Ultrasound-based radiomics for predicting the five major histological subtypes of epithelial ovarian cancer

BACKGROUND

Computational approaches have been proposed using radiomics in order to assess tumour heterogeneity, which is motivated by the concept that biomedical images may contain underlying pathophysiology information and has the potential to quantitatively measure the heterogeneity of intra- and intertumours. Ovarian cancer has the highest mortality among malignant tumours of female reproductive system and can be further divided into many subtypes with different management strategies and prognosis. The purpose of our study is to develop and validate ultrasound-based radiomics models to distinguish the five major histological subtypes of epithelial ovarian cancer.

METHODS

From January 2018 to August 2022, 1209 eligible ovarian cancer patients were enrolled. There were two subjects in this study: all patients (n = 1209) and patients with the five major histological subtypes (n = 1039). After image segmentation manually, radiomics features were extracted and some clinical characteristics were added. Nine feature selection methods were used to select the optimal predictive features. Seven classifiers were carried out to construct models. Choose the combination with the best predictive performance as the final result.

RESULTS

As for low-grade serous carcinoma, endometrioid carcinoma, and clear cell carcinoma, the models yields AUCs below 0.80 in the 10-fold cross-validation in the two groups. As for mucinous carcinoma, the AUCs were 0.83(95%CI, 0.74-0.93) and 0.89(95%CI, 0.83-0.95) in the validation cohorts and 0.80(95%CI, 0.73-0.87) and 0.86(95%CI, 0.78-0.94) in the 10-fold cross-validation in the two groups, respectively. As for high-grade serous carcinoma (HGSC), the models showed AUCs of 0.87(95%CI, 0.83-0.91) and 0.85(95%CI, 0.81-0.89) in the validation cohorts and 0.87(95%CI, 0.85-0.89) and 0.84(95%CI, 0.81-0.87) in the 10-fold cross-validation in the two groups, respectively, and exhibited high consistency between the predicted results and the actual outcomes, and brought great net benefits for patients.

CONCLUSIONS

The ultrasound-based radiomics models in discriminating HGSC and non-HGSC showed good predictive performance, as well as high consistency between the predicted results and the actual outcomes, and brought significant net benefits for patients.

Explainable AI-based feature importance analysis for ovarian cancer classification with ensemble methods

Introduction

Ovarian Cancer (OC) is one of the leading causes of cancer deaths among women. Despite recent advances in the medical field, such as surgery, chemotherapy, and radiotherapy interventions, there are only marginal improvements in the diagnosis of OC using clinical parameters, as the symptoms are very non-specific at the early stage. Owing to advances in computational algorithms, such as ensemble machine learning, it is now possible to identify complex patterns in clinical parameters. However, these complex patterns do not provide deeper insights into prediction and diagnosis. Explainable artificial intelligence (XAI) models, such as LIME and SHAP Kernels, can provide insights into the decision-making process of ensemble models, thus increasing their applicability.

Methods

The main aim of this study is to design a computer-aided diagnostic system that accurately classifies and detects ovarian cancer. To achieve this objective, a three-stage ensemble model and a game-theoretic approach based on SHAP values were built to evaluate and visualize the results, thus analyzing the important features responsible for prediction.

Results and Discussion

The results demonstrate the efficacy of the proposed model with an accuracy of 98.66%. The proposed model's consistency and advantages are compared with single classifiers. The SHAP values of the proposed model are validated using conventional statistical methods such as the p-test and Cohen's d-test to highlight the efficacy of the proposed method. To further validate the ranking of the features, we compared the p-values and Cohen's d-values of the top five and bottom five features. The study proposed and validated an AI-based method for the detection, diagnosis, and prognosis of OC using multi-modal real-life data, which mimics the move of a clinician approach with a demonstration of high performance. The proposed strategy can lead to reliable, accurate, and consistent AI solutions for the detection and management of OC with higher patient experience and outcomes at low cost, low morbidity, and low mortality. This can be beneficial for millions of women living in resource-constrained and challenging economies.

Imaging with mass spectrometry: Which ionization technique is best?

The use of mass spectrometry (MS) to acquire molecular images of biological tissues and other substrates has developed into an indispensable analytical tool over the past 25 years. Imaging mass spectrometry technologies are widely used today to study the in situ spatial distributions for a variety of analytes. Early MS images were acquired using secondary ion mass spectrometry and matrix-assisted laser desorption/ionization. Researchers have also designed and developed other ionization techniques in recent years to probe surfaces and generate MS images, including desorption electrospray ionization (DESI), nanoDESI, laser ablation electrospray ionization, and infrared matrix-assisted laser desorption electrospray ionization. Investigators now have a plethora of ionization techniques to select from when performing imaging mass spectrometry experiments. This brief perspective will highlight the utility and relative figures of merit of these techniques within the context of their use in imaging mass spectrometry.

