Search Results for author:
Found 54 papers, 20 papers with code
Radial Basis Feature Transformation to Arm CNNs Against Adversarial Attacks
The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations.
Representing Anatomical Trees by Denoising Diffusion of Implicit Neural Fields
We propose a novel approach for representing anatomical trees using INR, while also capturing the distribution of a set of trees via denoising diffusion in the space of INRs.
AFreeCA: Annotation-Free Counting for All
Consequently, we can generate counting data for any type of object and count them in an unsupervised manner.
Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
The remarkable progress of deep learning in dermatological tasks has brought us closer to achieving diagnostic accuracies comparable to those of human experts.
SYRAC: Synthesize, Rank, and Count
To address this, we use latent diffusion models to create two types of synthetic data: one by removing pedestrians from real images, which generates ranked image pairs with a weak but reliable object quantity signal, and the other by generating synthetic images with a predetermined number of objects, offering a strong but noisy counting signal.
SLiMe: Segment Like Me
Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image.
AI-based analysis of super-resolution microscopy: Biological discovery in the absence of ground truth
The nanoscale resolution of super-resolution microscopy has now enabled the use of fluorescent based molecular localization tools to study whole cell structural biology.
DermSynth3D: Synthesis of in-the-wild Annotated Dermatology Images
In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis.
The XAI Alignment Problem: Rethinking How Should We Evaluate Human-Centered AI Explainability Techniques
Optimizing XAI for plausibility regardless of the model decision correctness also jeopardizes model trustworthiness, because doing so breaks an important assumption in human-human explanation that plausible explanations typically imply correct decisions, and vice versa; and violating this assumption eventually leads to either undertrust or overtrust of AI models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Invisible Users: Uncovering End-Users' Requirements for Explainable AI via Explanation Forms and Goals
The EUCA study findings, the identified explanation forms and goals for technical specification, and the EUCA study dataset support the design and evaluation of end-user-centered XAI techniques for accessible, safe, and accountable AI.
MaskTune: Mitigating Spurious Correlations by Forcing to Explore
A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features.
CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions
While deep learning based approaches have demonstrated expert-level performance in dermatological diagnosis tasks, they have also been shown to exhibit biases toward certain demographic attributes, particularly skin types (e. g., light versus dark), a fairness concern that must be addressed.
FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning
Deep learning models have achieved great success in automating skin lesion diagnosis.
Transcending XAI Algorithm Boundaries through End-User-Inspired Design
The boundaries of existing explainable artificial intelligence (XAI) algorithms are confined to problems grounded in technical users' demand for explainability.
A Survey on Deep Learning for Skin Lesion Segmentation
We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance).
Multi-Sample $ζ$-mixup: Richer, More Realistic Synthetic Samples from a $p$-Series Interpolant
Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information.
Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?
The evaluation and MSFI metric can guide the design and selection of XAI algorithms to meet clinical requirements on multi-modal explanation.
Explainable Artificial Intelligence (XAI)
Feature Importance
Deep Multimodal Guidance for Medical Image Classification
Furthermore, in the case of brain tumor classification, our method outperforms the model trained on the superior modality while producing comparable results to the model that uses both modalities during inference.
Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis
Following the guidelines, we conducted a systematic evaluation on a novel problem of multi-modal medical image explanation with two clinical tasks, and proposed new evaluation metrics accordingly.
Computational Efficiency
Explainable artificial intelligence
+1
BoosterNet: Improving Domain Generalization of Deep Neural Nets Using Culpability-Ranked Features
Deep learning (DL) models trained to minimize empirical risk on a single domain often fail to generalize when applied to other domains.
Learning-to-Count by Learning-to-Rank: Weakly Supervised Object Counting & Localization Using Only Pairwise Image Rankings
Object counting and localization in dense scenes is a challenging class of image analysis problems that typically requires labour intensive annotations to learn to solve.
One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images
The maps highlight important features for AI model's prediction.
DEEMD: Drug Efficacy Estimation against SARS-CoV-2 based on cell Morphology with Deep multiple instance learning
DEEMD can be explored for use on other emerging viruses and datasets to rapidly identify candidate antiviral treatments in the future}.
Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes
Our lesion tracking algorithm achieves an average matching accuracy of 88% on a set of detected corresponding pairs of prominent lesions of subjects imaged in different poses, and an average longitudinal accuracy of 71% when encompassing additional errors due to lesion detection.
EUCA: the End-User-Centered Explainable AI Framework
The ability to explain decisions to end-users is a necessity to deploy AI as critical decision support.
Decision Making
Explainable artificial intelligence
Human-Computer Interaction
D-LEMA: Deep Learning Ensembles from Multiple Annotations -- Application to Skin Lesion Segmentation
To this end, we propose an ensemble of Bayesian fully convolutional networks (FCNs) for the segmentation task by considering two major factors in the aggregation of multiple ground truth annotations: (1) handling contradictory annotations in the training data originating from inter-annotator disagreements and (2) improving confidence calibration through the fusion of base models' predictions.
Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation
The segmentation of skin lesions is a crucial task in clinical decision support systems for the computer aided diagnosis of skin lesions.
Patch-based Non-Local Bayesian Networks for Blind Confocal Microscopy Denoising
The performance of our proposed method is evaluated on confocal microscopy images with real noise Poisson-Gaussian noise.
Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images
The semantic segmentation of skin lesions is an important and common initial task in the computer aided diagnosis of dermoscopic images.
Deep Learning for Biomedical Image Reconstruction: A Survey
Medical imaging is an invaluable resource in medicine as it enables to peer inside the human body and provides scientists and physicians with a wealth of information indispensable for understanding, modelling, diagnosis, and treatment of diseases.
Artificial Intelligence in Glioma Imaging: Challenges and Advances
We believe that these technical approaches will facilitate the development of a fully-functional AI tool in the clinical care of patients with gliomas.
Signed Input Regularization
To test the effectiveness of the proposed idea and compare it with other competing methods, we design several test scenarios, such as classification performance, uncertainty, out-of-distribution, and robustness analyses.
Deep Learning Models for Digital Pathology
We then discuss the challenges facing the validation and integration of such deep learning-based computational systems in clinical workflow and reflect on future opportunities for histopathology derived image measurements and better predictive modeling.
Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI
This paper presents a simple and effective generalization method for magnetic resonance imaging (MRI) segmentation when data is collected from multiple MRI scanning sites and as a consequence is affected by (site-)domain shifts.
Deep Semantic Segmentation of Natural and Medical Images: A Review
The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class.
WhiteNNer-Blind Image Denoising via Noise Whiteness Priors
Specifically, by using total variation and piecewise constancy priors along with noise whiteness priors such as auto-correlation and stationary losses, our network learns to decouple an input noisy image into the underlying signal and noise components.
Image Super Resolution via Bilinear Pooling: Application to Confocal Endomicroscopy
We compare the efficacy of our method to 11 other existing single image super resolution techniques that compensate for the reduction in image quality caused by the necessity of endomicroscope miniaturization.
Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis
Skin lesion segmentation is a vital task in skin cancer diagnosis and further treatment.
Learning to Segment Skin Lesions from Noisy Annotations
Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images.
Visual Diagnosis of Dermatological Disorders: Human and Machine Performance
Skin conditions are a global health concern, ranking the fourth highest cause of nonfatal disease burden when measured as years lost due to disability.
Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network
The ability to visualize tissue in varied contrasts in the form of MR pulse sequences in a single scan provides valuable insights to physicians, as well as enabling automated systems performing downstream analysis.
Improved Inference via Deep Input Transfer
Although numerous improvements have been made in the field of image segmentation using convolutional neural networks, the majority of these improvements rely on training with larger datasets, model architecture modifications, novel loss functions, and better optimizers.
InfoMask: Masked Variational Latent Representation to Localize Chest Disease
The scarcity of richly annotated medical images is limiting supervised deep learning based solutions to medical image analysis tasks, such as localizing discriminatory radiomic disease signatures.
A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations
The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations.
Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
Recently, there have been several successful deep learning approaches for automatically classifying chest X-ray images into different disease categories.
Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation
Semantic segmentation is an important preliminary step towards automatic medical image interpretation.
Can Deep Learning Relax Endomicroscopy Hardware Miniaturization Requirements?
In this work, we demonstrate that software-based techniques can be used to recover lost information due to endomicroscopy hardware miniaturization and reconstruct images of higher resolution.
Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation
The output imbalance refers to the imbalance between the false positives and false negatives of the inference model.
Select, Attend, and Transfer: Light, Learnable Skip Connections
Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients.
Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features
We reformulate the task of classifying clinical dermoscopic features within superpixels as a segmentation problem, and propose a fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images.
Machine Learning on Human Connectome Data from MRI
The purpose of this work is to review the literature on the topic of applying machine learning models to MRI-based connectome data.
Adaptable Precomputation for Random Walker Image Segmentation and Registration
Specifically, we dynamically determine the number of eigenvectors needed for a desired accuracy based on user input, and derive update equations for the eigenvectors when the edge weights or topology of the image graph are changed.
Incorporating prior knowledge in medical image segmentation: a survey
Medical image segmentation, the task of partitioning an image into meaningful parts, is an important step toward automating medical image analysis and is at the crux of a variety of medical imaging applications, such as computer aided diagnosis, therapy planning and delivery, and computer aided interventions.
Multi-Region Probabilistic Dice Similarity Coefficient using the Aitchison Distance and Bipartite Graph Matching
Probabilistic image segmentation is increasingly popular as it captures uncertainty in the results.
