Browsing by Author "Zabotti, Alen (55053365900)"

Salivary gland ultrasonography (SGUS) has proven to be a promising tool for diagnosing various diseases manifesting with abnormalities in salivary glands (SGs), including primary Sjögren's syndrome (pSS). At present, the major obstacle for establishing SUGS as a standardized tool for pSS diagnosis is its low inter/intra observer reliability. The aim of this study was to address this problem by proposing a robust deep learning-based solution for the automated segmentation of SGUS images. For these purposes, four architectures were considered: a fully convolutional neural network, fully convolutional “DenseNets” (FCN-DenseNet) network, U-Net, and LinkNet. During the course of the study, the growing HarmonicSS cohort included 1184 annotated SGUS images. Accordingly, the algorithms were trained using a transfer learning approach. With regard to the intersection-over-union (IoU), the top-performing FCN-DenseNet (IoU = 0.85) network showed a considerable margin above the inter-observer agreement (IoU = 0.76) and slightly above the intra-observer agreement (IoU = 0.84) between clinical experts. Considering its accuracy and speed (24.5 frames per second), it was concluded that the FCN-DenseNet could have wider applications in clinical practice. Further work on the topic will consider the integration of methods for pSS scoring, with the end goal of establishing SGUS as an effective noninvasive pSS diagnostic tool. To aid this progress, we created inference (frozen models) files for the developed models, and made them publicly available. © 2020 Elsevier Ltd

Salivary gland ultrasonography (SGUS) has proven to be a promising tool for diagnosing various diseases manifesting with abnormalities in salivary glands (SGs), including primary Sjögren's syndrome (pSS). At present, the major obstacle for establishing SUGS as a standardized tool for pSS diagnosis is its low inter/intra observer reliability. The aim of this study was to address this problem by proposing a robust deep learning-based solution for the automated segmentation of SGUS images. For these purposes, four architectures were considered: a fully convolutional neural network, fully convolutional “DenseNets” (FCN-DenseNet) network, U-Net, and LinkNet. During the course of the study, the growing HarmonicSS cohort included 1184 annotated SGUS images. Accordingly, the algorithms were trained using a transfer learning approach. With regard to the intersection-over-union (IoU), the top-performing FCN-DenseNet (IoU = 0.85) network showed a considerable margin above the inter-observer agreement (IoU = 0.76) and slightly above the intra-observer agreement (IoU = 0.84) between clinical experts. Considering its accuracy and speed (24.5 frames per second), it was concluded that the FCN-DenseNet could have wider applications in clinical practice. Further work on the topic will consider the integration of methods for pSS scoring, with the end goal of establishing SGUS as an effective noninvasive pSS diagnostic tool. To aid this progress, we created inference (frozen models) files for the developed models, and made them publicly available. © 2020 Elsevier Ltd

Background The transition from psoriasis (PsO) to psoriatic arthritis (PsA) and the early diagnosis of PsA is of considerable scientific and clinical interest for the prevention and interception of PsA. Objective To formulate EULAR points to consider (PtC) for the development of data-driven guidance and consensus for clinical trials and clinical practice in the field of prevention or interception of PsA and for clinical management of people with PsO at risk for PsA development. Methods A multidisciplinary EULAR task force of 30 members from 13 European countries was established, and the EULAR standardised operating procedures for development for PtC were followed. Two systematic literature reviews were conducted to support the task force in formulating the PtC. Furthermore, the task force proposed nomenclature for the stages before PsA, through a nominal group process to be used in clinical trials. Results Nomenclature for the stages preceding PsA onset, 5 overarching principles and 10 PtC were formulated. Nomenclature was proposed for three stages towards PsA development, namely people with PsO at higher risk of PsA, subclinical PsA and clinical PsA. The latter stage was defined as PsO and associated synovitis and it could be used as an outcome measure for clinical trials evaluating the transition from PsO to PsA. The overarching principles address the nature of PsA at its onset and underline the importance of collaboration of rheumatologists and dermatologists for strategies for prevention/interception of PsA. The 10 PtC highlight arthralgia and imaging abnormalities as key elements of subclinical PsA that can be used as potential short-term predictors of PsA development and useful items to design clinical trials for PsA interception. Traditional risk factors for PsA development (ie, PsO severity, obesity and nail involvement) may represent more long-term disease predictors and be less robust for short-term trials concerning the transition from PsO to PsA. Conclusion These PtC are helpful to define the clinical and imaging features of people with PsO suspicious to progress to PsA. This information will be helpful for identification of those who could benefit from a therapeutic intervention to attenuate, delay or prevent PsA development. © Author(s) (or their employer(s)) 2023. No commercial re-use. See rights and permissions. Published by BMJ.

