate that prolonged seismic survey noise did not lead to broader-scale displacement into suboptimal or higher-risk habitats, and suggest that impact assessments should focus on sublethal effects resulting from changes in foraging performance of animals within affected sites.