Identifying Explainable Machine Learning Models and a Novel SFRP2+ Fibroblast Signature as Predictors for Precision Medicine in Ovarian Cancer

Ovarian cancer (OC) is a type of malignant tumor with a consistently high mortality rate. The diagnosis of early-stage OC and identification of functional subsets in the tumor microenvironment are essential to the development of patient management strategies. However, the development of robust models remains unsatisfactory. We aimed to utilize artificial intelligence and single-cell analysis to address this issue. Two independent datasets were screened from the Gene Expression Omnibus (GEO) database and processed to obtain overlapping differentially expressed genes (DEGs) in stage II-IV vs. stage I diseases. Three explainable machine learning algorithms were integrated to construct models that could determine the tumor stage and extract important characteristic genes as diagnostic biomarkers. Correlations between cancer-associated fibroblast (CAF) infiltration and characteristic gene expression were analyzed using TIMER2.0 and their relationship with survival rates was comprehensively explored via the Kaplan-Meier plotter (KM-plotter) online database. The specific expression of characteristic genes in fibroblast subsets was investigated through single-cell analysis. A novel fibroblast subset signature was explored to predict immune checkpoint inhibitor (ICI) response and oncogene mutation through Tumor Immune Dysfunction and Exclusion (TIDE) and artificial neural network algorithms, respectively. We found that Support Vector Machine-Shapley Additive Explanations (SVM-SHAP), Extreme Gradient Boosting (XGBoost), and Random Forest (RF) successfully diagnosed early-stage OC (stage I). The area under the receiver operating characteristic curves (AUCs) of these models exceeded 0.990. Their overlapping characteristic gene, secreted frizzled-related protein 2 (SFRP2), was a risk factor that affected the overall survival of OC patients with stage II-IV disease (log-rank test: p < 0.01) and was specifically expressed in a fibroblast subset. Finally, the SFRP2+ fibroblast signature served as a novel predictor in evaluating ICI response and exploring pan-cancer tumor protein P53 (TP53) mutation (AUC = 0.853, 95% confidence interval [CI]: 0.829-0.877). In conclusion, the models based on SVM-SHAP, XGBoost, and RF enabled the early detection of OC for clinical decision making, and SFRP2+ fibroblast signature used in diagnostic models can inform OC treatment selection and offer pan-cancer TP53 mutation detection.

Rapid Multivariate Analysis Approach to Explore Differential Spatial Protein Profiles in Tissue

Spatially targeted proteomics analyzes the proteome of specific cell types and functional regions within tissue. While spatial context is often essential to understanding biological processes, interpreting sub-region-specific protein profiles can pose a challenge due to the high-dimensional nature of the data. Here, we develop a multivariate approach for rapid exploration of differential protein profiles acquired from distinct tissue regions and apply it to analyze a published spatially targeted proteomics data set collected from Staphylococcus aureus-infected murine kidney, 4 and 10 days postinfection. The data analysis process rapidly filters high-dimensional proteomic data to reveal relevant differentiating species among hundreds to thousands of measured molecules. We employ principal component analysis (PCA) for dimensionality reduction of protein profiles measured by microliquid extraction surface analysis mass spectrometry. Subsequently, k-means clustering of the PCA-processed data groups samples by chemical similarity. Cluster center interpretation revealed a subset of proteins that differentiate between spatial regions of infection over two time points. These proteins appear involved in tricarboxylic acid metabolomic pathways, calcium-dependent processes, and cytoskeletal organization. Gene ontology analysis further uncovered relationships to tissue damage/repair and calcium-related defense mechanisms. Applying our analysis in infectious disease highlighted differential proteomic changes across abscess regions over time, reflecting the dynamic nature of host-pathogen interactions.

XAI-enabled neural network analysis of metabolite spatial distributions

We used deep neural networks to process the mass spectrometry imaging (MSI) data of mouse muscle (young vs aged) and human cancer (tumor vs normal adjacent) tissues, with the aim of using explainable artificial intelligence (XAI) methods to rapidly identify biomarkers that can distinguish different classes of tissues, from several thousands of metabolite features. We also modified classic neural network architectures to construct a deep convolutional neural network that is more suitable for processing high-dimensional MSI data directly, instead of using dimension reduction techniques, and compared it to seven other machine learning analysis methods' performance in classification accuracy. After ascertaining the superiority of Channel-ResNet10, we used a novel channel selection-based XAI method to identify the key metabolite features that were responsible for its learning accuracy. These key metabolite biomarkers were then processed using MetaboAnalyst for pathway enrichment mapping. We found that Channel-ResNet10 was superior to seven other machine learning methods for MSI analysis, reaching > 98% accuracy in muscle aging and colorectal cancer datasets. We also used a novel channel selection-based XAI method to find that in young and aged muscle tissues, the differentially distributed metabolite biomarkers were especially enriched in the propanoate metabolism pathway, suggesting it as a novel target pathway for anti-aging therapy.

From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment

Machine learning (ML) is increasingly used in clinical oncology to diagnose cancers, predict patient outcomes, and inform treatment planning. Here, we review recent applications of ML across the clinical oncology workflow. We review how these techniques are applied to medical imaging and to molecular data obtained from liquid and solid tumor biopsies for cancer diagnosis, prognosis, and treatment design. We discuss key considerations in developing ML for the distinct challenges posed by imaging and molecular data. Finally, we examine ML models approved for cancer-related patient usage by regulatory agencies and discuss approaches to improve the clinical usefulness of ML.

Classification of Pancreatic Ductal Adenocarcinoma Using MALDI Mass Spectrometry Imaging Combined with Neural Networks

Despite numerous diagnostic and therapeutic advances, pancreatic ductal adenocarcinoma (PDAC) has a high mortality rate, and is the fourth leading cause of cancer death in developing countries. Besides its increasing prevalence, pancreatic malignancies are characterized by poor prognosis. Omics technologies have potential relevance for PDAC assessment but are time-intensive and relatively cost-intensive and limited by tissue heterogeneity. Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) can obtain spatially distinct peptide-signatures and enables tumor classification within a feasible time with relatively low cost. While MALDI-MSI data sets are inherently large, machine learning methods have the potential to greatly decrease processing time. We present a pilot study investigating the potential of MALDI-MSI in combination with neural networks, for classification of pancreatic ductal adenocarcinoma. Neural-network models were trained to distinguish between pancreatic ductal adenocarcinoma and other pancreatic cancer types. The proposed methods are able to correctly classify the PDAC types with an accuracy of up to 86% and a sensitivity of 82%. This study demonstrates that machine learning tools are able to identify different pancreatic carcinoma from complex MALDI data, enabling fast prediction of large data sets. Our results encourage a more frequent use of MALDI-MSI and machine learning in histopathological studies in the future.

