Artificial Intelligence Enabled Histological Prediction of Remission or Activity and Clinical Outcomes in Ulcerative Colitis.

BACKGROUND & AIMS: Microscopic inflammation has significant prognostic value in ulcerative colitis (UC); however, its assessment is complex with high interobserver variability. We aimed to develop and validate an artificial intelligence (AI) computer-aided diagnosis system to evaluate UC biopsies and predict prognosis. METHODS: A total of 535 digitalized biopsies (273 patients) were graded according to the PICaSSO Histologic Remission Index (PHRI), Robarts, and Nancy Histological Index. A convolutional neural network classifier was trained to distinguish remission from activity on a subset of 118 biopsies, calibrated on 42 and tested on 375. The model was additionally tested to predict the corresponding endoscopic assessment and occurrence of flares at 12 months. The system output was compared with human assessment. Diagnostic performance was reported as sensitivity, specificity, prognostic prediction through Kaplan-Meier, and hazard ratios of flares between active and remission groups. We externally validated the model in 154 biopsies (58 patients) with similar characteristics but more histologically active patients. RESULTS: The system distinguished histological activity/remission with sensitivity and specificity of 89% and 85% (PHRI), 94% and 76% (Robarts Histological Index), and 89% and 79% (Nancy Histological Index). The model predicted the corresponding endoscopic remission/activity with 79% and 82% accuracy for UC endoscopic index of severity and Paddington International virtual ChromoendoScopy ScOre, respectively. The hazard ratio for disease flare-up between histological activity/remission groups according to pathologist-assessed PHRI was 3.56, and 4.64 for AI-assessed PHRI. Both histology and outcome prediction were confirmed in the external validation cohort. CONCLUSION: We developed and validated an AI model that distinguishes histologic remission/activity in biopsies of UC and predicts flare-ups. This can expedite, standardize, and enhance histologic assessment in practice and trials.

Histological interpretation of spitzoid tumours: an extensive machine learning-based concordance analysis for improving decision making.

The histopathological classification of melanocytic tumours with spitzoid features remains a challenging task. We confront the complexities involved in the histological classification of these tumours by proposing machine learning (ML) algorithms that objectively categorise the most relevant features in order of importance. The data set comprises 122 tumours (39 benign, 44 atypical and 39 malignant) from four different countries. BRAF and NRAS mutation status was evaluated in 51. Analysis of variance score was performed to rank 22 clinicopathological variables. The Gaussian naive Bayes algorithm achieved in distinguishing Spitz naevus from malignant spitzoid tumours with an accuracy of 0.95 and kappa score of 0.87, utilising the 12 most important variables. For benign versus non-benign Spitz tumours, the test reached a kappa score of 0.88 using the 13 highest-scored features. Furthermore, for the atypical Spitz tumours (AST) versus Spitz melanoma comparison, the logistic regression algorithm achieved a kappa value of 0.66 and an accuracy rate of 0.85. When the three categories were compared most AST were classified as melanoma, because of the similarities on histological features between the two groups. Our results show promise in supporting the histological classification of these tumours in clinical practice, and provide valuable insight into the use of ML to improve the accuracy and objectivity of this process while minimising interobserver variability. These proposed algorithms represent a potential solution to the lack of a clear threshold for the Spitz/spitzoid tumour classification, and its high accuracy supports its usefulness as a helpful tool to improve diagnostic decision-making.

A virtual chromoendoscopy artificial intelligence system to detect endoscopic and histologic activity/remission and predict clinical outcomes in ulcerative colitis.

