arXiv subjects

Bogdan Georgescu

Publications and source records attributed to Bogdan Georgescu.

At least 19 recordsLinked to original sources

arXiv2026

Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR

Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this, Vision-Language (VL) object detection methods leverage grounding text information to enable powerful zero-shot and few-shot object detectors in the natural image domain [1, 2, 3, 4]. However, transferring these methods to the medical domain is challenging due to the absence of comparable quality and quantity of the grounding data. Regardless, significant contextual and non-imaging information exists in medical images that remains underutilized. Few-shot learning (FSL) techniques partially address this limitation but struggle to general ize to unseen medical findings and require extensive retraining when new findings are introduced [5, 6]. To overcome these challenges, we extend our prior EM-DETR framework [7] and introduce a scalable FS detection approach designed for efficient abnormality detection in Chest X-Ray (CXR) images under minimal supervision. The proposed architecture incorporates exemplar-based feature generation and domain-aware contrastive optimization, enabling effective adaptation to novel disease findings without exhaustive retraining. Our method achieves near state-of-the-art (SOTA) detection performance using less than 10% of the annotated data, demonstrating its potential for practical, annotation-efficient clinical deployment across both proprietary and public CXR datasets.

cs.CV↗

arXiv2026

Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models

While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains limited by the scarcity of diverse, annotated pulmonary nodule datasets. Diffusion-based generative models offer a promising strategy for data synthesis; however, many existing conditional approaches primarily optimize spatial reconstruction losses, which encourage voxel-wise similarity but may inadequately constrain lesion-level intensity distributions. As a result, these methods may produce over-smoothed texture profiles and underrepresent the distinct attenuation characteristics of different nodule subtypes, including solid, part-solid, and ground-glass nodules. To address this challenge, we propose a controllable latent diffusion model that synthesizes pulmonary nodules within full 3D CT volumes while accurately modeling nodule-specific intensity distributions. Specifically, rather than relying solely on spatial losses, we introduce a histogram-based regularization term that constrains voxel intensity distributions during the generative process. The model combines subtype, spatial mask, and Hounsfield unit (HU) histogram conditioning with the differentiable feature-space histogram regularization term to better align lesion-level intensity distributions, improving the visual plausibility and subtype consistency of synthesized nodules. Extensive experiments on lung CT data demonstrate that our framework achieves strong visual realism, validated through both quantitative metrics and a visual Turing test. Furthermore, when used for data augmentation, the generated nodules improve performance in downstream clinical tasks, particularly for underrepresented nodule subtypes, and show a potential benefit for subtype-informed malignancy classification.

cs.CV↗

arXiv2026

Specializing Foundation Models via Mixture of Low-Rank Experts for Comprehensive Head CT Analysis

Foundation models pre-trained on large-scale datasets demonstrate strong transfer learning capabilities; however, their adaptation to complex multi-label diagnostic tasks-such as comprehensive head CT finding detection-remains understudied. Standard parameter-efficient fine-tuning methods such as LoRA apply uniform adaptations across pathology types, which may limit performance for diverse medical findings. We propose a Mixture of Low-Rank Experts (MoLRE) framework that extends LoRA with multiple specialized low-rank adapters and unsupervised soft routing. This approach enables conditional feature adaptation with less than 0.5% additional parameters and without explicit pathology supervision. We present a comprehensive benchmark of MoLRE across six state-of-the-art medical imaging foundation models spanning 2D and 3D architectures, general-domain, medical-domain, and head CT-specific pretraining, and model sizes ranging from 7M to 431M parameters. Using over 70,000 non-contrast head CT scans with 75 annotated findings-including hemorrhage, infarction, trauma, mass lesions, structural abnormalities, and chronic changes-our experiments demonstrate consistent performance improvements across all models. Gains vary substantially: general-purpose and medical-domain models show the largest improvements (DINOv3-Base: +4.6%; MedGemma: +4.3%), whereas 3D CT-specialized or very large models show more modest gains (+0.2-1.3%). The combination of MoLRE and MedGemma achieves the highest average detection AUC of 0.917. These findings highlight the importance of systematic benchmarking on target clinical tasks, as pretraining domain, architecture, and model scale interact in non-obvious ways.