Multimodal Lung Cancer Subtyping Using Deep Learning Neural Networks on Whole Slide Tissue Images and MALDI MSI

Artificial intelligence (AI) has shown potential for facilitating the detection and classification of tumors. In patients with non-small cell lung cancer, distinguishing between the most common subtypes, adenocarcinoma (ADC) and squamous cell carcinoma (SqCC), is crucial for the development of an effective treatment plan. This task, however, may still present challenges in clinical routine. We propose a two-modality, AI-based classification algorithm to detect and subtype tumor areas, which combines information from matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) data and digital microscopy whole slide images (WSIs) of lung tissue sections. The method consists of first detecting areas with high tumor cell content by performing a segmentation of the hematoxylin and eosin-stained (H&E-stained) WSIs, and subsequently classifying the tumor areas based on the corresponding MALDI MSI data. We trained the algorithm on six tissue microarrays (TMAs) with tumor samples from N = 232 patients and used 14 additional whole sections for validation and model selection. Classification accuracy was evaluated on a test dataset with another 16 whole sections. The algorithm accurately detected and classified tumor areas, yielding a test accuracy of 94.7% on spectrum level, and correctly classified 15 of 16 test sections. When an additional quality control criterion was introduced, a 100% test accuracy was achieved on sections that passed the quality control (14 of 16). The presented method provides a step further towards the inclusion of AI and MALDI MSI data into clinical routine and has the potential to reduce the pathologist's work load. A careful analysis of the results revealed specific challenges to be considered when training neural networks on data from lung cancer tissue.

Advances, obstacles, and opportunities for machine learning in proteomics

The fields of proteomics and machine learning are both large disciplines, each producing well over 5,000 publications per year. However, studies combining both fields are still relatively rare, with only about 2% of recent proteomics papers including machine learning. This review, which focuses on the intersection of the fields, is intended to inspire proteomics researchers to develop skills and knowledge in the application of machine learning. A brief tutorial introduction to machine learning is provided, and research advances that rely on both fields, particularly as they relate to proteomics tools development and biomarker discovery, are highlighted. Key knowledge gaps and opportunities for scientific advancement are also enumerated.

Changes of Mass Spectra Patterns on a Brain Tissue Section Revealed by Deep Learning with Imaging Mass Spectrometry Data

The characteristic patterns of mass spectra in imaging mass spectrometry (IMS) strongly reflect the tissue environment. However, the boundaries formed where different tissue environments collide have not been visually assessed. In this study, IMS and convolutional neural network (CNN), one of the deep learning methods, were applied to the extraction of characteristic mass spectra patterns from training brain regions on rodents' brain sections. CNN produced classification models with high accuracy and low loss rate in any test data sets of mouse coronal sections measured by desorption electrospray ionization (DESI)-IMS and of mouse and rat sagittal sections by matrix-assisted laser desorption (MALDI)-IMS. On the basis of the extracted mass spectra pattern features, the histologically plausible segmentation and classification score imaging of the brain sections were obtained. The boundary imaging generated from classification scores showed the extreme changes of mass spectra patterns between the tissue environments, with no significant buffer zones for the intermediate state. The CNN-based analysis of IMS data is a useful tool for visually assessing the changes of mass spectra patterns on a tissue section, and it will contribute to a comprehensive view of the tissue environment.

Multi-Class Cancer Subtyping in Salivary Gland Carcinomas with MALDI Imaging and Deep Learning

Salivary gland carcinomas (SGC) are a heterogeneous group of tumors. The prognosis varies strongly according to its type, and even the distinction between benign and malign tumor is challenging. Adenoid cystic carcinoma (AdCy) is one subgroup of SGCs that is prone to late metastasis. This makes accurate tumor subtyping an important task. Matrix-assisted laser desorption/ionization (MALDI) imaging is a label-free technique capable of providing spatially resolved information about the abundance of biomolecules according to their mass-to-charge ratio. We analyzed tissue micro arrays (TMAs) of 25 patients (including six different SGC subtypes and a healthy control group of six patients) with high mass resolution MALDI imaging using a 12-Tesla magnetic resonance mass spectrometer. The high mass resolution allowed us to accurately detect single masses, with strong contributions to each class prediction. To address the added complexity created by the high mass resolution and multiple classes, we propose a deep-learning model. We showed that our deep-learning model provides a per-class classification accuracy of greater than 80% with little preprocessing. Based on this classification, we employed methods of explainable artificial intelligence (AI) to gain further insights into the spectrometric features of AdCys.

How (Not) to Generate a Highly Predictive Biomarker Panel Using Machine Learning

This review "teaches" researchers how to make their lackluster proteomics data look really impressive, by applying an inappropriate but pervasive strategy that selects features in a biased manner. The strategy is demonstrated and used to build a classification model with an accuracy of 92% and AUC of 0.98, while relying completely on random numbers for the data set. This "lesson" in data processing is not to be practiced by anyone; on the contrary, it is meant to be a cautionary tale showing that very unreliable results are obtained when a biomarker panel is generated first, using all the available data, and then tested by cross-validation. Data scientists describe the error committed in this scenario as having test data leak into the feature selection step, and it is currently a common mistake in proteomics biomarker studies that rely on machine learning. After the demonstration, advice is provided about how machine learning methods can be applied to proteomics data sets without generating artificially inflated accuracies.

