Cancer Biomarkers - Volume 33, issue 2

Authors: Rodland, Karin D. | Webb-Robertson, Bobbie-Jo | Srivastava, Sudhir

Article Type: Editorial

DOI: 10.3233/CBM-229001

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 171-172, 2022

Authors: Mikdadi, Dina | O’Connell, Kyle A. | Meacham, Philip J. | Dugan, Madeleine A. | Ojiere, Michael O. | Carlson, Thaddeus B. | Klenk, Juergen A.

Article Type: Research Article

Abstract: BACKGROUND: Artificial intelligence (AI), including machine learning (ML) and deep learning, has the potential to revolutionize biomedical research. Defined as the ability to “mimic” human intelligence by machines executing trained algorithms, AI methods are deployed for biomarker discovery. OBJECTIVE: We detail the advancements and challenges in the use of AI for biomarker discovery in ovarian and pancreatic cancer. We also provide an overview of associated regulatory and ethical considerations. METHODS: We conducted a literature review using PubMed and Google Scholar to survey the published findings on the use of AI in ovarian cancer, …pancreatic cancer, and cancer biomarkers. RESULTS: Most AI models associated with ovarian and pancreatic cancer have yet to be applied in clinical settings, and imaging data in many studies are not publicly available. Low disease prevalence and asymptomatic disease limits data availability required for AI models. The FDA has yet to qualify imaging biomarkers as effective diagnostic tools for these cancers. CONCLUSIONS: Challenges associated with data availability, quality, bias, as well as AI transparency and explainability, will likely persist. Explainable and trustworthy AI efforts will need to continue so that the research community can better understand and construct effective models for biomarker discovery in rare cancers. Show more

Keywords: Artificial intelligence, bias, biomarkers, machine learning, rare cancer

DOI: 10.3233/CBM-210301

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 173-184, 2022

Authors: Yoon, Hong-Jun | Stanley, Christopher | Christian, J. Blair | Klasky, Hilda B. | Blanchard, Andrew E. | Durbin, Eric B. | Wu, Xiao-Cheng | Stroup, Antoinette | Doherty, Jennifer | Schwartz, Stephen M. | Wiggins, Charles | Damesyn, Mark | Coyle, Linda | Tourassi, Georgia D.

Article Type: Research Article

Abstract: BACKGROUND: With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information. OBJECTIVE: The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information. The objective of the study is to quantify …the privacy vulnerability of the deep learning models for natural language processing and explore a proper way of securing patients’ information to mitigate confidentiality breaches. METHODS: The target model is the multitask convolutional neural network for information extraction from cancer pathology reports, where the data for training the model are from multiple state population-based cancer registries. This study proposes the following schemes to collect vocabularies from the cancer pathology reports; (a) words appearing in multiple registries, and (b) words that have higher mutual information. We performed membership inference attacks on the models in high-performance computing environments. RESULTS: The comparison outcomes suggest that the proposed vocabulary selection methods resulted in lower privacy vulnerability while maintaining the same level of clinical task performance. Show more

Keywords: Privacy, privacy-preserving training, deep learning, natural language processing, cancer epidemiology, artificial intelligence

DOI: 10.3233/CBM-210306

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 185-198, 2022

Authors: Tayob, Nabihah | Feng, Ziding

Article Type: Research Article

Abstract: BACKGROUND: Patients undergoing screening for early detection of cancer have serial biomarker measurements that are not traditionally being incorporated into decision making when evaluating biomarkers. OBJECTIVE: We discuss statistical learning algorithms that have the ability to learn from patient history to make personalized decision rules to improve the early detection of cancer. These artificial intelligence algorithms are able to learn in real time from data collected on the patient to identify changes in the patient that could signal asymptomatic cancer. METHODS: We discuss the parametric empirical Bayes (PEB) algorithm for a single biomarker …and a Bayesian screening algorithm for multiple biomarkers. RESULTS: We provide tools to implement these algorithms and discuss their clinical utility for the early detection of hepatocellular carcinoma (HCC). The PEB algorithm is a robust, easily implemented algorithm for defining patient specific thresholds that can improve the patient-level sensitivity of a biomarker in many settings, including HCC. The fully Bayesian algorithm, while more complex, can accommodate multiple biomarkers and further improve the clinical utility of the algorithms. CONCLUSIONS: These algorithms could be used in many clinical settings and we aim to guide the reader on how these algorithms may improve the detection performance of their biomarkers. Show more

Keywords: Statistical learning algorithms, cancer biomarkers, early detection, parametric empirical Bayes, Bayesian changepoint models

