Advancing cancer diagnostics with artificial intelligence and spectroscopy: identifying chemical changes associated with breast cancer

Subtype-Specific Detection in Stage Ia Breast Cancer: Integrating Raman Spectroscopy, Machine Learning, and Liquid Biopsy for Personalised Diagnostics

This study explores the integration of Raman spectroscopy (RS) with machine learning for the early detection and subtyping of breast cancer using blood plasma samples. We performed detailed spectral analyses, identifying significant spectral patterns associated with cancer biomarkers. Our findings demonstrate the potential for classifying the four major subtypes of breast cancer at stage Ia with an average sensitivity and specificity of 90% and 95%, respectively, and a cross-validated macro-averaged area under the curve (AUC) of 0.98. This research highlights efforts to integrate vibrational spectroscopy with machine learning, enhancing cancer diagnostics through a non-invasive, personalised approach for early detection and monitoring disease progression. This study is the first of its kind to utilise RS and machine learning to classify the four major breast cancer subtypes at stage Ia.

RamanSPy: An Open-Source Python Package for Integrative Raman Spectroscopy Data Analysis

Raman spectroscopy is a nondestructive and label-free chemical analysis technique, which plays a key role in the analysis and discovery cycle of various branches of science. Nonetheless, progress in Raman spectroscopic analysis is still impeded by the lack of software, methodological and data standardization, and the ensuing fragmentation and lack of reproducibility of analysis workflows thereof. To address these issues, we introduce RamanSPy, an open-source Python package for Raman spectroscopic research and analysis. RamanSPy provides a comprehensive library of tools for spectroscopic analysis that supports day-to-day tasks, integrative analyses, the development of methods and protocols, and the integration of advanced data analytics. RamanSPy is modular and open source, not tied to a particular technology or data format, and can be readily interfaced with the burgeoning ecosystem for data science, statistical analysis, and machine learning in Python. RamanSPy is hosted at https://github.com/barahona-research-group/RamanSPy, supplemented with extended online documentation, available at https://ramanspy.readthedocs.io, that includes tutorials, example applications, and details about the real-world research applications presented in this paper.

Distinct spectral signatures unfold ECM stiffness-triggered biochemical changes in breast cancer cells

Cancer progression often accompanies the stiffening of extracellular matrix (ECM) in and around the tumor, owing to extra deposition and cross-linking of collagen. Stiff ECM has been linked with poor prognosis and is known to fuel invasion and metastasis, notably in breast cancer. However, the underlying biochemical or metabolic changes and the cognate molecular signatures remain elusive. Here, we explored Raman spectroscopy to unveil the spectral fingerprints of breast cancer cells in response to extracellular mechanical cues. Using stiffness-tuneable hydrogels, we showed that cells grown on stiff ECM displayed morphological changes with high proliferation. We further demonstrated that Raman Spectroscopy, a label-free and non-invasive technique, could provide comprehensive information about the biochemical environment of breast cancer cells in response to varying ECM stiffness. Raman spectroscopic analysis classified the cells into distinct clusters based on principal component-based linear discriminant analysis (PC-LDA). Multivariate curve resolution-alternating least squares (MCR-ALS) analysis indicated that cells cultured on stiff ECM exhibited elevated nucleic acid content and lesser lipids. Interestingly, increased intensity of Raman bands corresponding to cytochrome-c was also observed in stiff ECM conditions, suggesting mitochondrial modulation. The key findings harboured by spectral profiles were also corroborated by transmission electron microscopy, confirming altered metabolic status as reflected by increased mitochondria number and decreased lipid droplets in response to ECM stiffening. Collectively, these findings not only give the spectral signatures for mechanoresponse but also provide the landscape of biochemical changes in response to ECM stiffening.

