Quantitative Analysis of Radiation-Associated Parenchymal Lung Change

Round 1

Reviewer 1 Report

Dear authors,

thank you very much for this interesting article concerning radiation-induced lung tissue changes. Radiotherapy plays an integral part of lung cancer treatment wordwide and radiation-induced pneumonitis and lung fibrosis are one of the most common side effects. The authors developed a new classification of lung tissue damages based on thoracic CT scans. The manuscript is well written and needs only minor issues to be corrected:

Introduction:

Please include a paragraph about the pathomechanism of radiation-induced lung fibrosis e.g.

doi: 10.1038/s41419-020-02846-7.

doi: 10.1186/s13014-020-01654-9.

doi: 10.1016/j.ijrobp.2004.12.072.

Results/Discussion part:

Very clear with good argumentation. Well done.

The manuscript presents a proof of principal study and needs further external Validation with state of the art treatment e.g. VMAT.

Author Response

Thank you very much for your kind review.

We have added a section to the introduction about the pathophysiology of RILD as you suggested.

Reviewer 2 Report

Title: Quantitative Analysis of Radiation-Associated Parenchymal Lung Change

Abstract

We present a novel classification system of the parenchymal features of Radiation Induced Lung Damage (RILD). We developed a deep learning network to automate the delineation of five classes of parenchymal textures. We quantify the volumetric change in classes after radiotherapy in order to allow detailed, quantitative descriptions of the evolution of lung parenchyma up to 24 months after RT, and correlate these with radiotherapy dose and respiratory outcomes. Diagnostic CTs were available pre-RT, and at 3, 6, 12 and 24-months post-RT, for forty-six subjects enrolled in a clinical trial of chemo-radiotherapy for non-small cell lung cancer. All 230 CT scans were segmented using our network. The five parenchymal classes showed distinct temporal patterns. Moderate correlation was seen between change in tissue class volume and clinical and dosimetric parameters e.g. Pearson correlation coefficient was ≤0.49 between V30 and change in Class 2 and was 0.39 between change in Class 1 and decline in FVC. The effect of local dose on tissue class revealed a strong dose-dependent relationship. Respiratory function measured by spirometry and MRC dyspnoea scores, after radiotherapy correlated with the measured radiological RILD. We demonstrate the potential of using our approach to analyse and understand the morphological and functional evolution of RILD in greater detail than previously possible.

General Comments:

Title: appropriate for the manuscript

Abstracts: concise/brief but inclusive of the general content of the manuscript

Methodology/protocol: the methods were appropriate and described in detail

Results: appropriately aligned/correlated with the methods; Tables and Figures are supportive

Discussion/Conclusion: supported by the results

                                    : “The parenchymal tissue classes we developed are related to both ‘global and local dose’ metrics, and--------“Isn’t this rather speculative?”

Author Response

Thank you very much for your kind review of our study.

As per your suggestion, we have amended one of the lines in the conclusion so as to not overstate what we have achieved.