Search

Abstract Given the high prevalence of lung cancer, an accurate diagnosis is crucial. In the diagnosis process, radiologists play an important role by examining numerous radiology exams to identify different types of nodules. To aid the clinicians’ analytical efforts, computer-aided diagnosis can streamline the process of identifying pulmonary nodules. For this purpose, medical reports can serve as valuable sources for automatically retrieving image annotations. Our study focused on converting medical reports into nodule annotations, matching textual information with manually annotated data from the Lung Nodule Database (LNDb)—a comprehensive repository of lung scans and nodule annotations. As a result of this study, we have released a tabular data file containing information from 292 medical reports in the LNDb, along with files detailing nodule characteristics and corresponding matches to the manually annotated data. The objective is to enable further research studies in lung cancer by bridging the gap between existing reports and additional manual annotations that may be collected, thereby fostering discussions about the advantages and disadvantages between these two data types.

Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population-based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVID-negative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.

Abstract The coronavirus disease 2019 (COVID-19) pandemic has impacted healthcare systems across the world. Chest radiography (CXR) can be used as a complementary method for diagnosing/following COVID-19 patients. However, experience level and workload of technicians and radiologists may affect the decision process. Recent studies suggest that deep learning can be used to assess CXRs, providing an important second opinion for radiologists and technicians in the decision process, and super-human performance in detection of COVID-19 has been reported in multiple studies. In this study, the clinical applicability of deep learning systems for COVID-19 screening was assessed by testing the performance of deep learning systems for the detection of COVID-19. Specifically, four datasets were used: (1) a collection of multiple public datasets (284.793 CXRs); (2) BIMCV dataset (16.631 CXRs); (3) COVIDGR (852 CXRs) and 4) a private dataset (6.361 CXRs). All datasets were collected retrospectively and consist of only frontal CXR views. A ResNet-18 was trained on each of the datasets for the detection of COVID-19. It is shown that a high dataset bias was present, leading to high performance in intradataset train-test scenarios (area under the curve 0.55–0.84 on the collection of public datasets). Significantly lower performances were obtained in interdataset train-test scenarios however (area under the curve > 0.98). A subset of the data was then assessed by radiologists for comparison to the automatic systems. Finetuning with radiologist annotations significantly increased performance across datasets (area under the curve 0.61–0.88) and improved the attention on clinical findings in positive COVID-19 CXRs. Nevertheless, tests on CXRs from different hospital services indicate that the screening performance of CXR and automatic systems is limited (area under the curve < 0.6 on emergency service CXRs). However, COVID-19 manifestations can be accurately detected when present, motivating the use of these tools for evaluating disease progression on mild to severe COVID-19 patients.

Backed by more powerful computational resources and optimized training routines, deep learning models have proven unprecedented performance and several benefits to extract information from chest X-ray data. This is one of the most common imaging exams, whose increasing demand is reflected in the aggravated radiologists’ workload. Consequently, healthcare would benefit from computer-aided diagnosis systems to prioritize certain exams and further identify possible pathologies. Pioneering work in chest X-ray analysis has focused on the identification of specific diseases, but to the best of the authors' knowledge no paper has specifically reviewed relevant work on abnormality detection and multi-label thoracic pathology classification. This paper focuses on those issues, selecting the leading chest X-ray based deep learning strategies for comparison. In addition, the paper discloses the current annotated public chest X-ray databases, covering the common thorax diseases.

Current state-of-the-art medical image segmentation methods require high quality datasets to obtain good performance. However, medical specialists often disagree on diagnosis, hence, datasets contain contradictory annotations. This, in turn, leads to difficulties in the optimization process of Deep Learning models and hinder performance. We propose a method to estimate uncertainty in Convolutional Neural Network (CNN) segmentation models, that makes the training of CNNs more robust to contradictory annotations. In this work, we model two types of uncertainty, heteroscedastic and epistemic, without adding any additional supervisory signal other than the ground-truth segmentation mask. As expected, the uncertainty is higher closer to vessel boundaries, and on top of thinner and less visible vessels where it is more likely for medical specialists to disagree. Therefore, our method is more suitable to learn from datasets created with heterogeneous annotators. We show that there is a correlation between the uncertainty estimated by our method and the disagreement in the segmentation provided by two different medical specialists. Furthermore, by explicitly modeling the uncertainty, the Intersection over Union of the segmentation network improves 5.7 percentage points.

Changes in the retinal vessel caliber are associated with a variety of major diseases, namely diabetes, hypertension and atherosclerosis. The clinical assessment of these changes in fundus images is tiresome and prone to errors and thus automatic methods are desirable for objective and precise caliber measurement. However, the variability of blood vessel appearance, image quality and resolution make the development of these tools a non-trivial task.A method for the estimation of vessel caliber in eye fundus images via vessel cross-sectional intensity profile model fitting is herein proposed. First, the vessel centerlines are determined and individual segments are extracted and smoothed by spline approximation. Then, the corresponding cross-sectional intensity profiles are determined, post-processed and ultimately fitted by newly proposed parametric models. These models are based on Difference-of-Gaussians (DoG) curves modified through a multiplying line with varying inclination. With this, the proposed models can describe profile asymmetry, allowing a good adjustment to the most difficult profiles, namely those showing central light reflex. Finally, the parameters of the best-fit model are used to determine the vessel width using ensembles of bagged regression trees with random feature selection.The performance of our approach is evaluated on the REVIEW public dataset by comparing the vessel cross-sectional profile fitting of the proposed modified DoG models with 7 and 8 parameters against a Hermite model with 6 parameters. Results on different goodness of fitness metrics indicate that our models are constantly better at fitting the vessel profiles. Furthermore, our width measurement algorithm achieves a precision close to the observers, outperforming state-of-the art methods, and retrieving the highest precision when evaluated using cross-validation. This high performance supports the robustness of the algorithm and validates its use in retinal vessel width measurement and possible integration in a system for retinal vasculature assessment.

Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs) is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

This Special Issue on Electrical and Computer Engineering includes selected papers from the 1st edition of the Symposium on Electrical and Computer Engineering (ECE 2015), one of the symposia included in the 1st Doctoral Congress in Engineering, held at FEUP, 11-12 June, 2015. ECE 2015 was an important forum for presenting the research activities of ECE students, particularly from the Doctoral Program in Electrical and Computer Engineering, at FEUP (PDEEC). ECE 2015 received a total of 42 two-page abstracts. The review process was carried out by members of the Symposium Scientific Committee and other reviewers. Each abstract was reviewed by at least two reviewers, and checked by the Program Committee. 37 abstracts were finally accepted and appear in the Symposium book of abstracts. From the 37 abstracts, 17 were presented in four oral sessions, and 20 in one poster session. We were very pleased to include two keynote talks: “The Internet of Things - Latest Trends and Future Perspectives” by Carlos Azeredo Leme, University of Lisbon, Portugal; “A Perspective on Virtual Radio Access Networks” by Luís M. Correia, University of Lisbon, Portugal. Six papers were invited to submit extended versions to this special issue, that were further reviewed and published in this issue. We would like to sincerely thank the authors for submitting these extended versions, and we thank the special issue reviewers for the careful evaluation and feedback provided to the authors. We also would like to express our gratitude to Luís Miguel Costa, for supporting the organization of this Special issue of the U.Porto Journal of Engineering. Finally, we are very pleased to give the readership of this Special Issue on ECE examples of the research developed by PDEEC students, from a vast area covered by the Electrical and Computer Engineering at FEUP and at the associated research institutes and research centers.

This article describes a method that improves the performance of previous approaches for the automatic detection of the common carotid artery (CCA) lumen centerline on longitudinal B-mode ultrasound images. We propose to detect several lumen centerline candidates using local symmetry analysis based on local phase information of dark structures at an appropriate scale. These candidates are analyzed with selection mechanisms that use symmetry, contrast or intensity features in combination with position-based heuristics. Several experimental results are provided to evaluate the robustness and performance of the proposed method in comparison with previous approaches. These results lead to the conclusion that our proposal is robust to noise, lumen artifacts, contrast variations and that is able to deal with the presence of CCA-like structures, significantly improving the performance of our previous approach, from 87.5% ± 0.7% of correct detections to 98.3% ± 0.3% in a set of 200 images.

Proliferative diabetic retinopathy (PDR) is an advanced diabetic retinopathy stage, characterized by neovascularization, which leads to ocular complications and severe vision loss. However, the available DR-labeled retinal image datasets have a small representation of images of the severest DR grades, and thus there is lack of PDR cases for training DR grading models. Additionally, the criteria for labelling these images in the publicly available datasets is not always clear, with some images which do not show typical PDR lesions being labeled as PDR due to the presence of photo-coagulation treatment and laser marks. This problem, together with the datasets' high class imbalance, leads to a limited variability of the samples, which the typical data augmentation and class balancing cannot fully mitigate. We propose a heuristic-based data augmentation scheme based on the synthesis of neovessel (NV)-like structures that compensates for the lack of PDR cases in DR-labeled datasets. The proposed neovessel generation algorithm relies on the general knowledge of common location and shape of these structures. NVs are generated and introduced in pre-existent retinal images which can then be used for enlarging deep neural networks' training sets. The data augmentation scheme was tested on multiple datasets, and allows to improve the model's capacity to detect NVs.

Diabetic retinopathy (DR) detection is a critical retinal image analysis task in the context of early blindness prevention. Unfortunately, in order to train a model to accurately detect DR based on the presence of different retinal lesions, typically a dataset with medical expert's annotations at the pixel level is needed. In this paper, a new methodology based on the multiple instance learning (MIL) framework is developed in order to overcome this necessity by leveraging the implicit information present on annotations made at the image level. Contrary to previous MIL-based DR detection systems, the main contribution of the proposed technique is the joint optimization of the instance encoding and the image classification stages. In this way, more useful mid-level representations of pathological images can be obtained. The explainability of the model decisions is further enhanced by means of a new loss function enforcing appropriate instance and mid-level representations. The proposed technique achieves comparable or better results than other recently proposed methods, with 90% area under the receiver operating characteristic curve (AUC) on Messidor, 93% AUC on DR1, and 96% AUC on DR2, while improving the interpretability of the produced decisions.

Abstract  This paper proposes a non-parametric method for the classification of thin-layer chromatographic (TLC) images from patterns represented in a dissimilarity space. Each pattern corresponds to a mixture of Gaussian approximation of the intensity profile. The methodology comprises various phases, including image processing and analysis steps to extract the chromatographic profiles and a classification phase to discriminate among two groups, one corresponding to normal cases and the other to three pathological classes. We present an extensive study of several dissimilarity-based approaches analysing the influence of the dissimilarity measure and the prototype selection method on the classification performance. The main conclusions of this paper are that, Match and Profile-difference dissimilarity measures present better results, and a new prototype selection methodology achieves a performance similar or even better than conventional methods. Furthermore, we also concluded that simplest classifiers, such as k-NN and linear discriminant classifiers (LDCs), present good performance being the overall classification error less than 10% for the four-class problem. [ABSTRACT FROM AUTHOR]