Artificial intelligence: opportunities and challenges in the clinical applications of triple-negative breast cancer

Triple-negative breast cancer (TNBC) accounts for 15-20% of all invasive breast cancer subtypes. Owing to its clinical characteristics, such as the lack of effective therapeutic targets, high invasiveness, and high recurrence rate, TNBC is difficult to treat and has a poor prognosis. Currently, with the accumulation of large amounts of medical data and the development of computing technology, artificial intelligence (AI), particularly machine learning, has been applied to various aspects of TNBC research, including early screening, diagnosis, identification of molecular subtypes, personalised treatment, and prediction of prognosis and treatment response. In this review, we discussed the general principles of artificial intelligence, summarised its main applications in the diagnosis and treatment of TNBC, and provided new ideas and theoretical basis for the clinical diagnosis and treatment of TNBC.

Serum Raman spectroscopy combined with convolutional neural network for rapid diagnosis of HER2-positive and triple-negative breast cancer

Breast cancer is common in women, and its number of patients ranks first among female malignant tumors. Breast cancer is highly heterogeneous, and different types of breast cancer have different biological behaviors and prognoses. Therefore, identifying the different types of breast cancer is of great help in formulating individualized treatment plans. Based on serum Raman spectroscopy and deep learning algorithms, we propose a fast and low-cost diagnosis method for screening triple-negative breast cancer, human epidermal growth factor receptor 2 (HER2)-positive breast cancer, and healthy controls. We collected 75 serum samples in this study, including 23 triple-negative breast cancers, 22 HER2-positive breast cancers, and 30 healthy controls. Using the preprocessed Raman spectra as the input of deep learning, three deep learning models, neural network language model (NNLM), bidirectional long-short-term memory network (BiLSTM), and convolutional neural network (CNN), were established, and the accuracy rates of the three models were 87.78%, 90.37%, and 91.11%, respectively. The experimental results demonstrate the feasibility of serum Raman spectroscopy combined with deep learning algorithms to diagnose breast cancer, which can be used as an effective auxiliary diagnosis method for breast cancer.

Artificial intelligence in melanoma: A systematic review

BACKGROUND

Melanoma accounts for the majority of skin cancer deaths. Artificial intelligence has been applied in many types of cancers, and in melanoma in recent years. However, no systematic review summarized the application of artificial intelligence in melanoma.

AIMS

This study aims to systematically review previously published articles to explore the application of artificial intelligence in melanoma.

MATERIALS & METHODS

PubMed database was used to search the eligible publications on August 1, 2020. The query term was "artificial intelligence" and "melanoma."

RESULTS

A total of 51 articles were included in this review. Artificial intelligence technique is mainly used in the evaluation of dermoscopic images, other image segmentation and processing, and artificial intelligence diagnosis system.

DISCUSSION

Artificial intelligence is also applied in metastasis prediction, drug response prediction, and prognosis of melanoma. Besides, patients' perspectives of artificial intelligence and collaboration of human and artificial intelligence in melanoma also attracted attention. The query term might not include all articles, and we could not examine the algorithms that were built without publication.

CONCLUSION

The performance of artificial intelligence in melanoma is satisfactory and the future for potential applications is enormous.

Lipidomic markers of breast cancer malignant tumor histological types

The molecular profile of a tumor is associated with its histological type and can be used both to study the mechanisms of tumor progression and to diagnose it. In this work, changes in the lipid profile of a malignant breast tumor and the adjacent tissue were studied. The potential possibility of determining the histological type of the tumor by its lipid profile was evaluated. Lipid profiling was performed by reverse-phase chromato-mass-spectrometric analysis the tissue of lipid extract with identification of lipids by characteristic fragments. Potential lipid markers of the histological type of tumor were determined using the Kruskal-Wallis test. Impact of lipid markers was calculated by MetaboAnalyst. Classification models were built by support vector machines with linear kernel and 1-vs-1 architecture. Models were validated by leave-one out cross-validation. Accuracy of models based on microenvironment tissue, were 99% and 75%, accuracy of models, based on tumor tissue, were 90% and 40% for the positive ion mode and negative ion mode respectively. The lipid profile of marginal (adjacent) tissue can be used for identification histological types of breast cancer. Glycerophospholipid metabolism pathway changes were statistically significant in the adjacent tissue and tumor tissue.

