Pasar al contenido principal

UN MODEL DE APRENDIZAJE AUTOMATICO Y DE BIG DATA PARA EVALUAR LA COMORBILIDAD CORAZON-CEREBRO

RTI2018-099898-B-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POMPEU FABRA CCT

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries

  • Sendra Balcells, Carla
  • Campello Román, Víctor Manuel|||0000-0003-1727-983X
  • Torrents Barrena, Jordina
  • Ahmed, Yahya Ali
  • Elattar, Mustafa
  • Ohene Botwe, Benard
  • Nyangulu, Pempho
  • Stones, William
  • Ammar, Mohammed
  • Benamer, Lamya Nawal
  • Bonet Carné, Elisenda|||0000-0003-0567-6141
Most artificial intelligence (AI) research and innovations have concentrated in high-income countries, where imaging data, IT infrastructures and clinical expertise are plentiful. However, slower progress has been made in limited-resource environments where medical imaging is needed. For example, in Sub-Saharan Africa, the rate of perinatal mortality is very high due to limited access to antenatal screening. In these countries, AI models could be implemented to help clinicians acquire fetal ultrasound planes for the diagnosis of fetal abnormalities. So far, deep learning models have been proposed to identify standard fetal planes, but there is no evidence of their ability to generalise in centres with low resources, i.e. with limited access to high-end ultrasound equipment and ultrasound data. This work investigates for the first time different strategies to reduce the domain-shift effect arising from a fetal plane classification model trained on one clinical centre with high-resource settings and transferred to a new centre with low-resource settings. To that end, a classifier trained with 1792 patients from Spain is first evaluated on a new centre in Denmark in optimal conditions with 1008 patients and is later optimised to reach the same performance in five African centres (Egypt, Algeria, Uganda, Ghana and Malawi) with 25 patients each. The results show that a transfer learning approach for domain adaptation can be a solution to integrate small-size African samples with existing large-scale databases in developed countries. In particular, the model can be re-aligned and optimised to boost the performance on African populations by increasing the recall to 0.92±0.04 and at the same time maintaining a high precision across centres. This framework shows promise for building new AI models generalisable across clinical centres with limited data acquired in challenging and heterogeneous conditions and calls for further research to develop new solutions for the usability of AI in countries with fewer resources and, consequently, in higher need of clinical support., This work received funding from the European Union’s 2020 research and innovation programme under Grant Agreement No. 825903 (euCanSHare project), as well as from the Spanish Ministry of Science, Innovation and Universities under grant agreement RTI2018-099898-B-I00. Additionally, the research leading to these results has received funding from Cerebra Foundation for the Brain Injured Child (Carmarthen, Wales, UK). This research was partly funded by a grant from the European Research Council (ERC) under the European Union’s Horizon Europe research and innovation programme (AIMIX project - grant agreement No. 101044779)., Peer Reviewed, Article signat per 20 autors/es: Carla Sendra-Balcells, Víctor M. Campello, Jordina Torrents-Barrena, Yahya Ali Ahmed, Mustafa Elattar, Benard Ohene-Botwe, Pempho Nyangulu, William Stones, Mohammed Ammar, Lamya Nawal Benamer, Harriet Nalubega Kisembo, Senai Goitom Sereke, Sikolia Z. Wanyonyi, Marleen Temmerman, Eduard Gratacós, Elisenda Bonet, Elisenda Eixarch, Kamil Mikolaj, Martin Grønnebæk Tolsgaard & Karim Lekadir.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries

