Robust machine learning challenge: An AIFM multicentric competition to spread knowledge, identify common pitfalls and recommend best practice.

Purpose: A novel and unconventional approach to a machine learning challenge was designed to spread knowledge, identify robust methods and highlight potential pitfalls about machine learning within the Medical Physics community.

Methods: A public dataset comprising 41 radiomic features and 535 patients was employed to assess the potential of radiomics in distinguishing between primary lung tumors and metastases. Each participant developed two classification models using: (i) all features (base model); (ii) only robust features (robust model).

Developing an ensemble machine learning study: Insights from a multi-center proof-of-concept study.

Background: To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance.

Microbial electrochemical Cr(VI) reduction in a soil continuous flow system.

Microbial electrochemical technologies represent innovative approaches to contaminated soil and groundwater remediation and provide a flexible framework for removing organic and inorganic contaminants by integrating electrochemical and biological techniques. To simulate in situ microbial electrochemical treatment of groundwater plumes, this study investigates Cr(VI) reduction within a bioelectrochemical continuous flow (BECF) system equipped with soil-buried electrodes, comparing it to abiotic and open-circuit controls. Continuous-flow systems were tested with two chromium-contaminated solutions (20-50 mg Cr(VI)/L).

Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study.

. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters.

Deep learning based joint fusion approach to exploit anatomical and functional brain information in autism spectrum disorders.

Background: The integration of the information encoded in multiparametric MRI images can enhance the performance of machine-learning classifiers. In this study, we investigate whether the combination of structural and functional MRI might improve the performances of a deep learning (DL) model trained to discriminate subjects with Autism Spectrum Disorders (ASD) with respect to typically developing controls (TD).

Material And Methods: We analyzed both structural and functional MRI brain scans publicly available within the ABIDE I and II data collections.

An integrated human health risk assessment framework for alkylphenols due to drinking water and crops' food consumption.

The increasing overexploitation and pollution of freshater resources are potential threats for public health, causing cross-contamination among the interconnected environmental compartments (freshwater, soil, crops). In particular, contaminants of emerging concern (CECs) originating from anthropic activities are not completely removed by wastewater treatments plants. This leads to their presence in drinking water (DW) sources, soil and crops intended for human consumption due to discharges of treated wastewater in surface waters and direct wastewater reuse practices.

Deriving quantitative information from multiparametric MRI via Radiomics: Evaluation of the robustness and predictive value of radiomic features in the discrimination of low-grade versus high-grade gliomas with machine learning.

Purpose: Analysis pipelines based on the computation of radiomic features on medical images are widely used exploration tools across a large variety of image modalities. This study aims to define a robust processing pipeline based on Radiomics and Machine Learning (ML) to analyze multiparametric Magnetic Resonance Imaging (MRI) data to discriminate between high-grade (HGG) and low-grade (LGG) gliomas.

Methods: The dataset consists of 158 multiparametric MRI of patients with brain tumor publicly available on The Cancer Imaging Archive, preprocessed by the BraTS organization committee.

Multi-site harmonization of MRI data uncovers machine-learning discrimination capability in barely separable populations: An example from the ABIDE dataset.

Machine Learning (ML) techniques have been widely used in Neuroimaging studies of Autism Spectrum Disorders (ASD) both to identify possible brain alterations related to this condition and to evaluate the predictive power of brain imaging modalities. The collection and public sharing of large imaging samples has favored an even greater diffusion of the use of ML-based analyses. However, multi-center data collections may suffer the batch effect, which, especially in case of Magnetic Resonance Imaging (MRI) studies, should be curated to avoid confounding effects for ML classifiers and masking biases.

Distinct DNA Methylation Profiles in Ovarian Tumors: Opportunities for Novel Biomarkers.

Aberrant methylation of multiple promoter CpG islands could be related to the biology of ovarian tumors and its determination could help to improve treatment strategies. DNA methylation profiling was performed using the Methylation Ligation-dependent Macroarray (MLM), an array-based analysis. Promoter regions of 41 genes were analyzed in 102 ovarian tumors and 17 normal ovarian samples.

Promoter methylation and downregulated expression of the gene in ovarian carcinoma.

is a gene involved in the development of mesodermal derivatives. As the ovaries and the female reproductive system are of mesodermal origin, the aim of the present study was to determine the methylation status of the gene promoter and the expression levels of in ovarian carcinoma, which is the most lethal and aggressive type of gynecological tumor, in order to determine the role of in the pathogenesis of ovarian carcinoma. This alteration could be used to predict tumor development, progression, recurrence and therapeutic effects.

DNA methylation profiling of esophageal adenocarcinoma using Methylation Ligation-dependent Macroarray (MLM).

Most types of cancer cells are characterized by aberrant methylation of promoter genes. In this study, we described a rapid, reproducible, and relatively inexpensive approach allowing the detection of multiple human methylated promoter genes from many tissue samples, without the need of bisulfite conversion. The Methylation Ligation-dependent Macroarray (MLM), an array-based analysis, was designed in order to measure methylation levels of 58 genes previously described as putative biomarkers of cancer.

Hydrocarbon degrading microbial communities in bench scale aerobic biobarriers for gasoline contaminated groundwater treatment.

BTEX compounds (benzene, toluene, ethylbenzene and xylenes) and methyl tert-butyl ether (MTBE) are some of the main constituents of gasoline and can be accidentally released in the environment. In this work the effect of bioaugmentation on the microbial communities in a bench scale aerobic biobarrier for gasoline contaminated water treatment was studied by 16S rRNA gene sequencing. Catabolic genes (tmoA and xylM) were quantified by qPCR, in order to estimate the biodegradation potential, and the abundance of total bacteria was estimated by the quantification of the number of copies of the 16S rRNA gene.