DOI: 10.3233/CBM-210307

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 199-210, 2022

Authors: Qureshi, Touseef Ahmad | Gaddam, Srinivas | Wachsman, Ashley Max | Wang, Lixia | Azab, Linda | Asadpour, Vahid | Chen, Wansu | Xie, Yibin | Wu, Bechien | Pandol, Stephen Jacob | Li, Debiao

Article Type: Research Article

Abstract: BACKGROUND: Early stage diagnosis of Pancreatic Ductal Adenocarcinoma (PDAC) is challenging due to the lack of specific diagnostic biomarkers. However, stratifying individuals at high risk of PDAC, followed by monitoring their health conditions on regular basis, has the potential to allow diagnosis at early stages. OBJECTIVE: To stratify high risk individuals for PDAC by identifying predictive features in pre-diagnostic abdominal Computed Tomography (CT) scans. METHODS: A set of CT features, potentially predictive of PDAC, was identified in the analysis of 4000 raw radiomic parameters extracted from pancreases in pre-diagnostic scans. The naïve Bayes …classifier was then developed for automatic classification of CT scans of the pancreas with high risk for PDAC. A set of 108 retrospective CT scans (36 scans from each healthy control, pre-diagnostic, and diagnostic group) from 72 subjects was used for the study. Model development was performed on 66 multiphase CT scans, whereas external validation was performed on 42 venous-phase CT scans. RESULTS: The system achieved an average classification accuracy of 86% on the external dataset. CONCLUSIONS: Radiomic analysis of abdominal CT scans can unveil, quantify, and interpret micro-level changes in the pre-diagnostic pancreas and can efficiently assist in the stratification of high risk individuals for PDAC. Show more

Keywords: Pancreatic Ductal Adenocarcinoma (PDAC), pancreatic cancer, PDAC prediction, radiomics, machine learning, abdominal CT scans

DOI: 10.3233/CBM-210273

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 211-217, 2022

Authors: Vance, Krysten | Alitinok, Alphan | Winfree, Seth | Jensen-Smith, Heather | Swanson, Benjamin J. | Grandgenett, Paul M. | Klute, Kelsey A. | Crichton, Daniel J. | Hollingsworth, Michael A.

Article Type: Research Article

Abstract: BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a formidable challenge for patients and clinicians. OBJECTIVE: To analyze the distribution of 31 different markers in tumor and stromal portions of the tumor microenvironment (TME) and identify immune cell populations to better understand how neoplastic, non-malignant structural, and immune cells, diversify the TME and influence PDAC progression. METHODS: Whole slide imaging (WSI) and cyclic multiplexed-immunofluorescence (MxIF) was used to collect 31 different markers over the course of nine distinctive imaging series of human PDAC samples. Image registration and machine learning algorithms were developed to largely automate …an imaging analysis pipeline identifying distinct cell types in the TME. RESULTS: A random forest algorithm accurately predicted tumor and stromal-rich areas with 87% accuracy using 31 markers and 77% accuracy using only five markers. Top tumor-predictive markers guided downstream analyses to identify immune populations effectively invading into the tumor, including dendritic cells, CD4+ T cells, and multiple immunoregulatory subtypes. CONCLUSIONS: Immunoprofiling of PDAC to identify differential distribution of immune cells in the TME is critical for understanding disease progression, response and/or resistance to treatment, and the development of new treatment strategies. Show more

Keywords: Pancreatic ductal adenocarcinoma (PDAC), tumor microenvironment (TME), multiplexed-immunofluorescence (MxIF), Whole Slide Imaging (WSI), machine-learning

DOI: 10.3233/CBM-210308

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 219-235, 2022

Authors: Stefanou, Ioannis K. | Dovrolis, Nikolas | Gazouli, Maria | Theodorou, Dimitrios | Zografos, Georgios K. | Toutouzas, Konstantinos G.