Immune-and Metabolism-Associated Molecular Classification of Ovarian Cancer

Ovarian cancer (OV) is a complex gynecological disease, and its molecular characteristics are not clear. In this study, the molecular characteristics of OV subtypes based on metabolic genes were explored through the comprehensive analysis of genomic data. A set of transcriptome data of 2752 known metabolic genes was used as a seed for performing non negative matrix factorization (NMF) clustering. Three subtypes of OV (C1, C2 and C3) were found in analysis. The proportion of various immune cells in C1 was higher than that in C2 and C3 subtypes. The expression level of immune checkpoint genes TNFRSF9 in C1 was higher than that of other subtypes. The activation scores of cell cycle, RTK-RAS, Wnt and angiogenesis pathway and ESTIMATE immune scores in C1 group were higher than those in C2 and C3 groups. In the validation set, grade was significantly correlated with OV subtype C1. Functional analysis showed that the extracellular matrix related items in C1 subtype were significantly different from other subtypes. Drug sensitivity analysis showed that C2 subtype was more sensitive to immunotherapy. Survival analysis of differential genes showed that the expression of PXDN and CXCL11 was significantly correlated with survival. The results of tissue microarray immunohistochemistry showed that the expression of PXDN was significantly correlated with tumor size and pathological grade. Based on the genomics of metabolic genes, a new OV typing method was developed, which improved our understanding of the molecular characteristics of human OV.

In Situ N-glycosylation Signatures of Epithelial Ovarian Cancer Tissue as Defined by MALDI Mass Spectrometry Imaging

The particularly high mortality of epithelial ovarian cancer (EOC) is in part linked to limited understanding of its molecular signatures. Although there are data available on in situ N-glycosylation in EOC tissue, previous studies focused primarily on neutral N-glycan species and, hence, still little is known regarding EOC tissue-specific sialylation. In this proof-of-concept study, we implemented MALDI mass spectrometry imaging (MALDI-MSI) in combination with sialic acid derivatization to simultaneously investigate neutral and sialylated N-glycans in formalin-fixed paraffin-embedded tissue microarray specimens of less common EOC histotypes and non-malignant borderline ovarian tumor (BOT). The applied protocol allowed detecting over 50 m/z species, many of which showed differential tissue distribution. Most importantly, it could be demonstrated that α2,6- and α2,3-sialylated N-glycans are enriched in tissue regions corresponding to tumor and adjacent tumor-stroma, respectively. Interestingly, analogous N-glycosylation patterns were observed in tissue cores of BOT, suggesting that regio-specific N-glycan distribution might occur already in non-malignant ovarian pathologies. All in all, our data provide proof that the combination of MALDI-MSI and sialic acid derivatization is suitable for delineating regio-specific N-glycan distribution in EOC and BOT tissues and might serve as a promising strategy for future glycosylation-based biomarker discovery studies.

Cancer Tissue Classification Using Supervised Machine Learning Applied to MALDI Mass Spectrometry Imaging

Simple Summary

Classic histopathological examination of tissues remains the mainstay for cancer diagnosis and staging. However, in some cases histopathologic analysis yields ambiguous results, leading to inconclusive disease classification. We set out to explore the diagnostic potential of mass spectrometry-based imaging for tumour classification based on proteomic fingerprints. Combining mass spectrometry with supervised machine learning, we were able to distinguish colorectal tumor from normal tissue with an overall accuracy of 98%. In addition, this approach was able to predict the presence of lymph node metastasis in primary tumour of endometrial cancer with an overall accuracy of 80%. These results highlight the potential of this technology to determine the optimal treatment for cancer patients to reduce morbidity and improve patients’ outcomes.

Abstract

Matrix assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) can determine the spatial distribution of analytes such as protein distributions in a tissue section according to their mass-to-charge ratio. Here, we explored the clinical potential of machine learning (ML) applied to MALDI MSI data for cancer diagnostic classification using tissue microarrays (TMAs) on 302 colorectal (CRC) and 257 endometrial cancer (EC)) patients. ML based on deep neural networks discriminated colorectal tumour from normal tissue with an overall accuracy of 98% in balanced cross-validation (98.2% sensitivity and 98.6% specificity). Moreover, our machine learning approach predicted the presence of lymph node metastasis (LNM) for primary tumours of EC with an accuracy of 80% (90% sensitivity and 69% specificity). Our results demonstrate the capability of MALDI MSI for complementing classic histopathological examination for cancer diagnostic applications.

Peptide Signatures for Prognostic Markers of Pancreatic Cancer by MALDI Mass Spectrometry Imaging

Despite the overall poor prognosis of pancreatic cancer there is heterogeneity in clinical courses of tumors not assessed by conventional risk stratification. This yields the need of additional markers for proper assessment of prognosis and multimodal clinical management. We provide a proof of concept study evaluating the feasibility of Matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) to identify specific peptide signatures linked to prognostic parameters of pancreatic cancer. On 18 patients with exocrine pancreatic cancer after tumor resection, MALDI imaging analysis was performed additional to histopathological assessment. Principal component analysis (PCA) was used to explore discrimination of peptide signatures of prognostic histopathological features and receiver operator characteristic (ROC) to identify which specific m/z values are the most discriminative between the prognostic subgroups of patients. Out of 557 aligned m/z values discriminate peptide signatures for the prognostic histopathological features lymphatic vessel invasion (pL, 16 m/z values, eight proteins), nodal metastasis (pN, two m/z values, one protein) and angioinvasion (pV, 4 m/z values, two proteins) were identified. These results yield proof of concept that MALDI-MSI of pancreatic cancer tissue is feasible to identify peptide signatures of prognostic relevance and can augment risk assessment.

