Adriano Lucieri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Adriano Lucieri has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Dengel
German Research Center for Artificial Intelligence (DFKI)
10 shared publications - Sheraz Ahmed
German Research Center for Artificial Intelligence
10 shared publications - Muhammad Naseer Bajwa
National University of Sciences and Technology (NUST), Islamabad, Pakistan
4 shared publications Andreas Dengel
Smart Data and Knowledge Services (SDS), Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI) GmbH, Kaiserslautern, Germany
2 shared publications- Christoph Balada
German Research Center for Artificial Intelligence (DFKI) 67663 Kaiserslautern Germany
2 shared publications - Fabian Schmeisser
Department of Computer Science Rheinland‐Pfälzische Technische Universität Kaiserslautern‐Landau Kaiserslautern Germany
2 shared publications
Latest Publications
- Open Access
- 19 October 2025
- Published by Springer Nature
- p. 159-183
Spectral Occlusion - Attribution Beyond Spatial Relevance Heatmaps
Real-world computer vision tasks in high-stakes domains like medicine often go beyond mere object localization. Accurate diagnoses often require the detection and combination of complex factors present in the input. Explanation is therefore particularly challenging, but also necessary due to the high stakes involved. Most existing explanation methods fall short in isolating distributed and overlapping features such as colors and textures. This paper introduces Spectral Occlusion (S-Occ), a method designed to address this limitation, providing multiple additional perspectives to the explanation of complex decisions. Beyond the conventional highlighting of spatial regions, S-Occ makes use of spectral manipulation to indicate dispersed image features such as colors and textures. Different visualizations offer an additional, nuanced insight into the model’s decision-making, resulting in a more holistic representation of the contributing factors. This can help to facilitate the explainability of complex systems. The method is evaluated quantitatively and qualitatively on real-world skin lesion analysis. S-Occ outperforms established methods by an average of 0.38 in explanation Sensitivity, demonstrating its ability to complement spatial attribution methods by facilitating the highlighting of non-trivial, decision-relevant factors. The method’s potential impact spans various high-stakes domains, with particular relevance in medical fields like dermatology and ophthalmology, where nuanced insights are imperative for trustworthy decision-making.
- 19 October 2025
- Published by Springer Nature
- p. 159-183
Open AccessSpectral Occlusion - Attribution Beyond Spatial Relevance Heatmaps
Real-world computer vision tasks in high-stakes domains like medicine often go beyond mere object localization. Accurate diagnoses often require the detection and combination of complex factors present in the input. Explanation is therefore particularly challenging, but also necessary due to the high stakes involved. Most existing explanation methods fall short in isolating distributed and overlapping features such as colors and textures. This paper introduces Spectral Occlusion (S-Occ), a method designed to address this limitation, providing multiple additional perspectives to the explanation of complex decisions. Beyond the conventional highlighting of spatial regions, S-Occ makes use of spectral manipulation to indicate dispersed image features such as colors and textures. Different visualizations offer an additional, nuanced insight into the model’s decision-making, resulting in a more holistic representation of the contributing factors. This can help to facilitate the explainability of complex systems. The method is evaluated quantitatively and qualitatively on real-world skin lesion analysis. S-Occ outperforms established methods by an average of 0.38 in explanation Sensitivity, demonstrating its ability to complement spatial attribution methods by facilitating the highlighting of non-trivial, decision-relevant factors. The method’s potential impact spans various high-stakes domains, with particular relevance in medical fields like dermatology and ophthalmology, where nuanced insights are imperative for trustworthy decision-making.
- 4 December 2024
- Published by Springer Nature
- p. 138-153
Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery
- 4 December 2024
- Published by Springer Nature
- p. 138-153
Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery
- Open Access
- 5 July 2023
- Published by Frontiers Media SA in Frontiers in Bioinformatics
- Vol. 3, 1194993
Translating theory into practice: assessing the privacy implications of concept-based explanations for biomedical AI
Artificial Intelligence (AI) has achieved remarkable success in image generation, image analysis, and language modeling, making data-driven techniques increasingly relevant in practical real-world applications, promising enhanced creativity and efficiency for human users. However, the deployment of AI in high-stakes domains such as infrastructure and healthcare still raises concerns regarding algorithm accountability and safety. The emerging field of explainable AI (XAI) has made significant strides in developing interfaces that enable humans to comprehend the decisions made by data-driven models. Among these approaches, concept-based explainability stands out due to its ability to align explanations with high-level concepts familiar to users. Nonetheless, early research in adversarial machine learning has unveiled that exposing model explanations can render victim models more susceptible to attacks. This is the first study to investigate and compare the impact of concept-based explanations on the privacy of Deep Learning based AI models in the context of biomedical image analysis. An extensive privacy benchmark is conducted on three different state-of-the-art model architectures (ResNet50, NFNet, ConvNeXt) trained on two biomedical (ISIC and EyePACS) and one synthetic dataset (SCDB). The success of membership inference attacks while exposing varying degrees of attribution-based and concept-based explanations is systematically compared. The findings indicate that, in theory, concept-based explanations can potentially increase the vulnerability of a private AI system by up to 16% compared to attributions in the baseline setting. However, it is demonstrated that, in more realistic attack scenarios, the threat posed by explanations is negligible in practice. Furthermore, actionable recommendations are provided to ensure the safe deployment of concept-based XAI systems. In addition, the impact of differential privacy (DP) on the quality of concept-based explanations is explored, revealing that while negatively influencing the explanation ability, DP can have an adverse effect on the models’ privacy.