Lab-scale tests and numerical simulations for in situ treatment of polluted groundwater.

Methyl tert-butyl ether (MTBE) is used at significant percentages as an additive of unleaded gasoline. The physical-chemical properties of the substance (water solubility, soil organic carbon-water partition coefficient) cause high mobility and high concentrations in groundwater. Laboratory scale batch and column tests and mathematical modeling were performed to study the feasibility of a biobarrier (BB), that is an in situ permeable biological barrier with or without inoculation, for the remediation of MTBE and other gasoline-derived pollutants (benzene, toluene, ethylbenzene, o-xylene and m+p-xylenes, BTEXs) polluted groundwater and to estimate kinetic constants.

Bisphenol A, nonylphenols, benzophenones, and benzotriazoles in soils, groundwater, surface water, sediments, and food: a review.

Contaminants of emerging concern (CECs) are not commonly monitored in the environment, but they can enter the environment from a variety of sources. The most worrying consequence of their wide use and environmental diffusion is the increase in the possible exposure pathways for humans. Moreover, knowledge of their behavior in the environment, toxicity, and biological effects is limited or not available for most CECs.

A road pavement full-scale test track containing stabilized bottom ashes.

This paper reports the results of a road pavement full-scale test track built by using stabilized bottom ash (SBA) from an Italian municipal solid waste incinerator as the aggregate in granular foundation, cement-bound mixes and asphalt concretes. The investigation focused on both the performance and the environmental compatibility of such mixes, especially with regard to the effects of mixing, laying and compaction. From the road construction point of view, the performance related to the effects of mixing, laying and compaction on constructability was assessed, as well as the volumetric and the mechanical properties.

Use of stabilized bottom ash for bound layers of road pavements.

This paper reports about the lab scale results obtained by using stabilized bottom ash (SBA) from an Italian municipal solid waste incinerator as aggregates in cement-bound mixes and asphalt concretes for road pavements. The investigation focused on SBA content. From the road construction point of view, performance related to compaction, volumetric and mechanical properties were assessed.

Biobarriers for groundwater treatment: a review.

Biobarriers (BBs) are a new type of in situ technology for the remediation of contaminated groundwater. In recent years, this remediation technique has been more and more used in place of traditional Pump & Treat systems or other in situ technologies both in the USA and Europe. This work reviews the main experiences of BBs.

A pilot study evaluating serum pro-prostate-specific antigen in patients with rising PSA following radical prostatectomy.

[-2]pro-prostate-specific antigen (2pPSA), a proform of PSA, is a new marker in patients at risk of prostate cancer. We explored the potential role of 2pPSA in the identification of patients with metastatic progression following radical prostatectomy for prostate cancer. Seventy-six patients with biochemical (PSA) recurrence following radical prostatectomy were studied retrospectively.

Effect of biochar on the fate of volatile petroleum hydrocarbons in an aerobic sandy soil.

Biochar addition to soil is currently being investigated as a novel technology to remediate polluted sites. A critical consideration is the impact of biochar on the intrinsic microbial pollutant degradation, in particular at sites polluted with a mixture of readily biodegradable and more persistent organic pollutants. We therefore studied the impact of biochar (2% on dry weight basis) on the fate of volatile petroleum hydrocarbons in an aerobic sandy soil with batch and column studies.

Kinetics of monomer biodegradation in soil.

In modern intensive agriculture, plastics are used in several applications (i.e. mulch films, drip irrigation tubes, string, clips, pots, etc.

Feasibility studies for the treatment and reuse of contaminated marine sediments.

This paper presents preliminary results of laboratory tests aimed at evaluating the easibility of the remediation of marine sediments, which are polluted by mercury and petroleum hydrocarbons, dredged at the bay of Augusta (SR, Italy). The treatment is composed of two sequential steps: in the first, a cement-based granular material is produced (based on a high performance concrete approach); then, the volatile and the semi-volatile compounds in the granular material are removed by a thermal desorption step. Treated materials could be reused or put into caissons, according to their mechanical properties and environmental compatibility.

Groundwater remediation by an in situ biobarrier: a bench scale feasibility test for methyl tert-butyl ether and other gasoline compounds.

Most gasoline contains high percentages of methyl tert-butyl ether (MTBE) as an additive. The physico-chemical properties of this substance (high water solubility, low sorption in soil) result in high mobility and dissolved concentrations in soil. In situ permeable biological barriers (biobarriers, BBs) can remediate MTBE polluted groundwater by allowing pure cultures or microbial consortia to degrade MTBE when aerobic conditions are present, either by direct metabolism or cometabolism.

A screening model for fate and transport of biodegradable polyesters in soil.

A numerical model for predicting the fate and transport of biodegradable polyester residues in soil, following successive applications of mulch film, was developed and applied. The polymer, applied on surface soil, was assumed to be converted into by-products (monomers), according to a first order kinetics with constant K(1deg). The monomers released were assumed to sorb on soil organic matter (according to a first-order kinetics with constant K(s)), to be leached with the seepage water, through vertical advection and hydrodynamic dispersion, and biodegraded (according to a first-order kinetics with constant K(b)).

Long-term exposure to dehydroepiandrosterone affects the transcriptional activity of the glucocorticoid receptor.

Although the antiglucocorticoid effects of dehydroepiandrosterone (DHEA) have been demonstrated in vivo in many systems, controversial results have been reported by in vitro studies. In order to elucidate the long-term antiglucocorticoid effects of DHEA in vitro in a context more physiological than what proposed by previous works, we set up a system consisting of a carcinoma cell line relying on endogenously produced glucocorticoid receptor (GR) and stably expressing a reporter gene ErbB-2 under the control of a GR-dependent MMTV promoter. These cells grown in presence of low levels of serum glucocorticoids (GC) showed a basal translocation and activity of endogenous GR.