Computed tomography attenuation in differential diagnosis of transudative and exudative pleural effusions.

OBJECTIVE: Pleural effusion is a common medical problem. It is important to decide whether the pleural fluid is a transudate or an exudate. This study aims to measure the attenuation values of pleural effusions on thorax computed tomography and to investigate the efficacy of this measurement in the diagnostic separation of transudates and exudates. MATERIALS AND METHODS: 380 cases who underwent thoracentesis and thorax computed tomography with pleural effusion were classified as exudates or transudates based on Light's criteria. Attenuation measurements in Hounsfield units were performed through the examination of thorax computed tomography images. RESULTS: 380 patients were enrolled (39 % women), the mean age was 69.9 ± 15.2 years. 125 (33 %) were transudates whereas 255 (67 %) were exudates. The attenuation values of exudates were significantly higher than transudates (15.1 ± 5.1 and 5.0 ± 3.4) (p < 0.001). When the attenuation cut-off was set at ≥ 10 HU, exudates were differentiated from transudates at high efficiency (sensitivity is 89.7 %, specificity is 94.4 %, PPV is 97 %, NPV is 81.9 %). When the cut-off value was accepted as < 6 HU, transudates were differentiated from exudates with 97.2 % specificity. CONCLUSION: The attenuation measurements of pleural fluids can be considered as an efficacious way of differentiating exudative and transudative pleural effusions.

A deep learning approach to hard exudates detection and disorganization of retinal inner layers identification on OCT images.

The purpose of the study was to detect Hard Exudates (HE) and classify Disorganization of Retinal Inner Layers (DRIL) implementing a Deep Learning (DL) system on optical coherence tomography (OCT) images of eyes with diabetic macular edema (DME). We collected a dataset composed of 442 OCT images on which we annotated 6847 HE and the presence of DRIL. A complex operational pipeline was defined to implement data cleaning and image transformations, and train two DL models. The state-of-the-art neural network architectures (Yolov7, ConvNeXt, RegNetX) and advanced techniques were exploited to aggregate the results (Ensemble learning, Edge detection) and obtain a final model. The DL approach reached good performance in detecting HE and classifying DRIL. Regarding HE detection the model got an AP@0.5 score equal to 34.4% with Precision of 48.7% and Recall of 43.1%; while for DRIL classification an Accuracy of 91.1% with Sensitivity and Specificity both of 91.1% and AUC and AUPR values equal to 91% were obtained. The P-value was lower than 0.05 and the Kappa coefficient was 0.82. The DL models proved to be able to identify HE and DRIL in eyes with DME with a very good accuracy and all the metrics calculated confirmed the system performance. Our DL approach demonstrated to be a good candidate as a supporting tool for ophthalmologists in OCT images analysis.

Automatic exudate and aneurysm segmentation in OCT images using UNET++ and hyperreflective-foci feature based bagged tree ensemble.

Diabetic retinopathy's signs, such as exudates (EXs) and aneurysms (ANs), initially develop from under the retinal surface detectable from optical coherence tomography (OCT) images. Detecting these signs helps ophthalmologists diagnose DR sooner. Detecting and segmenting exudates (EXs) and aneurysms (ANs) in medical images is challenging due to their small size, similarity to other hyperreflective regions, noise presence, and low background contrast. Furthermore, the scarcity of public OCT images featuring these abnormalities has limited the number of studies related to the automatic segmentation of EXs and ANs, and the reported performance of such studies has not been satisfactory. This work proposes an efficient algorithm that can automatically segment these anomalies by improving key steps in the process. The potential area where these hyper-reflective EXs and ANs occur was scoped by our method using a deep-learning U-Net++ program. From this area, the candidates for EX-AN were segmented using the adaptive thresholding method. Nine features based on appearances, locations, and shadow markers were extracted from these candidates. They were trained and tested using bagged tree ensemble classifiers to obtain only EX-AN blobs. The proposed method was tested on a collection of a public dataset comprising 80 images with hand-drawn ground truths. The experimental results showed that our method could segment EX-AN blobs with average recall, precision, and F1-measure as 87.9%, 86.1%, and 87.0%, respectively. Its F1-measure drastically outperformed two comparative methods, binary thresholding and watershed (BT-WS) and adaptive thresholding with shadow tracking (AT-ST), by 78.0% and 82.1%, respectively.

