Deep learning-enabled soft tissue tumor localization using spatially offset Raman spectral analysis: in-silico investigations

Jayasankar, S; Bajhaiya, Deepak; Sujatha, N.

doi:10.1088/1361-6463/ac8126

Cited by 5 publications

(3 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other approach integrates customized features with cnn networks, which has been demonstrated to be complimentary even for extremely large amounts of data [ 257 – 259 ]. Modern methods for classifying mass-like tumors often use a multiple workflow with a candidate sensor; this architecture condenses the image to a list of possibly cancerous tumors that are given to a deep CNN [ 260 – 264 ].…”

Section: Anatomical Domains Of Medical Imagesmentioning

confidence: 99%

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Iqbal

Qureshi

et al. 2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

show abstract

Section: Anatomical Domains Of Medical Imagesmentioning

confidence: 99%

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Iqbal

Qureshi

et al. 2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

show abstract

“…In recent years, transfer-learning-based algorithms have been extensively explored as strategies to reduce the high demand for large sets of training data [31,32]. These algorithms utilize the information obtained from the previous data, also known as the source data, to train the model on the new data, also known as the target data.…”

Section: Introductionmentioning

confidence: 99%

Using transfer-learning-based algorithms as data reduction strategies for volatile organic compounds classification using plasma spectroscopy

Zhang

Hsu

2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

This work presents the use of transfer-learning-based algorithms as data reduction strategies for classification of volatile organic compounds (VOCs) using optical emission spectroscopy (OES) of plasmas. The plasma used is generated with a home-made microplasma generation device (MGD) ignited in the mixtures of Ar and VOCs. The spectra are acquired from 10 MGDs. The VOC tested are methanol, ethanol, and isopropanol. VOCs are classified using a convolutional neural network (CNN). In addition, gradient-weighted class activation mapping (Grad-CAM) is used as the explainable artificial intelligent technique. It ensures the model classification is based upon rational plasma physics by considering appropriate wavelengths. The VOC concentrations are then quantified using linear regression and an artificial neural network (ANN). Transfer learning-based algorithms tested are parameter transfer, REPTILE, and self-training. Spectral data from 10 MGDs are grouped into source and target datasets. Ten MGDs are tested individually using a model that was trained on the rest nine MGDs. The three MGDs with the lowest accuracy are chosen as the target dataset, while the other seven MGDs make up the source dataset. The original target dataset has 22500 spectra and is further reduced to 12600, 9000, 1800, 225, and 22 spectra to test the behavior of each algorithm. With 225 spectra used for training, the model trained with the random initial (RI) model shows an accuracy of 0.82. The models trained with parameter transfer and REPTILE have accuracies of 0.98 and 0.95, respectively. Finally, an ANN model is used to quantify the VOC concentration with an R2 value of 0.9996. The results demonstrate the potential using transfer-learning-based algorithms as the data reduction strategies for classification of spectroscopic data.

show abstract

“…An increase in Source Detector Separation (SDS) improves the probability of collecting more photons originating from the depth facilitated by the diffuse optical scattering of the medium. Recent works have also demonstrated simultaneous tumor depth and thickness prediction for tumor margin analysis of the breast tissue using in-silico investigations of SORS 3 . Fiber optic probes are small, providing easy and direct access to the localized sample, precise control over illumination and collection area, accurate SDS fabrication capability, and an excellent probe-to-spectrometer interface.…”

Section: Introductionmentioning

confidence: 99%

Optimal core size of fiber optic Raman probes for sub-surface tumor depth prediction: in-silico investigations

Jayasankar

Sujatha

2023

Women in Optics and Photonics in India 2022

View full text Add to dashboard Cite

Raman spectroscopy is evolving as an indispensable tool in cancer diagnosis owing to its label-free molecular probing ability. However, subsurface tumor assessment is still challenging using Raman spectroscopy. Researchers have adopted Spatially Offset Raman Spectroscopy to facilitate subsurface analysis. Recent works have demonstrated simultaneous subsurface tumor depth and thickness prediction using in-silico Spatially Offset Raman Spectroscopy investigations. These investigations are aided by fiber optic probes providing a good signal collection interface between sample and spectrometer, remote accessibility, precise control over illumination area, and Source Detector Separation. Optimizing the optical fiber probe parameters for photon collection will improve the outcome of tumor assessment. In this work, we analyze the importance of fiber optic collection core radius in subsurface tumor depth prediction using Monte Carlo simulated Spatially Offset Raman Spectroscopy signals. Simulations are carried out for varying illumination and collection fiber core radii, depths, and tumor thicknesses. An optimal collection fiber core radius for sub-surface depth prediction is estimated with a regression model for a given illumination fiber core radius. This optimization would improve the subsurface tumor localization capabilities of Raman Spectroscopy

show abstract

Deep learning-enabled soft tissue tumor localization using spatially offset Raman spectral analysis: in-silico investigations

Cited by 5 publications

References 55 publications

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Using transfer-learning-based algorithms as data reduction strategies for volatile organic compounds classification using plasma spectroscopy

Optimal core size of fiber optic Raman probes for sub-surface tumor depth prediction: in-silico investigations

Contact Info

Product

Resources

About