Adrian Galdran

EDBT 2026 Demo / reviewers in the wild / expert

dblp:160/2676 · DBLP profile ↗

← Back

33ranked-venue papers

12as first author

16since 2021 · last 2026

0000-0002-5992-1520ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Applied, interdisciplinary, general and emerging computing · 19 · 6 first-author · 13 since 2021Graphics, computer vision, multimedia, augmented reality and games · 17 · 12 first-author · 8 since 2021Artificial intelligence and machine learning · 9 · 1 first-author · 3 since 2021Systems, architecture and hardware · 1Human-computer interaction and ubiquitous computing · 1

Year	Publication	Venue	Position
2026	JustRAIGS: Justified Referral in AI Glaucoma Screening Challenge abstract A major contributor to permanent vision loss is glaucoma. Early diagnosis is crucial for preventing vision loss due to glaucoma, making glaucoma screening essential. A more affordable method of glaucoma screening can be achieved by applying artificial intelligence to evaluate color fundus photographs (CFPs). We present the Justified Referral in AI Glaucoma Screening (JustRAIGS) challenge to further develop these AI algorithms for glaucoma screening and to assess their efficacy. To support this challenge, we have generated a distinctive big dataset containing more than 110,000 meticulously labeled CFPs obtained from approximately 60,000 patients and 500 distinct screening centers in the USA. Our objective is to assess the practicality of creating advanced and dependable AI systems that can take a CFP as input and produce the probability of referable glaucoma, as well as outputs for glaucoma justification by integrating both binary and multi-label classification tasks. This paper presents the evaluation of solutions provided by nine teams, recognizing the team with the highest level of performance. The highest achieved score of sensitivity at a specificity level of 95% was 85%, and the highest achieved score of Hamming losses average was 0.13. Additionally, we test the top three participants' algorithms on an external dataset to validate the performance and generalization of these models. The outcomes of this research can offer valuable insights into the development of intelligent systems for detecting glaucoma. Ultimately, findings can aid in the early detection and treatment of glaucoma patients, hence decreasing preventable vision impairment and blindness caused by glaucoma. Yeganeh Madadi, Hina Raja, Koen A. Vermeer, Hans G. Lemij, Xiaoqin Huang, Gitaek Kwon, Adrian Galdran, Miguel Ángel González Ballester, Dan Presil, Kristhian Aguilar, Victor F. Cavalcante, Celso B. Carvalho, Waldir S. S. Júnior, Mateus Oliveira, Charilaos Apostolidis, Aggelos K. Katsaggelos, Tomasz Kubrak, Ángela Casado, Jónathan Heras, Marcos Ortega 0001, Lucía Ramos, Philippe Zhang, Weili Jiang, Pierre-Henri Conze, Mathieu Lamard, Gwenolé Quellec, Mostafa El Habib Daho, Madukuri Shaurya, Anumeha Varma, Siamak Yousefi	IEEE Trans. Medical Imaging	11
2025	Low-dose computed tomography perceptual image quality assessment abstract In computed tomography (CT) imaging, optimizing the balance between radiation dose and image quality is crucial due to the potentially harmful effects of radiation on patients. Although subjective assessments by radiologists are considered the gold standard in medical imaging, these evaluations can be time-consuming and costly. Thus, objective methods, such as the peak signal-to-noise ratio and structural similarity index measure, are often employed as alternatives. However, these metrics, initially developed for natural images, may not fully encapsulate the radiologists' assessment process. Consequently, interest in developing deep learning-based image quality assessment (IQA) methods that more closely align with radiologists' perceptions is growing. A significant barrier to this development has been the absence of open-source datasets and benchmark models specific to CT IQA. Addressing these challenges, we organized the Low-dose Computed Tomography Perceptual Image Quality Assessment Challenge in conjunction with the Medical Image Computing and Computer Assisted Intervention 2023. This event introduced the first open-source CT IQA dataset, consisting of 1,000 CT images of various quality, annotated with radiologists' assessment