Distinct DNA Methylation Profiles in Ovarian Tumors: Opportunities for Novel Biomarkers.

Aberrant methylation of multiple promoter CpG islands could be related to the biology of ovarian tumors and its determination could help to improve treatment strategies. DNA methylation profiling was performed using the Methylation Ligation-dependent Macroarray (MLM), an array-based analysis. Promoter regions of 41 genes were analyzed in 102 ovarian tumors and 17 normal ovarian samples. An average of 29% of hypermethylated promoter genes was observed in normal ovarian tissues. This percentage increased slightly in serous, endometrioid, and mucinous carcinomas (32%, 34%, and 45%, respectively), but decreased in germ cell tumors (20%). Ovarian tumors had methylation profiles that were more heterogeneous than other epithelial cancers. Unsupervised hierarchical clustering identified four groups that are very close to the histological subtypes of ovarian tumors. Aberrant methylation of three genes (BRCA1, MGMT, and MLH1), playing important roles in the different DNA repair mechanisms, were dependent on the tumor subtype and represent powerful biomarkers for precision therapy. Furthermore, a promising relationship between hypermethylation of MGMT, OSMR, ESR1, and FOXL2 and overall survival was observed. Our study of DNA methylation profiling indicates that the different histotypes of ovarian cancer should be treated as separate diseases both clinically and in research for the development of targeted therapies.

DNA methylation profiling of esophageal adenocarcinoma using Methylation Ligation-dependent Macroarray (MLM).

Most types of cancer cells are characterized by aberrant methylation of promoter genes. In this study, we described a rapid, reproducible, and relatively inexpensive approach allowing the detection of multiple human methylated promoter genes from many tissue samples, without the need of bisulfite conversion. The Methylation Ligation-dependent Macroarray (MLM), an array-based analysis, was designed in order to measure methylation levels of 58 genes previously described as putative biomarkers of cancer. The performance of the design was proven by screening the methylation profile of DNA from esophageal cell lines, as well as microdissected formalin-fixed and paraffin-embedded (FFPE) tissues from esophageal adenocarcinoma (EAC). Using the MLM approach, we identified 32 (55%) hypermethylated promoters in EAC, and not or rarely methylated in normal tissues. Among them, 21promoters were found aberrantly methylated in more than half of tumors. Moreover, seven of them (ADAMTS18, APC, DKK2, FOXL2, GPX3, TIMP3 and WIF1) were found aberrantly methylated in all or almost all the tumor samples, suggesting an important role for these genes in EAC. In addition, dysregulation of the Wnt pathway with hypermethylation of several Wnt antagonist genes was frequently observed. MLM revealed a homogeneous pattern of methylation for a majority of tumors which were associated with an advanced stage at presentation and a poor prognosis. Interestingly, the few tumors presenting less methylation changes had a lower pathological stage. In conclusion, this study demonstrated the feasibility and accuracy of MLM for DNA methylation profiling of FFPE tissue samples.

Deep learning based joint fusion approach to exploit anatomical and functional brain information in autism spectrum disorders.

BACKGROUND: The integration of the information encoded in multiparametric MRI images can enhance the performance of machine-learning classifiers. In this study, we investigate whether the combination of structural and functional MRI might improve the performances of a deep learning (DL) model trained to discriminate subjects with Autism Spectrum Disorders (ASD) with respect to typically developing controls (TD). MATERIAL AND METHODS: We analyzed both structural and functional MRI brain scans publicly available within the ABIDE I and II data collections. We considered 1383 male subjects with age between 5 and 40 years, including 680 subjects with ASD and 703 TD from 35 different acquisition sites. We extracted morphometric and functional brain features from MRI scans with the Freesurfer and the CPAC analysis packages, respectively. Then, due to the multisite nature of the dataset, we implemented a data harmonization protocol. The ASD vs. TD classification was carried out with a multiple-input DL model, consisting in a neural network which generates a fixed-length feature representation of the data of each modality (FR-NN), and a Dense Neural Network for classification (C-NN). Specifically, we implemented a joint fusion approach to multiple source data integration. The main advantage of the latter is that the loss is propagated back to the FR-NN during the training, thus creating informative feature representations for each data modality. Then, a C-NN, with a number of layers and neurons per layer to be optimized during the model training, performs the ASD-TD discrimination. The performance was evaluated by computing the Area under the Receiver Operating Characteristic curve within a nested 10-fold cross-validation. The brain features that drive the DL classification were identified by the SHAP explainability framework. RESULTS: The AUC values of 0.66±0.05 and of 0.76±0.04 were obtained in the ASD vs. TD discrimination when only structural or functional features are considered, respectively. The joint fusion approach led to an AUC of 0.78±0.04. The set of structural and functional connectivity features identified as the most important for the two-class discrimination supports the idea that brain changes tend to occur in individuals with ASD in regions belonging to the Default Mode Network and to the Social Brain. CONCLUSIONS: Our results demonstrate that the multimodal joint fusion approach outperforms the classification results obtained with data acquired by a single MRI modality as it efficiently exploits the complementarity of structural and functional brain information.

Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study.

Objective. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters. This limited robustness hinders the generalizable validity of radiomics-assisted models. Our aim is to investigate a possible harmonization strategy based on matching image quality to improve feature robustness.Approach.We acquired CT scans of a phantom with two scanners across different dose levels and percentages of Iterative Reconstruction algorithms. The detectability index was used as a comprehensive task-based image quality metric. A statistical analysis based on the Intraclass Correlation Coefficient was performed to determine if matching image quality/appearance could enhance the robustness of radiomics features extracted from the phantom images. Additionally, an Artificial Neural Network was trained on these features to automatically classify the scanner used for image acquisition.Main results.We found that the ICC of the features across protocols providing a similar detectability index improves with respect to the ICC of the features across protocols providing a different detectability index. This improvement was particularly noticeable in features relevant for distinguishing between scanners.Significance.This preliminary study demonstrates that a harmonization based on image quality/appearance matching could improve radiomics features robustness and heterogeneous protocols can be used to obtain a similar image appearance in terms of the detectability index. Thus protocols with a lower dose level could be selected to reduce the amount of radiation dose delivered to the patient and simultaneously obtain a more robust quantitative analysis.

Developing an ensemble machine learning study: Insights from a multi-center proof-of-concept study.

BACKGROUND: To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance. We suggested a proof of concept to define an ensemble approach useful for integrating different algorithms proposed to solve the same clinical task. METHODS: The proposed approach was developed starting from a public database consisting of radiomic features extracted from CT images relating to 535 patients suffering from lung cancer. Seven algorithms were trained independently by participants in the AI4MP working group on Artificial Intelligence of the Italian Association of Physics in Medicine to discriminate metastatic from non-metastatic patients. The classification scores generated by these algorithms are used to train SVM classifier. The Explainable Artificial Intelligence approach is applied to the final model. The ensemble model was validated following an 80-20 hold-out and leave-one-out scheme on the training set. RESULTS: Compared to individual algorithms, a more accurate result was achieved. On the independent test the ensemble model achieved an accuracy of 0.78, a F1-score of 0.57 and a log-loss of 0.49. Shapley values representing the contribution of each algorithm to the final classification result of the ensemble model were calculated. This information represents an added value for the end user useful for evaluating the appropriateness of the classification result on a particular case. It also allows us to evaluate on a global level which methodological approaches of the individual algorithms are likely to have the most impact. CONCLUSION: Our proposal represents an innovative approach useful for integrating different algorithms that populate the literature and which lays the foundations for future evaluations in broader application scenarios.

Robust machine learning challenge: An AIFM multicentric competition to spread knowledge, identify common pitfalls and recommend best practice.