Artificial intelligence for detection of effusion and lipo-hemarthrosis in X-rays and CT of the knee.

BACKGROUND: Traumatic knee injuries are challenging to diagnose accurately through radiography and to a lesser extent, through CT, with fractures sometimes overlooked. Ancillary signs like joint effusion or lipo-hemarthrosis are indicative of fractures, suggesting the need for further imaging. Artificial Intelligence (AI) can automate image analysis, improving diagnostic accuracy and help prioritizing clinically important X-ray or CT studies. OBJECTIVE: To develop and evaluate an AI algorithm for detecting effusion of any kind in knee X-rays and selected CT images and distinguishing between simple effusion and lipo-hemarthrosis indicative of intra-articular fractures. METHODS: This retrospective study analyzed post traumatic knee imaging from January 2016 to February 2023, categorizing images into lipo-hemarthrosis, simple effusion, or normal. It utilized the FishNet-150 algorithm for image classification, with class activation maps highlighting decision-influential regions. The AI's diagnostic accuracy was validated against a gold standard, based on the evaluations made by a radiologist with at least four years of experience. RESULTS: Analysis included CT images from 515 patients and X-rays from 637 post traumatic patients, identifying lipo-hemarthrosis, simple effusion, and normal findings. The AI showed an AUC of 0.81 for detecting any effusion, 0.78 for simple effusion, and 0.83 for lipo-hemarthrosis in X-rays; and 0.89, 0.89, and 0.91, respectively, in CTs. CONCLUSION: The AI algorithm effectively detects knee effusion and differentiates between simple effusion and lipo-hemarthrosis in post-traumatic patients for both X-rays and selected CT images further studies are needed to validate these results.

Perifoveal exudative vascular anomalous complex (PEVAC).

We present three cases of patients aged 66, 80 and 23, who presented unilateral vision loss. Optical coherence tomography (OCT) in all of them showed macular oedema and a rounded lesion with hyperreflective wall, and fluorescein angiography (FAG) in two of them showed hyperfluorescent perifoveal aneurysmal dilations with exudation. None of the cases showed response to treatment after one year of follow-up, finally being diagnosed with Perifoveal Exudative Vascular Anomalous Complex (PEVAC).

Value of ultrasonography in determining the nature of pleural effusion: Analysis of 582 cases.

To explore the value of ultrasonography in the auxiliary diagnosis of pleural effusion, we retrospectively analyzed the ultrasonographic findings of 275 exudates and 307 transudates and summarized the ultrasonographic image features of pleural effusion according to patients' primary diseases. The findings of thoracic ultrasonography performed before the initial thoracentesis in 582 patients with subsequently confirmed exudative/transudative pleural effusion were analyzed with regard to the sonographic features of pleural effusion. In 275 cases with exudates, thoracic ultrasonography showed a complex septate appearance in 19 cases (6.9%), complex nonseptate appearance in 100 cases (36.4%), complex homogenous sign in 46 cases (16.7%), and pleural thickness > 3 mm in 105 cases. In contrast, in 307 patients with transudates, most patients (97.1%) had bilateral pleural effusion. Ultrasonographic images displayed anechoic appearance and absence of pleural thickening in a vast majority of cases (306, 99.7%; 301, 98%). These positive findings in the exudate were statistically higher than those in their counterparts (P < .05). In the empyema subgroup, the proportion of complex septate appearance, complex nonseptate appearance, complex homogenous sign, and pleural thickening was the highest, at 19/41, 12/41, 10/41, and 30/41, respectively. Ultrasonography is valuable in defining the nature of pleural effusion. Some sonographic features of pleural effusion, such as echogenicity, septation, and pleural thickening, may indicate a high risk of exudative pleural effusion.

