Digital imaging in the radiation oncology environment: a personal computer local area network solution

The Integration of Deep Learning in Radiotherapy: Exploring Challenges, Opportunities, and Future Directions through an Umbrella Review

This study investigates, through a narrative review, the transformative impact of deep learning (DL) in the field of radiotherapy, particularly in light of the accelerated developments prompted by the COVID-19 pandemic. The proposed approach was based on an umbrella review following a standard narrative checklist and a qualification process. The selection process identified 19 systematic review studies. Through an analysis of current research, the study highlights the revolutionary potential of DL algorithms in optimizing treatment planning, image analysis, and patient outcome prediction in radiotherapy. It underscores the necessity of further exploration into specific research areas to unlock the full capabilities of DL technology. Moreover, the study emphasizes the intricate interplay between digital radiology and radiotherapy, revealing how advancements in one field can significantly influence the other. This interdependence is crucial for addressing complex challenges and advancing the integration of cutting-edge technologies into clinical practice. Collaborative efforts among researchers, clinicians, and regulatory bodies are deemed essential to effectively navigate the evolving landscape of DL in radiotherapy. By fostering interdisciplinary collaborations and conducting thorough investigations, stakeholders can fully leverage the transformative power of DL to enhance patient care and refine therapeutic strategies. Ultimately, this promises to usher in a new era of personalized and optimized radiotherapy treatment for improved patient outcomes.

[The role of high-energy imaging in a radiotherapy service and its incorporation in a network]

To directly compare the clinical efficacy of electronic to film portal images and the advantages of comparing directly on the monitor the simulation image and the portal image.

MATERIAL AND METHODS

This study was designed to compare clinical efficacy of electronic to film portal images acquired using a liquid matrix ion-chamber electronic portal imaging device (EPID) and a conventional film system. Two radiation oncologists served as observers and evaluated a total of 30 sets of images for three different treatment sites: lung, pelvis, and head/neck. Each set of images included a simulation image, a portal film, a video paper print of electronic portal images, and a video prints of electronic portal images. Four to six anatomical landmarks were selected from each treatment site. Each observer was asked to rate each landmark in terms of its clinical visibility and to rate the ease of making the pertinent verification decision in the corresponding electronic and film portal images with the aid of the simulation image. The time needed to obtain and analyse a conventional portal image and an EPID would be analysed for the radiotherapist and the medical technicians.

RESULTS

Ratings for the visibility of landmarks and for the verification decision of treatment ports were similar for electronic and film images for most landmarks. However, vertebral bodies and several landmarks in the pelvis such as the acetabulum and pubic symphysis were more visible in the electronic portal images than in the portal film images. For the medical technicians, the EPID is more comfortable, and they do not need to develop any images.

CONCLUSION

The visibility of landmarks in electronic portal images is comparable to that in film portal images. Verification of treatment ports based only on electronic portal images acquired using an electronic portal imaging device is generally achievable. Thus the integration of the EPID and simulation image in a network provides more flexibility in the daily work of a medical radiotherapy team.

Portfolio: a prototype workstation for development and evaluation of tools for analysis and management of digital portal images

PURPOSE

The purpose of this investigation was to design and implement a prototype physician workstation, called PortFolio, as a platform for developing and evaluating, by means of controlled observer studies, user interfaces and interactive tools for analyzing and managing digital portal images. The first observer study was designed to measure physician acceptance of workstation technology, as an alternative to a view box, for inspection and analysis of portal images for detection of treatment setup errors.

METHODS AND MATERIALS

The observer study was conducted in a controlled experimental setting to evaluate physician acceptance of the prototype workstation technology exemplified by PortFolio. PortFolio incorporates a windows user interface, a compact kit of carefully selected image analysis tools, and an object-oriented data base infrastructure. The kit evaluated in the observer study included tools for contrast enhancement, registration, and multimodal image visualization. Acceptance was measured in the context of performing portal image analysis in a structured protocol designed to simulate clinical practice. The acceptability and usage patterns were measured from semistructured questionnaires and logs of user interactions.

RESULTS

Radiation oncologists, the subjects for this study, perceived the tools in PortFolio to be acceptable clinical aids. Concerns were expressed regarding user efficiency, particularly with respect to the image registration tools.

CONCLUSIONS

The results of our observer study indicate that workstation technology is acceptable to radiation oncologists as an alternative to a view box for clinical detection of setup errors from digital portal images. Improvements in implementation, including more tools and a greater degree of automation in the image analysis tasks, are needed to make PortFolio more clinically practical.

