Loss-Modified Transformer-Based U-Net for Accurate Segmentation of Fluids in Optical Coherence Tomography Images of Retinal Diseases.

Background: Optical coherence tomography (OCT) imaging significantly contributes to ophthalmology in the diagnosis of retinal disorders such as age-related macular degeneration and diabetic macular edema. Both diseases involve the abnormal accumulation of fluids, location, and volume, which is vitally informative in detecting the severity of the diseases. Automated and accurate fluid segmentation in OCT images could potentially improve the current clinical diagnosis. This becomes more important by considering the limitations of manual fluid segmentation as a time-consuming and subjective to error method. Methods: Deep learning techniques have been applied to various image processing tasks, and their performance has already been explored in the segmentation of fluids in OCTs. This article suggests a novel automated deep learning method utilizing the U-Net structure as the basis. The modifications consist of the application of transformers in the encoder path of the U-Net with the purpose of more concentrated feature extraction. Furthermore, a custom loss function is empirically tailored to efficiently incorporate proper loss functions to deal with the imbalance and noisy images. A weighted combination of Dice loss, focal Tversky loss, and weighted binary cross-entropy is employed. Results: Different metrics are calculated. The results show high accuracy (Dice coefficient of 95.52) and robustness of the proposed method in comparison to different methods after adding extra noise to the images (Dice coefficient of 92.79). Conclusions: The segmentation of fluid regions in retinal OCT images is critical because it assists clinicians in diagnosing macular edema and executing therapeutic operations more quickly. This study suggests a deep learning framework and novel loss function for automated fluid segmentation of retinal OCT images with excellent accuracy and rapid convergence result.

Optimal Deep Learning Architecture for Automated Segmentation of Cysts in OCT Images Using X-Let Transforms.

The retina is a thin, light-sensitive membrane with a multilayered structure found in the back of the eyeball. There are many types of retinal disorders. The two most prevalent retinal illnesses are Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). Optical Coherence Tomography (OCT) is a vital retinal imaging technology. X-lets (such as curvelet, DTCWT, contourlet, etc.) have several benefits in image processing and analysis. They can capture both local and non-local features of an image simultaneously. The aim of this paper is to propose an optimal deep learning architecture based on sparse basis functions for the automated segmentation of cystic areas in OCT images. Different X-let transforms were used to produce different network inputs, including curvelet, Dual-Tree Complex Wavelet Transform (DTCWT), circlet, and contourlet. Additionally, three different combinations of these transforms are suggested to achieve more accurate segmentation results. Various metrics, including Dice coefficient, sensitivity, false positive ratio, Jaccard index, and qualitative results, were evaluated to find the optimal networks and combinations of the X-let's sub-bands. The proposed network was tested on both original and noisy datasets. The results show the following facts: (1) contourlet achieves the optimal results between different combinations; (2) the five-channel decomposition using high-pass sub-bands of contourlet transform achieves the best performance; and (3) the five-channel decomposition using high-pass sub-bands formations out-performs the state-of-the-art methods, especially in the noisy dataset. The proposed method has the potential to improve the accuracy and speed of the segmentation process in clinical settings, facilitating the diagnosis and treatment of retinal diseases.

Differentiation of inflammatory papulosquamous skin diseases based on skin biophysical and ultrasonographic properties: A decision tree model.

