NEWS 2019

Radiomics Analysis for Clinical Decision Support in Nuclear Medicine
Radiomics – the high-throughput computation of quantitative image features extracted from medical imaging modalities- can be used to aid clinical decision support systems in order to build diagnostic, prognostic, and predictive models, which could ultimately improve personalized management based on individual characteristics. Various tools for radiomic features extraction are available, and the field gained a substantial scientific momentum for standardization and validation. Radiomics analysis of molecular imaging is expected to provide more comprehensive description of tissues than that of currently used parameters. A group of researchers including PREDICT ESR Sergey Primakov reviewed the workflow of radiomics, the challenges the field currently faces, and its potential for inclusion in clinical decision support systems to maximize disease characterization, and to improve clinical decision-making. They also present guidelines for standardization and implementation of radiomics in order to facilitate its transition to clinical use.

An article detailing this work was published in September 2019 in Seminars in Nuclear Medicine.

Radiomic features derived from FDG PET are independently associated with LC in patients with NSCLC undergoing SBRT and could therefore be combined in an accurate predictive model
Non‐small cell cancer (NSCLC) is usually associated with a poor prognosis. Over the past two decades, technological developments in target delineation, motion management, conformal treatment planning and daily image guidance have allowed the development of stereotactic body radiation therapy (SBRT). SBRT uses stereotactic targeting to facilitate the accurate delivery of a short course of high‐dose radiation to the target. SBRT has demonstrated high local control (LC) rates (85‐90%), comparable to those obtained with surgery in multiple prospective trials and is now a guideline‐recommended treatment for patients with early stage NSCLC who are medically unfit or unwilling to undergo surgery. Approximately 16% of patients present with early‐stage cT1‐T2 N0 disease at diagnosis.  Amongst these patients, therapeutic results are nonetheless highly variable, and new predictive factors of response to SBRT are needed to better individualize treatment.  Radiomic features are handcrafted metrics used to quantify tumour intensity, shape and heterogeneity, some of which have been shown to reflect intratumoural histopathological properties and to predict patients’ outcome in several pathologies including NSCLC when extracted from FDG PET, CT, or both.  In this retrospective study a group of researchers amongs whom PREDICT ESR Ronrick Da‐ano found that two radiomic features derived from FDG PET were independently associated with LC in patients with NSCLC undergoing SBRT and could be combined in an accurate predictive model. This model could provide local relapse‐related information and could be helpful in clinical decision‐making. 

An article detailing this discovery was published on November 15 in the Journal of Nuclear Medicine.


NEWS 2020


Deep learning in fracture detection: a narrative review
Artificial intelligence (AI) is a general term that implies the use of a computer to model intelligent behavior with minimal human intervention. AI, particularly deep learning, has recently made substantial strides in perception tasks allowing machines to better represent and interpret complex data. Deep learning is a subset of AI represented by the combination of artificial neuron layers. In the last years, deep learning has gained great momentum. In the field of orthopaedics and traumatology, some studies have been done using deep learning to detect fractures in radiographs. Deep learning studies to detect and classify fractures on computed tomography (CT) scans are even more limited. In this narrative review, PREDICT ESR Sergey Primakov together with colleagues provides a brief overview of deep learning technology: (1) they describe the ways in which deep learning until now has been applied to fracture detection on radiographs and CT examinations; (2) discuss what value deep learning offers to this field; and finally (3) comment on future directions of this technology.

An article describing this review was published on January 13 in Acta Orthopaedica.

The article:

Radiomics: from qualitative to quantitative imaging
Historically, medical imaging has been a qualitative or semi-quantitative modality. It is difficult to quantify what can be seen in an image, and to turn it into valuable predictive outcomes. As a result of advances in both computational hardware and machine learning algorithms, computers are making great strides in obtaining quantitative information from imaging and correlating it with outcomes. Radiomics, in its two forms "handcrafted and deep," is an emerging field that translates medical images into quantitative data to yield biological information and enable radiologic phenotypic profiling for diagnosis, theragnosis, decision support, and monitoring. Handcrafted radiomics is a multistage process in which features based on shape, pixel intensities, and texture are extracted from radiographs. Within this review, PREDICT ESR's William Rogers, Sithin Thulasi, Sergey Primakov, Manon Beuque, Fadila Zerka together with colleagues describe the steps: starting with quantitative imaging data, how it can be extracted, how to correlate it with clinical and biological outcomes, resulting in models that can be used to make predictions, such as survival, or for detection and classification used in diagnostics. The application of deep learning, the second arm of radiomics, and its place in the radiomics workflow is discussed, along with its advantages and disadvantages. To better illustrate the technologies being used, we provide real-world clinical applications of radiomics in oncology, showcasing research on the applications of radiomics, as well as covering its limitations and its future direction.

