Recently, significant progress has been achieved in developing deep learning-based approaches for estimating depth maps from monocular images. However, many existing methods rely on content and structure information extracted from RGB photographs, which often results in inaccurate depth estimation, particularly for regions with low texture or occlusions. To overcome these limitations, we propose a novel method that exploits contextual semantic information to predict precise depth maps from monocular images. Our approach leverages a deep autoencoder network incorporating high-quality semantic features from the state-of-the-art HRNet-v2 semantic segmentation model. By feeding the autoencoder network with these features, our method can effectively preserve the discontinuities of the depth images and enhance monocular depth estimation. Specifically, we exploit the semantic features related to the localization and boundaries of the objects in the image to improve the accuracy and robustness of the depth estimation. To validate the effectiveness of our approach, we tested our model on two publicly available datasets, NYU Depth v2 and SUN RGB-D. Our method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy of $85\%$, while minimizing the error $Rel$ by $0.12$, $RMS$ by $0.523$, and $lo{g}_{10}$ by $0.0527$. Our approach also demonstrated exceptional performance in preserving object boundaries and faithfully detecting small object structures in the scene.

Widespread eye conditions such as cataracts, diabetic retinopathy, and glaucoma impact people worldwide. Ophthalmology uses fundus photography for diagnosing these retinal disorders, but fundus images are prone to image quality challenges. Accurate diagnosis hinges on high-quality fundus images. Therefore, there is a need for image quality assessment methods to evaluate fundus images before diagnosis. Consequently, this paper introduces a deep learning model tailored for fundus images that supports large images. Our division method centres on preserving the original image’s high-resolution features while maintaining low computing and high accuracy. The proposed approach encompasses two fundamental components: an autoencoder model for input image reconstruction and image classification to classify the image quality based on the latent features extracted by the autoencoder, all performed at the original image size, without alteration, before reassembly for decoding networks. Through post hoc interpretability methods, we verified that our model focuses on key elements of fundus image quality. Additionally, an intrinsic interpretability module has been designed into the network that allows decomposing class scores into underlying concepts quality such as brightness or presence of anatomical structures. Experimental results in our model with EyeQ, a fundus image dataset with three categories (Good, Usable, and Rejected) demonstrate that our approach produces competitive outcomes compared to other deep learning-based methods with an overall accuracy of 0.9066, a precision of 0.8843, a recall of 0.8905, and an impressive F1-score of 0.8868. The code is publicly available at https://github.com/saifalkhaldiurv/VISTA_-Image-Quality-Assessment.

Introduction: Chronic cough is associated with serious morbidity and it is imperative that physicians investigate the complaint thoroughly. Bronchoscopy can provide a wealth of information, which can aid diagnosis and treatment, but it is invasive and carries risk. Objectives: To review bronchoscopy practices at the tertiary cough clinic in south Manchester. Methods: We reviewed electronic case notes of all patients referred for bronchoscopy over an 18 month period for chronic cough, documenting indications, complications, findings and treatment outcomes. Results: Of the 600 new patients reviewed in our clinic between 1st May 2017 and 31st October 2018, 96 (16%) were referred for a bronchoscopy. The most common indication was “suspected eosinophilic bronchitis (EB)” (40, 43%). Only 2 (2%) could not tolerate the procedure. Local sedation guidelines were followed for all remaining 94 patients. The majority (76, 80%) had macroscopically abnormal findings, the most common being tracheobronchomalacia or excessive dynamic airways collapse (28, 30%). All 94 patients had bronchioalveolar lavage (BAL) and 92 (98%) had endobronchial biopsies. Four (4%) had eosinophils of >3% on BAL (the accepted cut off for EB). Although 8 (9%) had eosinophils on biopsy, there was no correlation with BAL eosinophils. There were 8 cases of bleeding requiring cold saline/adrenaline caused by endobronchial biopsies. Conclusions: In a tertiary clinic setting, bronchoscopy is well tolerated in chronic cough patients. There are few complications and a high pick up rate of macroscopic abnormalities, with EB occurring infrequently. Clear guidance about the utility of bronchoscopy is lacking when investigating chronic cough.