- 5 July 2023
- Published by Frontiers Media SA in Frontiers in Bioinformatics
- Vol. 3, 1194993
Open AccessTranslating theory into practice: assessing the privacy implications of concept-based explanations for biomedical AI
Artificial Intelligence (AI) has achieved remarkable success in image generation, image analysis, and language modeling, making data-driven techniques increasingly relevant in practical real-world applications, promising enhanced creativity and efficiency for human users. However, the deployment of AI in high-stakes domains such as infrastructure and healthcare still raises concerns regarding algorithm accountability and safety. The emerging field of explainable AI (XAI) has made significant strides in developing interfaces that enable humans to comprehend the decisions made by data-driven models. Among these approaches, concept-based explainability stands out due to its ability to align explanations with high-level concepts familiar to users. Nonetheless, early research in adversarial machine learning has unveiled that exposing model explanations can render victim models more susceptible to attacks. This is the first study to investigate and compare the impact of concept-based explanations on the privacy of Deep Learning based AI models in the context of biomedical image analysis. An extensive privacy benchmark is conducted on three different state-of-the-art model architectures (ResNet50, NFNet, ConvNeXt) trained on two biomedical (ISIC and EyePACS) and one synthetic dataset (SCDB). The success of membership inference attacks while exposing varying degrees of attribution-based and concept-based explanations is systematically compared. The findings indicate that, in theory, concept-based explanations can potentially increase the vulnerability of a private AI system by up to 16% compared to attributions in the baseline setting. However, it is demonstrated that, in more realistic attack scenarios, the threat posed by explanations is negligible in practice. Furthermore, actionable recommendations are provided to ensure the safe deployment of concept-based XAI systems. In addition, the impact of differential privacy (DP) on the quality of concept-based explanations is explored, revealing that while negatively influencing the explanation ability, DP can have an adverse effect on the models’ privacy.
- Open Access
- 26 August 2022
- Published by Springer Nature in Health Information Science and Systems
- Vol. 10 (1) , 1-9
Holistic multi-class classification & grading of diabetic foot ulcerations from plantar thermal images using deep learning
Purpose: Diabetic foot is a common complication associated with diabetes mellitus (DM) leading to ulcerations in the feet. Due to diabetic neuropathy, most patients have reduced sensitivity to pain. As a result, minor injuries go unnoticed and progress into ulcers. The timely detection of potential ulceration points and intervention is crucial in preventing amputation. Changes in plantar temperature are one of the early signs of ulceration. Previous studies have focused on either binary classification or grading of DM severity, but neglect the holistic consideration of the problem. Moreover, multi-class studies exhibit severe performance variations between different classes. Methods: We propose a new convolutional neural network for discrimination between non-DM and five DM severity grades from plantar thermal images and compare its performance against pre-trained networks such as AlexNet and related works. We address the lack of data and imbalanced class distribution, prevalent in prior work, achieving well-balanced classification performance. Results: Our proposed model achieved the best performance with a mean accuracy of 0.9827, mean sensitivity of 0.9684 and mean specificity of 0.9892 in combined diabetic foot detection and grading. Conclusion: To the best of our knowledge, this study sets a new state-of-the-art in plantar foot thermogram detection and grading, while being the first to implement a holistic multi-class classification and grading solution. Reliable automatic thermogram grading is a first step towards the development of smart health devices for DM patients.
- 26 August 2022
- Published by Springer Nature in Health Information Science and Systems
- Vol. 10 (1) , 1-9
Open AccessHolistic multi-class classification & grading of diabetic foot ulcerations from plantar thermal images using deep learning
Purpose: Diabetic foot is a common complication associated with diabetes mellitus (DM) leading to ulcerations in the feet. Due to diabetic neuropathy, most patients have reduced sensitivity to pain. As a result, minor injuries go unnoticed and progress into ulcers. The timely detection of potential ulceration points and intervention is crucial in preventing amputation. Changes in plantar temperature are one of the early signs of ulceration. Previous studies have focused on either binary classification or grading of DM severity, but neglect the holistic consideration of the problem. Moreover, multi-class studies exhibit severe performance variations between different classes. Methods: We propose a new convolutional neural network for discrimination between non-DM and five DM severity grades from plantar thermal images and compare its performance against pre-trained networks such as AlexNet and related works. We address the lack of data and imbalanced class distribution, prevalent in prior work, achieving well-balanced classification performance. Results: Our proposed model achieved the best performance with a mean accuracy of 0.9827, mean sensitivity of 0.9684 and mean specificity of 0.9892 in combined diabetic foot detection and grading. Conclusion: To the best of our knowledge, this study sets a new state-of-the-art in plantar foot thermogram detection and grading, while being the first to implement a holistic multi-class classification and grading solution. Reliable automatic thermogram grading is a first step towards the development of smart health devices for DM patients.