cs.CV↗

arXiv2025

Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification

3D medical image classification is essential for modern clinical workflows. Medical foundation models (FMs) have emerged as a promising approach for scaling to new tasks, yet current research suffers from three critical pitfalls: data-regime bias, suboptimal adaptation, and insufficient task coverage. In this paper, we address these pitfalls and introduce AnyMC3D, a scalable 3D classifier adapted from 2D FMs. Our method scales efficiently to new tasks by adding only lightweight plugins (about 1M parameters per task) on top of a single frozen backbone. This versatile framework also supports multi-view inputs, auxiliary pixel-level supervision, and interpretable heatmap generation. We establish a comprehensive benchmark of 12 tasks covering diverse pathologies, anatomies, and modalities, and systematically analyze state-of-the-art 3D classification techniques. Our analysis reveals key insights: (1) effective adaptation is essential to unlock FM potential, (2) general-purpose FMs can match medical-specific FMs if properly adapted, and (3) 2D-based methods surpass 3D architectures for 3D classification. For the first time, we demonstrate the feasibility of achieving state-of-the-art performance across diverse applications using a single scalable framework (including 1st place in the VLM3D challenge), eliminating the need for separate task-specific models.

cs.CV↗

arXiv2025

Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and beyond

Detecting abnormalities in medical images poses unique challenges due to differences in feature representations and the intricate relationship between anatomical structures and abnormalities. This is especially evident in mammography, where dense breast tissue can obscure lesions, complicating radiological interpretation. Despite leveraging anatomical and semantic context, existing detection methods struggle to learn effective class-specific features, limiting their applicability across different tasks and imaging modalities. In this work, we introduce Exemplar Med-DETR, a novel multi-modal contrastive detector that enables feature-based detection. It employs cross-attention with inherently derived, intuitive class-specific exemplar features and is trained with an iterative strategy. We achieve state-of-the-art performance across three distinct imaging modalities from four public datasets. On Vietnamese dense breast mammograms, we attain an mAP of 0.7 for mass detection and 0.55 for calcifications, yielding an absolute improvement of 16 percentage points. Additionally, a radiologist-supported evaluation of 100 mammograms from an out-of-distribution Chinese cohort demonstrates a twofold gain in lesion detection performance. For chest X-rays and angiography, we achieve an mAP of 0.25 for mass and 0.37 for stenosis detection, improving results by 4 and 7 percentage points, respectively. These results highlight the potential of our approach to advance robust and generalizable detection systems for medical imaging.

cs.CV↗

arXiv2025

A Non-contrast Head CT Foundation Model for Comprehensive Neuro-Trauma Triage

Recent advancements in AI and medical imaging offer transformative potential in emergency head CT interpretation for reducing assessment times and improving accuracy in the face of an increasing request of such scans and a global shortage in radiologists. This study introduces a 3D foundation model for detecting diverse neuro-trauma findings with high accuracy and efficiency. Using large language models (LLMs) for automatic labeling, we generated comprehensive multi-label annotations for critical conditions. Our approach involved pretraining neural networks for hemorrhage subtype segmentation and brain anatomy parcellation, which were integrated into a pretrained comprehensive neuro-trauma detection network through multimodal fine-tuning. Performance evaluation against expert annotations and comparison with CT-CLIP demonstrated strong triage accuracy across major neuro-trauma findings, such as hemorrhage and midline shift, as well as less frequent critical conditions such as cerebral edema and arterial hyperdensity. The integration of neuro-specific features significantly enhanced diagnostic capabilities, achieving an average AUC of 0.861 for 16 neuro-trauma conditions. This work advances foundation models in medical imaging, serving as a benchmark for future AI-assisted neuro-trauma diagnostics in emergency radiology.

eess.IV↗

arXiv2023

Generation of Radiology Findings in Chest X-Ray by Leveraging Collaborative Knowledge

Among all the sub-sections in a typical radiology report, the Clinical Indications, Findings, and Impression often reflect important details about the health status of a patient. The information included in Impression is also often covered in Findings. While Findings and Impression can be deduced by inspecting the image, Clinical Indications often require additional context. The cognitive task of interpreting medical images remains the most critical and often time-consuming step in the radiology workflow. Instead of generating an end-to-end radiology report, in this paper, we focus on generating the Findings from automated interpretation of medical images, specifically chest X-rays (CXRs). Thus, this work focuses on reducing the workload of radiologists who spend most of their time either writing or narrating the Findings. Unlike past research, which addresses radiology report generation as a single-step image captioning task, we have further taken into consideration the complexity of interpreting CXR images and propose a two-step approach: (a) detecting the regions with abnormalities in the image, and (b) generating relevant text for regions with abnormalities by employing a generative large language model (LLM). This two-step approach introduces a layer of interpretability and aligns the framework with the systematic reasoning that radiologists use when reviewing a CXR.

cs.CV↗

arXiv2022

The Liver Tumor Segmentation Benchmark (LiTS)