Article Type: Research Article

Abstract: BACKGROUND: Gatrointestinal stromal tumors (GISTs) are the main mesenchymal tumors found in the gastrointestinal system. GISTs clinical phenotypes differ significantly and their molecular basis is not yet completely known. microRNAs (miRNAs) have been involved in carcinogenesis pathways by regulating gene expression at post-transcriptional level. OBJECTIVE: The aim of the present study was to elucidate the expression profiles of miRNAs relevant to gastric GIST carcinogenesis, and to identify miRNA signatures that can discriminate the GIST from normal cases. METHODS: miRNA expression was tested by miScript™miRNA PCR Array Human Cancer PathwayFinder kit and then we …used machine learning in order to find a miRNA profile that can predict the risk for GIST development. RESULTS: A number of miRNAs were found to be differentially expressed in GIST cases compared to healthy controls. Among them the hsa-miR-218-5p was found to be the best predictor for GIST development in our cohort. Additionally, hsa-miR-146a-5p, hsa-miR-222-3p, and hsa-miR-126-3p exhibit significantly lower expression in GIST cases compared to controls and were among the top predictors in all our predictive models. CONCLUSIONS: A machine learning classification approach may be accurate in determining the risk for GIST development in patients. Our findings indicate that a small number of miRNAs, with hsa-miR218-5p as a focus, may strongly affect the prognosis of GISTs. Show more

Keywords: miRNAs, cancer, GISTs, machine learning, artificial intelligence

DOI: 10.3233/CBM-210173

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 237-247, 2022

Authors: Liu, Shuai | Li, Ruikun | Liu, Qiufang | Sun, Dazheng | Yang, Hongxing | Pan, Herong | Wang, Lisheng | Song, Shaoli

Article Type: Review Article

Abstract: BACKGROUND: To explore an effective predictive model based on PET/CT radiomics for the prognosis of early-stage uterine cervical squamous cancer. METHODS: Preoperative PET/CT data were collected from 201 uterine cervical squamous cancer patients with stage IB-IIA disease (FIGO 2009) who underwent radical surgery between 2010 and 2015. The tumor regions were manually segmented, and 1318 radiomic features were extracted. First, model-based univariate analysis was performed to exclude features with small correlations. Then, the redundant features were further removed by feature collinearity. Finally, the random survival forest (RSF) was used to assess feature importance for multivariate analysis. …The prognostic models were established based on RSF, and their predictive performances were measured by the C-index and the time-dependent cumulative/dynamics AUC (C/D AUC). RESULTS: In total, 6 radiomic features (5 for CT and 1 for PET) and 6 clinicopathologic features were selected. The radiomic, clinicopathologic and combination prognostic models yielded C-indexes of 0.9338, 0.9019 and 0.9527, and the mean values of the C/D AUC (mC/D AUC) were 0.9146, 0.8645 and 0.9199, respectively. CONCLUSIONS: PET/CT radiomics could achieve approval power in predicting DFS in early-stage uterine cervical squamous cancer. Show more

Keywords: 18F-FDG PET/CT, radiomics, DFS, prediction, early-stage uterine cervical squamous cancer

DOI: 10.3233/CBM-210201

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 249-259, 2022

Authors: Elsayed, Inas | Elsayed, Nazik | Feng, Qiushi | Sheahan, Kieran | Moran, Bruce | Wang, Xiaosheng

Article Type: Research Article

Abstract: BACKGROUND: There is a current need for new markers with higher sensitivity and specificity to predict immune status and optimize immunotherapy use in colon cancer. OBJECTIVE: We aimed to investigate the multi-OMICs features associated with colon cancer immunity and response to immunotherapy. METHODS: We evaluated the association of multi-OMICs data from three colon cancer datasets (TCGA, CPTAC2, and Samstein) with antitumor immune signatures (CD8+ T cell infiltration, immune cytolytic activity, and PD-L1 expression). Using the log-rank test and hierarchical clustering, we explored the association of various OMICs features with survival …and immune status in colon cancer. RESULTS: Two gene mutations (TERT and ERBB4 ) correlated with antitumor cytolytic activity found also correlated with improved survival in immunotherapy-treated colon cancers. Moreover, the expression of numerous genes was associated with antitumor immunity, including GBP1 , GBP4 , GBP5 , NKG7 , APOL3 , IDO1 , CCL5 , and CXCL9 . We clustered colon cancer samples into four immuno-distinct clusters based on the expression levels of 82 genes. We have also identified two proteins (PREX1 and RAD50), ten miRNAs (hsa-miR-140, 146, 150, 155, 342, 59, 342, 511, 592 and 1977), and five oncogenic pathways (CYCLIN, BCAT, CAMP, RB, NRL, EIF4E, and VEGF signaling pathways) significantly correlated with antitumor immune signatures. CONCLUSION: These molecular features are potential markers of tumor immune status and response to immunotherapy. Show more

Keywords: Colon cancer, tumor immunity, cancer immunotherapy, multi-omics data, biomarkers

DOI: 10.3233/CBM-210222

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 261-271, 2022

Article Type: Retraction

DOI: 10.3233/CBM-220950

Citation: Cancer Biomarkers, vol. 33, no. 2, pp. 273-, 2022