Peer-reviewed Publications 📄

Everything from ecologial to medical to pure vision research, in reverse chronological order.

Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification, MICCAI

Accurate dermatological diagnosis naturally necessitates equitable performance across diverse populations, yet a systematic lack of expertly annotated images, especially for underrepresented skin tones and rare diseases, impedes progress toward measurably fair methods. We introduce cgDDI (Controllable Generation of Diverse Dermatological Imagery), a hybrid framework that (1) synthesizes realistic healthy skin samples without disturbing other input properties, (2) maps single-sample rare lesions onto novel skin-tones and locations non-parametrically, and (3) allows for efficient parametric generation with as few as 10 training samples. The framework supports both human and automated segmentation masking, enabling scalability to datasets without pre-made lesion masks. We grow a 656-image dataset by more than 400× and validate across two datasets: biopsy-confirmed Diverse Dermatology Images (DDI) and expert-verified Fitzpatrick17k (F17k). On the DDI benchmark, we achieve malignancy classification accuracy of 86.4% under synthetic-only training and 90.9% state-of-the-art performance with real data fine-tuning, alongside leading fairness metrics. Cross-dataset experiments show +13.9% accuracy improvements on unseen F17k data despite minimal disease overlap.

DermDepth: Toward Monocular Metric Scale 3D Reconstruction Models for Dermatology, MICCAI

Dermatological practice routinely involves measuring and tracking lesion size, morphology and texture, as critical components of wound or skin cancer screening, monitoring and diagnosis. To accomplish this task, practitioners often image the skin surface with commonly available off-the-shelf camera sensors. This has led to an overwhelming research focus on 2D methods while these objectives naturally benefit from 3D information. In this paper, we demonstrate that dense monocular 3D reconstructions, metric scale measurements and rich surface normal texture estimates are achievable for both dermoscopic and macroscopic cases without the need for additional hardware or multiple captures. We present DermDepth, the first single-view metric scale 3D model for the dermatological domain and D-Synth, the first synthetic dermoscopic dataset with pixel-perfect 3D information. Our experiments show training DermDepth on D-Synth corrects metric scale error from over 16× to under 1.1× for real dermoscopic data, while preserving geometric quality and increasing texture richness. Fine-tuning on a small amount of real clinical samples generalizes our method across three real-world benchmarks spanning the few mm to hundred cm range, diverse skin-tones, chronic wound cases and produces measurements broadly consistent with disease size reported in medical literature.

A Modular Fluorescent Camera Unit for Wound Imaging, Communications Biology

The researchers developed a hand-held fluorescent microscope featuring rapid set-up and sub-millimeter resolution for biological imaging. They applied this system to track pH and nitric oxide biomarkers in wound healing, using machine learning to identify spatial patterns. Their findings revealed that NO clustering shows high-concentration structures that decrease in size but intensify during the healing progression, potentially enabling prediction of healing stages.

TARDIS STRIDE: Spatio-Temporal Road Image Dataset and World Model for Autonomy, Preprint. Under review.

World models aim to simulate environments and enable effective agent behavior. However, modeling real-world environments presents unique challenges as they dynamically change across both space and, crucially, time. To capture these composed dynamics, we introduce a Spatio-Temporal Road Image Dataset for Exploration (STRIDE) permuting 360º panoramic imagery into rich interconnected observation, state and action nodes. Leveraging this structure, we can simultaneously model the relationship between egocentric views, positional coordinates, and movement commands across both space and time. We benchmark this dataset via TARDIS, a transformer-based generative world model that integrates spatial and temporal dynamics through a unified autoregressive framework trained on STRIDE. We demonstrate robust performance across a range of agentic tasks such as controllable photorealistic image synthesis, instruction following, autonomous self-control, and state-of-the-art georeferencing. These results suggest a promising direction towards sophisticated generalist agents--capable of understanding and manipulating the spatial and temporal aspects of their material environments--with enhanced embodied reasoning capabilities. Training code, datasets, and model checkpoints are made freely available.

Remote-Controlled Wireless Bioelectronics for Fluoxetine Therapy to Promote Wound Healing in a Porcine Model, AMT

Wound healing is a significant opportunity in biomedical science, requiring precise therapeutic delivery and real-time monitoring. Bioelectronic devices address this need and require further validation in large animal models that reflect human healing dynamics. This work introduces a wireless, remotely controlled bioelectronic platform with an iontophoretic pump to deliver fluoxetine, a selective serotonin reuptake inhibitor that modulates inflammation and promotes wound repair. Treatment over 3 days in a porcine model increased re-epithelialization by 37% and reduced inflammation, as shown by a 33% decrease in the ratio of pro-inflammatory M1 macrophages to pro-reparative M2 macrophages compared to controls. The platform accelerated early wound healing and stimulated neuronal growth at the wound site.

Programmable Delivery of Fluoxetine via Wearable Bioelectronics for Wound Healing In Vivo, AMT

The ability to deliver drugs with precise dosages at specific time points can significantly improve disease treatment while reducing side effects. Drug encapsulation for gradual delivery has opened the doors for a superior treatment regimen. To expand on this ability, programming bioelectronic devices to deliver small molecules enables ad-hoc personalized therapeutic profiles that are more complex than gradual release. Here, a wearable bioelectronic device with an integrated electrophoretic ion pump that affords on-demand drug delivery with precise dose control is introduced. Delivery of fluoxetine to wounds in mice result in a 27.2% decrease in the macrophage ratio (M1/M2) and a 39.9% increase in re-epithelialization, indicating a shorter inflammatory phase and faster overall healing. Programmable drug delivery using wearable bioelectronics in wounds introduces a broadly applicable strategy for the long-term delivery of a prescribed treatment regimen with minimal external intervention.