scores. As a benchmark, this challenge offers a comprehensive analysis of six submitted methods, providing valuable insight into their performance. This paper presents a summary of these methods and insights. This challenge underscores the potential for developing no-reference IQA methods that could exceed the capabilities of full-reference IQA methods, making a significant contribution to the research community with this novel dataset. The dataset is accessible at https://zenodo.org/records/7833096. Wonkyeong Lee, Fabian Wagner, Adrian Galdran, Yongyi Shi, Wenjun Xia, Ge Wang 0001, Xuanqin Mou, Md. Atik Ahamed, Abdullah-Al-Zubaer Imran, Jieun Oh, Kyung Sang Kim, Jong Tak Baek, Dongheon Lee 0002, Boohwi Hong, Philip Tempelman, Donghang Lyu, Adrian Kuiper, Lars van Blokland, Maria Baldeon Calisto, Scott S. Hsieh, Minah Han, Jongduk Baek, Andreas K. Maier, Adam S. Wang, Garry Gold, Jang Hwan Choi 0001	Medical Image Anal.	3
2025	Evaluation of techniques for automated classification and artery quantification of the circle of Willis on TOF-MRA images: The CROWN challenge abstract Assessing risk factors for intracranial aneurysm (IA) development on images is crucial for early detection of high-risk cases. IAs often form at bifurcations within the circle of Willis (CoW), but manual assessment of these arteries is both time-consuming and susceptible to inconsistencies. Previous studies on imaging markers for IA development lack sufficient evidence for clinical implications, highlighting the need for automated methods to assess CoW morphology. No systematic approach currently exists to identify the best methodological strategies. To address this, we organized a scientific challenge to compare various techniques against a clinical reference standard. Participants were tasked with (1) automated classification of CoW anatomical variants and (2) automated prediction of CoW artery diameters and bifurcation angles. We provided 300 TOF-MRA scans for training and another 300 for testing, all manually annotated. Submissions were evaluated using balanced accuracy, mean absolute error, and Pearson correlation coefficient metrics. This paper provides a detailed analysis of the results from six participating teams. The findings show that various methods may be suitable for automated CoW assessment, but that these need further improvement to meet clinical standards. The challenge remains open for future submissions, offering a benchmark for new techniques. Iris N. Vos, Ynte M. Ruigrok, Edwin Bennink, Mireille R. E. Velthuis, Barbara Paic, Maud E. H. Ophelders, Myrthe A. D. Buser, Bas H. M. van der Velden, Chen Geng 0002, Matthieu Coupet, Félix Dumais, Adrian Galdran, Wei Liu 0005, Madhu S. Nair, Mathieu Naudin, Preena K. P., Keerthi A. S. Pillai, Thierry Urruty, Yakang Dai, Kaiyuan Yang 0003, Fabio Musio, Bjoern Menze, Birgitta K. Velthuis, Hugo J. Kuijf	Medical Image Anal.	12
2024	The Centerline-Cross Entropy Loss for Vessel-Like Structure Segmentation: Better Topology Consistency Without Sacrificing Accuracy César Acebes, Abdel H. Moustafa, Oscar Camara 0001, Adrian Galdran	MICCAI (8)	4
2024	Do we really need dice? The hidden region-size biases of segmentation losses Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi, Ismail Ben Ayed	Medical Image Anal.	3
2024	Diabetic foot ulcers segmentation challenge report: Benchmark and analysis abstract Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and laborious. Recently, methods based on deep learning have shown excellent results in automatic segmentation of medical images, however, they require large-scale datasets for training, and there is limited consensus on which methods perform the best. The 2022 Diabetic Foot Ulcers segmentation challenge was held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention, which sought to address these issues and stimulate progress in this research domain. A training set of 2000 images exhibiting diabetic foot ulcers was released with corresponding segmentation ground truth masks. Of the 72 (approved) requests from 47 countries, 26 teams used this data to develop fully automated systems to predict the true segmentation masks on a test set of 2000 images, with the corresponding ground truth segmentation masks kept private. Predictions from participating teams were scored and ranked