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in \url{http://medicaldecathlon.com/}. In addition, both data and online evaluation are accessible via \url{www.lits-challenge.com}.

cs.CV↗

arXiv2022

Self-supervised Learning from 100 Million Medical Images

Building accurate and robust artificial intelligence systems for medical image assessment requires not only the research and design of advanced deep learning models but also the creation of large and curated sets of annotated training examples. Constructing such datasets, however, is often very costly -- due to the complex nature of annotation tasks and the high level of expertise required for the interpretation of medical images (e.g., expert radiologists). To counter this limitation, we propose a method for self-supervised learning of rich image features based on contrastive learning and online feature clustering. For this purpose we leverage large training datasets of over 100,000,000 medical images of various modalities, including radiography, computed tomography (CT), magnetic resonance (MR) imaging and ultrasonography. We propose to use these features to guide model training in supervised and hybrid self-supervised/supervised regime on various downstream tasks. We highlight a number of advantages of this strategy on challenging image assessment problems in radiography, CT and MR: 1) Significant increase in accuracy compared to the state-of-the-art (e.g., AUC boost of 3-7% for detection of abnormalities from chest radiography scans and hemorrhage detection on brain CT); 2) Acceleration of model convergence during training by up to 85% compared to using no pretraining (e.g., 83% when training a model for detection of brain metastases in MR scans); 3) Increase in robustness to various image augmentations, such as intensity variations, rotations or scaling reflective of data variation seen in the field.

cs.CV↗

arXiv2021

Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation

Simultaneous segmentation of multiple organs from different medical imaging modalities is a crucial task as it can be utilized for computer-aided diagnosis, computer-assisted surgery, and therapy planning. Thanks to the recent advances in deep learning, several deep neural networks for medical image segmentation have been introduced successfully for this purpose. In this paper, we focus on learning a deep multi-organ segmentation network that labels voxels. In particular, we examine the critical choice of a loss function in order to handle the notorious imbalance problem that plagues both the input and output of a learning model. The input imbalance refers to the class-imbalance in the input training samples (i.e., small foreground objects embedded in an abundance of background voxels, as well as organs of varying sizes). The output imbalance refers to the imbalance between the false positives and false negatives of the inference model. In order to tackle both types of imbalance during training and inference, we introduce a new curriculum learning based loss function. Specifically, we leverage Dice similarity coefficient to deter model parameters from being held at bad local minima and at the same time gradually learn better model parameters by penalizing for false positives/negatives using a cross entropy term. We evaluated the proposed loss function on three datasets: whole body positron emission tomography (PET) scans with 5 target organs, magnetic resonance imaging (MRI) prostate scans, and ultrasound echocardigraphy images with a single target organ i.e., left ventricular. We show that a simple network architecture with the proposed integrative loss function can outperform state-of-the-art methods and results of the competing methods can be improved when our proposed loss is used.

cs.CV↗

arXiv2021

Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment

Chest radiography is the most common radiographic examination performed in daily clinical practice for the detection of various heart and lung abnormalities. The large amount of data to be read and reported, with more than 100 studies per day for a single radiologist, poses a challenge in consistently maintaining high interpretation accuracy. The introduction of large-scale public datasets has led to a series of novel systems for automated abnormality classification. However, the labels of these datasets were obtained using natural language processed medical reports, yielding a large degree of label noise that can impact the performance. In this study, we propose novel training strategies that handle label noise from such suboptimal data. Prior label probabilities were measured on a subset of training data re-read by 4 board-certified radiologists and were used during training to increase the robustness of the training model to the label noise. Furthermore, we exploit the high comorbidity of abnormalities observed in chest radiography and incorporate this information to further reduce the impact of label noise. Additionally, anatomical knowledge is incorporated by training the system to predict lung and heart segmentation, as well as spatial knowledge labels. To deal with multiple datasets and images derived from various scanners that apply different post-processing techniques, we introduce a novel image normalization strategy. Experiments were performed on an extensive collection of 297,541 chest radiographs from 86,876 patients, leading to a state-of-the-art performance level for 17 abnormalities from 2 datasets. With an average AUC score of 0.880 across all abnormalities, our proposed training strategies can be used to significantly improve performance scores.