A heuristic approach to edge detection in on-line portal imaging

PURPOSE

Portal field edge detection is an essential component of several postprocessing techniques used in on-line portal imaging, including field shape verification, selective contrast enhancement, and treatment setup error detection. Currently edge detection of successive fractions in a multifraction portal image series involves the repetitive application of the same algorithm. As the number of changes in the field is small compared to the total number of fractions, standard edge detection algorithms essentially recalculate the same field shape numerous times. A heuristic approach to portal edge detection has been developed that takes advantage of the relatively few changes in the portal field shape throughout a fractionation series.

METHODS AND MATERIALS

The routine applies a standard edge detection routine to calculate an initial field edge and saves the edge information. Subsequent fractions are processed by applying an edge detection operator over a small region about each point of the previously defined contour, to determine any shifts in the field shape in the new image. Failure of this edge check indicates that a significant change in the field edge has occurred, and the original edge detection routine is applied to the image. Otherwise the modified edge contour is used to define the new edge.

RESULTS

Two hundred and eighty-one portal images collected from an electronic portal imaging device were processed by the edge detection routine. The algorithm accurately calculated each portal field edge, as well as reducing processing time in subsequent fractions of an individual portal field by a factor of up to 14.

CONCLUSIONS

The heuristic edge detection routine is an accurate and fast method for calculating portal field edges and determining field edge setup errors.

An evaluation of setup uncertainties for patients treated to pelvic sites

PURPOSE

Successful delivery of conformal fields requires stringent immobilization and treatment verification, as well as knowledge of the setup reproducibility. The purpose of this study was to compare the three-dimensional distribution of setup variations for patients treated to pelvic sites with electronic portal imaging devices (EPID) and portal film.

METHODS AND MATERIALS

Nine patients with genitourinary and gynecological cancers immobilized with custom casts and treated with a four-field whole-pelvis technique were imaged daily using an EPID and filmed once every five to seven treatments. The three-dimensional translational and rotational setup errors were determined using a technique that relies on anatomical landmarks identified on simulation and treatment images. The distributions of the translational and rotational variations in each dimension as well as the total displacement of the treatment isocenter from the simulation isocenter were determined.

RESULTS

Grouped analysis of all patients revealed average unidirectional translational deviations of less than 2 mm and a standard deviation of 5.3 mm. The average total undirected distance between the treatment and simulated isocenters was 8.3 mm with a standard deviation of 5 mm. Individual patient analysis revealed eight of nine patients had statistically significant nonzero mean translational variations (p < 0.05). Translational variations measured with film were an average of 1.4 mm less than those measured with EPID, but this difference was not statistically significant.

CONCLUSION

Translational variations measured in this study are in general agreement with previous studies. The use of the EPID in this study was less intrusive and may have resulted in less additional attention being given each imaging setup. This may explain the slightly larger average translational variations observed with EPID vs. film, and suggests that the use of EPIDs is a superior method for assessing the true extent of setup displacements. Although no statistically significant translational variations for the patient group overall were observed, 90% of patients had significant translational variations in at least one direction when analyzed separately. The margin to be added to the clinical target volume (CTV) to account for setup uncertainties will depend on whether it is possible to identify patients with significant translational variations, and to eliminate these displacements from routine treatments. The choice to eliminate these variations and to use a smaller CTV margin will have to be accompanied by stringent frequent position verification methods and repositioning.

The use of clinical computer workstations as an educational adjunct in prosthodontics

Current computer systems improve the health professional's ability to store, retrieve, and present visual data in a way never before possible. Health professionals in general are beginning to use computer-based digital imaging to improve the diagnosis and treatment planning of disease processes. The use of computer-based networks to transmit medical and dental data is in its infancy but promises to be the main form of data transmission of the future. This article outlines a few applications presently being used and developed at the Ohio State University College of Dentistry in the preclinical and clinical courses in prosthodontics.

Picture archiving and communications systems in radiation oncology (PACSRO): tools for a physician-based digital image review system

Digital imaging is becoming more and more important in the diagnosis, staging, and treatment of patients in radiation oncology. In order to facilitate the most efficient interface of this technology to physicians and other users of this information, a medical image display system (MID) has been developed at the Fox Chase Cancer Center (FCCC). The system runs on 20 personal computers situated in physicians offices as well as a modified system located in the radiation oncology conference room. Access to CT, MRI, and EPID information is achieved through an Ethernet connection to the hospital picture archiving and communications system (PACS). Over a 1-year period a total of 503 patients and 3845 images have been stored on the system. Physician approval using the MID system (without conventional films) was performed on 106 patients. Of these, 22%, 16%, 11%, 10%, and 9% consisted of breast, prostate, pelvic, lung, and head and neck patients, respectively. Digital images sent from a variety of image sources to the MID system take up to 15 s to process and format while image access and display can take 2-5 s, dependent upon image size and speed of the host computer.