according to their average Dice similarity coefficient of the ground truth masks and prediction masks. The winning team achieved a Dice of 0.7287 for diabetic foot ulcer segmentation. This challenge has now entered a live leaderboard stage where it serves as a challenging benchmark for diabetic foot ulcer segmentation. Moi Hoon Yap, Bill Cassidy, Michal Byra, Ting-Yu Liao, Huahui Yi, Adrian Galdran, Yung-Han Chen, Raphael Brüngel, Sven Koitka, Christoph M. Friedrich, Yu-Wen Lo, Ching-Hui Yang, Kang Li 0004, Qicheng Lao, Miguel Ángel González Ballester, Gustavo Carneiro 0001, Yi-Jen Ju, Juinn-Dar Huang, Joseph Pappachan, Neil D. Reeves, Vishnu Chandrabalan, Darren Dancey, Connah Kendrick	Medical Image Anal.	6
2024	AIROGS: Artificial Intelligence for Robust Glaucoma Screening Challenge abstract The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening. Coen de Vente, Koen A. Vermeer, Nicolas Jaccard, He Wang 0016, Hongyi Sun, Firas Khader, Daniel Truhn, Temirgali Aimyshev, Yerkebulan Zhanibekuly, Tien-Dung Le, Adrian Galdran, Miguel Ángel González Ballester, Gustavo Carneiro 0001, Devika R. G., Hrishikesh Panikkasseril Sethumadhavan, Densen Puthussery, Hong Liu 0007, Zekang Yang, Satoshi Kondo, Satoshi Kasai, Ashritha Durvasula, Jónathan Heras, Miguel Ángel Zapata, Teresa Araujo, Guilherme Aresta, Hrvoje Bogunovic, Mustafa Arikan, Yeong Chan Lee, Hyun Bin Cho, Yoon Ho Choi, Abdul Qayyum 0002, Muhammad Imran Razzak, Bram van Ginneken, Hans G. Lemij, Clara I. Sánchez	IEEE Trans. Medical Imaging	11
2023	Why is the Winner the Best? abstract International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work. Matthias Eisenmann, Annika Reinke, Vivienn Weru, Minu Tizabi, Fabian Isensee, Tim Adler, Sharib Ali, Vincent Andrearczyk, Marc Aubreville, Ujjwal Baid, Spyridon Bakas, Niranjan Balu, Sophia Bano, Jorge Bernal, Sebastian Bodenstedt, Alessandro Casella, Veronika Cheplygina, Marie Daum, Marleen de Bruijne, Adrien Depeursinge, Reuben Dorent, Jan Egger, David Gage Ellis, Sandy Engelhardt, Melanie Ganz-Benjaminsen, Noha M. Ghatwary, Gabriel Girard, Patrick Godau, Anubha Gupta, Lasse Hansen, Kanako Harada, Mattias P. Heinrich, Nicholas Heller, Alessa Hering, Arnaud Huaulmé, Pierre Jannin, A. Emre Kavur, Oldrich Kodym, Michal Kozubek 0001, Jianning Li 0002, Hongwei Li 0004, Jun Ma 0016, Carlos Martín-Isla, Bjoern Menze, J. Alison Noble, Valentin Oreiller, Nicolas Padoy, Sarthak Pati, Kelly Payette, Tim Rädsch, Jonathan Rafael-Patino, Vivek Singh Bawa, Stefanie Speidel, Carole H. Sudre, Kimberlin M. H. van Wijnen, Martin Wagner 0001, D. Wei, Amine Yamlahi, Moi Hoon Yap, C. Yuan, Maximilian Zenk, A. Zia, David Zimmerer, Dogu Baran Aydogan, Binod Bhattarai, Louise Bloch, Raphael Brüngel, J. Cho, C. Choi, Qi Dou 0001, Ivan Ezhov, Christoph M. Friedrich, C. Fuller, Rebati Raman Gaire, Adrian Galdran, Álvaro García-Faura, Maria Grammatikopoulou, S. Hong, Mostafa Jahanifar, I. Jang, Abdolrahim Kadkhodamohammadi, I. Kang, Florian Kofler, S. Kondo, Hugo J. Kuijf, M. Luu, Tomaz Martincic, Pedro Morais, Mohamed A. Naser, Bruno Oliveira 0002, David Owen 0001, S. Pang, Szymon Plotka, Élodie Puybareau, Nasir M. Rajpoot, K. Ryu, Numan Saeed, Adam J. Shephard, Dejan Stepec, Ronast Subedi, Guillaume Tochon, Helena R. Torres, Hélène Urien, João L. Vilaça, Kareem A. Wahid, Benedikt Wiestler, Marek Wodzinski, F. Xia, J. Xie, Z. Xiong, Sen Yang 0006, Klaus H. Maier-Hein, Paul F. Jaeger, Annette Kopp-Schneider, Lena Maier-Hein	CVPR	75
2023	Class Adaptive Network Calibration abstract Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functions as part of the learning objective, along-side a standard classification loss, with a hyper-parameter controlling the relative contribution of each term. Nevertheless, these methods share two major drawbacks: 1) the scalar balancing weight is the same for all classes, hindering the ability to address different intrinsic difficulties or imbalance among classes; and 2) the balancing weight is usually fixed without an adaptive strategy, which may prevent from reaching the best compromise between accuracy and calibration, and requires hyper-parameter search for each application. We propose Class Adaptive Label Smoothing (CALS) for calibrating deep networks, which allows to learn class-wise multipliers during training, yielding a powerful alternative to common label smoothing penalties. Our method builds on a general Augmented Lagrangian approach, a well-established technique in constrained optimization, but we introduce several modifications to tailor it for large-scale, class-adaptive training. Comprehensive evaluation and multiple comparisons on a variety of benchmarks, including standard and long-tailed image classification, semantic segmentation, and text classification, demonstrate the superiority of the proposed method. The code is available at https://github.com/by-liu/CALS. Bingyuan Liu, Jérôme Rony, Adrian Galdran, Jose Dolz, Ismail Ben Ayed	CVPR	3