BACKGROUND: The biophysical and ultrasonographic properties of the skin change in papulosquamous diseases. AIMS: : To identify biophysical and ultrasonographic properties for the differentiation of five main groups of papulosquamous skin diseases. METHODS: Fifteen biophysical and ultrasonographic parameters were measured by multiprobe adapter system and high-frequency ultrasonography in active lesions and normal control skin in patients with chronic eczema, psoriasis, lichen planus, pityriasis rosea and parapsoriasis/mycosis fungoides. Using histological diagnosis as a gold standard, a decision tree analysis was performed based on the mean percentage changes of these parameters [(lesion-control/control) ×100] for differentiation of the diseases. RESULTS: The accuracy of the decision tree model for differentiation of five diseases was 67% which developed based on changes in stratum corneum hydration, epidermal thickness, skin pH, melanin index, R0 (reciprocal of firmness) and erythema. Among the flowcharts for pairs of diseases, three models for differentiation had high accuracy (> 95%): those of psoriasis from lichen planus, pityriasis rosea, and parapsoriasis/mycosis fungoides. LIMITATIONS: Validation studies on a larger sample size in situations where the diagnosis is unclear are needed to confirm the accuracy and applicability of decision trees. CONCLUSION: Skin biophysical and ultrasonographic properties may help in the differentiation of papulosquamous diseases as simple and non-invasive tools.

Discriminating Tuberculous Pleural Effusion from Malignant Pleural Effusion Based on Routine Pleural Fluid Biomarkers, Using Mathematical Methods.

BACKGROUND: The differential diagnosis of tuberculous pleural effusion (TPE) and malignant pleural effusion (MPE) is difficult because the biochemical profiles are similar. The present study aimed to differentiate TPE from MPE, using a decision tree and a weighted sparse representation-based classification (WSRC) method, based on the best combination of routine pleural effusion fluid biomarkers. MATERIALS AND METHODS: The routine biomarkers of pleural fluid, including differential cell count, lactate dehydrogenase (LDH), protein, glucose and adenosine deaminase (ADA), were measured in 236 patients (100 with TPE and 136 with MPE). A Sequential Forward Selection (SFS) algorithm was employed to obtain the best combination of parameters for the classification of pleural effusions. Moreover, WSRC was compared to the standard sparse representation-based classification (SRC) and the Support Vector Machine (SVM) methods for classification accuracy. RESULTS: ADA provided the highest diagnostic performance in differentiating TPE from MPE, with 91.91% sensitivity and 74.0% specificity. The best combination of parameters for discriminating TPE from MPE included age, ADA, polynuclear leukocytes and lymphocytes. WSRC outperformed the SRC and SVM methods, with an area under the curve of 0.877, sensitivity of 93.38%, and specificity of 82.0%. The generated flowchart of the decision tree demonstrated 87.2% accuracy for discriminating TPE from MPE. CONCLUSION: This study indicates that a decision tree and a WSRC are novel, noninvasive, and inexpensive methods, which can be useful in discriminating between TPE and MPE, based on the combination of routine pleural fluid biomarkers.

Classification of Asthma Based on Nonlinear Analysis of Breathing Pattern.

Normal human breathing exhibits complex variability in both respiratory rhythm and volume. Analyzing such nonlinear fluctuations may provide clinically relevant information in patients with complex illnesses such as asthma. We compared the cycle-by-cycle fluctuations of inter-breath interval (IBI) and lung volume (LV) among healthy volunteers and patients with various types of asthma. Continuous respiratory datasets were collected from forty age-matched men including 10 healthy volunteers, 10 patients with controlled atopic asthma, 10 patients with uncontrolled atopic asthma, and 10 patients with uncontrolled non-atopic asthma during 60 min spontaneous breathing. Complexity of breathing pattern was quantified by calculating detrended fluctuation analysis, largest Lyapunov exponents, sample entropy, and cross-sample entropy. The IBI as well as LV fluctuations showed decreased long-range correlation, increased regularity and reduced sensitivity to initial conditions in patients with asthma, particularly in uncontrolled state. Our results also showed a strong synchronization between the IBI and LV in patients with uncontrolled asthma. Receiver operating characteristic (ROC) curve analysis showed that nonlinear analysis of breathing pattern has a diagnostic value in asthma and can be used in differentiating uncontrolled from controlled and non-atopic from atopic asthma. We suggest that complexity analysis of breathing dynamics may represent a novel physiologic marker to facilitate diagnosis and management of patients with asthma. However, future studies are needed to increase the validity of the study and to improve these novel methods for better patient management.