Molecular tissue profiling by MALDI imaging: recent progress and applications in cancer research

Matrix-assisted laser desorption/ionization (MALDI) imaging is an emergent technology that has been increasingly adopted in cancer research. MALDI imaging is capable of providing global molecular mapping of the abundance and spatial information of biomolecules directly in the tissues without labeling. It enables the characterization of a wide spectrum of analytes, including proteins, peptides, glycans, lipids, drugs, and metabolites and is well suited for both discovery and targeted analysis. An advantage of MALDI imaging is that it maintains tissue integrity, which allows correlation with histological features. It has proven to be a valuable tool for probing tumor heterogeneity and has been increasingly applied to interrogate molecular events associated with cancer. It provides unique insights into both the molecular content and spatial details that are not accessible by other techniques, and it has allowed considerable progress in the field of cancer research. In this review, we first provide an overview of the MALDI imaging workflow and approach. We then highlight some useful applications in various niches of cancer research, followed by a discussion of the challenges, recent developments and future prospect of this technique in the field.

Lipid Profiling in Cancer Diagnosis with Hand-Held Ambient Mass Spectrometry Probes: Addressing the Late-Stage Performance Concerns

Untargeted lipid fingerprinting with hand-held ambient mass spectrometry (MS) probes without chromatographic separation has shown promise in the rapid characterization of cancers. As human cancers present significant molecular heterogeneities, careful molecular modeling and data validation strategies are required to minimize late-stage performance variations of these models across a large population. This review utilizes parallels from the pitfalls of conventional protein biomarkers in reaching bedside utility and provides recommendations for robust modeling as well as validation strategies that could enable the next logical steps in large scale assessment of the utility of ambient MS profiling for cancer diagnosis. Six recommendations are provided that range from careful initial determination of clinical added value to moving beyond just statistical associations to validate lipid involvements in disease processes mechanistically. Further guidelines for careful selection of suitable samples to capture expected and unexpected intragroup variance are provided and discussed in the context of demographic heterogeneities in the lipidome, further influenced by lifestyle factors, diet, and potential intersect with cancer lipid pathways probed in ambient mass spectrometry profiling studies.

Use of MALDI Mass Spectrometry Imaging to Identify Proteomic Signatures in Aortic Aneurysms after Endovascular Repair

Endovascular repair (EVAR) has become the standard procedure in treating thoracic (TAA) or abdominal aortic aneurysms (AAA). Not entirely free of complications, a persisting perfusion of the aneurysm after EVAR, called Endoleak (EL), leads to reintervention and risk of secondary rupture. How the aortic wall responds to the implantation of a stentgraft and EL is mostly uncertain. We present a pilot study to identify peptide signatures and gain new insights in pathophysiological alterations of the aortic wall after EVAR using matrix-assisted laser desorption or ionization mass spectrometry imaging (MALDI-MSI). In course of or accompanying an open aortic repair, tissue sections from 15 patients (TAA = 5, AAA = 5, EVAR = 5) were collected. Regions of interest (tunica media and tunica adventitia) were defined and univariate (receiver operating characteristic analysis) statistical analysis for subgroup comparison was used. This proof-of-concept study demonstrates that MALDI-MSI is feasible to identify discriminatory peptide signatures separating TAA, AAA and EVAR. Decreased intensity distributions for actin, tropomyosin, and troponin after EVAR suggest impaired contractility in vascular smooth muscle cells. Furthermore, inability to provide energy caused by impaired respiratory chain function and continuous degradation of extracellular matrix components (collagen) might support aortic wall destabilization. In case of EL after EVAR, this mechanism may result in a weakened aortic wall with lacking ability to react on reinstating pulsatile blood flow.

Cross-Normalization of MALDI Mass Spectrometry Imaging Data Improves Site-to-Site Reproducibility

Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) is an established tool for the investigation of formalin-fixed paraffin-embedded (FFPE) tissue samples and shows a high potential for applications in clinical research and histopathological tissue classification. However, the applicability of this method to serial clinical and pharmacological studies is often hampered by inevitable technical variation and limited reproducibility. We present a novel spectral cross-normalization algorithm that differs from the existing normalization methods in two aspects: (a) it is based on estimating the full statistical distribution of spectral intensities and (b) it involves applying a non-linear, mass-dependent intensity transformation to align this distribution with a reference distribution. This method is combined with a model-driven resampling step that is specifically designed for data from MALDI imaging of tryptic peptides. This method was performed on two sets of tissue samples: a single human teratoma sample and a collection of five tissue microarrays (TMAs) of breast and ovarian tumor tissue samples (N = 241 patients). The MALDI MSI data was acquired in two labs using multiple protocols, allowing us to investigate different inter-lab and cross-protocol scenarios, thus covering a wide range of technical variations. Our results suggest that the proposed cross-normalization significantly reduces such batch effects not only in inter-sample and inter-lab comparisons but also in cross-protocol scenarios. This demonstrates the feasibility of cross-normalization and joint data analysis even under conditions where preparation and acquisition protocols themselves are subject to variation.