BACKGROUND: Endoscopic and histological remission (ER, HR) are therapeutic targets in ulcerative colitis (UC). Virtual chromoendoscopy (VCE) improves endoscopic assessment and the prediction of histology; however, interobserver variability limits standardized endoscopic assessment. We aimed to develop an artificial intelligence (AI) tool to distinguish ER/activity, and predict histology and risk of flare from white-light endoscopy (WLE) and VCE videos. METHODS: 1090 endoscopic videos (67 280 frames) from 283 patients were used to develop a convolutional neural network (CNN). UC endoscopic activity was graded by experts using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Paddington International virtual ChromoendoScopy ScOre (PICaSSO). The CNN was trained to distinguish ER/activity on endoscopy videos, and retrained to predict HR/activity, defined according to multiple indices, and predict outcome; CNN and human agreement was measured. RESULTS: The AI system detected ER (UCEIS ≤ 1) in WLE videos with 72 % sensitivity, 87 % specificity, and an area under the receiver operating characteristic curve (AUROC) of 0.85; for detection of ER in VCE videos (PICaSSO ≤ 3), the sensitivity was 79 %, specificity 95 %, and the AUROC 0.94. The prediction of HR was similar between WLE and VCE videos (accuracies ranging from 80 % to 85 %). The model's stratification of risk of flare was similar to that of physician-assessed endoscopy scores. CONCLUSIONS: Our system accurately distinguished ER/activity and predicted HR and clinical outcome from colonoscopy videos. This is the first computer model developed to detect inflammation/healing on VCE using the PICaSSO and the first computer tool to provide endoscopic, histologic, and clinical assessment.

PICaSSO Histologic Remission Index (PHRI) in ulcerative colitis: development of a novel simplified histological score for monitoring mucosal healing and predicting clinical outcomes and its applicability in an artificial intelligence system.

Histological remission is evolving as an important treatment target in UC. We aimed to develop a simple histological index, aligned to endoscopy, correlated with clinical outcomes, and suited to apply to an artificial intelligence (AI) system to evaluate inflammatory activity. METHODS: Using a set of 614 biopsies from 307 patients with UC enrolled into a prospective multicentre study, we developed the Paddington International virtual ChromoendoScopy ScOre (PICaSSO) Histologic Remission Index (PHRI). Agreement with multiple other histological indices and validation for inter-reader reproducibility were assessed. Finally, to implement PHRI into a computer-aided diagnosis system, we trained and tested a novel deep learning strategy based on a CNN architecture to detect neutrophils, calculate PHRI and identify active from quiescent UC using a subset of 138 biopsies. RESULTS: PHRI is strongly correlated with endoscopic scores (Mayo Endoscopic Score and UC Endoscopic Index of Severity and PICaSSO) and with clinical outcomes (hospitalisation, colectomy and initiation or changes in medical therapy due to UC flare-up). A PHRI score of 1 could accurately stratify patients' risk of adverse outcomes (hospitalisation, colectomy and treatment optimisation due to flare-up) within 12 months. Our inter-reader agreement was high (intraclass correlation 0.84). Our preliminary AI algorithm differentiated active from quiescent UC with 78% sensitivity, 91.7% specificity and 86% accuracy. CONCLUSIONS: PHRI is a simple histological index in UC, and it exhibits the highest correlation with endoscopic activity and clinical outcomes. A PHRI-based AI system was accurate in predicting histological remission.

Automatic Segmentation of the Retinal Nerve Fiber Layer by Means of Mathematical Morphology and Deformable Models in 2D Optical Coherence Tomography Imaging.

Glaucoma is a neurodegenerative disease process that leads to progressive damage of the optic nerve to produce visual impairment and blindness. Spectral-domain OCT technology enables peripapillary circular scans of the retina and the measurement of the thickness of the retinal nerve fiber layer (RNFL) for the assessment of the disease status or progression in glaucoma patients. This paper describes a new approach to segment and measure the retinal nerve fiber layer in peripapillary OCT images. The proposed method consists of two stages. In the first one, morphological operators robustly detect the coarse location of the layer boundaries, despite the speckle noise and diverse artifacts in the OCT image. In the second stage, deformable models are initialized with the results of the previous stage to perform a fine segmentation of the boundaries, providing an accurate measurement of the entire RNFL. The results of the RNFL segmentation were qualitatively assessed by ophthalmologists, and the measurements of the thickness of the RNFL were quantitatively compared with those provided by the OCT inbuilt software as well as the state-of-the-art methods.

Supervised Domain Adaptation for Automated Semantic Segmentation of the Atrial Cavity.

