https://hdl.handle.net/10807/95494 Tue, 04 Aug 2026 02:00:08 GMT 2026-08-04T02:00:08Z https://hdl.handle.net/10807/343036 Titolo: Liability in the Algorithmic Workplace: Embodied AI, Smart PPEs and the Third Element Autori: Faioli Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/10807/343036 2026-01-01T00:00:00Z https://hdl.handle.net/10807/341856 Titolo: Chinese Main-melody Cinema History, institutions, languages, and narratives Autori: Lepri Chiara Abstract: This thesis is dedicated to the study of Chinese propaganda cinema, with particular reference to the so- called “main-melody cinema” (zhuxuanlü dianying 主旋律电影), a category established in 1987 to main- tain the propagandistic tradition of cinema in the People’s Republic of China. Since the 2000s, main- melody cinema has become one of the most commercially successful genres in the Chinese film industry. The “main melody” is analysed here in two sections, both of which draw upon Chinese Media Studies and Chinese Film Studies. Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/10807/341856 2026-01-01T00:00:00Z https://hdl.handle.net/10807/341738 Titolo: Competenze socio-emotive e valutazione sostenibile a scuola. Dalla misurazione alla generatività: tempo, relazioni ed ecologiadella formazione Autori: Biagio Di Liberto Abstract: Il contributo rilegge la valutazione scolastica entro la pedagogia della complessità, integrando Sustainable Assessment (SA) e Social and Emotional Learning (SEL). Oltre i modelli certificativi, la valutazione è intesa come dispositivo etico-educativo, processuale e generativo, capace di promuovere autoregolazione, metacognizione, inclusione e benessere. La cornice teorica intreccia SEL, Assessment for Learning (AfL), Assessment as Learning (AaL) e Learning-Oriented Assessment (LOA), prendendo le distanze dalla “quantofrenia” valutativa (Hadji, 2023), propone una construct map della generatività didattica. Metodologicamente si presenta un micro-disegno di Design-Based Research (DBR) replicabile (4-6 settimane): sono delineati strumenti fit for purpose, routine leggere e raccolta di micro-evidenze per favorire trasferibilità. Tre dimensioni, temporale, sociale ed ecologica, rendono operativa la sostenibilità. La SA è assunta come pratica di cura pedagogica orientata alla giustizia educativa e al transfer di criteri e strategie: l’attenzione si sposta dal “quanto” al “come” e al “perché”, dall’accertamento dell’oggi alla capacità di trasferire criteri e strategie degli studenti in contesti inediti. Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/10807/341738 2026-01-01T00:00:00Z https://hdl.handle.net/10807/341539 Titolo: Prediction Of Homologous Recombination Deficiency (HRD) From H&E Whole Slide Images Using Attention-Based Multiple Instance Learning In Ovarian Cancer Autori: Vagni, Marica; Giudice, Elena; Anderson, Gloria; Sillano, Francesca; Cannizzaro, Maria Chiara; Musacchio, Lucia; Piermattei, Alessia; Valente, Michele; Fagotti, Anna; Martinelli, Enrica; Iacobelli, Valentina; Minucci, Angelo; Brisighelli, Francesca; Ghizzoni, Viola; Preziosi, Jessica; Pietrosante, Annamaria; Buttarelli, Marianna; Scambia, Giovanni; Nero, Camilla; Zormpas-Petridis, Konstantinos Abstract: Homologous Recombination Deficiency (HRD) is a robust, but complex to calculate, predictive biomarker for stratifying patients likely to benefit from PARP inhibition therapy. Although computational pathology algorithms have shown potential in predicting HRD status from routine hematoxylin and eosin (H&E) images, this study evaluates their efficacy specifically in ovarian cancer where the few existing studies have reported suboptimal performance. Genomic instability (GI) index and HRD status were calculated from sequencing data in 484 patients (52% HRD-positive). We adapted two state-of-the-art deep learning algorithms based on classification and regression approaches. For regression we predicted the GI and used zero as threshold to define HRD status. H&E images were split into non-overlapping patches; a pre-trained RetCCL foundation model was used to extract 2048 features from each patch after background extraction and stain-normalization. An attention-based multiple instance learning algorithm was trained on the extracted features to predict GI and HRD status, and generate interpretable feature-importance maps. Additionally, we experimented by applying automatic semantic segmentation, using a Unet model with ResNet50 encoder, to drive the algorithm’s attention on cancer tissue. We used five-fold cross-validation on 380 patients and applied the best fold in a hold-out test set of 104 patients. Our deep learning models predicted HRD with moderate accuracy in the validation and test sets both for classification (AUC=0.67/0.60, F1-score=0.57/0.50 respectively) and regression (F1-score=0.74/0.57 respectively) approaches. Interestingly, despite the fact the HRD is expressed by the cancer cells, attention maps instead showed focus on ovarian stroma areas [Figure 1A]. Focusing attention on tumour areas showed improvement and increased our algorithm’s ability to generalise in the test set (classification: AUC=0.69/0.63, F1-score= 0.76/0.65; regression: F1-score=0.74/0.60 for validation/test) [Figure 1B]. Computational pathology has the potential to predict HRD from H&E images in ovarian cancer. Guiding attention-based mechanisms with cancer tissue segmentation can improve the algorithm’s stability. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/10807/341539 2025-01-01T00:00:00Z