Unsupervised neural networks as a support tool for pathology diagnosis in MALDI-MSI experiments: A case study on thyroid biopsies. (1st April 2023)

• Record Type: Journal Article
• Authors: Nobile, Marco S.; Capitoli, Giulia; Sowirono, Virgil; Clerici, Francesca; Piga, Isabella; van Abeelen, Kirsten; Magni, Fulvio; Pagni, Fabio; Galimberti, Stefania; Cazzaniga, Paolo; Besozzi, Daniela
• Is Part Of: Expert systems with applications. Volume 215(2023)
• Publication Date: 2023-04-01
• Subjects: SOM Self-Organizing Maps -- MALDI Matrix Assisted Laser Desorption Ionization -- ToF Time of Flight -- MSI Mass Spectrometry Imaging -- LASSO Least Absolute Shrinkage and Selection Operator -- AI Artificial Intelligence -- FNA Fine Needle Aspiration -- DESI Desorption Electrospray Ionization -- DSUUL Discrimination of Spectra Using Unsupervised Learning -- ROI Region of Interest -- H&E Hematoxylin and Eosin -- ANN Artificial Neural Network -- BMU Best Matching Unit -- PTC Papillary Thyroid Carcinoma -- HP Hyperplastic -- HT Hashimoto Thyroiditis -- NIFTP Noninvasive Thyroid Neoplasm with Papillary-like Nuclear Features -- TIC Total Ion Current -- MAD Mean Absolute Deviation -- GPU Graphics Processing Unit -- SIMD Same Instruction Multiple Data; Self-Organizing Maps -- Unsupervised learning -- MALDI-MSI -- Mass spectrometry -- Thyroid carcinoma -- Precision medicine; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.119296
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Artificial intelligence is getting a foothold in medicine for disease screening and diagnosis. While typical machine learning methods require large labeled datasets for training and validation, their application is limited in clinical fields since ground truth information can hardly be obtained on a sizeable cohort of patients. Unsupervised neural networks – such as Self-Organizing Maps (SOMs) – represent an alternative approach to identifying hidden patterns in biomedical data. Here we investigate the feasibility of SOMs for the identification of malignant and non-malignant regions in liquid biopsies of thyroid nodules, on a patient-specific basis. MALDI-ToF (Matrix Assisted Laser Desorption Ionization - Time of Flight) mass spectrometry-imaging (MSI) was used to measure the spectral profile of bioptic samples. SOMs were then applied for the analysis of MALDI-MSI data of individual patients' samples, also testing various pre-processing and agglomerative clustering methods to investigate their impact on SOMs' discrimination efficacy. The final clustering was compared against the sample's probability to be malignant, hyperplastic or related to Hashimoto thyroiditis as quantified by multinomial regression with LASSO. Our results show that SOMs are effective in separating the areas of a sample containing benign cells from those containing malignant cells. Moreover, they allow to overlap the different areas of cytological glass slides with the corresponding proteomic profile image, and inspect the specific weight of every cellular component in bioptic samples. We envision that this approach could represent an effective means to assist pathologists in diagnostic tasks, avoiding the need to manually annotate cytological images and the effort in creating labeled datasets. Highlights: Application of unsupervised learning for automated clustering of spectra profiles. Methodology to identify morphological regions of interest in a bioptic sample. Methodology tested on a case study regarding mass spectra data from thyroid nodules. Comparison to supervised learning shows effectiveness in separating regions. Effective tool to assist pathologists by avoiding the need for manual annotation.