Implementation and Management Approach

The NeoMark project will pursue the identification of 'bio-signatures' of the disease by implementing a software environment enabling collection, storage, and integration of heterogeneous biological data - coming from clinical, laboratory, histological, transcriptomic and imaging information - aiming at modelling progression/ recurrence of regionally limited Oral Squamous Cell Carcinoma with two major purposes: 

1. to identify subjects at higher risk of cancer reoccurrence after reaching remission;
2. to detect early the presence of loco-regional recurrence undergoing traditional surgical plus medical treatment. 

The identification of a limited number of biomarkers, specific for the individual patient's profile of the disease, will be translated into a 'lab-on-chip' test device for early identification of potential risk of relapse.

The NeoMark clinical study and research will test the accuracy of this device on the enrolled patients, so providing data for a possible approval of this device by the European Authorities and by FDA. This ambitious goal may also lead us to the identification and development of an innovative, low-cost, portable, diagnostic device, usable by dentists and by physicians for OSCC screening purposes, so implementing the disease-prevention strategies of European health systems.

The NeoMark vision implies the identification of specific scientific objectives as well as technical objectives.

 The technologies developed in NeoMark will lead to the realisation of two functional environments: one for the definition of biomarker profiles and one for the follow-up of the evolution of the disease. They will be based on the 'fusion' of information from clinical data from:

• health records and standard laboratory markers;
• histological data from tumour mass specimens;
• high-throughput genomic data from tumour tissue specimens and circulating mononuclear cells, profiling gene expression at whole genome level by oligo-RNA microarrays;
• imaging data of the prime tumour mass (and secondary localisations if present) through imaging techniques, including image fusion, where relevant.

This vision pursued by NeoMark is based on  the development of innovative algorithms for the analysis of different categories of data (genomic, imaging, histology, biological, clinical), advance data organisation and data mining techniques, refined statistical tools, user-friendly and accurate user presentation methodologies, and user interfaces based on interoperable platforms.

A portable medical device to analyse this 'fingerprint' will also be produced at the end of the project, to facilitate and anticipate the prediction or detection of OSCC during screening of at-risk population and after treatment, during follow-ups.

The analysis of the heterogeneous data constitutes the cornerstone of the NeoMark artificial intelligence. This tool to assesses the risk of reoccurrence in the very early stages of treatment, i.e. as soon as the patient reaches remission, and efficiently and effectively models the disease evolution during the whole follow-up period based on a multitude of heterogeneous data, thus predicting the disease evolution. Using this tools physicians can stratify patients by reoccurrence risk probability at the time of diagnosis and use this information to decide the most appropriate treatment, and to monitor reoccurrence probability during patient's follow-up, so orienting the post-treatment therapeutic approach.

In NeoMark the progress of the disease in a total of almost 150 patients with oral squamous cell carcinoma is evaluated. Due to the complex nature of cancer, a collective approach must be considered which involves the integration and analysis of multiscale data. Specifically clinical, imaging and genomic data are assembled ranging in the scale of dimension and localisation. Moreover, a personalised genetic signature aims to capture patient-specific perturbations of the disease evolution in its molecular basis. For each patient the gene expression values before treatment (cancerous profile) and in the first stages of remission (cancer-free profile) are compared. The outcome is a set of differentially expressed genes representative for each patient, which constitute a personalised genetic signature. The expression of these genes from all follow-up visits is compared in turn with the cancerous and the cancer-free profile, calculating the correlation and the Euclidean distance; these metrics provide, respectively, a qualitative and quantitative measure of the patient's prognosis.

