Back to all available

Adaptive anisotropic convolutional network for renal neoplasm segmentation: A deep learning framework with directional feature learning

algorithms-and-analysis-of-algorithms
artificial-intelligence
computer-vision
scientific-computing-and-simulation
neural-networks

Abstract

Accurate segmentation of kidneys and renal tumors in CT images is crucial for the diagnosis of renal cancer. However, abdominal CT scans often exhibit anisotropic resolution between axial and cross-sectional directions. Conventional 3D convolutions assume isotropy, which leads to feature misalignment and degraded segmentation performance. To address this issue, we propose an adaptive anisotropic convolution module that integrates spatially separable convolution with standard 3D convolution through a dynamic selection mechanism. This adaptive fusion enhances feature extraction in anisotropic contexts. Furthermore, we design a deep 3D U-Net incorporating the proposed module and introduce cross-scale feature fusion in the encoder to mitigate detail loss during downsampling. Evaluated on the KiTS19 dataset (90 test cases). Our method achieves Dice scores of 97.04% for kidney and 85.10% for tumor segmentation, surpassing the baseline 3D U-Net by 1.19 and 3.30 percentage points, respectively, and outperforming state-of-the-art models such as nnFormer, 3DUX-Net, and SegMamba. These results demonstrate that our network significantly improves segmentation accuracy and offers robust technical support for renal cancer diagnosis.
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 Computer Science 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].