Atrial fibrillation (AF) is the most common cardiac arrhythmia. At present, cardiac ablation is the main treatment procedure for AF. To guide and plan this procedure, it is essential for clinicians to obtain patient-specific 3D geometrical models of the atria. For this, there is an interest in automatic image segmentation algorithms, such as deep learning (DL) methods, as opposed to manual segmentation, an error-prone and time-consuming method. However, to optimize DL algorithms, many annotated examples are required, increasing acquisition costs. The aim of this work is to develop automatic and high-performance computational models for left and right atrium (LA and RA) segmentation from a few labelled MRI volumetric images with a 3D Dual U-Net algorithm. For this, a supervised domain adaptation (SDA) method is introduced to infer knowledge from late gadolinium enhanced (LGE) MRI volumetric training samples (80 LA annotated samples) to a network trained with balanced steady-state free precession (bSSFP) MR images of limited number of annotations (19 RA and LA annotated samples). The resulting knowledge-transferred model SDA outperformed the same network trained from scratch in both RA (Dice equals 0.9160) and LA (Dice equals 0.8813) segmentation tasks.

Detection of Early Signs of Diabetic Retinopathy Based on Textural and Morphological Information in Fundus Images.

Estimated blind people in the world will exceed 40 million by 2025. To develop novel algorithms based on fundus image descriptors that allow the automatic classification of retinal tissue into healthy and pathological in early stages is necessary. In this paper, we focus on one of the most common pathologies in the current society: diabetic retinopathy. The proposed method avoids the necessity of lesion segmentation or candidate map generation before the classification stage. Local binary patterns and granulometric profiles are locally computed to extract texture and morphological information from retinal images. Different combinations of this information feed classification algorithms to optimally discriminate bright and dark lesions from healthy tissues. Through several experiments, the ability of the proposed system to identify diabetic retinopathy signs is validated using different public databases with a large degree of variability and without image exclusion.

CNNs for automatic glaucoma assessment using fundus images: an extensive validation.

BACKGROUND: Most current algorithms for automatic glaucoma assessment using fundus images rely on handcrafted features based on segmentation, which are affected by the performance of the chosen segmentation method and the extracted features. Among other characteristics, convolutional neural networks (CNNs) are known because of their ability to learn highly discriminative features from raw pixel intensities. METHODS: In this paper, we employed five different ImageNet-trained models (VGG16, VGG19, InceptionV3, ResNet50 and Xception) for automatic glaucoma assessment using fundus images. Results from an extensive validation using cross-validation and cross-testing strategies were compared with previous works in the literature. RESULTS: Using five public databases (1707 images), an average AUC of 0.9605 with a 95% confidence interval of 95.92-97.07%, an average specificity of 0.8580 and an average sensitivity of 0.9346 were obtained after using the Xception architecture, significantly improving the performance of other state-of-the-art works. Moreover, a new clinical database, ACRIMA, has been made publicly available, containing 705 labelled images. It is composed of 396 glaucomatous images and 309 normal images, which means, the largest public database for glaucoma diagnosis. The high specificity and sensitivity obtained from the proposed approach are supported by an extensive validation using not only the cross-validation strategy but also the cross-testing validation on, to the best of the authors' knowledge, all publicly available glaucoma-labelled databases. CONCLUSIONS: These results suggest that using ImageNet-trained models is a robust alternative for automatic glaucoma screening system. All images, CNN weights and software used to fine-tune and test the five CNNs are publicly available, which could be used as a testbed for further comparisons.

First-Stage Prostate Cancer Identification on Histopathological Images: Hand-Driven versus Automatic Learning.

Analysis of histopathological image supposes the most reliable procedure to identify prostate cancer. Most studies try to develop computer aid-systems to face the Gleason grading problem. On the contrary, we delve into the discrimination between healthy and cancerous tissues in its earliest stage, only focusing on the information contained in the automatically segmented gland candidates. We propose a hand-driven learning approach, in which we perform an exhaustive hand-crafted feature extraction stage combining in a novel way descriptors of morphology, texture, fractals and contextual information of the candidates under study. Then, we carry out an in-depth statistical analysis to select the most relevant features that constitute the inputs to the optimised machine-learning classifiers. Additionally, we apply for the first time on prostate segmented glands, deep-learning algorithms modifying the popular VGG19 neural network. We fine-tuned the last convolutional block of the architecture to provide the model specific knowledge about the gland images. The hand-driven learning approach, using a nonlinear Support Vector Machine, reports a slight outperforming over the rest of experiments with a final multi-class accuracy of 0.876 ± 0.026 in the discrimination between false glands (artefacts), benign glands and Gleason grade 3 glands.