- 25 July 2022
- Published by Springer Nature
- p. 46-61
Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification
- 25 July 2022
- Published by Springer Nature
- p. 46-61
Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification
- 17 March 2022
- Published by Springer Nature
- p. 727-754
Erklärbare KI in der medizinischen Diagnose – Erfolge und Herausforderungen
- 17 March 2022
- Published by Springer Nature
- p. 727-754
Erklärbare KI in der medizinischen Diagnose – Erfolge und Herausforderungen
- Top Cited Papers
- 5 January 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 215, 106620
ExAID: A multimodal explanation framework for computer-aided diagnosis of skin lesions
- 5 January 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 215, 106620
Top Cited PapersExAID: A multimodal explanation framework for computer-aided diagnosis of skin lesions
- 11 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (11) , 7834-7842
Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification
With the advent of machine learning in applications of critical infrastructure such as healthcare and energy, privacy is a growing concern in the minds of stakeholders. It is pivotal to ensure that neither the model nor the data can be used to extract sensitive information used by attackers against individuals or to harm whole societies through the exploitation of critical infrastructure. The applicability of machine learning in these domains is mostly limited due to a lack of trust regarding the transparency and the privacy constraints. Various safety-critical use cases (mostly relying on time-series data) are currently underrepresented in privacy-related considerations. By evaluating several privacy-preserving methods regarding their applicability on time-series data, we validated the inefficacy of encryption for deep learning, the strong dataset dependence of differential privacy, and the broad applicability of federated methods.
- 11 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (11) , 7834-7842
Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification
With the advent of machine learning in applications of critical infrastructure such as healthcare and energy, privacy is a growing concern in the minds of stakeholders. It is pivotal to ensure that neither the model nor the data can be used to extract sensitive information used by attackers against individuals or to harm whole societies through the exploitation of critical infrastructure. The applicability of machine learning in these domains is mostly limited due to a lack of trust regarding the transparency and the privacy constraints. Various safety-critical use cases (mostly relying on time-series data) are currently underrepresented in privacy-related considerations. By evaluating several privacy-preserving methods regarding their applicability on time-series data, we validated the inefficacy of encryption for deep learning, the strong dataset dependence of differential privacy, and the broad applicability of federated methods.
- Open Access
Deep Learning Based Decision Support for Medicine -- A Case Study on Skin Cancer Diagnosis
Early detection of skin cancers like melanoma is crucial to ensure high chances of survival for patients. Clinical application of Deep Learning (DL)-based Decision Support Systems (DSS) for skin cancer screening has the potential to improve the quality of patient care. The majority of work in the medical AI community focuses on a diagnosis setting that is mainly relevant for autonomous operation. Practical decision support should, however, go beyond plain diagnosis and provide explanations. This paper provides an overview of works towards explainable, DL-based decision support in medical applications with the example of skin cancer diagnosis from clinical, dermoscopic and histopathologic images. Analysis reveals that comparably little attention is payed to the explanation of histopathologic skin images and that current work is dominated by visual relevance maps as well as dermoscopic feature identification. We conclude that future work should focus on meeting the stakeholder's cognitive concepts, providing exhaustive explanations that combine global and local approaches and leverage diverse modalities. Moreover, the possibility to intervene and guide models in case of misbehaviour is identified as a major step towards successful deployment of AI as DL-based DSS and beyond.
Open AccessDeep Learning Based Decision Support for Medicine -- A Case Study on Skin Cancer Diagnosis
Early detection of skin cancers like melanoma is crucial to ensure high chances of survival for patients. Clinical application of Deep Learning (DL)-based Decision Support Systems (DSS) for skin cancer screening has the potential to improve the quality of patient care. The majority of work in the medical AI community focuses on a diagnosis setting that is mainly relevant for autonomous operation. Practical decision support should, however, go beyond plain diagnosis and provide explanations. This paper provides an overview of works towards explainable, DL-based decision support in medical applications with the example of skin cancer diagnosis from clinical, dermoscopic and histopathologic images. Analysis reveals that comparably little attention is payed to the explanation of histopathologic skin images and that current work is dominated by visual relevance maps as well as dermoscopic feature identification. We conclude that future work should focus on meeting the stakeholder's cognitive concepts, providing exhaustive explanations that combine global and local approaches and leverage diverse modalities. Moreover, the possibility to intervene and guide models in case of misbehaviour is identified as a major step towards successful deployment of AI as DL-based DSS and beyond.
- 17 November 2020
- Published by Springer Nature
- p. 185-193
Explaining AI-Based Decision Support Systems Using Concept Localization Maps
- 17 November 2020
- Published by Springer Nature
- p. 185-193
Explaining AI-Based Decision Support Systems Using Concept Localization Maps