Automated Detection, Segmentation, and Classification of Pleural Effusion From Computed Tomography Scans Using Machine Learning.

OBJECTIVE: This study trained and evaluated algorithms to detect, segment, and classify simple and complex pleural effusions on computed tomography (CT) scans. MATERIALS AND METHODS: For detection and segmentation, we randomly selected 160 chest CT scans out of all consecutive patients (January 2016-January 2021, n = 2659) with reported pleural effusion. Effusions were manually segmented and a negative cohort of chest CTs from 160 patients without effusions was added. A deep convolutional neural network (nnU-Net) was trained and cross-validated (n = 224; 70%) for segmentation and tested on a separate subset (n = 96; 30%) with the same distribution of reported pleural complexity features as in the training cohort (eg, hyperdense fluid, gas, pleural thickening and loculation). On a separate consecutive cohort with a high prevalence of pleural complexity features (n = 335), a random forest model was implemented for classification of segmented effusions with Hounsfield unit thresholds, density distribution, and radiomics-based features as input. As performance measures, sensitivity, specificity, and area under the curves (AUCs) for detection/classifier evaluation (per-case level) and Dice coefficient and volume analysis for the segmentation task were used. RESULTS: Sensitivity and specificity for detection of effusion were excellent at 0.99 and 0.98, respectively (n = 96; AUC, 0.996, test data). Segmentation was robust (median Dice, 0.89; median absolute volume difference, 13 mL), irrespective of size, complexity, or contrast phase. The sensitivity, specificity, and AUC for classification in simple versus complex effusions were 0.67, 0.75, and 0.77, respectively. CONCLUSION: Using a dataset with different degrees of complexity, a robust model was developed for the detection, segmentation, and classification of effusion subtypes. The algorithms are openly available at https://github.com/usb-radiology/pleuraleffusion.git.

Fast and Robust Exudate Detection in Retinal Fundus Images Using Extreme Learning Machine Autoencoders and Modified KAZE Features.

Diabetic retinopathy(DR) is a health condition that affects the retinal blood vessels(BV) and arises in over half of people living with diabetes. Exudates(EX) are significant indications of DR. Early detection and treatment can prevent vision loss in many cases. EX detection is a challenging problem for ophthalmologists due to its different sizes and elevations as retinal fundus images frequently have irregular illumination and are poorly contrasting. Manual detection of EX is a time-consuming process to diagnose a mass number of diabetic patients. In the domain of signal processing, both SIFT (scale-invariant feature transform) and SURF (speed-up robust feature) methods are predominant in scale-invariant location retrieval and have shown a range of advantages. But, when extended to medical images with corresponding weak contrast between reference features and neighboring areas, these methods cannot differentiate significant features. Considering these, in this paper, a novel method is proposed based on modified KAZE features, which is an emerging technique to extract feature points and extreme learning machine autoencoders(ELMAE) for robust and fast localization of the EX in fundus images. The main stages of the proposed method are pre-processing, OD localization, dimensionality reduction using ELMAE, and EX localization. The proposed method is evaluated based on the freely accessible retinal database DIARETDB0, DIARETDB1, e-Ophtha, MESSIDOR, and local retinal database collected from Silchar Medical College and Hospital(SMCH). The sensitivity, specificity, and accuracy obtained by the proposed method are 96.5%, 96.4%, and 97%, respectively, with the processing time of 3.19 seconds per image. The results of this study are satisfactory with state-of-the-art methods. The results indicate that the approach taken can detect EX with less processing time and accurately from the fundus images.

Automatic estimation of knee effusion from limited MRI data.

