Screening ovarian cancers with Raman spectroscopy of blood plasma coupled with machine learning data processing

Chen, Fengye; Sun, Chen; Yue, Zengqi; Zhang, Yuqing; Xu, Weijie; Shabbir, Sahar; Zou, Long; Lü, Weiguo; Wang, Wei; Xie, Zhenwei; Zhou, Lili; Lu, Yan; Yu, Jianhua

doi:10.1016/j.saa.2021.120355

Cited by 26 publications

(13 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chen et al used RS on serum to classify ovarian samples as normal, cystic or cancerous in a two-step binary classification regime [ 19 ]. The first step used an ANN to determine abnormal and healthy samples, using an ensemble method to select the best model architecture, with an accuracy of 94.8%.…”

Section: Resultsmentioning

confidence: 99%

“…Of those studies that split the data at the level of spectra, the best accuracies of 90%, 96.6%, 97.7%, 93.8% and 94.8% were achieved [ 19 , 25 , 26 , 29 , 35 ]. Of those studies splitting data at the level of subject or sample, the accuracies were: 84.4%, 99%, 81.8%, 98.3%, 83%, 87%, 92.9%, 81.3% and 62.5% [ 20 , 22 , 24 , 30 , 31 , 32 , 34 , 35 , 40 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature

et al. 2022

View full text Add to dashboard Cite

Raman Spectroscopy has long been anticipated to augment clinical decision making, such as classifying oncological samples. Unfortunately, the complexity of Raman data has thus far inhibited their routine use in clinical settings. Traditional machine learning models have been used to help exploit this information, but recent advances in deep learning have the potential to improve the field. However, there are a number of potential pitfalls with both traditional and deep learning models. We conduct a literature review to ascertain the recent machine learning methods used to classify cancers using Raman spectral data. We find that while deep learning models are popular, and ostensibly outperform traditional learning models, there are many methodological considerations which may be leading to an over-estimation of performance; primarily, small sample sizes which compound sub-optimal choices regarding sampling and validation strategies. Amongst several recommendations is a call to collate large benchmark Raman datasets, similar to those that have helped transform digital pathology, which researchers can use to develop and refine deep learning models.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature

et al. 2022

View full text Add to dashboard Cite

show abstract

“…With the aid of Artificial Intelligence (AI), we have seen unbelievable progressions in the medical profession (Pamungkas et al, 2022) (Chen et al, 2022;Kwon et al, 2019aKwon et al, , 2019bM et al, 2020)from cancer predictions using machine learning to covid-19 detection using deep learning. We may use data mining techniques to discover trends in the dataset now that there is a collection of medical records that have been labelled.…”

Section: Introductionmentioning

confidence: 99%

“…The use of data mining techniques in medical records has had a considerable impact on the fields of healthcare and biomedicine. (Chen et al, 2022;Kwon et al, 2019aKwon et al, , 2019bLu et al, 2020;M et al, 2020;Maharjan, 2020). This enables doctors to detect the beginning of a disease at an earlier stage.…”

Section: Introductionmentioning

confidence: 99%

Identification and Mitigation of Bias Using Explainable Artificial Intelligence (Xai) for Brain Stroke Prediction

Mohammed

George

2023

OJPS

View full text Add to dashboard Cite

Stroke is a time-sensitive illness that without rapid care and diagnosis can result in detrimental effects on the person. Caretakers need to enhance patient management by procedurally mining and storing the patient's medical records because of the increasing synergy between technology and medical diagnosis. Therefore, it is essential to explore how these risk variables interconnect with each other in patient health records and understand how they each individually affect stroke prediction. Using explainable Artificial Intelligence (XAI) techniques, we were able to show the imbalance dataset and improve our model’s accuracy, we showed how oversampling improves our model’s performance and used explainable AI techniques to further investigate the decision and oversample a feature to have even better performance. We showed and suggested explainable AI as a technique to improve model performance and serve as a level of trustworthiness for practitioners, we used four evaluation metrics, recall, precision, accuracy, and f1 score. The f1 score with the original data was 0% due to imbalanced data, the non-stroke data was significantly higher than the stroke data, the 2nd model has an f1 score of 81.78% and we used explainable AI techniques, Local Interpretable Model-agnostic Explanations (LIME) and SHapely Additive exPlanation (SHAP) to further analyse how the model came to a decision, this led us to investigate and oversample a specific feature to have a new f1 score of 83.34%. We suggest the use of explainable AI as a technique to further investigate a model’s method for decision-making.

show abstract

“…Owing to the diversity and richness of treatment success in the predictive model, the independent finding 8 studies equally observed the patient's new genetic information and pathogenesis photographs. In recent decades, most researchers have applied the machine learning techniques for predicting OC.…”

Section: Introductionmentioning

confidence: 99%

A hybridized channel selection approach with deep convolutional neural network for effective ovarian cancer prediction in periodic acid‐Schiff‐stained images

Ramasamy¹,

Kaliyaperumal

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary In today's world, cancers are becoming a crucial warning in current medical applications where they show a significant part in the prognosis and appraisal of ovarian malignancies in histopathological imaging. Automated approaches to systematize the formation and categorization of cancers in periodic acid‐Schiff (PAS)‐stained images have recently been quickly growing in the area of digital pathology. However, the existing literature lacks computerized approaches to systematize the localization and categorization of cancers in PAS‐stained images. In this work, a new deep fully connected convolutional neural network (DFCNN) along with hybridized channel selection (HCS) strategy has been proposed to diagnose ovarian cancers accurately in PAS‐stained images. Primarily, the HCS strategy selects the optimal channel for managing the input dataset. Afterward, the DFCNN is employed to extract the influential features from the PAS‐stained images. The autoencoder modeling can be carried out to build the proposed DFCNN layers. The appropriate layer selection in the proposed model facilitates to obtaining accurate cancer classification with minimal misclassification errors. The performance results manifest that the proposed model achieves a superior accuracy of 99.22% when compared with existing CNN+softmax, CNN+decision tree, and CNN+radial basis function models.

show abstract

Screening ovarian cancers with Raman spectroscopy of blood plasma coupled with machine learning data processing

Cited by 26 publications

References 52 publications

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature

Identification and Mitigation of Bias Using Explainable Artificial Intelligence (Xai) for Brain Stroke Prediction

A hybridized channel selection approach with deep convolutional neural network for effective ovarian cancer prediction in periodic acid‐Schiff‐stained images

Contact Info

Product

Resources

About