RESUMO
Cough is an important symptom in children with acute and chronic respiratory disease. Daily cough is common in Cystic Fibrosis (CF) and increased cough is a symptom of pulmonary exacerbation. To date, cough assessment is primarily subjective in clinical practice and research. Attempts to develop objective, automatic cough counting tools have faced reliability issues in noisy environments and practical barriers limiting long-term use. This single-center pilot study evaluated usability, acceptability and performance of a mechanoacoustic sensor (MAS), previously used for cough classification in adults, in 36 children with CF over brief and multi-day periods in four cohorts. Children whose health was at baseline and who had symptoms of pulmonary exacerbation were included. We trained, validated, and deployed custom deep learning algorithms for accurate cough detection and classification from other vocalization or artifacts with an overall area under the receiver-operator characteristic curve (AUROC) of 0.96 and average precision (AP) of 0.93. Child and parent feedback led to a redesign of the MAS towards a smaller, more discreet device acceptable for daily use in children. Additional improvements optimized power efficiency and data management. The MAS's ability to objectively measure cough and other physiologic signals across clinic, hospital, and home settings is demonstrated, particularly aided by an AUROC of 0.97 and AP of 0.96 for motion artifact rejection. Examples of cough frequency and physiologic parameter correlations with participant-reported outcomes and clinical measurements for individual patients are presented. The MAS is a promising tool in objective longitudinal evaluation of cough in children with CF.
RESUMO
Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are 'distracted' by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen's kappa of 0.764 with only 0.69% of the labeled Panda data.
Assuntos
Neoplasias da Próstata , Humanos , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/patologia , Masculino , Aprendizado de Máquina , Teorema de Bayes , Algoritmos , Interpretação de Imagem Assistida por Computador/métodos , Artefatos , Redes Neurais de ComputaçãoRESUMO
Automated semantic segmentation of histopathological images is an essential task in Computational Pathology (CPATH). The main limitation of Deep Learning (DL) to address this task is the scarcity of expert annotations. Crowdsourcing (CR) has emerged as a promising solution to reduce the individual (expert) annotation cost by distributing the labeling effort among a group of (non-expert) annotators. Extracting knowledge in this scenario is challenging, as it involves noisy annotations. Jointly learning the underlying (expert) segmentation and the annotators' expertise is currently a commonly used approach. Unfortunately, this approach is frequently carried out by learning a different neural network for each annotator, which scales poorly when the number of annotators grows. For this reason, this strategy cannot be easily applied to real-world CPATH segmentation. This paper proposes a new family of methods for CR segmentation of histopathological images. Our approach consists of two coupled networks: a segmentation network (for learning the expert segmentation) and an annotator network (for learning the annotators' expertise). We propose to estimate the annotators' behavior with only one network that receives the annotator ID as input, achieving scalability on the number of annotators. Our family is composed of three different models for the annotator network. Within this family, we propose a novel modeling of the annotator network in the CR segmentation literature, which considers the global features of the image. We validate our methods on a real-world dataset of Triple Negative Breast Cancer images labeled by several medical students. Our new CR modeling achieves a Dice coefficient of 0.7827, outperforming the well-known STAPLE (0.7039) and being competitive with the supervised method with expert labels (0.7723). The code is available at https://github.com/wizmik12/CRowd_Seg.
Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , HumanosRESUMO
Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems.