Raman spectroscopy: current applications in breast cancer diagnosis, challenges and future prospects

Despite significant improvements in the way breast cancer is managed and treated, it continues to persist as a leading cause of death worldwide. If detected and diagnosed early, when tumours are small and localised, there is a considerably higher chance of survival. However, current methods for detection and diagnosis lack the required sensitivity and specificity for identifying breast cancer at the asymptomatic or very early stages. Thus, there is a need to develop more rapid and reliable methods, capable of detecting disease earlier, for improved disease management and patient outcome. Raman spectroscopy is a non-destructive analytical technique that can rapidly provide highly specific information on the biochemical composition and molecular structure of samples. In cancer, it has the capacity to probe very early biochemical changes that accompany malignant transformation, even prior to the onset of morphological changes, to produce a fingerprint of disease. This review explores the application of Raman spectroscopy in breast cancer, including discussion on its capabilities in analysing both ex-vivo tissue and liquid biopsy samples, and its potential in vivo applications. The review also addresses current challenges and potential future uses of this technology in cancer research and translational clinical application.

The role of neural artificial intelligence for diagnosis and treatment planning in endodontics: A qualitative review

Introduction

The role of artificial intelligence (AI) is currently increasing in terms of diagnosing diseases and planning treatment in endodontics. However, findings from individual research studies are not systematically reviewed and compiled together. Hence, this study aimed to systematically review, appraise, and evaluate neural AI algorithms employed and their comparative efficacy to conventional methods in endodontic diagnosis and treatment planning.

Methods

The present research question focused on the literature search about different AI algorithms and models of AI assisted endodontic diagnosis and treatment planning. The search engine included databases such as Google Scholar, PubMed, and Science Direct with search criteria of primary research paper, published in English, and analyzed data on AI and its role in the field of endodontics.

Results

The initial search resulted in 785 articles, exclusion based on abstract relevance, animal studies, grey literature and letter to editors narrowed down the scope of selected articles to 11 accepted for review. The review data supported the findings that AI can play a crucial role in the area of endodontics, such as identification of apical lesions, classifying and numbering teeth, detecting dental caries, periodontitis and periapical disease, diagnosing different dental problems, helping dentists make referrals, and also helping them make plans for treatment of dental disorders in a timely and effective manner with greater accuracy.

Conclusion

AI with different models or frameworks and algorithms can help dentists to diagnose and manage endodontic problems with greater accuracy. However, endodontic fraternity needs to provide more emphasis on the utilization of AI, provision of evidence based guidelines and implementation of the AI models.

Elucidating the chemical and structural composition of breast cancer using Raman micro-spectroscopy

The current gold standard for breast cancer (BC) diagnosis is the histopathological assessment of biopsy samples. However, this approach limits the understanding of the disease in terms of biochemical changes. Raman spectroscopy has demonstrated its potential to provide diagnostic information and facilitate the prediction of the biochemical progression for different diseases in a rapid non-destructive manner. Raman micro-spectroscopy was used to characterize and differentiate breast cancer and normal breast samples. In this study, tissue microarrays of breast cancer biopsy samples (n=499) and normal breast (n=79) were analyzed using Raman micro-spectroscopy, and principal component analysis (PCA) was used for feature extraction. Linear discriminant analysis (LDA) was used for feature validation. Normal breast and breast cancer were successfully differentiated with a sensitivity of 90 % and specificity of 78 %. Dominance of lipids, specifically fatty acids, was identified in the normal tissue whereas proteins dominated the malignant spectra. Higher intensities of carotenoids, β-carotenoids, and cholesterol were identified in the normal breast while ceramide related peaks were mostly visible in the BC spectra. The biochemical characterization achieved with Raman micro-spectroscopy showed that this technique is a powerful and reliable tool for the monitoring and diagnosis of BC, regardless of the cohort heterogeneity. Raman spectroscopy also provided a powerful insight into the biochemical changes associated with the BC progression and evolution.

