Interpretable deep learning insights: Unveiling the role of 1 Gy volume on lymphopenia after radiotherapy in breast cancer.

BACKGROUND: Lymphopenia is known for its significance on poor survivals in breast cancer patients. Considering full dosimetric data, this study aimed to develop and validate predictive models for lymphopenia after radiotherapy (RT) in breast cancer. MATERIAL AND METHODS: Patients with breast cancer treated with adjuvant RT were eligible in this multicenter study. The study endpoint was lympopenia, defined as the reduction in absolute lymphocytes and graded lymphopenia after RT. The dose-volume histogram (DVH) data of related critical structures and clinical factors were taken into account for the development of dense neural network (DNN) predictive models. The developed DNN models were validated using external patient cohorts. RESULTS: A total of 918 consecutive patients with invasive breast cancer enrolled. The training, testing, and external validating datasets consisted of 589, 203, and 126 patients, respectively. Treatment volumes at nearly all dose levels of the DVH were significant predictors for lymphopenia following RT, including volumes at very low-dose 1 Gy (V1) of organs at risk (OARs) including lung, heart and body, especially ipsilateral-lung V1. A final DNN model, combining full DVH dosimetric parameters of OARs and three key clinical factors, achieved a predictive accuracy of 75 % or higher. CONCLUSION: This study demonstrated and externally validated the significance of full dosimetric data, particularly the volume of low dose at as low as 1 Gy of critical structures on lymphopenia after radiation in patients with breast cancer. The significance of V1 deserves special attention, as modern VMAT RT technology often has a relatively high value of this parameter. Further study is warranted for RT plan optimization.

Prospect of radiotherapy technology development in the era of immunotherapy.

Radiotherapy (RT) is one of the important modalities for cancer treatments. Mounting evidence suggests that the host immune system is involved in the tumor cell killing during RT, and future RT technology development should aim to minimize radiation dose to the immune system while maintaining a sufficient dose to the tumor. A brief history of RT technology development is first summarized. Three RT technologies, namely FLASH RT, proton therapy, and spatially fractionated RT (SFRT), are singled out for the era of immunotherapy. Besides the technical aspects, the mechanism of FLASH effect is discussed, which is likely the combined results of the recombination effect, oxygen depletion effect and immune sparing effect. The proton therapy should have the advantage of causing much less immune damage in comparison to X-ray based RT due to the Bragg peak. However, the relative biological effectiveness (RBE) uncertainty and range uncertainty may hinder the translation of this advantage into clinical benefit. Research approaches to overcome these two technical hurdles are discussed. Various SFRT approaches and their application are reviewed. These approaches are categorized as single-field 1D/2D SFRT, multi-field 3D SFRT and quasi-3D SFRT techniques. A 3D SFRT approach, which is achieved by placing the Bragg peak of a proton 2D SFRT field in discrete depths, may have special potential because all 3 technologies (FLASH RT, proton therapy and SFRT) may be used in this approach.