2023	Performance Metrics for Probabilistic Ordinal Classifiers Adrian Galdran	MICCAI (3)	1
2023	Multi-Head Multi-Loss Model Calibration Adrian Galdran, Johan Verjans, Gustavo Carneiro 0001, Miguel Ángel González Ballester	MICCAI (3)	1
2023	Calibrating segmentation networks with margin-based label smoothing Balamurali Murugesan, Bingyuan Liu, Adrian Galdran, Ismail Ben Ayed, Jose Dolz	Medical Image Anal.	3
2022	The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration abstract In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the cross-entropy during training, as it promotes the predicted softmax probabilities to match the one-hot label assignments. This yields a pre-softmax activation of the correct class that is significantly larger than the remaining activations. Recent evidence from the literature suggests that loss functions that embed implicit or explicit maximization of the entropy of predictions yield state-of-the-art calibration performances. We provide a unifying constrained-optimization perspective of current state-of-the-art calibration losses. Specifically, these losses could be viewed as approximations of a linear penalty (or a Lagrangian term) imposing equality constraints on logit distances. This points to an important limitation of such underlying equality constraints, whose ensuing gradients constantly push towards a non-informative solution, which might prevent from reaching the best compromise between the discriminative performance and calibration of the model during gradient-based optimization. Following our observations, we propose a simple and flexible generalization based on inequality constraints, which imposes a controllable margin on logit distances. Comprehensive experiments on a variety of image classification, semantic segmentation and NLP benchmarks demonstrate that our method sets novel state-of-the-art results on these tasks in terms of network calibration, without affecting the discriminative performance. The code is available at https://github.com/by-liu/MbLS. Bingyuan Liu, Ismail Ben Ayed, Adrian Galdran, Jose Dolz	CVPR	3
2022	Test Time Transform Prediction for Open Set Histopathological Image Recognition Adrian Galdran, Katherine Jane Hewitt, Narmin Ghaffari Laleh, Jakob Nikolas Kather, Gustavo Carneiro 0001, Miguel Ángel González Ballester	MICCAI (2)	1
2021	Balanced-MixUp for Highly Imbalanced Medical Image Classification Adrian Galdran, Gustavo Carneiro 0001, Miguel Ángel González Ballester	MICCAI (5)	1
2021	LNDb challenge on automatic lung cancer patient management João Pedrosa, Guilherme Aresta, Carlos Ferreira 0006, Gurraj Atwal, Hady Ahmady Phoulady, Rongzhen Chen, Jiaoliang Li, Liansheng Wang 0002, Adrian Galdran, Abdelhamid Bouchachia, Krishna Chaitanya Kaluva, Kiran Vaidhya, Abhijith Chunduru, Sambit Tarai, Sai Prasad Pranav Nadimpalli, Suthirth Vaidya, Ildoo Kim, Alexandr G. Rassadin, Zhenhuan Tian, Zhongwei Sun, Yizhuan Jia, Xuejun Men, António Cunha, Aurélio J. C. Campilho	Medical Image Anal.	10
2020	Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images Adrian Galdran, Jose Dolz, Hadi Chakor, Hervé Lombaert, Ismail Ben Ayed	MICCAI (5)	1
2019	Self-supervised blur detection from synthetically blurred scenes Aitor Alvarez-Gila, Adrian Galdran, Estíbaliz Garrote, Joost van de Weijer 0001	Image Vis. Comput.	2
2019	CATARACTS: Challenge on automatic tool annotation for cataRACT surgery Hassan Al Hajj, Mathieu Lamard, Pierre-Henri Conze, Soumali Roychowdhury, Xiaowei Hu 0001, Gabija Marsalkaite, Odysseas Zisimopoulos, Muneer Ahmad Dedmari, Fenqiang Zhao, Jonas Prellberg, Manish Sahu, Adrian Galdran, Teresa Araujo, Duc My Vo, Chandan Panda, Navdeep Dahiya, Satoshi Kondo, Zhengbing Bian, Gwenolé Quellec	Medical Image Anal.	12
