86,659 research outputs found
F. Gambardella, Vite connesse: l'abitare tra iperrealtà e perdita del mondo, in Il fenomeno vita. tra proprio e improprio, potenza e impotenza, singolare e comune, a cura di S. Prinzi
No full textLa visione dominante nelle nostre società sembra intendere la vita come un capitale di cui ogni individuo sarebbe dotato, collezione di crediti e skill che deve essere valorizzata per produrre performance caratterizzate da sempre maggiore rapidità, impatto, efficienza. Tutto sembra pensato per incrementare una vita di cui noi saremmo padroni, i cui progressi o regressi possono essere valutati secondo criteri quantitativi, per poter comparare le differenti vite e ottenere la migliore selezione possibile. Così si diffondono ovunque tecniche che si propongono di potenziare la vita, di renderla maggiormente produttiva, mentre imprese e istituzioni ne mettono a profitto ogni aspetto. Una frenesia che si rovescia nel suo contrario, in un paradossale sacrificio della vita, nella perdita di un controllo democratico, di una pianificazione che guarda al futuro. Come ci dimostrano la pandemia e la Guerra in Ucraina, che hanno rivelato i limiti delle pratiche di potenziamento, la fragilità della vita, la connessione inestricabile fra le nostre vite, la loro co-appartenenza a una più grande vita della specie. Se questi eventi sono il frutto delle modalità in cui la vita è stata istituita, allora, in questi tempi in cui tutta l’umanità è messa di fronte a sfide di carattere sanitario, bellico, ecologico, il fenomeno vita va forse ripensato alla radice, come incontro più che come competizione, come riconoscimento, comunicazione
Vite connesse: l'abitare tra iperrealtà e perdita del mondo
No full textLa visione dominante nelle nostre società sembra intendere la vita come un capitale di cui ogni individuo sarebbe dotato, collezione di crediti e skill che deve essere valorizzata per produrre performance caratterizzate da sempre maggiore rapidità, impatto, efficienza. Tutto sembra pensato per incrementare una vita di cui noi saremmo padroni, i cui progressi o regressi possono essere valutati secondo criteri quantitativi, per poter comparare le differenti vite e ottenere la migliore selezione possibile. Così si diffondono ovunque tecniche che si propongono di potenziare la vita, di renderla maggiormente produttiva, mentre imprese e istituzioni ne mettono a profitto ogni aspetto. Una frenesia che si rovescia nel suo contrario, in un paradossale sacrificio della vita, nella perdita di un controllo democratico, di una pianificazione che guarda al futuro. Come ci dimostrano la pandemia e la Guerra in Ucraina, che hanno rivelato i limiti delle pratiche di potenziamento, la fragilità della vita, la connessione inestricabile fra le nostre vite, la loro co-appartenenza a una più grande vita della specie. Se questi eventi sono il frutto delle modalità in cui la vita è stata istituita, allora, in questi tempi in cui tutta l’umanità è messa di fronte a sfide di carattere sanitario, bellico, ecologico, il fenomeno vita va forse ripensato alla radice, come incontro più che come competizione, come riconoscimento, comunicazione
Breast Cancer Localization and Classification in Mammograms Using YoloV5
No full textMammography screening is the main examination for breast cancer early detection, and has shown important benefits in reducing advanced and fatal disease rates. In this paper a YoloV5 model for simulta- neous breast cancer localization and classification in mammograms is proposed. Two public dataset were used for training and test. The CBIS-DDSM dataset, composed of scanned film mammograms, was used as a source dataset to implement the Transfer Learning tech- nique on the target INbreast dataset, composed of Full-Field Digital mammograms. The Small YoloV5 model combined with a large data- augmentation strategy was the best developed solution. A improvement of 0.103 mAP was found when Transfer Learning technique was imple- mented on the INbreast dataset. The performance was encouraging, resulting in a mAP of 0.838 ± 0.042, Recall of 0.722 ± 0.096, and Precision of 0.917 ± 0.077, calculated using the 5-Fold CV. The recog- nition rate achieved with the Transfer Learning on Full-Field Digital mammograms, encouraging future analysis on a proprietary dataset
Breast Cancer Malignancy Prediction through Explainable Models based on a Multimodal Signature of Features
No full textBreast cancer classification through ultrasound imaging poses a significant challenge due to the inherent noise present in ultrasound images. The radiologist’s reporting process aims to assess the lesions within the images following the Breast Imaging-Reporting and Data System (BI-RADS). This work investigates whether the medical knowledge, represented by the BI-RADS information, augmented by pixel-based quantitative features, can improve breast cancer classification. Machine learning classifiers, including XGBoost, Random Forest, and Support Vector Machine, were trained with an intelligible multimodal signature composed of the BI-RADS and radiomic features. Exploiting the intrinsic interpretability of our model input, the work aims to obtain an explainable predictive model using post-hoc explanation methods. A proprietary dataset composed of 237 B-mode ultrasound scans was acquired, and a total of 103 radiomics features were extracted. Before the training of classifiers, a pipeline for selecting an informative and non-redundant signature was implemented. A 10-fold Cross-Validation repeated 20 times was considered for the training in 80% of the dataset, and the best model in terms of accuracy was selected for testing on the remaining 20%. Our results prove how the medical knowledge, represented by the BI-RADS information, is enhanced with the use of radiomic features. XGBoost was the best model, showing an AUROC of 0.977 ± 0.029 and 0.956 in the training and test phases, respectively. In addition, the implemented global explanation using the SHAP method and exploiting the intelligibility of radiomic features, allowed us to confirm some important model findings