Nanogenomics and Artificial Intelligence: A Dynamic Duo for the Fight Against Breast Cancer

Application software is utilized to aid in the diagnosis of breast cancer. Yet, recent advances in artificial intelligence (AI) are addressing challenges related to the detection, classification, and monitoring of different types of tumors. AI can apply deep learning algorithms to perform automated analysis on mammographic or histologic examinations. Large volume of data generated by digitalized mammogram or whole-slide images can be interoperated through advanced machine learning. This enables fast evaluation of every tissue patch on an image, resulting in a quicker more sensitivity, and more reproducible diagnoses compared to human performance. On the other hand, cancer cell-exosomes which are extracellular vesicles released by cancer cells into the blood circulation, are being explored as cancer biomarker. Recent studies on cancer-exosome-content revealed that the encapsulated miRNA and other biomolecules are indicative of tumor sub-type, possible metastasis and prognosis. Thus, theoretically, through nanogenomicas, a profile of each breast tumor sub-type, estrogen receptor status, and potential metastasis site can be constructed. Then, a laboratory instrument, fitted with an AI program, can be used to diagnose suspected patients by matching their sera miRNA and biomolecules composition with the available template profiles. In this paper, we discuss the advantages of establishing a nanogenomics-AI-based breast cancer diagnostic approach, compared to the gold standard radiology or histology based approaches that are currently being adapted to AI. Also, we discuss the advantages of building the diagnostic and prognostic biomolecular profiles for breast cancers based on the exosome encapsulated content, rather than the free circulating miRNA and other biomolecules.

Raman Microscopy: Progress in Research on Cancer Cell Sensing

In the last decade, Raman Spectroscopy (RS) was demonstrated to be a label-free, non-invasive and non-destructive optical spectroscopy allowing the improvement in diagnostic accuracy in cancer and analytical assessment for cell sensing. This review discusses how Raman spectra can lead to a deeper molecular understanding of the biochemical changes in cancer cells in comparison to non-cancer cells, analyzing two key examples, leukemia and breast cancer. The reported Raman results provide information on cancer progression and allow the identification, classification, and follow-up after chemotherapy treatments of the cancer cells from the liquid biopsy. The key obstacles for RS applications in cancer cell diagnosis, including quality, objectivity, number of cells and velocity of the analysis, are considered. The use of multivariant analysis, such as principal component analysis (PCA) and linear discriminate analysis (LDA), for an automatic and objective assessment without any specialized knowledge of spectroscopy is presented. Raman imaging for cancer cell mapping is shown and its advantages for routine clinical pathology practice and live cell imaging, compared to single-point spectral analysis, are debated. Additionally, the combination of RS with microfluidic devices and high-throughput screening for improving the velocity and the number of cells analyzed are also discussed. Finally, the combination of the Raman microscopy (RM) with other imaging modalities, for complete visualization and characterization of the cells, is described.

Raman spectral discrimination in human liquid biopsies of oesophageal transformation to adenocarcinoma

The aim of this study was to determine whether Raman spectroscopy combined with chemometric analysis can be applied to interrogate biofluids (plasma, serum, saliva and urine) towards detecting oesophageal stages through to oesophageal adenocarcinoma [normal/squamous epithelium, inflammatory, Barrett's, low-grade dysplasia, high-grade dysplasia and oesophageal adenocarcinoma (OAC)]. The chemometric analysis of the spectral data was performed using principal component analysis, successive projections algorithm or genetic algorithm (GA) followed by quadratic discriminant analysis (QDA). The genetic algorithm quadratic discriminant analysis (GA-QDA) model using a few selected wavenumbers for saliva and urine samples achieved 100% classification for all classes. For plasma and serum, the GA-QDA model achieved excellent accuracy in all oesophageal stages (>90%). The main GA-QDA features responsible for sample discrimination were: 1012 cm^-1 (C─O stretching of ribose), 1336 cm^-1 (Amide III and CH₂ wagging vibrations from glycine backbone), 1450 cm^-1 (methylene deformation) and 1660 cm^-1 (Amide I). The results of this study are promising and support the concept that Raman on biofluids may become a useful and objective diagnostic tool to identify oesophageal disease stages from squamous epithelium to OAC.

Towards development of a novel universal medical diagnostic method: Raman spectroscopy and machine learning

This review summarizes recent progress made using Raman spectroscopy and machine learning for potential universal medical diagnostic applications.