Juan Sebastian Otálora Montenegro

• PhD
• PostDoc Position at Inselspital, Universitätsspital Bern

The field of computational pathology has recently seen rapid advances driven by the development of modern vision foundation models (FMs), typically trained on vast collections of pathology images. Recent studies demonstrate that increasing the training data set and model size and integrating domain-specific image processing techniques can significa...

Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model....

Computational pathology targets the automatic analysis of Whole Slide Images (WSI). WSIs are high-resolution digitized histopathology images, stained with chemical reagents to highlight specific tissue structures and scanned via whole slide scanners. The application of different parameters during WSI acquisition may lead to stain color heterogeneit...

The digitalization of clinical workflows and the increasing performance of deep learning algorithms are paving the way towards new methods for tackling cancer diagnosis. However, the availability of medical specialists to annotate digitized images and free-text diagnostic reports does not scale with the need for large datasets required to train rob...

Glaucoma is an eye condition that leads to loss of vision and blindness if not diagnosed in time. Diagnosis requires human experts to estimate in a limited time subtle changes in the shape of the optic disc from retinal fundus images. Deep learning methods have been satisfactory in classifying and segmenting diseases in retinal fundus images, assis...

Computational pathology is a domain of increasing scientific and social interest. The automatic analysis of histopathology images stained with Hematoxylin and Eosin (H&E) can help clinicians diagnose and quantify diseases. Computer vision methods based on deep learning can perform on par or better than pathologists in specific tasks. Nevertheless,...

Computational pathology is a domain that aims to develop algorithms to automatically analyze large digitized histopathology images, called whole slide images (WSI). WSIs are produced scanning thin tissue samples that are stained to make specific structures visible. They show stain colour heterogeneity due to different preparation and scanning setti...

Whole slide images (WSIs) are often provided with global annotations in the form of pathology reports. Local annotations are less frequently available, as obtaining them is time consuming. Global annotations do not include information about the regions of interest or the magnification levels used for the diagnosis. This fact can limit the training...

Computational pathology is a domain that aims to develop algorithms to automatically analyze large digitized histopathology images, called whole slide images (WSI). WSIs are produced scanning thin tissue samples that are stained to make specific structures visible. They show stain colour heterogeneity due to different preparation and scanning setti...

Algorithms proposed in computational pathology can allow to automatically analyze digitized tissue samples of histopathological images to help diagnosing diseases. Tissue samples are scanned at a high-resolution and usually saved as images with several magnification levels, namely whole slide images (WSIs). Convolutional neural networks (CNNs) repr...

Adopting Convolutional Neural Networks (CNNs) in daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of transparency and explainability of the decision making. With physicians being accountable for the diagnosis, it is fundamental that CNNs provide a clear interpretation of their learning paradi...

Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model....

Adopting Convolutional Neural Networks (CNNs) in the daily routine of pathological diagnosis requires not only near-perfect precision, but also sufficient generalization to data shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model. Building on top of...

Convolutional neural networks (CNNs) are state-of-the-art computer vision techniques for various tasks, particularly for image classification. However, there are domains where the training of classification models that generalize on several datasets is still an open challenge because of the highly heterogeneous data and the lack of large datasets w...

Background One challenge to train deep convolutional neural network (CNNs) models with whole slide images (WSIs) is providing the required large number of costly, manually annotated image regions. Strategies to alleviate the scarcity of annotated data include: using transfer learning, data augmentation and training the models with less expensive im...

Training classification models in the medical domain is often difficult due to data heterogeneity (related to acquisition procedures) and due to the difficulty of getting sufficient amounts of annotations from specialized experts. It is particularly true in digital pathology, where models do not generalize easily. This paper presents a novel approa...

Free-text reporting has been the main approach in clinical pathology practice for decades. Pathology reports are an essential information source to guide the treatment of cancer patients and for cancer registries, which process high volumes of free-text reports annually. Information coding and extraction are usually performed manually and it is an...

Deep Convolutional Neural Networks (CNN) are at the backbone of the state–of–the art methods to automatically analyze Whole Slide Images (WSIs) of digital tissue slides. One challenge to train fully-supervised CNN models with WSIs is providing the required amount of costly, manually annotated data. This paper presents a semi-weakly supervised model...

This paper presents an information fusion method for the automatic classification and retrieval of prostate histopathology whole-slide images (WSIs). The approach employs a weakly-supervised machine learning model that combines a bag-of-features representation, kernel methods, and deep learning. The primary purpose of the method is to incorporate t...

Deep Convolutional Neural Networks (CNN) are at the backbone of the state-of-the art methods to automatically analyze Whole Slide Images (WSIs) of digital tissue slides. One challenge to train fully-supervised CNN models with WSIs is providing the required amount of costly, manually annotated data. This paper presents a semi-weakly supervised model...

The opaqueness of deep learning limits its deployment in critical application scenarios such as cancer grading in medical images. In this paper, a framework for guiding CNN training is built on top of successful existing techniques of hard parameter sharing, with the main goal of explicitly introducing expert knowledge in the training objectives. T...

Prostate cancer (PCa) is one of the most frequent cancers in men. Its grading is required before initiating its treatment. The Gleason Score (GS) aims at describing and measuring the regularity in gland patterns observed by a pathologist on the microscopic or digital images of prostate biopsies and prostatectomies. Deep Learning-based (DL) models a...

Hematoxylin and Eosin (H&E) are one of the main tissue stains used in histopathology to discriminate between nuclei and extracellular material while performing a visual analysis of the tissue. However, histopathology slides are often characterized by stain color heterogeneity, due to different tissue preparation settings at different pathology inst...

In recent years, large amounts of digital histopathology images have become available. Such images can be useful for pathologists, however, searching for specific cases and similarities within them is not straightforward. In this work, we present a content-based retrieval system and a scale detection method that can allow browsing in heterogeneous...

