21 research outputs found
Giovanna Garzoni Miniaturist at the Savoy Court: Imaging and Materials Investigations to Discover the Painting Technique
No full textThe exhibition “The Ladies of Art”, held at the Palazzo Reale in Milan in 2021, focused on the history of women artists during the 16th and 17th centuries. As part of the exhibition, a series of diagnostic analyses have been carried out on two paintings, thanks to the collaboration of several research institutions. The considered artworks consist of two paintings on parchments, realized by Giovanna Garzoni at the Savoy Court in the 17th century. Diagnostic analyses were performed using different, complementary, and non-invasive techniques: high-resolution multiband imaging, hyperspectral imaging, optical microscopy, X-ray fluorescence, and FORS spectrometry, combined with advanced post-processing techniques, in order to map and distinguish the pigments and the underdrawing of both the paintings. This research is the first conducted on these paintings and one of the few on the entire works of this important miniaturist. The results showed an incredibly meticulous painting technique, with a detailed metal point underdrawing and painstaking brushstrokes to describe the details with a high degree of realism. Precious materials, such as gold and lapislazuli, were identified and mapped. The findings of this work represent a new contribution of knowledge, which helps to lessen the lack of information for systematic studies on the artistic production of G. Garzoni
Comparison of Transfer Learning and Conventional Machine Learning Applied to Structural Brain MRI for the Early Diagnosis and Prognosis of Alzheimer's Disease
No full textAlzheimer's Disease (AD) is the most common neurodegenerative disease, with 10% prevalence in the elder population. Conventional Machine Learning (ML) was proven effective in supporting the diagnosis of AD, while very few studies investigated the performance of deep learning and transfer learning in this complex task. In this paper, we evaluated the potential of ensemble transfer-learning techniques, pretrained on generic images and then transferred to structural brain MRI, for the early diagnosis and prognosis of AD, with respect to a fusion of conventional-ML approaches based on Support Vector Machine directly applied to structural brain MRI. Specifically, more than 600 subjects were obtained from the ADNI repository, including AD, Mild Cognitive Impaired converting to AD (MCIc), Mild Cognitive Impaired not converting to AD (MCInc), and cognitively-normal (CN) subjects. We used T1-weighted cerebral-MRI studies to train: (1) an ensemble of five transfer-learning architectures pretrained on generic images; (2) a 3D Convolutional Neutral Network (CNN) trained from scratch on MRI volumes; and (3) a fusion of two conventional-ML classifiers derived from different feature extraction/selection techniques coupled to SVM. The AD-vs-CN, MCIc-vs-CN, MCIc-vs-MCInc comparisons were investigated. The ensemble transfer-learning approach was able to effectively discriminate AD from CN with 90.2% AUC, MCIc from CN with 83.2% AUC, and MCIc from MCInc with 70.6% AUC, showing comparable or slightly lower results with the fusion of conventional-ML systems (AD from CN with 93.1% AUC, MCIc from CN with 89.6% AUC, and MCIc from MCInc with AUC in the range of 69.1–73.3%). The deep-learning network trained from scratch obtained lower performance than either the fusion of conventional-ML systems and the ensemble transfer-learning, due to the limited sample of images used for training. These results open new prospective on the use of transfer learning combined with neuroimages for the automatic early diagnosis and prognosis of AD, even if pretrained on generic images
Documenting Cultural Heritage in very hostile fruition contexts: The synoptic visualization of Giottesque frescoes by Multispectral and 3D Close-range Imaging
No full textThe paper reports the results obtained from the digital survey of Giottesque frescoes in the Archiepiscopal Palace of Milan. Multispectral Imaging and Image Based Modelling techniques have allowed the study, the high-resolution documentation and the virtual reassembly of the fragmented frescoes: the integration of spectral data with RGB ortho-images and 3D models has supported the interpretation of the pictorial cycle by virtually relocating the fresco fragments and evaluating their consistency from a technical, iconographic and art-historical point of view. The experimental results show that the proposed approach has great potential for the documentation of wall paintings preserved in highly hostile contexts of fruition. Due to its versatility and portability in the field, its sub-millimetric accuracy, and the different outputs that can be generated, Close-Range Digital Photogrammetry has proven to be the ideal tool in case of scattered and difficult-to-access data
The Giotto’s workshop in the XXI century : looking inside the “God the Father with Angels” gable
