Log-Gaussian gamma processes for training Bayesian neural networks in Raman and CARS spectroscopies.

We propose an approach utilizing gamma-distributed random variables, coupled with log-Gaussian modeling, to generate synthetic datasets suitable for training neural networks. This addresses the challenge of limited real observations in various applications. We apply this methodology to both Raman and coherent anti-Stokes Raman scattering (CARS) spectra, using experimental spectra to estimate gamma process parameters. Parameter estimation is performed using Markov chain Monte Carlo methods, yielding a full Bayesian posterior distribution for the model which can be sampled for synthetic data generation. Additionally, we model the additive and multiplicative background functions for Raman and CARS with Gaussian processes. We train two Bayesian neural networks to estimate parameters of the gamma process which can then be used to estimate the underlying Raman spectrum and simultaneously provide uncertainty through the estimation of parameters of a probability distribution. We apply the trained Bayesian neural networks to experimental Raman spectra of phthalocyanine blue, aniline black, naphthol red, and red 264 pigments and also to experimental CARS spectra of adenosine phosphate, fructose, glucose, and sucrose. The results agree with deterministic point estimates for the underlying Raman and CARS spectral signatures.

Evaluating different deep learning models for efficient extraction of Raman signals from CARS spectra.

The nonresonant background (NRB) contribution to the coherent anti-Stokes Raman scattering (CARS) signal distorts the spectral line shapes and thus degrades the chemical information. Hence, finding an effective approach for removing NRB and extracting resonant vibrational signals is a challenging task. In this work, a bidirectional LSTM (Bi-LSTM) neural network is explored for the first time to remove the NRB in the CARS spectra automatically, and the results are compared with those of three DL models reported in the literature, namely, convolutional neural network (CNN), long short-term memory (LSTM) neural network, and very deep convolutional autoencoders (VECTOR). The results of the synthetic test data have shown that the Bi-LSTM model accurately extracts the spectral lines throughout the range. In contrast, the other three models' efficiency deteriorated while predicting the peaks on either end of the spectra, which resulted in a 60 times higher mean square error than that of the Bi-LSTM model. The Pearson correlation analysis demonstrated that Bi-LSTM model performance stands out from the rest, where 94% of the test spectra have correlation coefficients of more than 0.99. Finally, these four models were evaluated on four complex experimental CARS spectra, namely, protein, yeast, DMPC, and ADP, where the Bi-LSTM model has shown superior performance, followed by CNN, VECTOR, and LSTM. This comprehensive study provides a giant leap toward simplifying the analysis of complex CARS spectroscopy and microscopy.

Effect of non-resonant background on the extraction of Raman signals from CARS spectra using deep neural networks.

We report the retrieval of the Raman signal from coherent anti-Stokes Raman scattering (CARS) spectra using a convolutional neural network (CNN) model. Three different types of non-resonant backgrounds (NRBs) were explored to simulate the CARS spectra viz (1) product of two sigmoids following the original SpecNet model, (2) Single Sigmoid, and (3) fourth-order polynomial function. Later, 50 000 CARS spectra were separately synthesized using each NRB type to train the CNN model and, after training, we tested its performance on 300 simulated test spectra. The results have shown that imaginary part extraction capability is superior for the model trained with Polynomial NRB, and the extracted line shapes are in good agreement with the ground truth. Moreover, correlation analysis was carried out to compare the retrieved Raman signals to real ones, and a higher correlation coefficient was obtained for the model trained with the Polynomial NRB (on average, ∼0.95 for 300 test spectra), whereas it was ∼0.89 for the other NRBs. Finally, the predictive capability is evaluated on three complex experimental CARS spectra (DMPC, ADP, and yeast), where the Polynomial NRB model performance is found to stand out from the rest. This approach has a strong potential to simplify the analysis of complex CARS spectroscopy and can be helpful in real-time microscopy imaging applications.

Deep Bayesian baseline for segmenting diabetic retinopathy lesions: Advances and challenges.

