Raman spectral pattern recognition of breast cancer: A machine learning strategy based on feature fusion and adaptive hyperparameter optimization

• Published in: Heliyon Vol. 9; no. 7; p. e18148
• Main Authors: Li, Qingbo, Zhang, Zhixiang, Ma, Zhenhe
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.07.2023; Elsevier
• Subjects: algorithms; Breast cancer; breast neoplasms; chemical structure; Feature fusion; Hyperparameter optimization; MSEA; Pattern recognition; probability; Raman spectroscopy; signal-to-noise ratio; viability; vibration; Hyperparameter optimization; Breast cancer; Feature fusion; Pattern recognition; Raman spectroscopy; MSEA
• DOI: 10.1016/j.heliyon.2023.e18148
• ISSN: 2405-8440

Raman spectroscopy, as a kind of molecular vibration spectroscopy, provides abundant information for measuring components and molecular structure in the early detection and diagnosis of breast cancer. Currently, portable Raman spectrometers have simplified and made equipment application more affordable, albeit at the cost of sacrificing the signal-to-noise ratio (SNR). Consequently, this necessitates a higher recognition rate from pattern recognition algorithms. Our study employs a feature fusion strategy to reduce the dimensionality of high-dimensional Raman spectra and enhance the discriminative information between normal tissues and tumors. In the conducted random experiment, the classifier achieved a performance of over 96% for all three average metrics: accuracy, sensitivity, and specificity. Additionally, we propose a multi-parameter serial encoding evolutionary algorithm (MSEA) and integrate it into the Adaptive Local Hyperplane K-nearest Neighbor classification algorithm (ALHK) for adaptive hyperparameter optimization. The implementation of serial encoding tackles the predicament of parallel optimization in multi-hyperparameter vector problems. To bolster the convergence of the optimization algorithm towards a global optimal solution, an exponential viability function is devised for nonlinear processing. Moreover, an improved elitist strategy is employed for individual selection, effectively eliminating the influence of probability factors on the robustness of the optimization algorithm. This study further optimizes the hyperparameter space through sensitivity analysis of hyperparameters and cross-validation experiments, leading to superior performance compared to the ALHK algorithm with manual hyperparameter configuration. [Display omitted] •MSEA-ALHK model is proposed for adaptive hyperparameter optimization.•Feature fusion enhances the difference of Raman spectra between different types of breast tissue from the perspective of mid-level data fusion.•Embedding the feature selection method into the feature fusion process helps to interpret the biochemical differences of breast tissue characteristic peaks.