Impact of Wavelet Kernels on Predictive Capability of Radiomic Features: A Case Study on COVID-19 Chest X-ray Images
No full textRadiomic analysis allows for the detection of imaging biomarkers supporting decision-making processes in clinical environments, from diagnosis to prognosis. Frequently, the original set of radiomic features is augmented by considering high-level features, such as wavelet transforms. However, several wavelets families (so called kernels) are able to generate different multi-resolution representations of the original image, and which of them produces more salient images is not yet clear. In this study, an in-depth analysis is performed by comparing different wavelet kernels and by evaluating their impact on predictive capabilities of radiomic models. A dataset composed of 1589 chest X-ray images was used for COVID-19 prognosis prediction as a case study. Random forest, support vector machine, and XGBoost were trained (on a subset of 1103 images) after a rigorous feature selection strategy to build-up the predictive models. Next, to evaluate the models generalization capability on unseen data, a test phase was performed (on a subset of 486 images). The experimental findings showed that Bior1.5, Coif1, Haar, and Sym2 kernels guarantee better and similar performance for all three machine learning models considered. Support vector machine and random forest showed comparable performance, and they were better than XGBoost. Additionally, random forest proved to be the most stable model, ensuring an appropriate balance between sensitivity and specificity
A Yolo-Based Model for Breast Cancer Detection in Mammograms
No full textThis work aims to implement an automated data-driven model for breast cancer detection in mammograms to support physicians' decision process within a breast cancer screening or detection program. The public available CBIS-DDSM and the INbreast datasets were used as sources to implement the transfer learning technique on full-field digital mammography proprietary dataset. The proprietary dataset reflects a real heterogeneous case study, consisting of 190 masses, 46 asymmetries, and 71 distortions. Several Yolo architectures were compared, including YoloV3, YoloV5, and YoloV5-Transformer. In addition, Eigen-CAM was implemented for model introspection and outputs explanation by highlighting all the suspicious regions of interest within the mammogram. The small YoloV5 model resulted in the best developed solution obtaining an mAP of 0.621 on proprietary dataset. The saliency maps computed via Eigen-CAM have proven capable solution reporting all regions of interest also on incorrect prediction scenarios. In particular, Eigen-CAM produces a substantial reduction in the incidence of false negatives, although accompanied by an increase in false positives. Despite the presence of hard-to-recognize anomalies such as asymmetries and distortions on the proprietary dataset, the trained model showed encouraging detection capabilities. The combination of Yolo predictions and the generated saliency maps represent two complementary outputs for the reduction of false negatives. Nevertheless, it is imperative to regard these outputs as qualitative tools that invariably necessitate clinical radiologic evaluation. In this view, the model represents a trusted predictive system to support cognitive and decision-making, encouraging its integration into real clinical practice
MUGI-MRI: Enhancing Breast Cancer Classification through Multiplex Graph Neural Networks in DCE-MRI
No full textDynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) involves acquiring a sequence of MRIs during the administration of a contrast agent. Radiologists then aim to discern the contrast uptake differences between malignant and benign lesions for tumor classification. Regrettably, existing literature underutilizes the temporal structure inherent to DCEMRI time series, leading to tumor classifications based on individual instants rather than entire sequences. This research introduces two Graph Neural Network (GNN)-based methods designed to aggregate information from multiple instants within the DCE-MRI sequence. Each lesion undergoes manual segmentation, and radiomic features are individually extracted from each time instant of the DCE-MRI sequence. Two graph construction methodologies are proposed: (i) a fully connected graph topology, aiming to represent each temporal instant as a node in a graph; (ii) a multiplex network, named MUGI-MRI (MUltiplex Graph neural network for Integration of MRI), where each layer identifies an instant of the DCE-MRI sequence. MUGI-MRI achieves an AUROC of 0.8017 ± 0.1146, showcasing promising performance in lesion classification. In addition to improving upon current state-of-the-art, the integration capability of MUGIMRI addresses the problem of imbalance between sensitivity and specificity, which affects numerous studies in the realm of DCE-MRI. Our findings strongly indicate that the aggregation of information across all time instants is pivotal for enhancing the diagnostic process, and vastly superior to a simplistic instant-wise analysis. While applied to MRI sequences, our approach can be extended to general problems of multimodal data integration
PROFILO ENDOCRINO E DENSITA’ MINERALE OSSEA IN ADOLESCENTI CON COAGULOPATIE CONGENITE IN TERAPIA CON ESTROPROGESTINICI
No full textNew perspectives in breath by breath determination of alveolar trans-membrane gas exchange at the onset of exercise in humans
No full text
- …