PURPOSE: A novel and unconventional approach to a machine learning challenge was designed to spread knowledge, identify robust methods and highlight potential pitfalls about machine learning within the Medical Physics community. METHODS: A public dataset comprising 41 radiomic features and 535 patients was employed to assess the potential of radiomics in distinguishing between primary lung tumors and metastases. Each participant developed two classification models using: (i) all features (base model); (ii) only robust features (robust model). Both models were validated with cross-validation and on unseen data. The population stability index (PSI) was used as diagnostic metric for implementation issues. Performance was compared to reference. Base and robust models were compared in terms of performance and stability (coefficient of variation (CoV) of prediction probabilities). RESULTS: PSI detected potential implementation errors in 70 % of models. The dataset exhibited strong imbalance. The average Gmean (i.e. an appropriate metric for imbalance) among all participants was 0.67 ± 0.01, significantly higher than reference Gmean of 0.50 ± 0.04. Robust models performances were slightly worse than base models (p < 0.05). Regarding stability, robust models exhibited lower median CoV on training set only. CONCLUSION: AI4MP-Challenge models overperformed the reference, significantly improving the Gmean. Exclusion of less-robust features did not improve model robustness and it should be avoided when confounding effects are absent. Other methods, like harmonization or data augmentation, should be evaluated. This study demonstrated how the collaborative effort to foster knowledge on machine learning among medical physicists, through interactive sessions and exchange of information among participants, can result in improved models.

Deriving quantitative information from multiparametric MRI via Radiomics: Evaluation of the robustness and predictive value of radiomic features in the discrimination of low-grade versus high-grade gliomas with machine learning.

PURPOSE: Analysis pipelines based on the computation of radiomic features on medical images are widely used exploration tools across a large variety of image modalities. This study aims to define a robust processing pipeline based on Radiomics and Machine Learning (ML) to analyze multiparametric Magnetic Resonance Imaging (MRI) data to discriminate between high-grade (HGG) and low-grade (LGG) gliomas. METHODS: The dataset consists of 158 multiparametric MRI of patients with brain tumor publicly available on The Cancer Imaging Archive, preprocessed by the BraTS organization committee. Three different types of image intensity normalization algorithms were applied and 107 features were extracted for each tumor region, setting the intensity values according to different discretization levels. The predictive power of radiomic features in the LGG versus HGG categorization was evaluated by using random forest classifiers. The impact of the normalization techniques and of the different settings in the image discretization was studied in terms of the classification performances. A set of MRI-reliable features was defined selecting the features extracted according to the most appropriate normalization and discretization settings. RESULTS: The results show that using MRI-reliable features improves the performance in glioma grade classification (AUC=0.93±0.05) with respect to the use of raw (AUC=0.88±0.08) and robust features (AUC=0.83±0.08), defined as those not depending on image normalization and intensity discretization. CONCLUSIONS: These results confirm that image normalization and intensity discretization strongly impact the performance of ML classifiers based on radiomic features. Thus, special attention should be provided in the image preprocessing step before typical radiomic and ML analysis are carried out.

Multi-site harmonization of MRI data uncovers machine-learning discrimination capability in barely separable populations: An example from the ABIDE dataset.

Machine Learning (ML) techniques have been widely used in Neuroimaging studies of Autism Spectrum Disorders (ASD) both to identify possible brain alterations related to this condition and to evaluate the predictive power of brain imaging modalities. The collection and public sharing of large imaging samples has favored an even greater diffusion of the use of ML-based analyses. However, multi-center data collections may suffer the batch effect, which, especially in case of Magnetic Resonance Imaging (MRI) studies, should be curated to avoid confounding effects for ML classifiers and masking biases. This is particularly important in the study of barely separable populations according to MRI data, such as subjects with ASD compared to controls with typical development (TD). Here, we show how the implementation of a harmo- nization protocol on brain structural features unlocks the case-control ML separation capability in the analysis of a multi-center MRI dataset. This effect is demonstrated on the ABIDE data collection, involving subjects encompassing a wide age range. After data harmonization, the overall ASD vs. TD discrimination capability by a Random Forest (RF) classifier improves from a very low performance (AUC = 0.58 ± 0.04) to a still low, but reasonably significant AUC = 0.67 ± 0.03. The performances of the RF classifier have been evaluated also in the age-specific subgroups of children, adolescents and adults, obtaining AUC = 0.62 ± 0.02, AUC = 0.65 ± 0.03 and AUC = 0.69 ± 0.06, respectively. Specific and consistent patterns of anatomical differences related to the ASD condition have been identified for the three different age subgroups.

Long-term exposure to dehydroepiandrosterone affects the transcriptional activity of the glucocorticoid receptor.

