Search Results (6)

Explainable Artificial Intelligence (XAI) is increasingly important in computer vision, aiming to connect complex model outputs with human understanding. This review provides a focused comparative analysis of representative XAI methods in four main categories, attribution-based, activation-based, perturbation-based, and transformer-based approaches, selected from a broader literature landscape. Attribution-based methods like Grad-CAM highlight key input regions using gradients and feature activation. Activation-based methods analyze the responses of internal neurons or feature maps to identify which parts of the input activate specific layers or units, helping to reveal hierarchical feature representations. Perturbation-based techniques, such as RISE, assess feature importance through input modifications without accessing internal model details. Transformer-based methods, which use self-attention, offer global interpretability by tracing information flow across layers. We evaluate these methods using metrics such as faithfulness, localization accuracy, efficiency, and overlap with medical annotations. We also propose a hierarchical taxonomy to classify these methods, reflecting the diversity of XAI techniques. Results show that RISE has the highest faithfulness but is computationally expensive, limiting its use in real-time scenarios. Transformer-based methods perform well in medical imaging, with high IoU scores, though interpreting attention maps requires care. These findings emphasize the need for context-aware evaluation and hybrid XAI methods balancing interpretability and efficiency. The review ends by discussing ethical and practical challenges, stressing the need for standard benchmarks and domain-specific tuning. Full article

Chronic inflammatory bowel diseases, such as Crohn’s disease and ulcerative colitis, present diagnostic challenges due to their complex and heterogeneous nature. While histology remains fundamental for accurate diagnosis, a multidisciplinary approach incorporating clinical, endoscopic, and imaging modalities is increasingly recognized as essential for comprehensive evaluation. This article delves into the importance of integrating various diagnostic techniques in the assessment of IBD. Colonoscopy and histology, with its ability to directly visualize the intestinal mucosa, play a central role in the diagnostic process. However, histological analysis alone may not suffice, necessitating the inclusion of advanced imaging techniques, such as magnetic resonance enterography (MRE), computed tomography enterography (CTE), and intestinal ultrasound (IUS). These techniques provide valuable insights into the disease’s extent, severity, and complications, and should be used in conjunction with biochemical parameters. These modalities complement traditional endoscopic and histological findings, offering a more holistic understanding of the disease process. A multidisciplinary approach that incorporates clinical, endoscopic, histological, serological, and imaging assessments enables clinicians to achieve a more accurate and timely diagnosis of IBD. Moreover, this integrated approach facilitates personalized treatment strategies tailored to individual patient needs, ultimately improving clinical outcomes and quality of life for those affected by chronic inflammatory bowel diseases. Full article

Haemophilic arthropathy (HA) is one of the most serious complications of haemophilia. It starts with joint bleeding, leading to synovitis which, in turn, can cause damage to the cartilage and subchondral bone, eventually inducing degenerative joint disease. Despite significant improvements in haemophilia treatment over the past two decades and recent guidelines from ISTH and WFH recommending FVIII trough levels of at least 3 IU/dL during prophylaxis, patients with haemophilia still develop joint disease. The pathophysiology of HA is complex, involving both inflammatory and degenerative components. Early diagnosis is key for proper management. Imaging can detect joint subclinical changes and influence prophylaxis. Magnetic resonance imagining (MRI) and ultrasound are the most frequently used methods in comprehensive haemophilia care centres. Biomarkers of joint health have been proposed to determine osteochondral joint deterioration, but none of these biomarkers has been validated or used in clinical practice. Early prophylaxis is key in all severe haemophilia patients to prevent arthropathy. Treatment is essentially based on prophylaxis intensification and chronic joint pain management. However, there remain significant gaps in the knowledge of the mechanisms responsible for HA and prognosis-influencing factors. Better understanding in this area could produce more effective interventions likely to ultimately prevent or attenuate the development of HA. Full article

