Emmanouil Koutoulakis

Mr. Emmanouil Koutoulakis

Institute of Computer Science, Foundation for Research and Technology Hellas, Heraklion, Greece
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2023 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
EMEmmanouil Markodimitrakis
Emmanouil Markodimitrakis
SLSiyu LIN
Siyu LIN
EKEmmanouil Koutoulakis
Emmanouil Koutoulakis
DMDiana Marcela Marín-Castrillón
Diana Marcela Marín-Castrillón
Francisco Aarón Tovar SáezFrancisco Aarón Tovar Sáez
Francisco Aarón Tovar Sáez
Alain LalandeAlain Lalande
Alain Lalande
Ascending aortic aneurysm is a pathology that is important to be supervised and treated. During the years the aorta dilates, it becomes stiff, and its elastic properties decrease. In some cases, the aortic wall can rupture leading to aortic dissection with a high mortality rate. The main reference standard to measure when the patient needs to undertake surgery is the aortic diameter. However, the aortic diameter was shown not to be sufficient to predict aortic dissection, implying other characteristics should be considered. Therefore, the main objective of this work is to assess in-vivo the elastic properties of four different quadrants of the ascending aorta and compare the results with equivalent properties obtained ex-vivo. The database consists of 73 cine-MRI sequences of thoracic aorta acquired in axial orientation at the level of the pulmonary trunk. All the patients have dilated aorta and surgery is required. The exams were acquired just prior to surgery, each consisting of 30 slices on average across the cardiac cycle. Multiple deep learning architectures have been explored with different hyperparameters and settings to automatically segment the contour of the aorta on each image and then automatically calculate the aortic compliance. A semantic segmentation U-Net network outperforms the rest explored networks with a Dice score of 98.09% (±0.96%) and a Hausdorff distance of 4.88 mm (±1.70 mm). Local aortic compliance and local aortic wall strain were calculated from the segmented surfaces for each quadrant and then compared with elastic properties obtained ex-vivo. Good agreement was observed between Young’s modulus and in-vivo strain. Our results suggest that the lateral and posterior quadrants are the stiffest. In contrast, the medial and anterior quadrants have the lowest aortic stiffness. The in-vivo stiffness tendency agrees with the values obtained ex-vivo. We can conclude that our automatic segmentation method is robust and compatible with clinical practice (thanks to a graphical user interface), while the in-vivo elastic properties are reliable and compatible with the ex-vivo ones.

15 November 2023 in Algorithms
Verified
Journal Article
Open access
PDF file
EKEmmanouil Koutoulakis
Emmanouil Koutoulakis
LMLouis Marage
Louis Marage
EMEmmanouil Markodimitrakis
Emmanouil Markodimitrakis
LALeone Aubignac
Leone Aubignac
CJCatherine JENNY
Catherine JENNY
Alain LalandeAlain Lalande
Alain Lalande
MR-Linac is a recent device combining a linear accelerator with an MRI scanner. The improved soft tissue contrast of MR images is used for optimum delineation of tumors or organs at risk (OARs) and precise treatment delivery. Automatic segmentation of OARs can contribute to alleviating the time-consuming process for radiation oncologists and improving the accuracy of radiation delivery by providing faster, more consistent, and more accurate delineation of target structures and organs at risk. It can also help reduce inter-observer variability and improve the consistency of contouring while reducing the time required for treatment planning. In this work, state-of-the-art deep learning techniques were evaluated based on 2D and 2.5D training strategies to develop a comprehensive tool for the accurate segmentation of pelvic OARs dedicated to 0.35 T MR-Linac. In total, 103 cases with 0.35 T MR images of the pelvic region were investigated. Experts considered and contoured the bladder, rectum, and femoral heads as OARs and the prostate as the target volume. For the training of the neural network, 85 patients were randomly selected, and 18 were used for testing. Multiple U-Net-based architectures were considered, and the best model was compared using both 2D and 2.5D training strategies. The evaluation of the models was performed based on two metrics: the Dice similarity coefficient (DSC) and the Hausdorff distance (HD). In the 2D training strategy, Residual Attention U-Net (ResAttU-Net) had the highest scores among the other deep neural networks. Due to the additional contextual information, the configured 2.5D ResAttU-Net performed better. The overall DSC were 0.88 ± 0.09 and 0.86 ± 0.10, and the overall HD was 1.78 ± 3.02 mm and 5.90 ± 7.58 mm for 2.5D and 2D ResAttU-Net, respectively. The 2.5D ResAttU-Net provides accurate segmentation of OARs without affecting the computational cost. The developed end-to-end pipeline will be merged with the treatment planning system for in-time automatic segmentation.

