Application of semi-supervised convolutional neural network regression model based on data augmentation and process spectral labeling in Raman predictive modeling of cell culture processes

Min, Rui; Wang, Zhi; Zhuang, Yingping; Yi, Xiaoping

doi:10.1016/j.bej.2022.108774

Cited by 13 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can make it challenging to develop accurate models for rare or new diseases. One potential solution to the lack of labeled data is to use techniques such as data augmentation, which can be used to increase the size of the dataset artificially [ 123 ].…”

Section: Challenges Potential Solutions and Future Prospects Of Ai Me...mentioning

confidence: 99%

Evaluation of artificial intelligence techniques in disease diagnosis and prediction

Nia

Kaplanoğlu

Nasab

2023

Discov Artif Intell

120

View full text Add to dashboard Cite

A broad range of medical diagnoses is based on analyzing disease images obtained through high-tech digital devices. The application of artificial intelligence (AI) in the assessment of medical images has led to accurate evaluations being performed automatically, which in turn has reduced the workload of physicians, decreased errors and times in diagnosis, and improved performance in the prediction and detection of various diseases. AI techniques based on medical image processing are an essential area of research that uses advanced computer algorithms for prediction, diagnosis, and treatment planning, leading to a remarkable impact on decision-making procedures. Machine Learning (ML) and Deep Learning (DL) as advanced AI techniques are two main subfields applied in the healthcare system to diagnose diseases, discover medication, and identify patient risk factors. The advancement of electronic medical records and big data technologies in recent years has accompanied the success of ML and DL algorithms. ML includes neural networks and fuzzy logic algorithms with various applications in automating forecasting and diagnosis processes. DL algorithm is an ML technique that does not rely on expert feature extraction, unlike classical neural network algorithms. DL algorithms with high-performance calculations give promising results in medical image analysis, such as fusion, segmentation, recording, and classification. Support Vector Machine (SVM) as an ML method and Convolutional Neural Network (CNN) as a DL method is usually the most widely used techniques for analyzing and diagnosing diseases. This review study aims to cover recent AI techniques in diagnosing and predicting numerous diseases such as cancers, heart, lung, skin, genetic, and neural disorders, which perform more precisely compared to specialists without human error. Also, AI's existing challenges and limitations in the medical area are discussed and highlighted.

show abstract

Section: Challenges Potential Solutions and Future Prospects Of Ai Me...mentioning

confidence: 99%

Evaluation of artificial intelligence techniques in disease diagnosis and prediction

Nia

Kaplanoğlu

Nasab

2023

Discov Artif Intell

120

View full text Add to dashboard Cite

show abstract

“…CNN is a generic model based on deep learning which has recently been under considerable attention in biopharmaceutical industry (Khodabandehlou et al, 2023;Liu et al, 2024;Min et al, 2023).…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…In parallel, the US Food and Drug Administration established Process Analytical Technology (PAT) in 2004 to encourage drug manufacturers to deploy automated sampling and advanced sensing methods to improve quality (Hinz, 2006). The adoption of PAT by biopharmaceutical industry over the past decade contributed to the process yield increment and development of robust real‐time monitoring of cell culture processes (Berry et al, 2016; Min et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Integration of just‐in‐time learning with variational autoencoder for cell culture process monitoring based on Raman spectroscopy

Rashedi,

Khodabandehlou,

Wang

et al. 2024

Biotech & Bioengineering

View full text Add to dashboard Cite

Protein production in the biopharmaceutical industry necessitates the utilization of multiple analytical techniques and control methodologies to ensure both safety and consistency. To facilitate real‐time monitoring and control of cell culture processes, Raman spectroscopy has emerged as a versatile analytical technology. This technique, categorized as a Process Analytical Technology, employs chemometric models to establish correlations between Raman signals and key variables of interest. One notable approach for achieving real‐time monitoring is through the application of just‐in‐time learning (JITL), an industrial soft sensor modeling technique that utilizes Raman signals to estimate process variables promptly. The conventional Raman‐based JITL method relies on the K‐nearest neighbor (KNN) algorithm with Euclidean distance as the similarity measure. However, it falls short of addressing the impact of data uncertainties. To rectify this limitation, this study endeavors to integrate JITL with a variational autoencoder (VAE). This integration aims to extract dominant Raman features in a nonlinear fashion, which are expressed as multivariate Gaussian distributions. Three experimental runs using different cell lines were chosen to compare the performance of the proposed algorithm with commonly utilized methods in the literature. The findings indicate that the VAE–JITL approach consistently outperforms partial least squares, convolutional neural network, and JITL with KNN similarity measure in accurately predicting key process variables.

show abstract

“…In another work, Fukuhara et al used deep CNN to recognize and visualize effective features of Raman spectra by calculating important regions in the spectra based on the weights in pooling and fully-connected layers (Fukuhara et al, 2019). Using Raman spectra and offline measurements, Min et al built a regression model using CNNs (Min et al, 2023). Two data augmentation strategies are used to increase the size of training data, and then a one-dimensional CNN is trained to correlate offline measurements with Raman spectra.…”

Section: Introductionmentioning

confidence: 99%

“…Despite their promising results, the model is not appropriately validated since it only uses data from a single cell line for training and validation, so different models must be built for different types of cells. The accuracy of the final model is dependent on the accuracy of the data augmentation approach, and the model needs to be retrained when the culture changes (Min et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy

Khodabandehlou,

Rashedi,

Wang

et al. 2024

Biotech & Bioengineering

View full text Add to dashboard Cite

Advanced process control in the biopharmaceutical industry often lacks real‐time measurements due to resource constraints. Raman spectroscopy and Partial Least Squares (PLS) models are often used to monitor bioprocess cultures in real‐time. In spite of the ease of training, the accuracy of the PLS model is impacted if it is not used to predict quality attributes for the cell lines it is trained on. To address this issue, a deep convolutional neural network (CNN) is proposed for offline modeling of metabolites using Raman spectroscopy. By utilizing asymmetric least squares smoothing to adjust Raman spectra baselines, a generic training data set is created by amalgamating spectra from various cell lines and operating conditions. This data set, combined with their derivatives, forms a two‐dimensional model input. The CNN model is developed and validated for predicting different quality variables against measurements from various continuous and fed‐batch experimental runs. Validation results confirm that the deep CNN model is an accurate generic model of the process to predict real‐time quality attributes, even in experimental runs not included in the training data. This model is robust and versatile, requiring no recalibration when deployed at different sites to monitor various cell lines and experimental runs.

show abstract

Application of semi-supervised convolutional neural network regression model based on data augmentation and process spectral labeling in Raman predictive modeling of cell culture processes

Cited by 13 publications

References 38 publications

Evaluation of artificial intelligence techniques in disease diagnosis and prediction

Evaluation of artificial intelligence techniques in disease diagnosis and prediction

Integration of just‐in‐time learning with variational autoencoder for cell culture process monitoring based on Raman spectroscopy

Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy

Contact Info

Product

Resources

About