Although the antiglucocorticoid effects of dehydroepiandrosterone (DHEA) have been demonstrated in vivo in many systems, controversial results have been reported by in vitro studies. In order to elucidate the long-term antiglucocorticoid effects of DHEA in vitro in a context more physiological than what proposed by previous works, we set up a system consisting of a carcinoma cell line relying on endogenously produced glucocorticoid receptor (GR) and stably expressing a reporter gene ErbB-2 under the control of a GR-dependent MMTV promoter. These cells grown in presence of low levels of serum glucocorticoids (GC) showed a basal translocation and activity of endogenous GR. The cells reacted to high concentrations of dexamethasone increasing GR nuclear import, although down-regulating receptor expression, and enhancing GR-dependent transcriptional activity, as shown by EMSA assay and expression of the reporter gene ErbB-2. The response to GC was also functional since the increase of ErbB-2 boosted cellular growth. On the contrary, 72h of incubation with DHEA diminished basal GR-dependent reporter expression and abated cellular proliferation. Analysing molecular mechanisms responsible for this failed transcriptional activity, upon prolonged treatment with DHEA we observed a slow nuclear import of GR not followed by its recruitment to DNA. These data add novel information about the long-term effects of DHEA in vitro.

Promoter methylation and downregulated expression of the TBX15 gene in ovarian carcinoma.

TBX15 is a gene involved in the development of mesodermal derivatives. As the ovaries and the female reproductive system are of mesodermal origin, the aim of the present study was to determine the methylation status of the TBX15 gene promoter and the expression levels of TBX15 in ovarian carcinoma, which is the most lethal and aggressive type of gynecological tumor, in order to determine the role of TBX15 in the pathogenesis of ovarian carcinoma. This alteration could be used to predict tumor development, progression, recurrence and therapeutic effects. The study was conducted on 80 epithelial ovarian carcinoma and 17 control cases (normal ovarian and tubal tissues). TBX15 promoter methylation was first determined by pyrosequencing following bisulfite modification, then by cloning and sequencing, in order to obtain information about the epigenetic haplotype. Immunohistochemical analysis was performed to evaluate the correlation between the methylation and protein expression levels. Data revealed a statistically significant increase of the TBX15 promoter region methylation in 82% of the tumor samples and in various histological subtypes. Immunohistochemistry showed an inverse correlation between methylation levels and the expression of the TBX15 protein. Furthermore, numerous tumor samples displayed varying degrees of intratumor heterogeneity. Thus, the present study determined that ovarian carcinoma typically expresses low levels of TBX15 protein, predominantly due to an epigenetic mechanism. This may have a role in the pathogenesis of ovarian carcinoma independent of the histological subtype.

A pilot study evaluating serum pro-prostate-specific antigen in patients with rising PSA following radical prostatectomy.

[-2]pro-prostate-specific antigen (2pPSA), a proform of PSA, is a new marker in patients at risk of prostate cancer. We explored the potential role of 2pPSA in the identification of patients with metastatic progression following radical prostatectomy for prostate cancer. Seventy-six patients with biochemical (PSA) recurrence following radical prostatectomy were studied retrospectively. Diagnostic imaging performed at the time of biochemical recurrence confirmed metastatic disease in 31 of the 76 patients. Serum samples were collected and stored at the time of imaging-confirmed metastatic progression or at the most recent procedure for patients with negative imaging. Median values of PSA, free PSA (fPSA), %fPSA, 2pPSA and prostate health index (PHI) were compared between metastatic and non-metastatic patients by the Mann-Whitney U test. The results of each test were then correlated with metastatic status by univariate and multivariate logistic regression analysis. PSA, fPSA, %fPSA, 2pPSA serum concentrations and PHI values were statistically significantly higher in patients with metastatic disease. Results of the multivariate analysis revealed that 2pPSA remained a statistically significant predictor of imaging-proven metastatic prostate cancer among patients with biochemical recurrence. At a cut-off value of 12.25 pg/ml, 2pPSA outperformed the other markers in terms of sensitivity and specificity (97 and 80%, respectively) with respect to imaging-confirmed metastatic progression. This is the first study suggesting that 2pPSA predicts diagnostic imaging-proven metastatic disease in previously resected prostate cancer patients with biochemical recurrence. Our results merit validation in a prospective study.