Discovery of Spatial Peptide Signatures for Neuroblastoma Risk Assessment by MALDI Mass Spectrometry Imaging

Simple Summary

The childhood tumor, neuroblastoma, has a broad clinical presentation. Risk assessment at diagnosis is particularly difficult in molecularly heterogeneous high-risk cases. Here we investigate the potential of imaging mass spectrometry to directly detect intratumor heterogeneity on the protein level in tissue sections. We show that this approach can produce discriminatory peptide signatures separating high- from low- and intermediate-risk tumors, identify 8 proteins aassociated with these signatures and validate two marker proteins using tissue immunostaining that have promise for further basic and translational research in neuroblastoma. We provide proof-of-concept that mass spectrometry-based technology could assist early risk assessment in neuroblastoma and provide insights into peptide signature-based detection of intratumor heterogeneity.

Abstract

Risk classification plays a crucial role in clinical management and therapy decisions in children with neuroblastoma. Risk assessment is currently based on patient criteria and molecular factors in single tumor biopsies at diagnosis. Growing evidence of extensive neuroblastoma intratumor heterogeneity drives the need for novel diagnostics to assess molecular profiles more comprehensively in spatial resolution to better predict risk for tumor progression and therapy resistance. We present a pilot study investigating the feasibility and potential of matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) to identify spatial peptide heterogeneity in neuroblastoma tissues of divergent current risk classification: high versus low/intermediate risk. Univariate (receiver operating characteristic analysis) and multivariate (segmentation, principal component analysis) statistical strategies identified spatially discriminative risk-associated MALDI-based peptide signatures. The AHNAK nucleoprotein and collapsin response mediator protein 1 (CRMP1) were identified as proteins associated with these peptide signatures, and their differential expression in the neuroblastomas of divergent risk was immunohistochemically validated. This proof-of-concept study demonstrates that MALDI-MSI combined with univariate and multivariate analysis strategies can identify spatially discriminative risk-associated peptide signatures in neuroblastoma tissues. These results suggest a promising new analytical strategy improving risk classification and providing new biological insights into neuroblastoma intratumor heterogeneity.

Diagnosis of melanoma by imaging mass spectrometry: Development and validation of a melanoma prediction model

BACKGROUND

The definitive diagnosis of melanocytic neoplasia using solely histopathologic evaluation can be challenging. Novel techniques that objectively confirm diagnoses are needed. This study details the development and validation of a melanoma prediction model from spatially resolved multivariate protein expression profiles generated by imaging mass spectrometry (IMS).

METHODS

Three board-certified dermatopathologists blindly evaluated 333 samples. Samples with triply concordant diagnoses were included in this study, divided into a training set (n = 241) and a test set (n = 92). Both the training and test sets included various representative subclasses of unambiguous nevi and melanomas. A prediction model was developed from the training set using a linear support vector machine classification model.

RESULTS

We validated the prediction model on the independent test set of 92 specimens (75 classified correctly, 2 misclassified, and 15 indeterminate). IMS detects melanoma with a sensitivity of 97.6% and a specificity of 96.4% when evaluating each unique spot. IMS predicts melanoma at the sample level with a sensitivity of 97.3% and a specificity of 97.5%. Indeterminate results were excluded from sensitivity and specificity calculations.

CONCLUSION

This study provides evidence that IMS-based proteomics results are highly concordant to diagnostic results obtained by careful histopathologic evaluation from a panel of expert dermatopathologists.

Classification of Molecular Subtypes of High-Grade Serous Ovarian Cancer by MALDI-Imaging

Simple Summary

High-grade serous ovarian cancer (HGSOC) accounts for 70% of ovarian carcinomas with sobering survival rates. The mechanisms mediating treatment efficacy are still poorly understood with no adequate biomarkers of response to treatment and risk assessment. This variability of treatment response might be due to its molecular heterogeneity. Therefore, identification of biomarkers or molecular signatures to stratify patients and offer personalized treatment is of utmost priority. Currently, comprehensive gene expression profiling is time- and cost-extensive and limited by tissue heterogeneity. Thus, it has not been implemented into clinical practice. This study demonstrates for the first time a spatially resolved, time- and cost-effective approach to stratifying HGSOC patients by combining novel matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI-IMS) technology with machine-learning algorithms. Eventually, MALDI-derived predictive signatures for treatment efficacy, recurrent risk, or, as demonstrated here, molecular subtypes might be utilized for emerging clinical challenges to ultimately improve patient outcomes.

Abstract

Despite the correlation of clinical outcome and molecular subtypes of high-grade serous ovarian cancer (HGSOC), contemporary gene expression signatures have not been implemented in clinical practice to stratify patients for targeted therapy. Hence, we aimed to examine the potential of unsupervised matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI-IMS) to stratify patients who might benefit from targeted therapeutic strategies. Molecular subtyping of paraffin-embedded tissue samples from 279 HGSOC patients was performed by NanoString analysis (ground truth labeling). Next, we applied MALDI-IMS paired with machine-learning algorithms to identify distinct mass profiles on the same paraffin-embedded tissue sections and distinguish HGSOC subtypes by proteomic signature. Finally, we devised a novel approach to annotate spectra of stromal origin. We elucidated a MALDI-derived proteomic signature (135 peptides) able to classify HGSOC subtypes. Random forest classifiers achieved an area under the curve (AUC) of 0.983. Furthermore, we demonstrated that the exclusion of stroma-associated spectra provides tangible improvements to classification quality (AUC = 0.988). Moreover, novel MALDI-based stroma annotation achieved near-perfect classifications (AUC = 0.999). Here, we present a concept integrating MALDI-IMS with machine-learning algorithms to classify patients according to distinct molecular subtypes of HGSOC. This has great potential to assign patients for personalized treatment.