2018	On the Duality Between Retinex and Image Dehazing abstract Image dehazing deals with the removal of undesired loss of visibility in outdoor images due to the presence of fog. Retinex is a color vision model mimicking the ability of the Human Visual System to robustly discount varying illuminations when observing a scene under different spectral lighting conditions. Retinex has been widely explored in the computer vision literature for image enhancement and other related tasks. While these two problems are apparently unrelated, the goal of this work is to show that they can be connected by a simple linear relationship. Specifically, most Retinex-based algorithms have the characteristic feature of always increasing image brightness, which turns them into ideal candidates for effective image dehazing by directly applying Retinex to a hazy image whose intensities have been inverted. In this paper, we give theoretical proof that Retinex on inverted intensities is a solution to the image dehazing problem. Comprehensive qualitative and quantitative results indicate that several classical and modern implementations of Retinex can be transformed into competing image dehazing algorithms performing on pair with more complex fog removal methods, and can overcome some of the main challenges associated with this problem. Adrian Galdran, Aitor Alvarez-Gila, Alessandro Bria, Javier Vazquez-Corral, Marcelo Bertalmío	CVPR	1
2018	Weakly Supervised Fog Detection abstract Image dehazing tries to solve an undesired loss of visibility in outdoor images due to the presence of fog. Recently, machine-learning techniques have shown great dehazing ability. However, in order to be trained, they require training sets with pairs of foggy images and their clean counterparts, or a depth-map. In this paper, we propose to learn the appearance of fog from weakly-labeled data. Specifically, we only require a single label per-image stating if it contains fog or not. Based on the Multiple-Instance Learning framework, we propose a model that can learn from image-level labels to predict if an image contains haze reasoning at a local level. Fog detection performance of the proposed method compares favorably with two popular techniques, and the attention maps generated by the model demonstrate that it effectively learns to disregard sky regions as indicative of the presence of fog, a common pitfall of current image dehazing techniques. Adrian Galdran, Pedro Costa 0005, Javier Vazquez-Corral, Aurélio J. C. Campilho	ICIP	1
2018	MedAL: Accurate and Robust Deep Active Learning for Medical Image Analysis abstract Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance. However, such large labeled datasets are costly to acquire. Active learning techniques can be used to minimize the number of required training labels while maximizing the model's performance. In this work, we propose a novel sampling method that queries the unlabeled examples that maximize the average distance to all training set examples in a learned feature space. We then extend our sampling method to define a better initial training set, without the need for a trained model, by using Oriented FAST and Rotated BRIEF (ORB) feature descriptors. We validate MedAL on 3 medical image datasets and show that our method is robust to different dataset properties. MedAL is also efficient, achieving 80% accuracy on the task of Diabetic Retinopathy detection using only 425 labeled images, corresponding to a 32% reduction in the number of required labeled examples compared to the standard uncertainty sampling technique, and a 40% reduction compared to random sampling. Asim Smailagic, Pedro Costa 0005, Hae Young Noh, Devesh Walawalkar, Kartik Khandelwal, Adrian Galdran, Mostafa Mirshekari, Jonathon Fagert, Susu Xu, Pei Zhang 0001, Aurélio J. C. Campilho	ICMLA	6