No full textGod the Father with Angels (about 1330, tempera on panel) by Giotto is the Gable of the altarpiece of Baroncelli Chapel in the church of Santa Croce in Florence. Very little is known about its history since the separation from the so-called Baroncelli Polyptych. Now at the San Diego Museum of Art, the Gable had never been studied by means of scientific methods before our team took the opportunity to during the exhibition “Giotto, l'Italia” held in Milan. Exploiting the integration of different knowledge, technologies and resources of our team, we were able to provide data for understanding the organizational model of Giotto's workshop performing non-invasive analyses with portable instruments during closing hours of exhibition (four diagnostic campaigns, six hours of work/campaign, no interruption of the exhibition). The achieved results confirm the painting technique based on different layers of pigments, a technique already used by Giotto. Combining the effectiveness of scanning MA-XRF with the responsive of IR reflectography and IR false colour, we moved step by step toward the discovery of Giotto's palette for the flesh tones in God the Father with Angels. FORS and XRF single point analyses were performed on some selected areas too. The IR reflectography results support the hypothesis of a detailed underdrawing with both thin and flat brushstrokes. By applying image-processing algorithms to the collected reflectograms, we obtained quantitative objective measures supporting the hypothesis that a guide could have been used in the realization of human figures; this means the use of sketches for the face of “God the Father” and for the faces of angels
AI applications to medical images: From machine learning to deep learning
No full textPurpose: Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. Methods: A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. Results: We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way. Conclusions: Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice
Artificial intelligence applied on chest X-ray can aid in the diagnosis of {COVID}-19 infection: a first experience from Lombardy, Italy
No full textBackground: We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. Methods: We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as the reference standard. Results: At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74–0.81), 0.82 specificity (95% CI 0.78–0.85), and 0.89 area under the curve (AUC) (95% CI 0.86–0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72–0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73–0.87), and 0.81 AUC (95% CI 0.73–0.87). Radiologists’ reading obtained 0.63 sensitivity (95% CI 0.52–0.74) and 0.78 specificity (95% CI 0.61–0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52–0.74) and 0.86 specificity (95% CI 0.71–0.95) in Centre 2. Conclusions: This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance
AI applications to medical images: From machine learning to deep learning
No full textPurpose: Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. Methods: A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. Results: We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way. Conclusions: Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practic
Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia
No full textWe assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia
Giotto Unveiled: New Developments in Imaging and Elemental Analysis Techniques for Cultural Heritage
No full textThe Giotto’s masterpiece God the Father with Angels, never investigated till now, was studied by our team of local researchers, involved in application of scientific methods for cultural heritage since many years. Exploiting the integration of different knowledges, technologies and resources of our team, we were able to provide data to understand the painting technique, the pigment used and the underdrawing of this Giotto’s painting. We performed the following non-invasive analyses: Macro-XRF scanning (MA-XRF), Fiber optic reflectance spectroscopy (FORS), high resolution IR scanning reflectography, infrared false color (IRFC). Only portable instrumentations were used, with operating times compatible with the opening hours of exhibition. In particular, the analytical campaign was the opportunity to test the portable IR scanning prototype based on a peculiar spherical scanning system characterized by light weight and low cost motorized head. The analytical results revealed a painting technique already used by Giotto and based on different superimposed pigment layers. By combining the effectiveness of scanning portable-XRF (pXRF) with the responsive of image spectroscopic analysis, we move step by step toward the discovery of Giotto’s palette, with particular attention to the flesh tones in God the Father with Angels. The imaging data support the hypothesis of a detailed underlying sketch that includes also a drawing characterized by larger brush signs; the use of patrones for the face of “God” was supposed thanks to comparison with other Giotto masterpieces
Development and Validation of an AI-driven Mammographic Breast Density Classification Tool Based on Radiologist Consensus
No full textMammographic breast density (BD) is commonly visually assessed using the Breast Imaging Reporting and Data System (BI-RADS) four-category scale. To overcome inter- and intraobserver variability of visual assessment, the authors retrospectively developed and externally validated a software for BD classification based on convolutional neural networks from mammograms obtained between 2017 and 2020. The tool was trained using the majority BD category determined by seven board-certified radiologists who independently visually assessed 760 mediolateral oblique (MLO) images in 380 women (mean age, 57 years +/- 6 [SD]) from center 1; this process mimicked training from a consensus of several human readers. External validation of the model was performed by the three radiologists whose BD assessment was closest to the majority (consensus) of the initial seven on a dataset of 384 MLO images in 197 women (mean age, 56 years +/- 13) obtained from center 2. The model achieved an accuracy of 89.3% in distinguishing BI-RADS a or b (nondense breasts) versus c or d (dense breasts) categories, with an agreement of 90.4% (178 of 197 mammograms) and a reliability of 0.807 (Cohen k) compared with the mode of the three readers. This study demonstrates accuracy and reliability of a fully automated software for BD classification