Tracking systems for virtual rehabilitation: objective performance vs. subjective experience. A practical scenario.

Motion tracking systems are commonly used in virtual reality-based interventions to detect movements in the real world and transfer them to the virtual environment. There are different tracking solutions based on different physical principles, which mainly define their performance parameters. However, special requirements have to be considered for rehabilitation purposes. This paper studies and compares the accuracy and jitter of three tracking solutions (optical, electromagnetic, and skeleton tracking) in a practical scenario and analyzes the subjective perceptions of 19 healthy subjects, 22 stroke survivors, and 14 physical therapists. The optical tracking system provided the best accuracy (1.074 ± 0.417 cm) while the electromagnetic device provided the most inaccurate results (11.027 ± 2.364 cm). However, this tracking solution provided the best jitter values (0.324 ± 0.093 cm), in contrast to the skeleton tracking, which had the worst results (1.522 ± 0.858 cm). Healthy individuals and professionals preferred the skeleton tracking solution rather than the optical and electromagnetic solution (in that order). Individuals with stroke chose the optical solution over the other options. Our results show that subjective perceptions and preferences are far from being constant among different populations, thus suggesting that these considerations, together with the performance parameters, should be also taken into account when designing a rehabilitation system.

MICIL: Multiple-Instance Class-Incremental Learning for skin cancer whole slide images.

Artificial intelligence (AI) agents encounter the problem of catastrophic forgetting when they are trained in sequentially with new data batches. This issue poses a barrier to the implementation of AI-based models in tasks that involve ongoing evolution, such as cancer prediction. Moreover, whole slide images (WSI) play a crucial role in cancer management, and their automated analysis has become increasingly popular in assisting pathologists during the diagnosis process. Incremental learning (IL) techniques aim to develop algorithms capable of retaining previously acquired information while also acquiring new insights to predict future data. Deep IL techniques need to address the challenges posed by the gigapixel scale of WSIs, which often necessitates the use of multiple instance learning (MIL) frameworks. In this paper, we introduce an IL algorithm tailored for analyzing WSIs within a MIL paradigm. The proposed Multiple Instance Class-Incremental Learning (MICIL) algorithm combines MIL with class-IL for the first time, allowing for the incremental prediction of multiple skin cancer subtypes from WSIs within a class-IL scenario. Our framework incorporates knowledge distillation and data rehearsal, along with a novel embedding-level distillation, aiming to preserve the latent space at the aggregated WSI level. Results demonstrate the algorithm's effectiveness in addressing the challenge of balancing IL-specific metrics, such as intransigence and forgetting, and solving the plasticity-stability dilemma.

Uninformed Teacher-Student for hard-samples distillation in weakly supervised mitosis localization.