2018	End-to-End Supervised Lung Lobe Segmentation abstract The segmentation and characterization of the lung lobes are important tasks for Computer Aided Diagnosis (CAD) systems related to pulmonary disease. The detection of the fissures that divide the lung lobes is non-trivial when using classical methods that rely on anatomical information like the localization of the airways and vessels. This work presents a fully automatic and supervised approach to the problem of the segmentation of the five pulmonary lobes from a chest Computer Tomography (CT) scan using a Fully Regularized V-Net (FRV- Net), a 3D Fully Convolutional Neural Network trained end-to- end. Our network was trained and tested in a custom dataset that we make publicly available. It can correctly separate the lobes even in cases when the fissure is not well delineated, achieving 0.93 in per-lobe Dice Coefficient and 0.85 in the inter-lobar Dice Coefficient in the test set. Both quantitative and qualitative results show that the proposed method can learn to produce correct lobe segmentations even when trained on a reduced dataset. Filipe T. Ferreira, Patrick Sousa, Adrian Galdran, Marta R. Sousa, Aurélio J. C. Campilho	IJCNN	3
2018	A No-Reference Quality Metric for Retinal Vessel Tree Segmentation Adrian Galdran, Pedro Costa 0005, Alessandro Bria, Teresa Araujo, Ana Maria Mendonça, Aurélio J. C. Campilho	MICCAI (1)	1
2018	A Pixel-Wise Distance Regression Approach for Joint Retinal Optical Disc and Fovea Detection Maria Inês Meyer, Adrian Galdran, Ana Maria Mendonça, Aurélio J. C. Campilho	MICCAI (2)	2
2018	Image dehazing by artificial multiple-exposure image fusion Adrian Galdran	Signal Process.	1
2018	End-to-End Adversarial Retinal Image Synthesis abstract In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality. Pedro Costa 0005, Adrian Galdran, Maria Inês Meyer, Meindert Niemeijer, Michael D. Abràmoff, Ana Maria Mendonça, Aurélio J. C. Campilho	IEEE Trans. Medical Imaging	2
2017	Illumination Correction by Dehazing for Retinal Vessel Segmentation abstract Assessment of retinal vessels is fundamental for the diagnosis of many disorders such as heart diseases, diabetes and hypertension. The imaging of retina using advanced fundus camera has become a standard in computer-assisted diagnosis of opthalmic disorders. Modern cameras produce high quality color digital images, but during the acquisition process the light reflected by the retinal surface generates a luminosity and contrast variation. Irregular illumination can introduce severe distortions in the resulting images, decreasing the visibility of anatomical structures and consequently demoting the performance of the automated segmentation of these structures. In this paper, a novel approach for illumination correction of color fundus images is proposed and applied as preprocessing step for retinal vessel segmentation. Our method builds on the connection between two different phenomena, shadows and haze, and works by removing the haze from the image in the inverted intensity domain. This is shown to be equivalent to correct the nonuniform illumination in the original intensity domain. We tested the proposed method as preprocessing stage of two vessel segmentation methods, one unsupervised based on mathematical morphology, and one supervised based on deep learning Convolutional Neural Networks (CNN). Experiments were performed on the publicly available retinal image database DRIVE. Statistically significantly better vessel segmentation performance was achieved in both test cases when illumination correction was applied. Benedetta Savelli, Alessandro Bria, Adrian Galdran, Claudio Marrocco, Mario Molinara, Aurélio J. C. Campilho, Francesco Tortorella	CBMS	3
2017	Deflectometry setup definition for automatic chrome surface inspection abstract A recurrent problem in the industrial sector is the quality control and surface inspection of reflecting pieces with non-planar surfaces. This is an extended and non-solved problem because it is related not only to the material itself but also to the coating. This problem appears in a wide spectrum of industrial sectors such as automation, aeronautics or orthopaedics. In recent years, a new imaging technology called deflectometry has been introduced in the field of surface inspection for industrial applications. This technology features a high resolution camera and a dedicated illumination system-based on displaying fringe patterns in a monitor-allowing the detection of irregularities in surfaces. However, the introduction of this technology into automated quality control systems remains a challenging task, due to the wide range of defects and shapes that can appear. It becomes thus necessary to characterize different types of errors and their associated detection setups. In this paper we propose a novel methodology to define and analyse the best setup for each pattern. We also explore an efficient technique to maximize the number of different pieces inspected without modifying the setup of the acquisition system. Experimental results show that the presented methodology defines an inspection method that can be installed in an automatic quality control device for non-planar surfaces analysis of manufactured products. Alberto Isasi-Andrieu, Estíbaliz Garrote, Pedro M. Iriondo, David Aldama-Gant, Adrian Galdran	ETFA	5