INFORM: INFrared-based ORganizational Measurements of tumor and its microenvironment to predict patient survival

The structure and organization of a tumor and its microenvironment are often associated with cancer outcomes due to spatially varying molecular composition and signaling. A persistent challenge is to use this physical and chemical spatial organization to understand cancer progression. Here, we present a high-definition infrared imaging-based organizational measurement framework (INFORM) that leverages intrinsic chemical contrast of tissue to label unique components of the tumor and its microenvironment. Using objective and automated computational methods, further, we determine organization characteristics important for prediction. We show that the tumor spatial organization assessed with this framework is predictive of overall survival in colon cancer that adds to capability from clinical variables such as stage and grade, approximately doubling the risk of death in high-risk individuals. Our results open an all-digital avenue for measuring and studying the association between tumor spatial organization and disease progression.

Histo-molecular differentiation of renal cancer subtypes by mass spectrometry imaging and rapid proteome profiling of formalin-fixed paraffin-embedded tumor tissue sections

Pathology differentiation of renal cancer types is challenging due to tissue similarities or overlapping histological features of various tumor (sub) types. As assessment is often manually conducted outcomes can be prone to human error and therefore require high-level expertise and experience. Mass spectrometry can provide detailed histo-molecular information on tissue and is becoming increasingly popular in clinical settings. Spatially resolving technologies such as mass spectrometry imaging and quantitative microproteomics profiling in combination with machine learning approaches provide promising tools for automated tumor classification of clinical tissue sections.

In this proof of concept study we used MALDI-MS imaging (MSI) and rapid LC-MS/MS-based microproteomics technologies (15 min/sample) to analyze formalin-fixed paraffin embedded (FFPE) tissue sections and classify renal oncocytoma (RO, n = 11), clear cell renal cell carcinoma (ccRCC, n = 12) and chromophobe renal cell carcinoma (ChRCC, n = 5). Both methods were able to distinguish ccRCC, RO and ChRCC in cross-validation experiments. MSI correctly classified 87% of the patients whereas the rapid LC-MS/MS-based microproteomics approach correctly classified 100% of the patients.

This strategy involving MSI and rapid proteome profiling by LC-MS/MS reveals molecular features of tumor sections and enables cancer subtype classification. Mass spectrometry provides a promising complementary approach to current pathological technologies for precise digitized diagnosis of diseases.

MALDI-MSI-A Step Forward in Overcoming the Diagnostic Challenges in Ovarian Tumors

This study presents the use of matrix-assisted laser desorption and ionization mass spectrometry imaging (MALDI-MSI) directly on the tissue of two ovarian tumors that often present a diagnostic challenge, a low-grade serous borderline ovarian tumor and ovarian fibrothecoma. Different spatial distribution of m/z values within the tissue samples was observed, and regiospecific peaks were identified. Among the 106 peaks in the borderline ovarian tumor five, regiospecific peaks (m/z: 2861.35; 2775.79; 3368.34; 3438.43; 4936.37) were selected using FlexImaging software. Subsequently, the distribution of those selected peaks was visualized on the fibrothecoma tissue section, which demonstrated the differences in the tissue homo-/heterogeneous structure of both tumors. The comparison with the histopathological staining of the ovarian borderline tumor tissue section, obtained during serial sectioning, showed a close correlation of the molecular map with the morphological and histopathological features of the tissue and allowed the identification of different tissue types within the sample. This study highlights the potential significance of MSI in enabling morphological characterization of ovarian tumors as well as correct diagnosis and further prognosis than thus far seen in the literature. Osteopontin, tropomyosin and orosomucoid are only a couple of the molecules investigated using MALDI-MSI in ovarian cancer research. This study, in line with the available literature, proves the potential of MALDI-MSI to overcome the current limitations of classic histopathological examination giving a more in-depth insight into the tissue structure and thus lead to the more accurate differential diagnosis of ovarian tumors, especially in the most challenging cases.

Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes

Simple Summary

Diagnostic subtyping of non-small cell lung cancer is paramount for therapy stratification. Our study shows that the subtyping into pulmonary adenocarcinoma and pulmonary squamous cell carcinoma by mass spectrometry imaging is rapid and accurate using limited tissue material.

Abstract

Subtyping of non-small cell lung cancer (NSCLC) is paramount for therapy stratification. In this study, we analyzed the largest NSCLC cohort by mass spectrometry imaging (MSI) to date. We sought to test different classification algorithms and to validate results obtained in smaller patient cohorts. Tissue microarrays (TMAs) from including adenocarcinoma (ADC, n = 499) and squamous cell carcinoma (SqCC, n = 440), were analyzed. Linear discriminant analysis, support vector machine, and random forest (RF) were applied using samples randomly assigned for training (66%) and validation (33%). The m/z species most relevant for the classification were identified by on-tissue tandem mass spectrometry and validated by immunohistochemistry (IHC). Measurements from multiple TMAs were comparable using standardized protocols. RF yielded the best classification results. The classification accuracy decreased after including less than six of the most relevant m/z species. The sensitivity and specificity of MSI in the validation cohort were 92.9% and 89.3%, comparable to IHC. The most important protein for the discrimination of both tumors was cytokeratin 5. We investigated the largest NSCLC cohort by MSI to date and found that the classification of NSCLC into ADC and SqCC is possible with high accuracy using a limited set of m/z species.

Identification of Homo sapiens cancer classes based on fusion of hidden gene features

Classification of Homo sapiens cancer genes in molecular level is a challenging research issue as they are extremely pseudo random in nature. Signature gene features need to be exposed to distinctly identify the gene class. Tree-structured filter bank is chosen to perform feature extraction and dimension reduction of the genes. Extracted gene features are fused using Gaussian mixture probability distribution function and identify different cancer classes depending on amount of correlation and exploiting maximum likelihood function. The algorithm is tested on 161 sample gene data of 7 different cancer classes. Sensitivity, specificity, accuracy, precision and F-score are used as metrics to judge the performance of the system and ROC is plotted in comparison with existing electrical network model based classifier. The proposed classifier can identify more than stated number of cancer classes which is a major limitation of the existing electrical network based method. The proposed algorithm is validated by comparing the results with other seven existing image processing based methods.