BACKGROUND AND OBJECTIVE: Mitotic activity is a crucial biomarker for diagnosing and predicting outcomes for different types of cancers, particularly breast cancer. However, manual mitosis counting is challenging and time-consuming for pathologists, with moderate reproducibility due to biopsy slide size, low mitotic cell density, and pattern heterogeneity. In recent years, deep learning methods based on convolutional neural networks (CNNs) have been proposed to address these limitations. Nonetheless, these methods have been hampered by the available data labels, which usually consist only of the centroids of mitosis, and by the incoming noise from annotated hard negatives. As a result, complex algorithms with multiple stages are often required to refine the labels at the pixel level and reduce the number of false positives. METHODS: This article presents a novel weakly supervised approach for mitosis detection that utilizes only image-level labels on histological hematoxylin and eosin (H&E) images, avoiding the need for complex labeling scenarios. Also, an Uninformed Teacher-Student (UTS) pipeline is introduced to detect and distill hard samples by comparing weakly supervised localizations and the annotated centroids, using strong augmentations to enhance uncertainty. Additionally, an automatic proliferation score is proposed that mimicks the pathologist-annotated mitotic activity index (MAI). The proposed approach is evaluated on three publicly available datasets for mitosis detection on breast histology samples, and two datasets for mitotic activity counting in whole-slide images. RESULTS: The proposed framework achieves competitive performance with relevant prior literature in all the datasets used for evaluation without explicitly using the mitosis location information during training. This approach challenges previous methods that rely on strong mitosis location information and multiple stages to refine false positives. Furthermore, the proposed pipeline for hard-sample distillation demonstrates promising dataset-specific improvements. Concretely, when the annotation has not been thoroughly refined by multiple pathologists, the UTS model offers improvements of up to ∼4% in mitosis localization, thanks to the detection and distillation of uncertain cases. Concerning the mitosis counting task, the proposed automatic proliferation score shows a moderate positive correlation with the MAI annotated by pathologists at the biopsy level on two external datasets. CONCLUSIONS: The proposed Uninformed Teacher-Student pipeline leverages strong augmentations to distill uncertain samples and measure dissimilarities between predicted and annotated mitosis. Results demonstrate the feasibility of the weakly supervised approach and highlight its potential as an objective evaluation tool for tumor proliferation.

Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease.

Integrating artificial intelligence into inflammatory bowel disease (IBD) has the potential to revolutionise clinical practice and research. Artificial intelligence harnesses advanced algorithms to deliver accurate assessments of IBD endoscopy and histology, offering precise evaluations of disease activity, standardised scoring, and outcome prediction. Furthermore, artificial intelligence offers the potential for a holistic endo-histo-omics approach by interlacing and harmonising endoscopy, histology, and omics data towards precision medicine. The emerging applications of artificial intelligence could pave the way for personalised medicine in IBD, offering patient stratification for the most beneficial therapy with minimal risk. Although artificial intelligence holds promise, challenges remain, including data quality, standardisation, reproducibility, scarcity of randomised controlled trials, clinical implementation, ethical concerns, legal liability, and regulatory issues. The development of standardised guidelines and interdisciplinary collaboration, including policy makers and regulatory agencies, is crucial for addressing these challenges and advancing artificial intelligence in IBD clinical practice and trials.

Labeling confidence for uncertainty-aware histology image classification.

Deep learning-based models applied to digital pathology require large, curated datasets with high-quality (HQ) annotations to perform correctly. In many cases, recruiting expert pathologists to annotate large databases is not feasible, and it is necessary to collect additional labeled data with varying label qualities, e.g., pathologists-in-training (henceforth, non-expert annotators). Learning from datasets with noisy labels is more challenging in medical applications since medical imaging datasets tend to have instance-dependent noise and suffer from high inter/intra-observer variability. In this paper, we design an uncertainty-driven labeling strategy with which we generate soft labels from 10 non-expert annotators for multi-class skin cancer classification. Based on this soft annotation, we propose an uncertainty estimation-based framework to handle these noisy labels. This framework is based on a novel formulation using a dual-branch min-max entropy calibration to penalize inexact labels during the training. Comprehensive experiments demonstrate the promising performance of our labeling strategy. Results show a consistent improvement by using soft labels with standard cross-entropy loss during training (∼4.0% F1-score) and increases when calibrating the model with the proposed min-max entropy calibration (∼6.6% F1-score). These improvements are produced at negligible cost, both in terms of annotation and calculation.

Deep learning system for classification of ploidy status using time-lapse videos.