Assuntos
Corantes , Neoplasias , Algoritmos , Teorema de Bayes , Cor , Humanos , Processamento de Imagem Assistida por Computador/métodos , Neoplasias/diagnóstico por imagem , Neoplasias/patologia , Coloração e RotulagemRESUMO
Smoking is the leading cause of preventable death worldwide. Cigarette smoke includes thousands of chemicals that are harmful and cause tobacco-related diseases. To date, the causality between human exposure to specific compounds and the harmful effects is unknown. A first step in closing the gap in knowledge has been measuring smoking topography, or how the smoker smokes the cigarette (puffs, puff volume, and duration). However, current gold-standard approaches to smoking topography involve expensive, bulky, and obtrusive sensor devices, creating unnatural smoking behavior and preventing their potential for real-time interventions in the wild. Although motion-based wearable sensors and their corresponding machine-learned models have shown promise in unobtrusively tracking smoking gestures, they are notorious for confounding smoking with other similar hand-to-mouth gestures such as eating and drinking. In this paper, we present SmokeMon, a chest-worn thermal-sensing wearable system that can capture spatial, temporal, and thermal information around the wearer and cigarette all day to unobtrusively and passively detect smoking events. We also developed a deep learning-based framework to extract puffs and smoking topography. We evaluate SmokeMon in both controlled and free-living experiments with a total of 19 participants, more than 110 hours of data, and 115 smoking sessions achieving an F1-score of 0.9 for puff detection in the laboratory and 0.8 in the wild. By providing SmokeMon as an open platform, we provide measurement of smoking topography in free-living settings to enable testing of smoking topography in the real world, with potential to facilitate timely smoking cessation interventions.
RESUMO
BACKGROUND AND OBJECTIVE: Color variations in digital histopathology severely impact the performance of computer-aided diagnosis systems. They are due to differences in the staining process and acquisition system, among other reasons. Blind color deconvolution techniques separate multi-stained images into single stained bands which, once normalized, can be used to eliminate these negative color variations and improve the performance of machine learning tasks. METHODS: In this work, we decompose the observed RGB image in its hematoxylin and eosin components. We apply Bayesian modeling and inference based on the use of Super Gaussian sparse priors for each stain together with prior closeness to a given reference color-vector matrix. The hematoxylin and eosin components are then used for image normalization and classification of histological images. The proposed framework is tested on stain separation, image normalization, and cancer classification problems. The results are measured using the peak signal to noise ratio, normalized median intensity and the area under ROC curve on five different databases. RESULTS: The obtained results show the superiority of our approach to current state-of-the-art blind color deconvolution techniques. In particular, the fidelity to the tissue improves 1,27 dB in mean PSNR. The normalized median intensity shows a good normalization quality of the proposed approach on the tested datasets. Finally, in cancer classification experiments the area under the ROC curve improves from 0.9491 to 0.9656 and from 0.9279 to 0.9541 on Camelyon-16 and Camelyon-17, respectively, when the original and processed images are used. Furthermore, these figures of merits are better than those obtained by the methods compared with. CONCLUSIONS: The proposed framework for blind color deconvolution, normalization and classification of images guarantees fidelity to the tissue structure and can be used both for normalization and classification. In addition, color deconvolution enables the use of the optical density space for classification, which improves the classification performance.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , Teorema de Bayes , Cor , Distribuição NormalRESUMO
The volume of labeled data is often the primary determinant of success in developing machine learning algorithms. This has increased interest in methods for leveraging crowds to scale data labeling efforts, and methods to learn from noisy crowd-sourced labels. The need to scale labeling is acute but particularly challenging in medical applications like pathology, due to the expertise required to generate quality labels and the limited availability of qualified experts. In this paper we investigate the application of Scalable Variational Gaussian Processes for Crowdsourcing (SVGPCR) in digital pathology. We compare SVGPCR with other crowdsourcing methods using a large multi-rater dataset where pathologists, pathology residents, and medical students annotated tissue regions breast cancer. Our study shows that SVGPCR is competitive with equivalent methods trained using gold-standard pathologist generated labels, and that SVGPCR meets or exceeds the performance of other crowdsourcing methods based on deep learning. We also show how SVGPCR can effectively learn the class-conditional reliabilities of individual annotators and demonstrate that Gaussian-process classifiers have comparable performance to similar deep learning methods. These results suggest that SVGPCR can meaningfully engage non-experts in pathology labeling tasks, and that the class-conditional reliabilities estimated by SVGPCR may assist in matching annotators to tasks where they perform well.