cs.CV↗

arXiv2020

Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT

Purpose: To present a method that automatically segments and quantifies abnormal CT patterns commonly present in coronavirus disease 2019 (COVID-19), namely ground glass opacities and consolidations. Materials and Methods: In this retrospective study, the proposed method takes as input a non-contrasted chest CT and segments the lesions, lungs, and lobes in three dimensions, based on a dataset of 9749 chest CT volumes. The method outputs two combined measures of the severity of lung and lobe involvement, quantifying both the extent of COVID-19 abnormalities and presence of high opacities, based on deep learning and deep reinforcement learning. The first measure of (PO, PHO) is global, while the second of (LSS, LHOS) is lobewise. Evaluation of the algorithm is reported on CTs of 200 participants (100 COVID-19 confirmed patients and 100 healthy controls) from institutions from Canada, Europe and the United States collected between 2002-Present (April, 2020). Ground truth is established by manual annotations of lesions, lungs, and lobes. Correlation and regression analyses were performed to compare the prediction to the ground truth. Results: Pearson correlation coefficient between method prediction and ground truth for COVID-19 cases was calculated as 0.92 for PO (P < .001), 0.97 for PHO(P < .001), 0.91 for LSS (P < .001), 0.90 for LHOS (P < .001). 98 of 100 healthy controls had a predicted PO of less than 1%, 2 had between 1-2%. Automated processing time to compute the severity scores was 10 seconds per case compared to 30 minutes required for manual annotations. Conclusion: A new method segments regions of CT abnormalities associated with COVID-19 and computes (PO, PHO), as well as (LSS, LHOS) severity scores.

eess.IV↗

arXiv2020

No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks

Detecting malignant pulmonary nodules at an early stage can allow medical interventions which may increase the survival rate of lung cancer patients. Using computer vision techniques to detect nodules can improve the sensitivity and the speed of interpreting chest CT for lung cancer screening. Many studies have used CNNs to detect nodule candidates. Though such approaches have been shown to outperform the conventional image processing based methods regarding the detection accuracy, CNNs are also known to be limited to generalize on under-represented samples in the training set and prone to imperceptible noise perturbations. Such limitations can not be easily addressed by scaling up the dataset or the models. In this work, we propose to add adversarial synthetic nodules and adversarial attack samples to the training data to improve the generalization and the robustness of the lung nodule detection systems. To generate hard examples of nodules from a differentiable nodule synthesizer, we use projected gradient descent (PGD) to search the latent code within a bounded neighbourhood that would generate nodules to decrease the detector response. To make the network more robust to unanticipated noise perturbations, we use PGD to search for noise patterns that can trigger the network to give over-confident mistakes. By evaluating on two different benchmark datasets containing consensus annotations from three radiologists, we show that the proposed techniques can improve the detection performance on real CT data. To understand the limitations of both the conventional networks and the proposed augmented networks, we also perform stress-tests on the false positive reduction networks by feeding different types of artificially produced patches. We show that the augmented networks are more robust to both under-represented nodules as well as resistant to noise perturbations.

eess.IV↗

arXiv2020

Machine Learning Automatically Detects COVID-19 using Chest CTs in a Large Multicenter Cohort

Objectives: To investigate machine-learning classifiers and interpretable models using chest CT for detection of COVID-19 and differentiation from other pneumonias, ILD and normal CTs. Methods: Our retrospective multi-institutional study obtained 2096 chest CTs from 16 institutions (including 1077 COVID-19 patients). Training/testing cohorts included 927/100 COVID-19, 388/33 ILD, 189/33 other pneumonias, and 559/34 normal (no pathologies) CTs. A metric-based approach for classification of COVID-19 used interpretable features, relying on logistic regression and random forests. A deep learning-based classifier differentiated COVID-19 via 3D features extracted directly from CT attenuation and probability distribution of airspace opacities. Results: Most discriminative features of COVID-19 are percentage of airspace opacity and peripheral and basal predominant opacities, concordant with the typical characterization of COVID-19 in the literature. Unsupervised hierarchical clustering compares feature distribution across COVID-19 and control cohorts. The metrics-based classifier achieved AUC=0.83, sensitivity=0.74, and specificity=0.79 of versus respectively 0.93, 0.90, and 0.83 for the DL-based classifier. Most of ambiguity comes from non-COVID-19 pneumonia with manifestations that overlap with COVID-19, as well as mild COVID-19 cases. Non-COVID-19 classification performance is 91% for ILD, 64% for other pneumonias and 94% for no pathologies, which demonstrates the robustness of our method against different compositions of control groups. Conclusions: Our new method accurately discriminates COVID-19 from other types of pneumonia, ILD, and no pathologies CTs, using quantitative imaging features derived from chest CT, while balancing interpretability of results and classification performance, and therefore may be useful to facilitate diagnosis of COVID-19.