2017	EyeQual: Accurate, Explainable, Retinal Image Quality Assessment abstract Given a retinal image, can we automatically determine whether it is of high quality (suitable for medical diagnosis)? Can we also explain our decision, pinpointing the region or regions that led to our decision? Images from human retinas are vital for the diagnosis of multiple health issues, like hypertension, diabetes, and Alzheimer's; low quality images may force the patient to come back again for a second scanning, wasting time and possibly delaying treatment. However, existing retinal image quality assessment methods are either black boxes without explanations of the results or depend heavily on feature engineering or on complex and error-prone anatomical structures' segmentation. Therefore, we propose EyeQual, that solves exactly this problem. EyeQual is novel, fast for inference, accurate and explainable, pinpointing low-quality regions on the image. We evaluated EyeQual on two real datasets where it achieved 100% accuracy taking just 36 milliseconds for each image. Pedro Costa 0005, Aurélio J. C. Campilho, Bryan Hooi, Asim Smailagic, Kris Makoto Kitani, Shenghua Liu, Christos Faloutsos, Adrian Galdran	ICMLA	8
2017	Fusion-Based Variational Image Dehazing abstract We propose a novel image-dehazing technique based on the minimization of two energy functionals and a fusion scheme to combine the output of both optimizations. The proposed fusion-based variational image-dehazing (FVID) method is a spatially varying image enhancement process that first minimizes a previously proposed variational formulation that maximizes contrast and saturation on the hazy input. The iterates produced by this minimization are kept, and a second energy that shrinks faster intensity values of well-contrasted regions is minimized, allowing to generate a set of difference-of-saturation (DiffSat) maps by observing the shrinking rate. The iterates produced in the first minimization are then fused with these DiffSat maps to produce a haze-free version of the degraded input. The FVID method does not rely on a physical model from which to estimate a depth map, nor it needs a training stage on a database of human-labeled examples. Experimental results on a wide set of hazy images demonstrate that FVID better preserves the image structure on nearby regions that are less affected by fog, and it is successfully compared with other current methods in the task of removing haze degradation from faraway regions. Adrian Galdran, Javier Vazquez-Corral, David Pardo, Marcelo Bertalmío	IEEE Signal Process. Lett.	1
2015	Automatic Red-Channel underwater image restoration Adrian Galdran, David Pardo, Artzai Picón, Aitor Alvarez-Gila	J. Vis. Commun. Image Represent.	1
2015	Enhanced Variational Image Dehazing abstract Images obtained under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to overcome this problem. In this work, we extend a well-known perception-inspired variational framework for single image dehazing. Two main improvements are proposed. First, we replace the value used by the framework for the gray-world hypothesis by an estimation of the mean of the clean image. Second, we add a set of new terms to the energy functional for maximizing the interchannel contrast. Experimental results show that the proposed enhanced variational image dehazing (EVID) method outperforms other state-of-the-art methods both qualitatively and quantitatively. In particular, when the illuminant is uneven, our EVID method is the only one that recovers realistic colors, avoiding the appearance of strong chromatic artifacts. Adrian Galdran, Javier Vazquez-Corral, David Pardo, Marcelo Bertalmío	SIAM J. Imaging Sci.	1