  • Sendra Balcells, Carla
  • Campello Román, Víctor Manuel
  • Torrents Barrena, Jordina
  • Ahmed, Yahya Ali
  • Elattar, Mustafa
  • Ohene Botwe, Benard
  • Nyangulu, Pempho
  • Stones, William
  • Ammar, Mohammed
  • Benamer, Lamya Nawal
  • Bonet Carné, Elisenda
Most artificial intelligence (AI) research and innovations have concentrated in high-income countries, where imaging data, IT infrastructures and clinical expertise are plentiful. However, slower progress has been made in limited-resource environments where medical imaging is needed. For example, in Sub-Saharan Africa, the rate of perinatal mortality is very high due to limited access to antenatal screening. In these countries, AI models could be implemented to help clinicians acquire fetal ultrasound planes for the diagnosis of fetal abnormalities. So far, deep learning models have been proposed to identify standard fetal planes, but there is no evidence of their ability to generalise in centres with low resources, i.e. with limited access to high-end ultrasound equipment and ultrasound data. This work investigates for the first time different strategies to reduce the domain-shift effect arising from a fetal plane classification model trained on one clinical centre with high-resource settings and transferred to a new centre with low-resource settings. To that end, a classifier trained with 1792 patients from Spain is first evaluated on a new centre in Denmark in optimal conditions with 1008 patients and is later optimised to reach the same performance in five African centres (Egypt, Algeria, Uganda, Ghana and Malawi) with 25 patients each. The results show that a transfer learning approach for domain adaptation can be a solution to integrate small-size African samples with existing large-scale databases in developed countries. In particular, the model can be re-aligned and optimised to boost the performance on African populations by increasing the recall to 0.92±0.04 and at the same time maintaining a high precision across centres. This framework shows promise for building new AI models generalisable across clinical centres with limited data acquired in challenging and heterogeneous conditions and calls for further research to develop new solutions for the usability of AI in countries with fewer resources and, consequently, in higher need of clinical support., This work received funding from the European Union’s 2020 research and innovation programme under Grant Agreement No. 825903 (euCanSHare project), as well as from the Spanish Ministry of Science, Innovation and Universities under grant agreement RTI2018-099898-B-I00. Additionally, the research leading to these results has received funding from Cerebra Foundation for the Brain Injured Child (Carmarthen, Wales, UK). This research was partly funded by a grant from the European Research Council (ERC) under the European Union’s Horizon Europe research and innovation programme (AIMIX project - grant agreement No. 101044779)., Peer Reviewed, Article signat per 20 autors/es: Carla Sendra-Balcells, Víctor M. Campello, Jordina Torrents-Barrena, Yahya Ali Ahmed, Mustafa Elattar, Benard Ohene-Botwe, Pempho Nyangulu, William Stones, Mohammed Ammar, Lamya Nawal Benamer, Harriet Nalubega Kisembo, Senai Goitom Sereke, Sikolia Z. Wanyonyi, Marleen Temmerman, Eduard Gratacós, Elisenda Bonet, Elisenda Eixarch, Kamil Mikolaj, Martin Grønnebæk Tolsgaard & Karim Lekadir., Postprint (published version)
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Minimising multi-centre radiomics variability through image normalisation, a pilot study

  • Campello, Victor M.|||0000-0003-1727-983X
  • Martín-Isla, Carlos
  • Izquierdo, Cristian
  • Guala, Andrea|||0000-0002-5006-8164
  • Rodríguez Palomares, José F.|||0000-0002-7229-9780
  • Viladés Medel, David|||0000-0002-3638-9703
  • Descalzo, Martin|||0000-0003-3736-7191
  • Karakas, Mahir
  • Çavuş, Ersin
  • Raisi-Estabragh, Zahra
  • Petersen, Steffen E.|||0000-0003-4622-5160
  • Escalera, Sergio|||0000-0003-0617-8873
  • Seguí, Santi
  • Lekadir, Karim|||0000-0002-9456-1612
Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features' variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification (balanced accuracy in between 0.78 ± 0.08 and 0.79 ± 0.09). Models trained with features from images without normalisation showed the worst performance overall (balanced accuracy in between 0.45 ± 0.28 and 0.60 ± 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance

  • Izquierdo, Cristian
  • Casas, Guillem|||0000-0001-7122-320X
  • Martin-Isla, Carlos
  • Campello, Victor M.|||0000-0003-1727-983X
  • Guala, Andrea|||0000-0002-5006-8164
  • Gkontra, Polyxeni|||0000-0001-8828-6143
  • Rodríguez Palomares, José F|||0000-0002-7229-9780
  • Lekadir, Karim|||0000-0002-9456-1612
Left Ventricular (LV) Non-compaction (LVNC), Hypertrophic Cardiomyopathy (HCM), and Dilated Cardiomyopathy (DCM) share morphological and functional traits that increase the diagnosis complexity. Additional clinical information, besides imaging data such as cardiovascular magnetic resonance (CMR), is usually required to reach a definitive diagnosis, including electrocardiography (ECG), family history, and genetics. Alternatively, indices of hypertrabeculation have been introduced, but they require tedious and time-consuming delineations of the trabeculae on the CMR images. In this paper, we propose a radiomics approach to automatically encode differences in the underlying shape, gray-scale and textural information in the myocardium and its trabeculae, which may enhance the capacity to differentiate between these overlapping conditions. A total of 118 subjects, including 35 patients with LVNC, 25 with HCM, 37 with DCM, as well as 21 healthy volunteers (NOR), underwent CMR imaging. A comprehensive radiomics characterization was applied to LV short-axis images to quantify shape, first-order, co-occurrence matrix, run-length matrix, and local binary patterns. Conventional CMR indices (LV volumes, mass, wall thickness, LV ejection fraction-LVEF-), as well as hypertrabeculation indices by Petersen and Jacquier, were also analyzed. State-of-the-art Machine Learning (ML) models (one-vs.-rest Support Vector Machine-SVM-, Logistic Regression-LR-, and Random Forest Classifier-RF-) were used for one-vs.-rest classification tasks. The use of radiomics models for the automated diagnosis of LVNC, HCM, and DCM resulted in excellent one-vs.-rest ROC-AUC values of 0.95 while generating these results without the need for the delineation of the trabeculae. First-order and texture features resulted to be among the most discriminative features in the obtained radiomics signatures, indicating their added value for quantifying relevant tissue patterns in cardiomyopathy differential diagnosis.