Early diagnosis of retinopathy is essential for preventing retinal complications and visual impairment due to diabetes. For the detection of retinopathy lesions from retinal images, several automatic approaches based on deep neural networks have been developed in the recent years. Most of the proposed methods produce point estimates of pixels belonging to the lesion areas and give no or little information on the uncertainty of method predictions. However, the latter can be essential in the examination of the medical condition of the patient when the goal is early detection of abnormalities. This work extends the recent research with a Bayesian framework by considering the parameters of a convolutional neural network as random variables and utilizing stochastic variational dropout based approximation for uncertainty quantification. The framework includes an extended validation procedure and it allows analyzing lesion segmentation distributions, model calibration and prediction uncertainties. Also the challenges related to the deep probabilistic model and uncertainty quantification are presented. The proposed method achieves area under precision-recall curve of 0.84 for hard exudates, 0.641 for soft exudates, 0.593 for haemorrhages, and 0.484 for microaneurysms on IDRiD dataset.

Performance comparison of publicly available retinal blood vessel segmentation methods.

Retinal blood vessel structure is an important indicator of many retinal and systemic diseases, which has motivated the development of various image segmentation methods for the blood vessels. In this study, two supervised and three unsupervised segmentation methods with a publicly available implementation are reviewed and quantitatively compared with each other on five public databases with ground truth segmentation of the vessels. Each method is tested under consistent conditions with two types of preprocessing, and the parameters of the methods are optimized for each database. Additionally, possibility to predict the parameters of the methods by the linear regression model is tested for each database. Resolution of the input images and amount of the vessel pixels in the ground truth are used as predictors. The results show the positive influence of preprocessing on the performance of the unsupervised methods. The methods show similar performance for segmentation accuracy, with the best performance achieved by the method by Azzopardi et al. (Acc 94.0) on ARIADB, the method by Soares et al. (Acc 94.6, 94.7) on CHASEDB1 and DRIVE, and the method by Nguyen et al. (Acc 95.8, 95.5) on HRF and STARE. The method by Soares et al. performed better with regard to the area under the ROC curve. Qualitative differences between the methods are discussed. Finally, it was possible to predict the parameter settings that give performance close to the optimized performance of each method.

Wavelet prism decomposition analysis applied to CARS spectroscopy: a tool for accurate and quantitative extraction of resonant vibrational responses.

We propose an approach, based on wavelet prism decomposition analysis, for correcting experimental artefacts in a coherent anti-Stokes Raman scattering (CARS) spectrum. This method allows estimating and eliminating a slowly varying modulation error function in the measured normalized CARS spectrum and yields a corrected CARS line-shape. The main advantage of the approach is that the spectral phase and amplitude corrections are avoided in the retrieved Raman line-shape spectrum, thus significantly simplifying the quantitative reconstruction of the sample's Raman response from a normalized CARS spectrum in the presence of experimental artefacts. Moreover, the approach obviates the need for assumptions about the modulation error distribution and the chemical composition of the specimens under study. The method is quantitatively validated on normalized CARS spectra recorded for equimolar aqueous solutions of D-fructose, D-glucose, and their disaccharide combination sucrose.

Constructing benchmark databases and protocols for medical image analysis: diabetic retinopathy.

We address the performance evaluation practices for developing medical image analysis methods, in particular, how to establish and share databases of medical images with verified ground truth and solid evaluation protocols. Such databases support the development of better algorithms, execution of profound method comparisons, and, consequently, technology transfer from research laboratories to clinical practice. For this purpose, we propose a framework consisting of reusable methods and tools for the laborious task of constructing a benchmark database. We provide a software tool for medical image annotation helping to collect class label, spatial span, and expert's confidence on lesions and a method to appropriately combine the manual segmentations from multiple experts. The tool and all necessary functionality for method evaluation are provided as public software packages. As a case study, we utilized the framework and tools to establish the DiaRetDB1 V2.1 database for benchmarking diabetic retinopathy detection algorithms. The database contains a set of retinal images, ground truth based on information from multiple experts, and a baseline algorithm for the detection of retinopathy lesions.