FEDD - Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification, MICCAI

Skin diseases affect millions of people worldwide, across all ethnicities. Increasing diagnosis accessibility requires fair and accurate segmentation and classification of dermatology images. However, the scarcity of annotated medical images, especially for rare diseases and un- derrepresented skin tones, poses a challenge to the development of fair and accurate models. In this study, we introduce a Fair, Efficient, and Diverse Diffusion-based framework for skin lesion segmentation and ma- lignancy classification. FEDD leverages semantically meaningful feature embeddings learned through a denoising diffusion probabilistic backbone and processes them via linear probes to achieve state-of-the-art perfor- mance on Diverse Dermatology Images (DDI). We achieve an improve- ment in intersection over union of 0.18, 0.13, 0.06, and 0.07 while using only 5%, 10%, 15%, and 20% labeled samples, respectively. Additionally, FEDD trained on 10% of DDI demonstrates malignancy classification ac- curacy of 81%, 14% higher compared to the state-of-the-art. We showcase high efficiency in data-constrained scenarios while providing fair perfor- mance for diverse skin tones and rare malignancy conditions. Our newly annotated DDI segmentation masks and training code can be found on https://github.com/hectorcarrion/fedd

HealNet - Self-supervised Acute Wound Heal-Stage Classification, MICCAI

Identifying, tracking, and predicting wound heal-stage progression is a fundamental task towards proper diagnosis, effective treatment, facilitating healing, and reducing pain. Traditionally, a medical expert might observe a wound to determine the current healing state and recommend treatment. However, sourcing experts who can produce such a diagnosis solely from visual indicators can be difficult, time-consuming and expensive. In addition, lesions may take several weeks to undergo the healing process, demanding resources to monitor and diagnose continually. Automating this task can be challenging; datasets that follow wound progression from onset to maturation are small, rare, and often collected without computer vision in mind. To tackle these challenges, we introduce a self-supervised learning scheme composed of (a) learning embeddings of wound’s temporal dynamics, (b) clustering for automatic stage discovery, and (c) fine-tuned classification. The proposed self-supervised and flexible learning framework is biologically inspired and trained on a small dataset with zero human labeling. The HealNet framework achieved high pre-text and downstream classification accuracy; when evaluated on held-out test data, HealNet achieved 97.7% pre-text accuracy and 90.62% heal-stage classification accuracy.

Automatic wound detection and size estimation using deep learning algorithms, PLOS

Evaluating and tracking wound size is a fundamental metric for the wound assessment process. Good location and size estimates can enable proper diagnosis and effective treatment. Traditionally, laboratory wound healing studies include a collection of images at uniform time intervals exhibiting the wounded area and the healing process in the test animal, often a mouse. These images are then manually observed to determine key metrics —such as wound size progress— relevant to the study. However, this task is a time-consuming and laborious process. In addition, defining the wound edge could be subjective and can vary from one individual to another even among experts. Furthermore, as our understanding of the healing process grows, so does our need to efficiently and accurately track these key factors for high throughput (e.g., over large-scale and long-term experiments). Thus, in this study, we develop a deep learning-based image analysis pipeline that aims to intake non-uniform wound images and extract relevant information such as the location of interest, wound only image crops, and wound periphery size over-time metrics. In particular, our work focuses on images of wounded laboratory mice that are used widely for translationally relevant wound studies and leverages a commonly used ring-shaped splint present in most images to predict wound size. We apply the method to a dataset that was never meant to be quantified and, thus, presents many visual challenges. Additionally, the data set was not meant for training deep learning models and so is relatively small in size with only 256 images. We compare results to that of expert measurements and demonstrate preservation of information relevant to predicting wound closure despite variability from machine-to-expert and even expert-to-expert. The proposed system resulted in high fidelity results on unseen data with minimal human intervention. Furthermore, the pipeline estimates acceptable wound sizes when less than 50% of the images are missing reference objects.

Honeybee Re-identification in Video: New Datasets and Impact of Self-supervision, VISAPP

This paper presents an experimental study of long-term re-identification of honeybees from the appearance of their abdomen in videos. The first contribution is composed of two image datasets of single honeybees ex- tracted from 12 days of video and annotated with information about their identity on long-term and short-term scales. The long-term dataset contains 8,962 images associated to 181 known identities and used to evaluate the long-term re-identification of individuals. The short-term dataset contains 109,654 images associated to 4,949 short-term tracks that provide multiple views of an individual suitable for self-supervised training. A deep convolutional network was trained to map an image of the honeybee’s abdomen to a 128 dimensional fea- ture vector using several approaches. Re-identification was evaluated in test setups that capture different levels of difficulty: from the same hour to a different day. The results show using the short-term self-supervised in- formation for training performed better than the supervised long-term dataset, with best performance achieved by using both. Ablation studies show the impact of the quantity of data used in training as well as the impact of augmentation, which will guide the design of future systems for individual identification.