Technology solution

The versatile user requirements and especially the integration of heterogeneous input data required a careful design of the NeoMark system. Our goal was to integrate as much functionality as possible in a single unified service oriented system, achieving great flexibility and usability. These properties increase the user acceptance and may decrease human error. The proposed architecture is a service-oriented architecture (SOA) able to support the use of Web services to ensure interoperability between different systems. There are some individual applications that work as modules in the system in order to provide a single starting point to meet the needs of the users that can add new information, review and edit available data and make analyses with the stored information. The main module of this architecture is the data repository located on the NeoMark Server. For the interaction with this central component there are some different tools for Data Entry, Genomic Analyses, Imaging processing, Data Mining and Security. Some of those tools have a web-based access point and the others for some computational constraints are located on the client's machine, but always with an interaction with the central unit. The NeoMark System is scalable because we can easily add in new hospitals or centres that after a small initialisation procedure (Sensitive Data database and standalone application) can immediately start with the data storage and with the data analyses. The central repository stores all the collected heterogeneous data coming from the different modules and layers of the system, duly anonymised to ensure privacy. Sensitive patient's data, used by physicians to deliver therapy, are stored in separate local databases in each specific hospital's network in order to be accessible only by local authorised doctors.

The NeoMark Integrated platform integrates all the different components in charge of data collection and data analysis and provides data representation and reporting functionalities used by physicians to monitor patient's status and to take decisions on treatments and therapies.

Most of the user interaction is done via the web interface. The physician can manage patients, enter clinical data, view all features and the NeoMark results. The clinician can upload genomic data and researchers can view anonymous statistics, which could serve as a base for future research on oral cancer. However there are three exceptions to this architecture:

• The NeoMark Electronic Health Records management tool is the data collection tool, specifically designed for the collection, storage and management of all etherogeneous and multiscale data used in NeoMark. The tool collects data manually inserted by the authorised physicians and researchers, uploaded from the Image Processing Tool and from the Genomic Data Cleaning and Filtering Tool and presents data aggregations and reoccurrence risk prediction and disease evolution trends in paper and on screen.
• The NeoMark Image Processing Tool. This standalone Win64 application is installed on the radiologist's workstation. It is used to semi-automatically extract relevant features from medical images. Due to the huge amount of imaging data and the computational complexity of the sophisticated image processing and analysis algorithms, it was not feasible to integrate this functionality in the rest of the system. However the tool is connected to the NeoMark system via a network connection. The task of the feature extraction module is to extract from that huge amount of data meaningful numeric features from tumours and suspicious lymph nodes that appear to be important for reoccurrence prediction.
• The Genomic Data Cleaning and Filtering is used to analyse information taken from gene expression data coming from Feature Extraction (FE) files. The analyses in based on Control and Duplicate Features, Filtering of Genes based on low data quality and Filtering of Genes with high number of missing values taken from. The relevant information that is stored in the database is Feature Name, Probe Name Gene Name, Systematic Name, Description and Log2-ratio. Application generates as output a cleaned file with a small dimension that contains only this relevant information and that can be uploaded from a specific page of NeoMark WebApplication into the database.
• The Data Analysis and risk Prediction tool. The proposed prognostic model is based on DBNs, which are temporal extensions of Bayesian Networks (BNs). A snapshot of the patient's medical condition is acquired during every predefined follow-up by the doctor. By exploiting the information of history snapshots we aim to model the progression of the disease in the future. In the first step we filter the initial pool of genes by removing duplicate and control genes, as well as genes with high percentage of missing values.
• The PCR Chip Upload Tool. This tool downloads genomic features from a PCR chip reader device and submits them to the NeoMark system. Due to the direct access to external hardware, this tool could not be integrated, but rather is a standalone application which is installed on the clinician's workstation. The qRT-PCR platform is under development in STMicroelectronics, in order to obtain quantitative information about the PCR amplification of the targeted genes. It is a portable, real-time, integrated analytical system based on qRT-PCR performed in an array of silicon micro chambers. The small size of the components, as well as its low power requirements make this system an ideal candidate for further miniaturisation into a hand-held, point-of-care device. The qRT-PCR lab-on-chip is disposable and relatively inexpensive in order to make this method of analysis economically viable. The excellent thermal conductivity of silicon makes it ideal in applications requiring rapid cycles of heating and cooling.