Classification of Inflammatory Bowel Disease from Formalin-Fixed, Paraffin-Embedded Tissue Biopsies via Imaging Mass Spectrometry

PURPOSE

Discrimination between ulcerative colitis (UC) and Crohn's disease (CD) by histologic features alone can be challenging and often leads to inaccurate initial diagnoses in inflammatory bowel disease (IBD) patients. This is mostly due to an overlap of clinical and histologic features. However, exact diagnosis is not only important for patient treatment but it also has a socioeconomic impact. It is therefore important to develop and improve diagnostic tools complementing traditional histomorphological approaches.

EXPERIMENTAL DESIGN

In this retrospective proof-of-concept study, the utilization of MALDI imaging is explored in combination with multi-variate data analysis methods to classify formalin-fixed, paraffin-embedded (FFPE) colon biopsies from UC (87 biopsies, 14 patients), CD (71 biopsies, 14 patients), and normal colonic (21 biopsies, 14 patients) tissues.

RESULTS

The proposed method results in an overall balanced accuracy of 85.7% on patient and of 80.4% on sample level, thus demonstrating that the assessment of IBD from FFPE tissue specimens via MALDI imaging is feasible.

CONCLUSIONS AND CLINICAL RELEVANCE

The results emphasize the high potential of this method to distinguish IBD subtypes in FFPE tissue sections, which is a prerequisite for further investigations in retrospective multicenter studies, as well as for a future implementation into clinical routine.

Discovery of Prognostic Markers for Early-Stage High-Grade Serous Ovarian Cancer by Maldi-Imaging

With regard to relapse and survival, early-stage high-grade serous ovarian (HGSOC) patients comprise a heterogeneous group and there is no clear consensus on first-line treatment. Currently, no prognostic markers are available for risk assessment by standard targeted immunohistochemistry and novel approaches are urgently required. Here, we applied MALDI-imaging mass spectrometry (MALDI-IMS), a new method to identify distinct mass profiles including protein signatures on paraffin-embedded tissue sections. In search of prognostic biomarker candidates, we compared proteomic profiles of primary tumor sections from early-stage HGSOC patients with either recurrent (RD) or non-recurrent disease (N = 4; each group) as a proof of concept study. In total, MALDI-IMS analysis resulted in 7537 spectra from the malignant tumor areas. Using receiver operating characteristic (ROC) analysis, 151 peptides were able to discriminate between patients with RD and non-RD (AUC > 0.6 or < 0.4; p < 0.01), and 13 of them could be annotated to proteins. Strongest expression levels of specific peptides linked to Keratin type1 and Collagen alpha-2(I) were observed and associated with poor prognosis (AUC > 0.7). These results confirm that in using IMS, we could identify new candidates to predict clinical outcome and treatment extent for patients with early-stage HGSOC.

Mass spectrometry imaging to detect lipid biomarkers and disease signatures in cancer

BACKGROUND

Current methods to identify, classify, and predict tumor behavior mostly rely on histology, immunohistochemistry, and molecular determinants. However, better predictive markers are required for tumor diagnosis and evaluation. Due, in part, to recent technological advancements, metabolomics and lipid biomarkers have become a promising area in cancer research. Therefore, there is a necessity for novel and complementary techniques to identify and visualize these molecular markers within tumors and surrounding tissue.

RECENT FINDINGS

Since its introduction, mass spectrometry imaging (MSI) has proven to be a powerful tool for mapping analytes in biological tissues. By adding the label-free specificity of mass spectrometry to the detailed spatial information of traditional histology, hundreds of lipids can be imaged simultaneously within a tumor. MSI provides highly detailed lipid maps for comparing intra-tumor, tumor margin, and healthy regions to identify biomarkers, patterns of disease, and potential therapeutic targets. In this manuscript, recent advancement in sample preparation and MSI technologies are discussed with special emphasis on cancer lipid research to identify tumor biomarkers.

CONCLUSION

MSI offers a unique approach for biomolecular characterization of tumor tissues and provides valuable complementary information to histology for lipid biomarker discovery and tumor classification in clinical and research cancer applications.

Novel methods in adrenal research: a metabolomics approach

Metabolic alterations have implications in a spectrum of tissue functions and disease. Aided by novel molecular biological and computational tools, our understanding of physiological and pathological processes underpinning endocrine and endocrine-related disease has significantly expanded over the last decade. Herein, we focus on novel metabolomics-related methodologies in adrenal research: in situ metabolomics by mass spectrometry imaging, steroid metabolomics by gas and liquid chromatography-mass spectrometry, energy pathway metabologenomics by liquid chromatography-mass spectrometry-based metabolomics of Krebs cycle intermediates, and cellular reprogramming to generate functional steroidogenic cells and hence to modulate the steroid metabolome. All four techniques to assess and/or modulate the metabolome in biological systems provide tremendous opportunities to manage neoplastic and non-neoplastic disease of the adrenal glands in the era of precision medicine. In this context, we discuss emerging clinical applications and/or promising metabolic-driven research towards diagnostic, prognostic, predictive and therapeutic biomarkers in tumours arising from the adrenal gland and extra-adrenal paraganglia as well as modern approaches to delineate and reprogram adrenal metabolism.