This paper studies the national projects defended by Spanish political parties on the basis of the image they project in relation to women’s roles. To do so, we start with a critical review of nations and welfare states as masculinized projects, and from this we design a strategy based on the analysis of the manifestos issued by each political party in 2020 on International Women’s Day. The results obtained reflect the existence of three different ways of understanding the nation from a gender perspective: the first bloc, formed by the two conservative parties, PP and VOX, reproduces the nation by basing their discourse on gender inequalities, with a great weight of care for women; the second, formed by the most progressive parties (IU and Podemos), is situated in a clearly feminist perspective; the third, formed by the PSOE, shows a mixture of ideas that is reflected in considering both sexes as political subjects of feminism, and in presenting a discourse of the liberal and socialist current. Full article

According to literature and despite their commercial success, state-of-the-art two-stage non-iterative geographic object-based image analysis (GEOBIA) systems and three-stage iterative geographic object-oriented image analysis (GEOOIA) systems, where GEOOIA/GEOBIA, remain affected by a lack of productivity, general consensus and research. To outperform the Quality Indexes of Operativeness (OQIs) of existing GEOBIA/GEOOIA systems in compliance with the Quality Assurance Framework for Earth Observation (QA4EO) guidelines, this methodological work is split into two parts. Based on an original multi-disciplinary Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis of the GEOBIA/GEOOIA approaches, the first part of this work promotes a shift of learning paradigm in the pre-attentive vision first stage of a remote sensing (RS) image understanding system (RS-IUS), from sub-symbolic statistical model-based (inductive) image segmentation to symbolic physical model-based (deductive) image preliminary classification capable of accomplishing image sub-symbolic segmentation and image symbolic pre-classification simultaneously. In the present second part of this work, a novel hybrid (combined deductive and inductive) RS-IUS architecture featuring a symbolic deductive pre-attentive vision first stage is proposed and discussed in terms of: (a) computational theory (system design), (b) information/knowledge representation, (c) algorithm design and (d) implementation. As proof-of-concept of symbolic physical model-based pre-attentive vision first stage, the spectral knowledge-based, operational, near real-time, multi-sensor, multi-resolution, application-independent Satellite Image Automatic Mapper™ (SIAM™) is selected from existing literature. To the best of these authors’ knowledge, this is the first time a symbolic syntactic inference system, like SIAM™, is made available to the RS community for operational use in a RS-IUS pre-attentive vision first stage, to accomplish multi-scale image segmentation and multi-granularity image pre-classification simultaneously, automatically and in near real-time. Full article

According to existing literature and despite their commercial success, state-of-the-art two-stage non-iterative geographic object-based image analysis (GEOBIA) systems and three-stage iterative geographic object-oriented image analysis (GEOOIA) systems, where GEOOIA/GEOBIA, remain affected by a lack of productivity, general consensus and research. To outperform the degree of automation, accuracy, efficiency, robustness, scalability and timeliness of existing GEOBIA/GEOOIA systems in compliance with the Quality Assurance Framework for Earth Observation (QA4EO) guidelines, this methodological work is split into two parts. The present first paper provides a multi-disciplinary Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis of the GEOBIA/GEOOIA approaches that augments similar analyses proposed in recent years. In line with constraints stemming from human vision, this SWOT analysis promotes a shift of learning paradigm in the pre-attentive vision first stage of a remote sensing (RS) image understanding system (RS-IUS), from sub-symbolic statistical model-based (inductive) image segmentation to symbolic physical model-based (deductive) image preliminary classification. Hence, a symbolic deductive pre-attentive vision first stage accomplishes image sub-symbolic segmentation and image symbolic pre-classification simultaneously. In the second part of this work a novel hybrid (combined deductive and inductive) RS-IUS architecture featuring a symbolic deductive pre-attentive vision first stage is proposed and discussed in terms of: (a) computational theory (system design); (b) information/knowledge representation; (c) algorithm design; and (d) implementation. As proof-of-concept of symbolic physical model-based pre-attentive vision first stage, the spectral knowledge-based, operational, near real-time Satellite Image Automatic Mapper™ (SIAM™) is selected from existing literature. To the best of these authors’ knowledge, this is the first time a symbolic syntactic inference system, like SIAM™, is made available to the RS community for operational use in a RS-IUS pre-attentive vision first stage, to accomplish multi-scale image segmentation and multi-granularity image pre-classification simultaneously, automatically and in near real-time. Full article