Search

In this article we provide an analysis focusing on clinical use of two deep learning-based automatic detection tools in the field of radiology. The value of these technologies conceived to assist the physicians in the reading of imaging data (like X-rays) is generally assessed by the human-machine performance comparison, which does not take into account the complexity of the interpretation process of radiologists in its social, tacit and emotional dimensions. In this radiological vision work, data which informs the physician about the context surrounding a visible anomaly are essential to the definition of its pathological nature. Likewise, experiential data resulting from the contextual tacit knowledge that regulates professional conduct allows for the assessment of an anomaly according to the radiologist's, and patient's, experience. These data, which remain excluded from artificial intelligence processing, question the gap between the norms incorporated by the machine and those leveraged in the daily work of radiologists. The possibility that automated detection may modify the incorporation or the exercise of tacit knowledge raises questions about the impact of AI technologies on medical work. This article aims to highlight how the standards that emerge from the observation practices of radiologists challenge the automation of their vision work, but also under what conditions AI technologies are considered "objective" and trustworthy by professionals.

This paper examines a kind of explainable AI, centered around what we term pro-hoc explanations, that is a form of support that consists of offering alternative explanations (one for each possible outcome) instead of a specific post-hoc explanation following specific advice. Specifically, our support mechanism utilizes explanations by examples, featuring analogous cases for each category in a binary setting. Pro-hoc explanations are an instance of what we called frictional AI, a general class of decision support aimed at achieving a useful compromise between the increase of decision effectiveness and the mitigation of cognitive risks, such as over-reliance, automation bias and deskilling. To illustrate an instance of frictional AI, we conducted an empirical user study to investigate its impact on the task of radiological detection of vertebral fractures in x-rays. Our study engaged 16 orthopedists in a ‘human-first, second-opinion’ interaction protocol. In this protocol, clinicians first made initial assessments of the x-rays without AI assistance and then provided their final diagnosis after considering the pro-hoc explanations. Our findings indicate that physicians, particularly those with less experience, perceived pro-hoc XAI support as significantly beneficial, even though it did not notably enhance their diagnostic accuracy. However, their increased confidence in final diagnoses suggests a positive overall impact. Given the promisingly high effect size observed, our results advocate for further research into pro-hoc explanations specifically, and into the broader concept of frictional AI.

This paper deals with mineralogical-petrographic, microstructural and geochemical analyses for the archaeometric characterization of silicate-bearing granoblastic marbles from the so-called Waldensian Valleys of Piedmont (i.e. Pellice, Germanasca and lower Chisone valleys, Cottian Alps, Italy). These stones, belonging to the Dora-Maira Massif of the Penninic domain (pre-Carboniferous), are often associated with a talc-bearing mineralization. Since the XIV century, “Waldensian” marbles have been subjected to a relatively intense extractive activity (nowadays almost completely abandoned) and have been widely used, especially during XVI-XIX century, for decoration purposes and as building materials in the Duchy of Savoy, as well as later, in Italy and abroad. Fifteen samples representing four lithofacies and commercial types (named “Statuary white”, “Bardiglio gray”, “Zebrato gray” and “Cipollino green” marbles) from four different quarries (named Cabitto, La Majera, Rocca Corba, and Caugis), were studied through a multianalytical approach. The isotopic signature, combined with the mineral chemistry, allowed tracing marbles origin uniquely. The resulting database can be employed either in the cultural heritage, or in the conservation and restoration science, to identify each “Waldensian” marble from different decorative stones with similar microstructural and/or compositional features, but different origin.

The overburning test method was developed to simulate and predict lime densification, agglomeration, and sporadic melting at the highest potential temperature of lime kilns. These events, that belong to the so-called ‘‘sticking tendency” phenomenon, are associated to formation of crusts, occlusions, and blockages in vertical lime kilns. In this work, fifty carbonate rocks, their insoluble residues, and derived burnt products were investigated through a multianalytical approach. Four groups of rocks having different burnability were identified. In addition, three fundamental mechanisms were related to the abovementioned phenomena: dehydration melting, solid-state, and liquid-phase sintering processes.