This review was published February 26 2020 in The British Journal of Radiology.

MARCH 2020
Systematic Review of Privacy-Preserving Distributed Machine Learning From Federated Databases in Health Care
Big data for health care is one of the potential solutions to deal with the numerous challenges of health care, such as rising cost, aging population, precision medicine, universal health coverage, and the increase of noncommunicable diseases. However, data centralization for big data raises privacy and regulatory concerns. Covered topics include (1) an introduction to privacy of patient data and distributed learning as a potential solution to preserving these data, a description of the legal context for patient data research, and a definition of machine/deep learning concepts; (2) a presentation of the adopted review protocol; (3) a presentation of the search results; and (4) a discussion of the findings, limitations of the review, and future perspectives. One can learn from separate and isolated datasets without patient data ever leaving the individual clinical institutes. Distributed learning promises great potential to facilitate big data for medical application, in particular for international consortiums. PREDICT ESR Fadila Zerka and colleagues reviewed the major implementations of distributed learning in health care.

This review was published on March 5 in JCO Clinical Cancer Informatics.

JUNE 2020
Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies
A group of researchers among with ESR Ronrick Da-ano found that multicenter studies are needed to demonstrate the clinical potential value of radiomics as a prognostic tool. However, variability in scanner models, acquisition protocols and reconstruction settings are unavoidable and radiomic features are notoriously sensitive to these factors, which hinders pooling them in a statistical analysis. A statistical harmonization method called ComBat was developed to deal with the “batch effect” in gene expression microarray data and was used in radiomics studies to deal with the “center-effect”. Their goal was to evaluate modifications in ComBat allowing for more flexibility in choosing a reference and improving robustness of the estimation. Two modified ComBat versions were evaluated: M-ComBat allows to transform all features distributions to a chosen reference, instead of the overall mean, providing more flexibility. B-ComBat adds bootstrap and Monte Carlo for improved robustness in the estimation. BM-ComBat combines both modifications. The four versions were compared regarding their ability to harmonize features in a multicenter context in two different clinical datasets. The first contains 119 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging and positron emission tomography imaging. In that case ComBat was applied with 3 labels corresponding to each center. The second one contains 98 locally advanced laryngeal cancer patients from 5 centers with contrast-enhanced computed tomography. In that specific case, because imaging settings were highly heterogeneous even within each of the five centers, unsupervised clustering was used to determine two labels for applying ComBat. The impact of each harmonization was evaluated through three different machine learning pipelines for the modelling step in predicting the clinical outcomes, across two performance metrics (balanced accuracy and Matthews correlation coefficient). Before harmonization, almost all radiomic features had significantly different distributions between labels. These differences were successfully removed with all ComBat versions. The predictive ability of the radiomic models was always improved with harmonization and the improved ComBat provided the best results. This was observed consistently in both datasets, through all machine learning pipelines and performance metrics. The proposed modifications allow for more flexibility and robustness in the estimation. They also slightly but consistently improve the predictive power of resulting radiomic models.

This article was published on June 24 2020 in SCIENTIFIC REPORTS

JULY 2020
Segmenting Hepatocellular Carcinoma in Multi-phase CT
Liver cancer diagnosis and treatment response assessment typically rely on the inspection of multi-phase contrast-enhanced computed tomography (CT) or magnetic resonance (MR) images. To date, various methods were proposed to automatically segment liver lesions in single time-step CT; but limited research addressed image analysis of multiple contrast phases. In this paper, we propose a multi-encoder 3D U-Net which, inspired by radiological practice, combines complementary tumour characteristics from both the arterial phase (AP) and portal venous phase (PVP) CT images. ESR Nora Vogt and colleagues demonstrate that encoder-decoder networks with disentangled feature extraction in two encoder streams outperform the baseline U-Nets that process single-phase data alone or apply input-level fusion for stacks of multi-phase data as channel input. Finally, they make use of a public single-phase CT liver tumour dataset for the pre-training of network parameters to improve the generalisation capabilities of their networks.

This conference paper was published on July 8 2020 in Medical Image Understanding and Analysis. MIUA 2020. Communications in Computer and Information Science