Accuracy improvement of quantification information using super-resolution with convolutional neural network for microscopy images

Zheng

Biomedical Signal Processing and Control

2022

Objective Medical image analysis is particularly important for doctors to differential diagnosis of diseases. Due to the outbreak of COVID-19, how to diagnose COVID-19 accurately has become a key issue. High-resolution lung CT images can provide more diagnostic information, so there is an urgent need to develop a super-resolution method to improve the resolution of medical images. Methods In this paper, a method based on double paths with residual information distillation for medical images super resolution (DRIDSR) is established. In the low-frequency path, shallow convolutional network is used to get low-frequency features, while in the high-frequency path, a residual information distillation module (RIDM) is designed to obtain clearer high-frequency features. RIDM cascades multiple residual blocks, and uses the output of each residual block as the input of IDB for further information distillation. Finally, it merges the information left by multiple IDBs as output. Results The proposed method is tested on the public dataset COVID-CT. The DRIDSR reconstruction quality of the algorithm is higher than that of the SRCNN, ESPCN, VDSR, IMDN and PAN method (+2.21 dB, +2.41 dB, +1.42 dB, +0.43 dB, +0.54 dB improvement, respectively) at × 3 upscale factor and (+2.35 dB, +2.17 dB, +1.59 dB, +0.48 dB, +0.56 dB increase, respectively) at ×4 upscale factor. While the number of parameters and analysis time of our model are reduced. Conclusions It is demonstrated that DRIDSR network can obtain better performance and better HR medical images than several state-of-the-art SR methods in terms of objective indicators and subjective evaluation.

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Double paths network with residual information distillation for improving lung CT image super resolution

Zheng

Biomedical Signal Processing and Control

2022

“…In this study, since API data were similar to text data, MLP networks had higher performance. Moreover, CNNs have had better outcomes in classification image data [69][70][71][72][73][74] .…”

Section: Discussionmentioning

confidence: 99%

AptaNet as a deep learning approach for aptamer–protein interaction prediction

Emami

Ferdousi

2021

Sci Rep

Aptamers are short oligonucleotides (DNA/RNA) or peptide molecules that can selectively bind to their specific targets with high specificity and affinity. As a powerful new class of amino acid ligands, aptamers have high potentials in biosensing, therapeutic, and diagnostic fields. Here, we present AptaNet—a new deep neural network—to predict the aptamer–protein interaction pairs by integrating features derived from both aptamers and the target proteins. Aptamers were encoded by using two different strategies, including k-mer and reverse complement k-mer frequency. Amino acid composition (AAC) and pseudo amino acid composition (PseAAC) were applied to represent target information using 24 physicochemical and conformational properties of the proteins. To handle the imbalance problem in the data, we applied a neighborhood cleaning algorithm. The predictor was constructed based on a deep neural network, and optimal features were selected using the random forest algorithm. As a result, 99.79% accuracy was achieved for the training dataset, and 91.38% accuracy was obtained for the testing dataset. AptaNet achieved high performance on our constructed aptamer-protein benchmark dataset. The results indicate that AptaNet can help identify novel aptamer–protein interacting pairs and build more-efficient insights into the relationship between aptamers and proteins. Our benchmark dataset and the source codes for AptaNet are available in: https://github.com/nedaemami/AptaNet.

“…A well-trained convolutional NN could potentially automate this process and obtain accurate results with much higher efficiency. Another interesting direction is the ML-based super-resolution, which has been successfully applied to different optical microscopy techniques 61,62,67,68 . Better resolution can in principle be achieved in near-field imaging using ML-assisted algorithms, which would help circumvent current problems such as the fabrication of ultra-sharp tips, limited detector sensitivity, and insufficient signal-to-noise ratio.…”

Section: Discussionmentioning

confidence: 99%

“…For example, extracting the polariton wavelength and quality factor from near-field images of various van der Waals materials is routinely done by manual fitting procedures. , A well-trained convolutional NN could potentially automate this process and obtain accurate results with much higher efficiency. Another interesting direction is the ML-based super-resolution, which has been successfully applied to different optical microscopy techniques. ,,, Better resolution can in principle be achieved in near-field imaging using ML-assisted algorithms, which would help circumvent current problems, such as the fabrication of ultrasharp tips, limited detector sensitivity, and an insufficient signal-to-noise ratio. Other applications, such as optimizing the tip design for enhanced scattering, can benefit from the help of ML as well. , …”

Section: Discussionmentioning

confidence: 99%

Hybrid Machine Learning for Scanning Near-Field Optical Spectroscopy

Yao

et al. 2021

ACS Photonics

The underlying physics behind an experimental observation often lacks a simple analytical description. This is especially the case for scanning probe microscopy techniques, where the interaction between the probe and the sample is nontrivial. Realistic modeling to include the details of the probe is always exponentially more difficult than its "spherical cow" counterparts. On the other hand, a well-trained artificial neural network based on real data can grasp the hidden correlation between the signal and sample properties. In this work, we show that, via a combination of model calculation and experimental data acquisition, a physics-infused hybrid neural network can predict the tip-sample interaction in the widely used scattering-type scanning near-field optical microscope. This hybrid network provides a long-sought solution for accurate extraction of material properties from tip-specific raw data. The methodology can be extended to other scanning probe microscopy techniques as well as other data-oriented physical problems in general.