Back to all available

SHAP-Enhanced ultrasound radiomics for assessing pathological complete response to neoadjuvant chemotherapy in breast cancer

oncology
radiology-and-medical-imaging

Abstract

Objective: This study aimed to develop an interpretable ultrasound radiomics model, using SHapley Additive exPlanations (SHAP) analysis, to predict pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer patients by integrating imaging features and clinical data.

Methods: A total of 131 breast cancer patients who underwent preoperative NAC were enrolled and randomly assigned to a training set (n =  91 ) and a test set (n =  40 ) at a ratio of 7:3. P re-NAC aPre-NAC treatment 2 cycles ultrasound images were collected, and radiomic features were extracted and screened from pre-treatment to post-treatment, Deand lta ((prpre-treatment-post-treatmentpre - treatment ) images. Logistic regression (LR ) was used to construct pre-treatment radiomics ( PreRad), post-treatment radiomics (PostRad), Delta radiomics ( DeltaRad ), and clinic models to predict the efficacy of NAC. The SHAP method explained the LR model by prioritizing the importance of features in terms of assessment contribution.

Results: The DltaRad model demonstrated the highest performance (among PreRad, PostRad, and DeltaRad models ), with an AUC of 0.882 in the training set and 0.758 in the test sets. The combined model, integrating DeltaRad features and clinical information, achieved an AUC of 0.951 in the training sets and 0.898 in the test sets. This model outperformed those based solely on clinical information or other radiomic features. The SHAP scatter plot illustrated that the feature’s value affected the feature’s impact attributed to the model, and the SHAP waterfall chart showed the integration of features’ impact attributed to individual response.

Conclusion: The combined model, interpreted using the SHAP method, can effectively assess pCR in breast cancer patients undergoing NAC, providing understandable guidance for personalized treatment strategies.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].