Knee effusion is a common comorbidity in osteoarthritis. To quantify the amount of effusion, semi quantitative assessment scales have been developed that classify fluid levels on an integer scale from 0 to 3. In this work, we investigated the use of a neural network (NN) that used MRI Osteoarthritis Knee Scores effusion-synovitis (MOAKS-ES) values to distinguish physiologic fluid levels from higher fluid levels in MR images of the knee. We evaluate its effectiveness on low-resolution images to examine its potential in low-field, low-cost MRI. We created a dense NN (dNN) for detecting effusion, defined as a nonzero MOAKS-ES score, from MRI scans. Both the training and performance evaluation of the network were conducted using public radiological data from the Osteoarthritis Initiative (OAI). The model was trained using sagittal turbo-spin-echo (TSE) MR images from 1628 knees. The accuracy was compared to VGG16, a commonly used convolutional classification network. Robustness of the dNN was assessed by adding zero-mean Gaussian noise to the test images with a standard deviation of 5-30% of the maximum test data intensity. Also, inference was performed on a test data set of 163 knees, which includes a smaller test set of 36 knees that was also assessed by a musculoskeletal radiologist and the performance of the dNN and the radiologist compared. For the larger test data set, the dNN performed with an average accuracy of 62%. In addition, the network proved robust to noise, classifying the noisy images with minimal degradation to accuracy. When given MRI scans with 5% Gaussian noise, the network performed similarly, with an average accuracy of 61%. For the smaller 36-knee test data set, assessed both by the dNN and by a radiologist, the network performed better than the radiologist on average. Classifying knee effusion from low-resolution images with a similar accuracy as a human radiologist using neural networks is feasible, suggesting automatic assessment of images from low-cost, low-field scanners as a potentially useful assessment tool.

Deep CNN with Hybrid Binary Local Search and Particle Swarm Optimizer for Exudates Classification from Fundus Images.

Diabetic retinopathy is a chronic condition that causes vision loss if not detected early. In the early stage, it can be diagnosed with the aid of exudates which are called lesions. However, it is arduous to detect the exudate lesion due to the availability of blood vessels and other distractions. To tackle these issues, we proposed a novel exudates classification from the fundus image known as hybrid convolutional neural network (CNN)-based binary local search optimizer-based particle swarm optimization algorithm. The proposed method from this paper exploits image augmentation to enlarge the fundus image to the required size without losing any features. The features from the resized fundus images are extracted as a feature vector and fed into the feed-forward CNN as the input. Henceforth, it classifies the exudates from the fundus image. Further, the hyperparameters are optimized to reduce the computational complexities by utilization of binary local search optimizer (BLSO) and particle swarm optimization (PSO). The experimental analysis is conducted on the public ROC and real-time ARA400 datasets and compared with the state-of-art works such as support vector machine classifiers, multi-modal/multi-scale, random forest, and CNN for the performance metrics. The classification accuracy is high for the proposed work, and thus, our proposed outperforms all the other approaches.

Dual-Branch Network With Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation in Color Fundus Images.

Automated segmentation of hard exudates in colour fundus images is a challenge task due to issues of extreme class imbalance and enormous size variation. This paper aims to tackle these issues and proposes a dual-branch network with dual-sampling modulated Dice loss. It consists of two branches: large hard exudate biased segmentation branch and small hard exudate biased segmentation branch. Both of them are responsible for their own duties separately. Furthermore, we propose a dual-sampling modulated Dice loss for the training such that our proposed dual-branch network is able to segment hard exudates in different sizes. In detail, for the first branch, we use a uniform sampler to sample pixels from predicted segmentation mask for Dice loss calculation, which leads to this branch naturally be biased in favour of large hard exudates as Dice loss generates larger cost on misidentification of large hard exudates than small hard exudates. For the second branch, we use a re-balanced sampler to oversample hard exudate pixels and undersample background pixels for loss calculation. In this way, cost on misidentification of small hard exudates is enlarged, which enforces the parameters in the second branch fit small hard exudates well. Considering that large hard exudates are much easier to be correctly identified than small hard exudates, we propose an easy-to-difficult learning strategy by adaptively modulating the losses of two branches. We evaluate our proposed method on two public datasets and the results demonstrate that ours achieves state-of-the-art performance.

Intraretinal, sub-retinal, and sub-retinal pigmented epithelium fluid in non-exudative age-related macular degeneration: follow-up with OCT imaging.