Opportunistic communications are expected to play a crucial role in enabling context-aware vehicular services. A widely investigated opportunistic communication paradigm for storing a piece of content probabilistically in a geographical area is Floating Content (FC). A key issue in the practical deployment of FC is how to tune content replication a...

One of the main obstacles for the implementation of deep convolutional neural networks (DCNNs) in the clinical pathology workflow is their low capability to overcome variability in slide preparation and scanner configuration, that leads to changes in tissue appearance. Some of these variations may not be not included in the training data, which mea...

Background: The introduction of digital pathology into clinical practice has led to the development of clinical workflows with digital images, in connection with pathology reports. Still, most of the current work is time-consuming manual analysis of image areas at different scales. Links with data in the biomedical literature are rare, and a need...

Background and objectives:Spectral Domain Optical Coherence Tomography (SD-OCT) is a volumetric imag-ing technique that allows measuring patterns between layers such as small amounts of fluid. Since 2012, automaticmedical image analysis performance has steadily increased through the use of deep learning models that automaticallylearn relevant featu...

Opportunistic communications are expected to playa crucial role in enabling context-aware vehicular services. A widely investigated opportunistic communication paradigm for storing a piece of content probabilistically in a geographica larea is Floating Content (FC). A key issue in the practical deployment of FC is how to tune content replication an...

A novel method to detect and classify several classes of diseased and healthy lung tissue in CT (Computed Tomography), based on the fusion of Riesz and deep learning features, is presented. First, discriminative parametric lung tissue texture signatures are learned from Riesz representations using a one–versus–one approach. The signatures are gener...

Floating Content (FC) is a communication paradigm for the local dissemination of contextualized information through D2D connectivity, in a way which minimizes the use of resources while achieving some specified performance target. Existing approaches to FC dimensioning are based on unrealistic system assumptions that make them, highly inaccurate an...

Handling the tremendous amount of network data, produced by the explosive growth of mobile traffic volume, is becoming of main priority to achieve desired performance targets efficiently. Opportunistic communication such as FloatingContent (FC), can be used to offload part of the cellular traffic volume to vehicular-to-vehicular communication (V2V)...

Floating Content (FC) is a communication paradigm for the local dissemination of contextualized information through D2D connectivity, in a way which minimizes the use of resources while achieving some specified performance target. Existing approaches to FC dimensioning are based on unrealistic system assumptions that make them, highly inaccurate an...

Open access medical content databases such as PubMed Central and TCGA offer possibilities to obtain large amounts of images for training deep learning models. Nevertheless, accurate labeling of large-scale medical datasets is not available and poses challenging tasks for using such datasets. Predicting unknown magnification levels and standardize s...

Clinical practice is getting increasingly stressful for pathologists due to increasing complexity and time constraints. Histopathology is slowly shifting to digital pathology, thus creating opportunities to allow pathologists to improve reading quality or save time using Artificial Intelligence (AI)-based applications. We aim to enhance the practic...

Detecting the scale of histopathology images is important because it allows to exploit various sources of information to train deep learning (DL) models to recognise biological structures of interest. Large open access databases with images exist, such as The Cancer Genome Atlas (TCGA) and PubMed Central but very few models can use such datasets be...

Diabetic macular edema (DME) is one of the most common eye complication caused by diabetes mellitus, resulting in partial or total loss of vision. Optical Coherence Tomography (OCT) volumes have been widely used to diagnose different eye diseases, thanks to their sensitivity to represent small amounts of fluid, thickness between layers and swelling...

Diabetic macular edema (DME) is one of the most common eye complication caused by diabetes mellitus, resulting in partial or total loss of vision. Optical Coherence Tomography (OCT) volumes have been widely used to diagnose different eye diseases, thanks to their sensitivity to represent small amounts of fluid, thickness between layers and swelling...

Training deep convolutional neural network for classification in medical tasks is often difficult due to the lack of annotated data samples. Deep convolutional networks (CNN) has been successfully used as an automatic detection tool to support the grading of diabetic retinopathy and macular edema. Nevertheless, the manual annotation of exudates in...

The current gold standard for interpreting patient tissue samples is the visual inspection of whole–slide histopathology images (WSIs) by pathologists. They generate a pathology report describing the main findings relevant for diagnosis and treatment planning. Searching for similar cases through repositories for differential diagnosis is often not...

Diabetic macular edema is one of the leading causes of legal blindness worldwide. Early, and accessible, detection of ophthalmological diseases is especially important in developing countries, where there are major limitations to access to specialized medical diagnosis and treatment. Deep learning models, such as deep convolutional neural networks...

Medulloblastoma (MB) is a type of brain cancer that represent roughly 25% of all brain tumors in children. In the anaplastic medulloblastoma subtype, it is important to identify the degree of irregularity and lack of organizations of cells as this correlates to disease aggressiveness and is of clinical value when evaluating patient prognosis. This...

The traditional perspectives on trauma studies have understood traumatic events as naturally existing. By the end of the 1990s a group of cultural sociologists started to develop a new perspective, which they refer to as the Cultural Trauma Theory. This perspective suggests that inherently traumatic events do not exist and that trauma, instead, res...

The traditional perspectives on trauma studies have understood traumatic events as naturally existing. By the end of the 1990s a group of cultural sociologists started to develop a new perspective, which they refer to as the Cultural Trauma Theory. This perspective suggests that inherently traumatic events do not exist and that trauma, instead, res...

The paper presents an online matrix factorization algorithm for multilabel learning. This method addresses the multi-label annotation problem finding a joint embedding that represents both instances and labels in a common latent space. An important characteristic of the novel method is its scalability, which is a consequence of its formulation as a...