OBJECTIVE: To develop a spatiotemporal model for de prediction of euploid and aneuploid embryos using time-lapse videos from 10-115 hours after insemination (hpi). DESIGN: Retrospective study. MAIN OUTCOME MEASURES: The research used an end-to-end approach to develop an automated artificial intelligence system capable of extracting features from images and classifying them, considering spatiotemporal dependencies. A convolutional neural network extracted the most relevant features from each video frame. A bidirectional long short-term memory layer received this information and analyzed the temporal dependencies, obtaining a low-dimensional feature vector that characterized each video. A multilayer perceptron classified them into 2 groups, euploid and noneuploid. RESULTS: The model performance in accuracy fell between 0.6170 and 0.7308. A multi-input model with a gate recurrent unit module performed better than others; the precision (or positive predictive value) is 0.8205 for predicting euploidy. Sensitivity, specificity, F1-Score and accuracy are 0.6957, 0.7813, 0.7042, and 0.7308, respectively. CONCLUSIONS: This article proposes an artificial intelligence solution for prioritizing euploid embryo transfer. We can highlight the identification of a noninvasive method for chromosomal status diagnosis using a deep learning approach that analyzes raw data provided by time-lapse incubators. This method demonstrated potential automation of the evaluation process, allowing spatial and temporal information to encode.

ProGleason-GAN: Conditional progressive growing GAN for prostatic cancer Gleason grade patch synthesis.

BACKGROUND AND OBJECTIVE: Prostate cancer is one of the most common diseases affecting men. The main diagnostic and prognostic reference tool is the Gleason scoring system. An expert pathologist assigns a Gleason grade to a sample of prostate tissue. As this process is very time-consuming, some artificial intelligence applications were developed to automatize it. The training process is often confronted with insufficient and unbalanced databases which affect the generalisability of the models. Therefore, the aim of this work is to develop a generative deep learning model capable of synthesising patches of any selected Gleason grade to perform data augmentation on unbalanced data and test the improvement of classification models. METHODOLOGY: The methodology proposed in this work consists of a conditional Progressive Growing GAN (ProGleason-GAN) capable of synthesising prostate histopathological tissue patches by selecting the desired Gleason Grade cancer pattern in the synthetic sample. The conditional Gleason Grade information is introduced into the model through the embedding layers, so there is no need to add a term to the Wasserstein loss function. We used minibatch standard deviation and pixel normalisation to improve the performance and stability of the training process. RESULTS: The reality assessment of the synthetic samples was performed with the Frechet Inception Distance (FID). We obtained an FID metric of 88.85 for non-cancerous patterns, 81.86 for GG3, 49.32 for GG4 and 108.69 for GG5 after post-processing stain normalisation. In addition, a group of expert pathologists was selected to perform an external validation of the proposed framework. Finally, the application of our proposed framework improved the classification results in SICAPv2 dataset, proving its effectiveness as a data augmentation method. CONCLUSIONS: ProGleason-GAN approach combined with a stain normalisation post-processing provides state-of-the-art results regarding Frechet's Inception Distance. This model can synthesise samples of non-cancerous patterns, GG3, GG4 or GG5. The inclusion of conditional information about the Gleason grade during the training process allows the model to select the cancerous pattern in a synthetic sample. The proposed framework can be used as a data augmentation method.

A Spitzoid Tumor dataset with clinical metadata and Whole Slide Images for Deep Learning models.

Spitzoid tumors (ST) are a group of melanocytic tumors of high diagnostic complexity. Since 1948, when Sophie Spitz first described them, the diagnostic uncertainty remains until now, especially in the intermediate category known as Spitz tumor of unknown malignant potential (STUMP) or atypical Spitz tumor. Studies developing deep learning (DL) models to diagnose melanocytic tumors using whole slide imaging (WSI) are scarce, and few used ST for analysis, excluding STUMP. To address this gap, we introduce SOPHIE: the first ST dataset with WSIs, including labels as benign, malignant, and atypical tumors, along with the clinical information of each patient. Additionally, we explain two DL models implemented as validation examples using this database.

WWFedCBMIR: World-Wide Federated Content-Based Medical Image Retrieval.