BACKGROUND/OBJECTIVES: To evaluate the presence and evolution of fluid in non-exudative age-related macular degeneration (AMD) through serial OCT. SUBJECTS/METHODS: A retrospective analysis of eyes with non-exudative AMD with a minimum of 4 year follow-up was done. Parameters including intraretinal fluid (IRF), subretinal fluid (SRF), and sub-retinal pigment epithelium (RPE) fluid (SRPEF); subfoveal choroidal thickness (SFCT) and type of drusen were evaluated using optical coherence tomography (OCT) scans at baseline and follow up visits. RESULTS: Seventy-two eyes (in 63 patients) were followed up for an average of 5.83 ± 2.17 years. A total of 26/72 (36%) and 29/65 (52%) of the non-exudative eyes had fluid during baseline and the last visit. Seven eyes (10%) out of 72 eyes converted into exudative AMD or neo-vascular AMD (nAMD) during the study period. SRPEF at baseline was most common fluid location for non-exudative eyes that eventually converted to nAMD. CONCLUSION: Non-exudative fluid including IRF, SRF, and SRPEF is seen in patients with non-exudative AMD with increasing incidence during long term follow-up.

Non-invasive characterization of pleural and pericardial effusions using T1 mapping by magnetic resonance imaging.

AIMS: Differentiating exudative from transudative effusions is clinically important and is currently performed via biochemical analysis of invasively obtained samples using Light's criteria. Diagnostic performance is however limited. Biochemical composition can be measured with T1 mapping using cardiovascular magnetic resonance (CMR) and hence may offer diagnostic utility for assessment of effusions. METHODS AND RESULTS: A phantom consisting of serially diluted human albumin solutions (25-200 g/L) was constructed and scanned at 1.5 T to derive the relationship between fluid T1 values and fluid albumin concentration. Native T1 values of pleural and pericardial effusions from 86 patients undergoing clinical CMR studies retrospectively analysed at four tertiary centres. Effusions were classified using Light's criteria where biochemical data was available (n = 55) or clinically in decompensated heart failure patients with presumed transudative effusions (n = 31). Fluid T1 and protein values were inversely correlated both in the phantom (r = -0.992) and clinical samples (r = -0.663, P < 0.0001). T1 values were lower in exudative compared to transudative pleural (3252 ± 207 ms vs. 3596 ± 213 ms, P < 0.0001) and pericardial (2749 ± 373 ms vs. 3337 ± 245 ms, P < 0.0001) effusions. The diagnostic accuracy of T1 mapping for detecting transudates was very good for pleural and excellent for pericardial effusions, respectively [area under the curve 0.88, (95% CI 0.764-0.996), P = 0.001, 79% sensitivity, 89% specificity, and 0.93, (95% CI 0.855-1.000), P < 0.0001, 95% sensitivity; 81% specificity]. CONCLUSION: Native T1 values of effusions measured using CMR correlate well with protein concentrations and may be helpful for discriminating between transudates and exudates. This may help focus the requirement for invasive diagnostic sampling, avoiding unnecessary intervention in patients with unequivocal transudative effusions.

CT Texture analysis and CT scores for characterization of fluid collections.

BACKGROUND: Texture analysis derived from Computed tomography (CT) might be able to better characterize fluid collections undergoing CT-guided percutaneous drainage treatment. The present study tested, whether texture analysis can reflect microbiology results in fluid collections suspicious for septic focus. METHODS: Overall, 320 patients with 402 fluid collections were included into this retrospective study. All fluid collections underwent CT-guided drainage treatment and were microbiologically evaluated. Clinically, serologically parameters and conventional imaging findings as well as textures features were included into the analysis. A new CT score was calculated based upon imaging features alone. Established CT scores were used as a reference standard. RESULTS: The present score achieved a sensitivity of 0.78, a specificity of 0.69, area under curve (AUC 0.82). The present score and the score by Gnannt et al. (AUC 0.81) were both statistically better than the score by Radosa et al. (AUC 0.75). Several texture features were statistically significant between infected fluid collections and sterile fluid collections, but these features were not significantly better compared with conventional imaging findings. CONCLUSIONS: Texture analysis is not superior to conventional imaging findings for characterizing fluid collections. A novel score was calculated based upon imaging parameters alone with similar diagnostic accuracy compared to established scores using imaging and clinical features.

