The holiday season is a time of recharging, reflecting, and often also reading. Since our hearts pump for improving radiotherapy with AI throughout the year, our holiday readings also include a paper or two on the topic. As a gift to you, we have put together a little list of such publications. Enjoy!
Radiotherapy treatment planning in the age of AI
Are artificial intelligence and the use of it in radiotherapy something you are not yet that familiar with? Or maybe you understand the basics of AI in a different setting but are a bit skeptical about it in terms of radiation oncology?
A way to take a bit better look at the topic could be to check out an article by Dandan Zheng, Julian C. Hong, Chunhao Wang, and Xiaofeng Zhu. Published at the end of 2019, it generally recaps AI in radiotherapy, and the key points are as relevant as ever. The article reviews what the biggest impacts of AI algorithms are and the potential of automation in radiotherapy. Not to forget also the challenges we have to keep in mind. It also touches on the topic of how harnessing AI does not pose threat to jobs but the contrary: it is a tool that has the potential to optimize the valuable time of clinicians resulting in better plans for patients. You can find the article here.
As we learn from the article by Zheng et al. (2019), time save is indeed a very important and straightforward impact of harnessing AI in radiotherapy. But what else? Proper automation of time-consuming manual tasks such as contouring makes it also possible to standardize the processes to a completely new extent. We at MVision lift standardization to be the key element in improving radiotherapy treatment planning for both clinicians and patients.
You don’t have to take our word for it. Here are some inter-observer studies that back up the need for, you guessed it, contouring standardization:
Radiotherapy and radiology: Joint efforts for modern radiation planning and practice by Thariat et al. published in 2012
Automatic delineation for replanning in nasopharynx radiotherapy: What is the agreement among experts to be considered as a benchmark? by Mattiucci et al. published in 2013
Deep deconvolutional neural network for target segmentation of nasopharyngeal cancer in planning computed tomography images by Men et al. published in 2017.
Evaluation of AI-based contouring tools in prostate cancer RT
Anni Borkvel, Eduard Gershkevitsh, Merve Adamson, Kati Kolk, and Daniil Zolotuhhin from North Estonia Medical Centre studied the accuracy and efficiency gain for prostate cancer patient contouring when using AI-based contouring tools. The study included the assessment of results from two vendors and included MVision AI segmentation service as the other. You can read the poster itself or check out a presentation by one of the writers, Anni Borkvel, held at ESTRO 2020.
Evaluation of deep learning to augment image-guided radiotherapy for head and neck and prostate cancers
Published this year by Ozan Oktay et al., the paper explores clinically acceptable auto contouring solutions that can be integrated into existing workflows and used in different domains of radiotherapy. The results were evident: auto-segmentation poses significant opportunities for the transformation of radiation treatment planning. Furthermore, the study found that the approach overall contributes to the practical challenges of scalable adoption across health care systems.
Don’t forget to read also our recently published paper A Deep Learning-Based Automated CT Segmentation of Prostate Cancer Anatomy for Radiation Therapy Planning – A Retrospective Multicenter Study. You can find it here.
The references in the text above:
- Zheng, Dandan, et al. “Radiotherapy Treatment Planning in the Age of AI: Are We Ready Yet?.” (2019): 1533033819894577.
- Thariat, Juliette, et al. “Radiotherapy and radiology: joint efforts for modern radiation planning and practice.” Diagnostic and Interventional Imaging 93.5 (2012): 342-350.
- Mattiucci, GIan Cario, et al. “Automatic delineation for replanning in nasopharynx radiotherapy: what is the agreement among experts to be considered as benchmark?.” Acta Oncologica 52.7 (2013): 1417-1422.
- Awan, Musaddiq, et al. “Auto-segmentation of the brachial plexus assessed with TaCTICS–A software platform for rapid multiple-metric quantitative evaluation of contours.” Acta Oncologica 54.4 (2015): 562-566.
- Men, Kuo, et al. “Deep deconvolutional neural network for target segmentation of nasopharyngeal cancer in planning computed tomography images.” Frontiers in oncology 7 (2017): 315.
- Oktay O, Nanavati J, Schwaighofer A, et al. Evaluation of Deep Learning to Augment Image-Guided Radiotherapy for Head and Neck and Prostate Cancers. JAMA Netw Open. 2020;3(11):e2027426. doi:10.1001/jamanetworkopen.2020.27426
- Kiljunen, Timo, et al. “A Deep Learning-Based Automated CT Segmentation of Prostate Cancer Anatomy for Radiation Therapy Planning-A Retrospective Multicenter Study.” Diagnostics 10.11 (2020): 959.