Germline BRCA 1-2 status prediction through ovarian ultrasound images radiogenomics: a hypothesis generating study (PROBE study)

Nero, Camilla; Ciccarone, Francesca; Boldrini, Luca; Lenkowicz, Jacopo; Paris, Ida; Capoluongo, Ettore; Testa, Antonia Carla; Fagotti, Anna; Valentini, Vincenzo; Scambia, Giovanni

doi:10.1038/s41598-020-73505-2

Cited by 23 publications

(24 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, radiomics and radiogenomics, may play a significant role thanks to the quantitative noninvasive and repeatable analysis of standard clinical imaging that encompasses the whole tumor volume, taking into account the hetMNA. Radiomics features may be associated with specific molecular pathways or mutations, offering reliable predictive tools for clinicians in breast cancer [20], glioma [14], lung cancer [15,21] and even in healthy tissue [22]. Furthermore, CT represent the most common modality used to diagnose and stage NB and for this reason the images are easily accessible even for retrospective analysis.…”

Section: Discussionmentioning

confidence: 99%

Radiogenomics prediction for MYCN amplification in Neuroblastoma: a hypothesis generating study

Giannatale

Paolo

Curione

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: MYCN amplification represents a powerful prognostic factor in neuroblastoma (NB) and may occasionally account for intratumoral heterogeneity. Radiomics is an emerging field of advanced image analysis that aims to extract a large number of quantitative features from standard radiological images, providing valuable clinical information Procedure: In this retrospective study, we aimed to create a radiogenomics model by correlating computed tomography (CT) radiomics analysis with MYCN status and overall survival (OS). NB lesions were segmented on pre-therapy CT scans and radiomics features subsequently extracted using a dedicated library. Dimensionality reduction/features selection approaches were then used for features procession and logistic regression models have been developed for the considered outcome. Results: Seventy-eight patients were included in this study, 24 presented MYCN amplification. In total, 232 radiomics features were extracted. Eight features were selected through Boruta algorithm and 2 features were lastly chosen through Pearson correlation analysis: mean of voxel intensity histogram (p=0.0082) and zone size non-uniformity (p=0.038). Five-times repeated 3-fold cross-validation logistic regression models yielded an Area Under the Curve (AUC) value of 0.879 on the training and 0.865 on the testing set for MYCN. No statistical significant difference has been observed comparing radiomics predicted and actual OS data. Conclusions: CT based radiomics is able to predict MYCN amplification status and OS in NB, paving the way to the in depth analysis of imaging based biomarkers that could enhance outcomes prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Radiogenomics prediction for MYCN amplification in Neuroblastoma: a hypothesis generating study

Giannatale

Paolo

Curione

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Non-parametric algorithms, by using a number of parameters which is not limited, are usually slower and require larger dataset. These include classification and Regression Trees (CART) [13,14], K-Nearest Neighbours (KNN) [15,16], and Support Vector Machines (SVM). SVM, based on finding a hyperplane that best divides the data into two classes in the feature space, is among most popular ML algorithm and is employed for both classification [7,10,[17][18][19][20] and regression [16].…”

Section: Machine Learning and Deep Learning In Imagingmentioning

confidence: 99%

Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy

Avanzo

Porzio²,

Lorenzon

et al. 2021

Physica Medica

View full text Add to dashboard Cite

To perform a systematic review on the research on the application of artificial intelligence (AI) to imaging published in Italy and identify its fields of application, methods and results. Materials and Methods: A Pubmed search was conducted using terms Artificial Intelligence, Machine Learning, Deep learning, imaging, and Italy as affiliation, excluding reviews and papers outside time interval 2015-2020. In a second phase, participants of the working group AI4MP on Artificial Intelligence of the Italian Association of Physics in Medicine (AIFM) searched for papers on AI in imaging. Results: The Pubmed search produced 794 results. 168 studies were selected, of which 122 were from Pubmed search and 46 from the working group. The most used imaging modality was MRI (44%) followed by CT(12%) ad radiography/mammography (11%). The most common clinical indication were neurological diseases (29%) and diagnosis of cancer (25%). Classification was the most common task for AI (57%) followed by segmentation (16%). 65% of studies used machine learning and 35% used deep learning. We observed a rapid increase of research in Italy on artificial intelligence in the last 5 years, peaking at 155% from 2018 to 2019.