[Regional classification-guided wavelet Y-Net network for hard exudate segmentation in fundus images].

OBJECTIVE: We propose an hard exudate(EX)segmentation algorithm based on regional classification-guided wavelet Y-Net network to eliminate the influence of optic disc on EX segmentation process. METHODS: The wavelet Y-Net network was an end-to-end fundus image EX segmentation network, which combined the regional detection of optic disc and hard exudates segmentation by regional classification-guided EX segmentation to effectively reduce the interference of optic disc in EX segmentation.To avoid failure of small EX region segmentation caused by information loss due to down-sampling operation, discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT) were introduced to replace the traditional pooling down-sampling and up-sampling operations.Meanwhile, the inception module based on residual connection was used to obtain the multi-scale features.The proposed algorithm was trained and tested on the IDRiD and e-ophtha EX datasets and evaluated at the pixel level. RESULTS: For IDRiD and e-ophtha EX datasets, the proposed algorithm achieved accuracy rates of 0.9858 and 0.9938 with AUC values of 0.9880 and 0.9986, respectively. CONCLUSION: The proposed method can effectively avoid the influence of the optic disc, retain the image details, and improve the effect of EX segmentation.

EAD-Net: A Novel Lesion Segmentation Method in Diabetic Retinopathy Using Neural Networks.

Diabetic retinopathy (DR) is a common chronic fundus disease, which has four different kinds of microvessel structure and microvascular lesions: microaneurysms (MAs), hemorrhages (HEs), hard exudates, and soft exudates. Accurate detection and counting of them are a basic but important work. The manual annotation of these lesions is a labor-intensive task in clinical analysis. To solve the problem, we proposed a novel segmentation method for different lesions in DR. Our method is based on a convolutional neural network and can be divided into encoder module, attention module, and decoder module, so we refer it as EAD-Net. After normalization and augmentation, the fundus images were sent to the EAD-Net for automated feature extraction and pixel-wise label prediction. Given the evaluation metrics based on the matching degree between detected candidates and ground truth lesions, our method achieved sensitivity of 92.77%, specificity of 99.98%, and accuracy of 99.97% on the e_ophtha_EX dataset and comparable AUPR (Area under Precision-Recall curve) scores on IDRiD dataset. Moreover, the results on the local dataset also show that our EAD-Net has better performance than original U-net in most metrics, especially in the sensitivity and F1-score, with nearly ten percent improvement. The proposed EAD-Net is a novel method based on clinical DR diagnosis. It has satisfactory results on the segmentation of four different kinds of lesions. These effective segmentations have important clinical significance in the monitoring and diagnosis of DR.

Mastoid effusion on temporal bone MRI in patients with Bell's palsy and Ramsay Hunt syndrome.

This study aimed to investigate the incidence of mastoid effusion on temporal bone magnetic resonance imaging (MRI) in patients with Bell's palsy (BP) and Ramsay Hunt syndrome (RHS), and evaluate the usefulness of mastoid effusion in early differential diagnosis between BP and RHS. The incidence of mastoid effusion on 3.0 T-temporal bone MRI, which was conducted within 10 days after the onset of acute facial nerve palsy, was compared between 131 patients with BP and 33 patients with RHS. Findings of mastoid cavity on temporal bone MRI were classified into three groups as normal mastoid, mastoid effusion, and sclerotic change, and the incidence of ipsilesional mastoid effusion was significantly higher in RHS than BP (P < 0.001). Tympanic membrane was normal in 7 of 14 RHS patients with mastoid effusion, and injected without middle ear effusion in 7 patients. This study highlights significantly higher incidence of ipsilesional mastoid effusion in RHS than BP, and suggests that the presence of mastoid effusion may provide additional information for differential diagnosis between RHS and BP.