The paper proposes a federated content-based medical image retrieval (FedCBMIR) tool that utilizes federated learning (FL) to address the challenges of acquiring a diverse medical data set for training CBMIR models. CBMIR is a tool to find the most similar cases in the data set to assist pathologists. Training such a tool necessitates a pool of whole-slide images (WSIs) to train the feature extractor (FE) to extract an optimal embedding vector. The strict regulations surrounding data sharing in hospitals makes it difficult to collect a rich data set. FedCBMIR distributes an unsupervised FE to collaborative centers for training without sharing the data set, resulting in shorter training times and higher performance. FedCBMIR was evaluated by mimicking two experiments, including two clients with two different breast cancer data sets, namely BreaKHis and Camelyon17 (CAM17), and four clients with the BreaKHis data set at four different magnifications. FedCBMIR increases the F1 score (F1S) of each client from 96% to 98.1% in CAM17 and from 95% to 98.4% in BreaKHis, with 11.44 fewer hours in training time. FedCBMIR provides 98%, 96%, 94%, and 97% F1S in the BreaKHis experiment with a generalized model and accomplishes this in 25.53 fewer hours of training.

Durable 3D murine ex vivo retina glaucoma models for optical coherence tomography.

Durable and standardized phantoms with optical properties similar to native healthy and disease-like biological tissues are essential tools for the development, performance testing, calibration and comparison of label-free high-resolution optical coherence tomography (HR-OCT) systems. Available phantoms are based on artificial materials and reflect thus only partially ocular properties. To address this limitation, we have performed investigations on the establishment of durable tissue phantoms from ex vivo mouse retina for enhanced reproduction of in vivo structure and complexity. In a proof-of-concept study, we explored the establishment of durable 3D models from dissected mouse eyes that reproduce the properties of normal retina structures and tissue with glaucoma-like layer thickness alterations. We explored different sectioning and preparation procedures for embedding normal and N-methyl-D-aspartate (NMDA)-treated mouse retina in transparent gel matrices and epoxy resins, to generate durable three-dimensional tissue models. Sample quality and reproducibility were quantified by thickness determination of the generated layered structures utilizing computer-assisted segmentation of OCT B-scans that were acquired with a commercial HR-OCT system at a central wavelength of 905 nm and analyzed with custom build software. Our results show that the generated 3D models feature thin biological layers close to current OCT resolution limits and glaucoma-like tissue alterations that are suitable for reliable HR-OCT performance characterization. The comparison of data from resin-embedded tissue with native murine retina in gels demonstrates that by utilization of appropriate preparation protocols, highly stable samples with layered structures equivalent to native tissues can be fabricated. The experimental data demonstrate our concept as a promising approach toward the fabrication of durable biological 3D models suitable for high-resolution OCT system performance characterization supporting the development of optimized instruments for ophthalmology applications.

Annotation protocol and crowdsourcing multiple instance learning classification of skin histological images: The CR-AI4SkIN dataset.

Digital Pathology (DP) has experienced a significant growth in recent years and has become an essential tool for diagnosing and prognosis of tumors. The availability of Whole Slide Images (WSIs) and the implementation of Deep Learning (DL) algorithms have paved the way for the appearance of Artificial Intelligence (AI) systems that support the diagnosis process. These systems require extensive and varied data for their training to be successful. However, creating labeled datasets in histopathology is laborious and time-consuming. We have developed a crowdsourcing-multiple instance labeling/learning protocol that is applied to the creation and use of the CR-AI4SkIN dataset.2 CR-AI4SkIN contains 271 WSIs of 7 Cutaneous Spindle Cell (CSC) neoplasms with expert and non-expert labels at region and WSI levels. It is the first dataset of these types of neoplasms made available. The regions selected by the experts are used to learn an automatic extractor of Regions of Interest (ROIs) from WSIs. To produce the embedding of each WSI, the representations of patches within the ROIs are obtained using a contrastive learning method, and then combined. Finally, they are fed to a Gaussian process-based crowdsourcing classifier, which utilizes the noisy non-expert WSI labels. We validate our crowdsourcing-multiple instance learning method in the CR-AI4SkIN dataset, addressing a binary classification problem (malign vs. benign). The proposed method obtains an F1 score of 0.7911 on the test set, outperforming three widely used aggregation methods for crowdsourcing tasks. Furthermore, our crowdsourcing method also outperforms the supervised model with expert labels on the test set (F1-score = 0.6035). The promising results support the proposed crowdsourcing multiple instance learning annotation protocol. It also validates the automatic extraction of interest regions and the use of contrastive embedding and Gaussian process classification to perform crowdsourcing classification tasks.