19 May 2025
Verified
Conference Paper
Closed access
EKEmmanouil Koutoulakis
Emmanouil Koutoulakis
Eleftherios TrivizakisEleftherios Trivizakis
Eleftherios Trivizakis
VKVassilis Koutoulidis
Vassilis Koutoulidis
LMLia A. Moulopoulos
Lia A. Moulopoulos
ETEvangelos Terpos
Evangelos Terpos
KMKostas Marias
Kostas Marias
Multiple myeloma is a plasma cell neoplasm with genetic complexity that originates in pre-malignant stages due to genomic alterations, leading to malignant plasma cell proliferation. Monitoring alterations in bone marrow during treatment for multiple myeloma may optimize patient outcomes. Multiple myeloma is a neoplasm that can distort bones, compromising the efficacy of conventional segmentation methodologies during the evaluation of whole body low dose computed tomography. A combination of pre-trained deep learning and traditional image analysis techniques for wholebody bone marrow segmentation is explored in this study. The pre-trained TotalSegmentator model was used to segment the entire skeleton in order to isolate key regions of interest and reduce pixel imbalances between the background and the bone pixels. A clustering technique was adapted to identify the bone marrow pixels and morphological operations were employed to refine the segmentation mask. The qualitative analysis performed by experienced radiologists shows promising results. The proposed segmentation pipeline allows accurate and fast annotation of the whole-body bone marrow imaging in multiple myeloma patients, achieving an IoU of $0.79 \pm 0.05$ on the available cohort with femur bone annotations.

15 October 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Alexandros KanterakisAlexandros Kanterakis
Alexandros Kanterakis
NKNikos Kanakaris
Nikos Kanakaris
EKEmmanouil Koutoulakis
Emmanouil Koutoulakis
KPKonstantina Pitianou
Konstantina Pitianou
NKNikos Karacapilidis
Nikos Karacapilidis
George PotamiasGeorge Potamias
George Potamias
Today, there are excellent resources for the semantic annotation of biomedical text. These resources span from ontologies, tools for NLP, annotators, and web services. Most of these are available either in the form of open source components (i.e., MetaMap) or as web services that offer free access (i.e., Whatizit). In order to use these resources in automatic text annotation pipelines, researchers face significant technical challenges. For open-source tools, the challenges include the setting up of the computational environment, the resolution of dependencies, as well as the compilation and installation of the software. For web services, the challenge is implementing clients to undertake communication with the respective web APIs. Even resources that are available as Docker containers (i.e., NCBO annotator) require significant technical skills for installation and setup. This work deals with the task of creating ready-to-install and run Research Objects (ROs) for a large collection of components in biomedical text analysis. These components include (a) tools such as cTAKES, NOBLE Coder, MetaMap, NCBO annotator, BeCAS, and Neji; (b) ontologies from BioPortal, NCBI BioSystems, and Open Biomedical Ontologies; and (c) text corpora such as BC4GO, Mantra Gold Standard Corpus, and the COVID-19 Open Research Dataset. We make these resources available in OpenBio.eu, an open-science RO repository and workflow management system. All ROs can be searched, shared, edited, downloaded, commented on, and rated. We also demonstrate how one can easily connect these ROs to form a large variety of text annotation pipelines.

19 May 2025
Verified
Conference Paper
Closed access
Eleftherios TrivizakisEleftherios Trivizakis
Eleftherios Trivizakis
EKEmmanouil Koutoulakis
Emmanouil Koutoulakis
VKVassilis Koutoulidis
Vassilis Koutoulidis
LMLia A. Moulopoulos
Lia A. Moulopoulos
ETEvangelos Terpos
Evangelos Terpos
KMKostas Marias
Kostas Marias
Multiple myeloma is a plasma cell malignancy with an underlying genetic complexity that develops from an early stage prior to malignancy progression because of recurrent genomic mutations. The disease triggers malignant plasma cell production in the bone marrow. The prognostic stratification of patients with multiple myeloma according to the international staging systems is based on specific criteria that incorporate laboratory examinations and chromosomal aberrations. Evaluating these cytogenetic abnormalities requires invasive bone marrow aspiration, which might be unsuccessful, especially when the bone marrow is dry tap. In this study, a novel machine learning model is used to match a robust radiomic signature to the underlying cytogenetic status, including del(13q), $t(4; 14)$, and $\operatorname{amp}(1 q 21)$. Whole-body bone marrow masks were used to extract radiomics from the selected groups of bones. A machine learning analysis was employed to predict the expression of key chromosomal alterations and the subsequent cytogenetic risk. The proposed machine learning analysis based on sacrum and pelvis radiomics achieved the highest performance with an AUC of $0.76 \pm 0.03$ among other radiocytogenetic models.