show abstract

“…In breast cancer, testing of tumour biopsy now makes it possible to identify certain mutations that drive treatment resistance, permitting better risk assessment and aiding the search for targeted therapies [ 11 ]. In ovarian cancer, germline mutations in BRCA1 and BRCA2 may support identification of potentially at-risk family members through cascade testing, or the offer of germline testing to the direct family members of a positive patient [ 12 , 13 ]. The homologous recombination deficiency (HRD) testing [ 14 ] which incorporates new genomic instability assessment algorithms, offers the opportunity to enhance the utility for BRCA testing in ovarian, breast, pancreatic and other cancers [ 14 ].…”

Section: Biomarkers In Action: Clinical Use Casesmentioning

confidence: 99%

“…In thyroid cancer, knowing the oncogenic molecular driver helps to determine the aggressiveness of the tumour and/or to identify the most appropriate systemic or targeted therapy [ 11 ]. Across the entire range of cancer—“pan-cancer” as well as tumour agnostics—there is potential in the integration of molecular information, identifying actionable mutations with broad molecular profiling, matching the right targeted therapy to the detected actionable mutation, and evaluating treatment outcome [ 5 , 12 ]. Applications combining testing using next generation sequencing with artificial intelligence and machine learning may ultimately help chart entire clinical pathways [ 12 ].…”

Section: Biomarkers In Action: Clinical Use Casesmentioning

confidence: 99%

Bringing Onco-Innovation to Europe’s Healthcare Systems: The Potential of Biomarker Testing, Real World Evidence, Tumour Agnostic Therapies to Empower Personalised Medicine

Horgan¹,

Ciliberto

Conte

et al. 2021

Cancers

View full text Add to dashboard Cite

Rapid and continuing advances in biomarker testing are not being matched by uptake in health systems, and this is hampering both patient care and innovation. It also risks costing health systems the opportunity to make their services more efficient and, over time, more economical. The potential that genomics has brought to biomarker testing in diagnosis, prediction and research is being realised, pre-eminently in many cancers, but also in an ever-wider range of conditions—notably BRCA1/2 testing in ovarian, breast, pancreatic and prostate cancers. Nevertheless, the implementation of genetic testing in clinical routine setting is still challenging. Development is impeded by country-related heterogeneity, data deficiencies, and lack of policy alignment on standards, approval—and the role of real-world evidence in the process—and reimbursement. The acute nature of the problem is compellingly illustrated by the particular challenges facing the development and use of tumour agnostic therapies, where the gaps in preparedness for taking advantage of this innovative approach to cancer therapy are sharply exposed. Europe should already have in place a guarantee of universal access to a minimum suite of biomarker tests and should be planning for an optimum testing scenario with a wider range of biomarker tests integrated into a more sophisticated health system articulated around personalised medicine. Improving healthcare and winning advantages for Europe’s industrial competitiveness and innovation require an appropriate policy framework—starting with an update to outdated recommendations. We show herein the main issues and proposals that emerged during the previous advisory boards organised by the European Alliance for Personalized Medicine which mainly focus on possible scenarios of harmonisation of both oncogenetic testing and management of cancer patients.

show abstract

Germline BRCA 1-2 status prediction through ovarian ultrasound images radiogenomics: a hypothesis generating study (PROBE study)

Cited by 23 publications

References 50 publications

Radiogenomics prediction for MYCN amplification in Neuroblastoma: a hypothesis generating study

Radiogenomics prediction for MYCN amplification in Neuroblastoma: a hypothesis generating study

Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy

Bringing Onco-Innovation to Europe’s Healthcare Systems: The Potential of Biomarker Testing, Real World Evidence, Tumour Agnostic Therapies to Empower Personalised Medicine

Contact Info

Product

Resources

About