Radiomics in oncology - uncovering tumor phenotype from medical images: a short introduction

Radiomics is a promising method to quantify and describe the tumor phenotype on medical images. High numbers of image features are extracted from medical images and can be used within a clinical decision support system by integrating this data with clinical and pathological variables. Herein, we give a short introduction into this image analysis method and present an overview on the workflow.

How to PROceed? Reviewing obstacles and perspectives in patient-centered digital care in radiation oncology

As the general public is increasing their online presence and is becoming confident with the digital infrastructure, an opportunity for patient-centered digital care has arisen. Electronic patient-reported outcomes, (e)PRO in short, may facilitate enhanced clinical management of radiation oncology patients. This might enable the physicians to take the initiative and counteract symptoms or undesired side effects before they aggravate and thus, reducing treatment-associated costs. In this article, we review the impetus for and modalities of (e)PRO-based data acquisition and handling in research and routine. We conclude that prospective and technical studies are needed to prove the clinical significance of (e)PROs to pave the way to monetary compensation and widespread application.

Procedural Creation of Medical Reports with Hierarchical Information Processing in Radiation Oncology

Background: For many years, the oncological doctor's letter has been the pivotal means of information transfer to general practitioners, medical specialists or medical consultants. Yet, both creator and recipient require a high level of abstraction, retentiveness and analysis due to the large number of diagnoses and therapies. In contrast to the commonly used structure of doctor's letters, where all diagnoses and therapies are listed in sequential order with all diagnoses first, it is by no means trivial to establish the important chronological and hierarchical context in the description of oncological cases. Additional aspects of importance are the integration of these letters into existing clinical and departmental information systems (for example via HL7 interface), various export formats (for example PDF, HTML), fax and encrypted email. Moreover these letters need a modern layout that, among others, meets the requirements of corporate design. Methods: The requirements for a doctor's letter system are manifold and can only be represented rudimentarily via a normal word processing system. Due to this deficiency we developed a system that covers all special features and requirements for clinical use. The system is based on a scalable and extensible client-server architecture. We use the programming languages Harbour, C++, PHP and JavaScript, Microsoft SQL database for data storage and the HL7 standard as the interface to other information systems such as hospital information system (HIS). Export formats are PDF, HTML/XML. Layouts are generated with TeX, LaTeX and MikTeX. Results: The aforementioned requirements were resolved with the doctor's letter and finding system IntDok. The hierarchical presentation of diagnoses, histologies and therapies provides the recipient with a first outline of the course of the disease. A strict procedure controls the whole process of document compilation and assists the user with many highly regarded tools such as text blocks, import and export (PDF and HTML/XML including barcodes) functions or HL7 interface to other information systems. The software also provides a sophisticated mail merging. All content from previous letters can easily be inserted into the current document. A TeX-server automatically provides document layout including supreme hyphenation so that uniform and perfect appearance (corporate design) is guaranteed. The documents are saved in a MS-SQL database (almost 230,000 documents since 1991), independent of any proprietary formats such as MS-Word. Conclusion: Creation of documents is fast, simple and well-structured. Sophisticated tools guarantee the optimal use of human resources and time. The system is an important module in our overall digital work environment.

Multimodal Document Management in Radiotherapy, an Update

Background: In 2013, we presented a study entitled “Multimodal document management in radiotherapy”, demonstrating the excellent routine performance of the system about four years after its initiation by evaluating a sample of n=500 documents. During this time the system saw additional developments and significant improvements: the most important innovative step being the automatic document processing. This has been completely reworked, to minimize staff-machine interaction, to increase processing speed and to further simplify the overall document handling. This improved system has been running practically without any problems for several months. Methods: While reworking the automatic document processing, we have developed algorithms that allow us to transfer documents with varying type, within a single scanning procedure, into our departmental system. The system identifies and corrects for any arbitrary order or rotation of scanned pages. Finally, after the transfer into the departmental system, all documents are in the correct order and they are automatically linked to the respective patient record. Results: According to our surveys, the error rate of the system, as in the previous version, is 0%. Compared to manual scanning and mapping of documents, we can quantify a 30-fold increase in the processing speed. In spite of these additional and elaborate processes, code optimizations yielded a processing speed increase of 20%. Pre-sorting of the documents (e.g., medical reports, or documents of informed consents) can be completely dispensed with the automated correction for jumbled documents or document rotations. In this manner 25,000 documents are automatically processed each year in the Department of Radiation Oncology at the University of Freiburg. Conclusion: With the methods presented in this study, and some additional bug fixes, and small improvements, automatic document processing of our departmental system was significantly improved without compromising the error rate. Keywords: Clinic management, documents, workflow, optimisation, efficiency, automation, Mosaiq, oncology informatics

A Step Forward in Cancer Informatics—It Is Mandatory to Make Guidelines Machine Readable

Clinical guidelines are general recommendations for practicing clinicians regarding prevention, diagnosis and treatment of a given disease. One of the most comprehensive and used guidelines are developed and regularly updated by the National Comprehensive Cancer Network (NCCN). Guidelines are readily available for download in portable document format (PDF). A machine-readable representation of NCCN guidelines is currently not available. In this writing, we argue on the necessity that clinical guidelines should be published in a machine-readable format. After review of the available literature, we describe the most important achievements in the field. Publication of guidelines in a machine-readable form may also be beneficial for other scientific and technical disciplines.

The Informatics of the Planning Target Volume -- why it cannot and should not be changed

The ICRU defined the Planning Target Volume (PTV) as a static and geometrical volume in 1993. Radiation oncologists continue to manually alter PTVs in their daily practice when critical organs at risk (OAR) are too close to high dose PTVs. This practice is examined and shown to be non-standard (defies the ICRU definitions), inaccurate (all DVHs look perfect when the plan is manifestly NOT perfect), and useless for outcomes research (automatically analysed DVHs will find situations where the PTV_unaltered overlaps the OAR_unaltered, but will fail to find situations where an OAR_unaltered would be overlapped by a PTV_unaltered, but is not overlapped by a PTV_altered.