Adapted generative latent diffusion models for accurate pathological analysis in chest X-ray images.

Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges.

Does imbalance in chest X-ray datasets produce biased deep learning approaches for COVID-19 screening?

BACKGROUND: The health crisis resulting from the global COVID-19 pandemic highlighted more than ever the need for rapid, reliable and safe methods of diagnosis and monitoring of respiratory diseases. To study pulmonary involvement in detail, one of the most common resources is the use of different lung imaging modalities (like chest radiography) to explore the possible affected areas. METHODS: The study of patient characteristics like sex and age in pathologies of this type is crucial for gaining knowledge of the disease and for avoiding biases due to the clear scarcity of data when developing representative systems. In this work, we performed an analysis of these factors in chest X-ray images to identify biases. Specifically, 11 imbalance scenarios were defined with female and male COVID-19 patients present in different proportions for the sex analysis, and 6 scenarios where only one specific age range was used for training for the age factor. In each study, 3 different approaches for automatic COVID-19 screening were used: Normal vs COVID-19, Pneumonia vs COVID-19 and Non-COVID-19 vs COVID-19. The study was validated using two public chest X-ray datasets, allowing a reliable analysis to support the clinical decision-making process. RESULTS: The results for the sex-related analysis indicate this factor slightly affects the system in the Normal VS COVID-19 and Pneumonia VS COVID-19 approaches, although the identified differences are not relevant enough to worsen considerably the system. Regarding the age-related analysis, this factor was observed to be influencing the system in a more consistent way than the sex factor, as it was present in all considered scenarios. However, this worsening does not represent a major factor, as it is not of great magnitude. CONCLUSIONS: Multiple studies have been conducted in other fields in order to determine if certain patient characteristics such as sex or age influenced these deep learning systems. However, to the best of our knowledge, this study has not been done for COVID-19 despite the urgency and lack of COVID-19 chest x-ray images. The presented results evidenced that the proposed methodology and tested approaches allow a robust and reliable analysis to support the clinical decision-making process in this pandemic scenario.

End-to-end multi-task learning approaches for the joint epiretinal membrane segmentation and screening in OCT images.

BACKGROUND AND OBJECTIVES: The Epiretinal Membrane (ERM) is an ocular disease that can cause visual distortions and irreversible vision loss. Patient sight preservation relies on an early diagnosis and on determining the location of the ERM in order to be treated and potentially removed. In this context, the visual inspection of the images in order to screen for ERM signs is a costly and subjective process. METHODS: In this work, we propose and study three end-to-end fully-automatic approaches for the simultaneous segmentation and screening of ERM signs in Optical Coherence Tomography images. These convolutional approaches exploit a multi-task learning context to leverage inter-task complementarity in order to guide the training process. The proposed architectures are combined with three different state of the art encoder architectures of reference in order to provide an exhaustive study of the suitability of each of the approaches for these tasks. Furthermore, these architectures work in an end-to-end manner, entailing a significant simplification of the development process since they are able to be trained directly from annotated images without the need for a series of purpose-specific steps. RESULTS: In terms of segmentation, the proposed models obtained a precision of 0.760 ± 0.050, a sensitivity of 0.768 ± 0.210 and a specificity of 0.945 ± 0.011. For the screening task, these models achieved a precision of 0.963 ± 0.068, a sensitivity of 0.816 ± 0.162 and a specificity of 0.983 ± 0.068. The obtained results show that these multi-task approaches are able to perform competitively with or even outperform single-task methods tailored for either the segmentation or the screening of the ERM. CONCLUSIONS: These results highlight the advantages of using complementary knowledge related to the segmentation and screening tasks in the diagnosis of this relevant pathology, constituting the first proposal to address the diagnosis of the ERM from a multi-task perspective.

Automatic macular edema identification and characterization using OCT images.

BACKGROUND AND OBJECTIVE: The detection and characterization of the intraretinal fluid accumulation constitutes a crucial ophthalmological issue as it provides useful information for the identification and diagnosis of the different types of Macular Edema (ME). These types are clinically defined, according to the clinical guidelines, as: Serous Retinal Detachment (SRD), Diffuse Retinal Thickening (DRT) and Cystoid Macular Edema (CME). Their accurate identification and characterization facilitate the diagnostic process, determining the disease severity and, therefore, allowing the clinicians to achieve more precise analysis and suitable treatments. METHODS: This paper proposes a new fully automatic system for the identification and characterization of the three types of ME using Optical Coherence Tomography (OCT) images. In the case of SRD and CME edemas, multilevel image thresholding approaches were designed and combined with the application of ad-hoc clinical restrictions. The case of DRT edemas, given their complexity and fuzzy regional appearance, was approached by a learning strategy that exploits intensity, texture and clinical-based information to identify their presence. RESULTS: The system provided satisfactory results with F-Measures of 87.54% and 91.99% for the DRT and CME detections, respectively. In the case of SRD edemas, the system correctly detected all the cases that were included in the designed dataset. CONCLUSIONS: The proposed methodology offered an accurate performance for the individual identification and characterization of the three different types of ME in OCT images. In fact, the method is capable to handle the ME analysis even in cases of significant severity with the simultaneous existence of the three ME types that appear merged inside the retinal layers.