eess.IV↗

arXiv2020

Quantifying and Leveraging Predictive Uncertainty for Medical Image Assessment

The interpretation of medical images is a challenging task, often complicated by the presence of artifacts, occlusions, limited contrast and more. Most notable is the case of chest radiography, where there is a high inter-rater variability in the detection and classification of abnormalities. This is largely due to inconclusive evidence in the data or subjective definitions of disease appearance. An additional example is the classification of anatomical views based on 2D Ultrasound images. Often, the anatomical context captured in a frame is not sufficient to recognize the underlying anatomy. Current machine learning solutions for these problems are typically limited to providing probabilistic predictions, relying on the capacity of underlying models to adapt to limited information and the high degree of label noise. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose a system that learns not only the probabilistic estimate for classification, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that this approach is essential to account for the inherent ambiguity characteristic of medical images from different radiologic exams including computed radiography, ultrasonography and magnetic resonance imaging. In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e.g., by 8% to 0.91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs. In addition, we show that using uncertainty-driven bootstrapping to filter the training data, one can achieve a significant increase in robustness and accuracy.

eess.IV↗

arXiv2020

3D Tomographic Pattern Synthesis for Enhancing the Quantification of COVID-19

The Coronavirus Disease (COVID-19) has affected 1.8 million people and resulted in more than 110,000 deaths as of April 12, 2020. Several studies have shown that tomographic patterns seen on chest Computed Tomography (CT), such as ground-glass opacities, consolidations, and crazy paving pattern, are correlated with the disease severity and progression. CT imaging can thus emerge as an important modality for the management of COVID-19 patients. AI-based solutions can be used to support CT based quantitative reporting and make reading efficient and reproducible if quantitative biomarkers, such as the Percentage of Opacity (PO), can be automatically computed. However, COVID-19 has posed unique challenges to the development of AI, specifically concerning the availability of appropriate image data and annotations at scale. In this paper, we propose to use synthetic datasets to augment an existing COVID-19 database to tackle these challenges. We train a Generative Adversarial Network (GAN) to inpaint COVID-19 related tomographic patterns on chest CTs from patients without infectious diseases. Additionally, we leverage location priors derived from manually labeled COVID-19 chest CTs patients to generate appropriate abnormality distributions. Synthetic data are used to improve both lung segmentation and segmentation of COVID-19 patterns by adding 20% of synthetic data to the real COVID-19 training data. We collected 2143 chest CTs, containing 327 COVID-19 positive cases, acquired from 12 sites across 7 countries. By testing on 100 COVID-19 positive and 100 control cases, we show that synthetic data can help improve both lung segmentation (+6.02% lesion inclusion rate) and abnormality segmentation (+2.78% dice coefficient), leading to an overall more accurate PO computation (+2.82% Pearson coefficient).

eess.IV↗

arXiv2020

One-to-one Mapping for Unpaired Image-to-image Translation

Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple domains. However, in existing approaches, there is no guarantee that the mapping between two image domains is unique or one-to-one. Here we propose a self-inverse network learning approach for unpaired image-to-image translation. Building on top of CycleGAN, we learn a self-inverse function by simply augmenting the training samples by swapping inputs and outputs during training and with separated cycle consistency loss for each mapping direction. The outcome of such learning is a proven one-to-one mapping function. Our extensive experiments on a variety of datasets, including cross-modal medical image synthesis, object transfiguration, and semantic labeling, consistently demonstrate clear improvement over the CycleGAN method both qualitatively and quantitatively. Especially our proposed method reaches the state-of-the-art result on the cityscapes benchmark dataset for the label to photo unpaired directional image translation.

cs.CV↗

arXiv2019

Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation

The one-to-one mapping is necessary for many bidirectional image-to-image translation applications, such as MRI image synthesis as MRI images are unique to the patient. State-of-the-art approaches for image synthesis from domain X to domain Y learn a convolutional neural network that meticulously maps between the domains. A different network is typically implemented to map along the opposite direction, from Y to X. In this paper, we explore the possibility of only wielding one network for bi-directional image synthesis. In other words, such an autonomous learning network implements a self-inverse function. A self-inverse network shares several distinct advantages: only one network instead of two, better generalization and more restricted parameter space. Most importantly, a self-inverse function guarantees a one-to-one mapping, a property that cannot be guaranteed by earlier approaches that are not self-inverse. The experiments on three datasets show that, compared with the baseline approaches that use two separate models for the image synthesis along two directions, our self-inverse network achieves better synthesis results in terms of standard metrics. Finally, our sensitivity analysis confirms the feasibility of learning a self-inverse function for the bidirectional image translation.

cs.CV↗