Background The transition from psoriasis (PsO) to psoriatic arthritis (PsA) and the early diagnosis of PsA is of considerable scientific and clinical interest for the prevention and interception of PsA. Objective To formulate EULAR points to consider (PtC) for the development of data-driven guidance and consensus for clinical trials and clinical practice in the field of prevention or interception of PsA and for clinical management of people with PsO at risk for PsA development. Methods A multidisciplinary EULAR task force of 30 members from 13 European countries was established, and the EULAR standardised operating procedures for development for PtC were followed. Two systematic literature reviews were conducted to support the task force in formulating the PtC. Furthermore, the task force proposed nomenclature for the stages before PsA, through a nominal group process to be used in clinical trials. Results Nomenclature for the stages preceding PsA onset, 5 overarching principles and 10 PtC were formulated. Nomenclature was proposed for three stages towards PsA development, namely people with PsO at higher risk of PsA, subclinical PsA and clinical PsA. The latter stage was defined as PsO and associated synovitis and it could be used as an outcome measure for clinical trials evaluating the transition from PsO to PsA. The overarching principles address the nature of PsA at its onset and underline the importance of collaboration of rheumatologists and dermatologists for strategies for prevention/interception of PsA. The 10 PtC highlight arthralgia and imaging abnormalities as key elements of subclinical PsA that can be used as potential short-term predictors of PsA development and useful items to design clinical trials for PsA interception. Traditional risk factors for PsA development (ie, PsO severity, obesity and nail involvement) may represent more long-term disease predictors and be less robust for short-term trials concerning the transition from PsO to PsA. Conclusion These PtC are helpful to define the clinical and imaging features of people with PsO suspicious to progress to PsA. This information will be helpful for identification of those who could benefit from a therapeutic intervention to attenuate, delay or prevent PsA development. © Author(s) (or their employer(s)) 2023. No commercial re-use. See rights and permissions. Published by BMJ.

Salivary gland ultrasonography (SGUS) has shown good potential in the diagnosis of primary Sjögren's syndrome (pSS). However, a series of international studies have reported needs for improvements of the existing pSS scoring procedures in terms of inter/intra observer reliability before being established as standardized diagnostic tools. The present study aims to solve this problem by employing radiomics features and artificial intelligence (AI) algorithms to make the pSS scoring more objective and faster compared to human expert scoring. The assessment of AI algorithms was performed on a two-centric cohort, which included 600 SGUS images (150 patients) annotated using the original SGUS scoring system proposed in 1992 for pSS. For each image, we extracted 907 histogram-based and descriptive statistics features from segmented salivary glands. Optimal feature subsets were found using the genetic algorithm based wrapper approach. Among the considered algorithms (seven classifiers and five regressors), the best preforming was the multilayer perceptron (MLP) classifier (κ = 0.7). The MLP over-performed average score achieved by the clinicians (κ = 0.67) by the considerable margin, whereas its reliability was on the level of human intra-observer variability (κ = 0.71). The presented findings indicate that the continuously increasing HarmonicSS cohort will enable further advancements in AI-based pSS scoring methods by SGUS. In turn, this may establish SGUS as an effective noninvasive pSS diagnostic tool, with the final goal to supplement current diagnostic tests. © 2013 IEEE.

Salivary gland ultrasonography (SGUS) has shown good potential in the diagnosis of primary Sjögren's syndrome (pSS). However, a series of international studies have reported needs for improvements of the existing pSS scoring procedures in terms of inter/intra observer reliability before being established as standardized diagnostic tools. The present study aims to solve this problem by employing radiomics features and artificial intelligence (AI) algorithms to make the pSS scoring more objective and faster compared to human expert scoring. The assessment of AI algorithms was performed on a two-centric cohort, which included 600 SGUS images (150 patients) annotated using the original SGUS scoring system proposed in 1992 for pSS. For each image, we extracted 907 histogram-based and descriptive statistics features from segmented salivary glands. Optimal feature subsets were found using the genetic algorithm based wrapper approach. Among the considered algorithms (seven classifiers and five regressors), the best preforming was the multilayer perceptron (MLP) classifier (κ = 0.7). The MLP over-performed average score achieved by the clinicians (κ = 0.67) by the considerable margin, whereas its reliability was on the level of human intra-observer variability (κ = 0.71). The presented findings indicate that the continuously increasing HarmonicSS cohort will enable further advancements in AI-based pSS scoring methods by SGUS. In turn, this may establish SGUS as an effective noninvasive pSS diagnostic tool, with the final goal to supplement current diagnostic tests. © 2013 IEEE.