CT Liver Segmentation via PVT-based Encoding and Refined Decoding

TL;DR

This paper introduces PVTFormer, a novel deep learning model based on a pretrained pyramid vision transformer, designed for accurate liver segmentation from CT scans, achieving state-of-the-art results on the LiTS 2017 benchmark.

Contribution

The paper presents PVTFormer, combining PVT v2 with residual upsampling and hierarchical decoding, a novel architecture for improved liver segmentation accuracy.

Findings

Achieved a dice coefficient of 86.78% on LiTS 2017

Attained a mean Intersection over Union (mIoU) of 78.46%

Obtained a Hausdorff Distance of 3.50, indicating precise segmentation

Abstract

Accurate liver segmentation from CT scans is essential for effective diagnosis and treatment planning. Computer-aided diagnosis systems promise to improve the precision of liver disease diagnosis, disease progression, and treatment planning. In response to the need, we propose a novel deep learning approach, \textit{\textbf{PVTFormer}}, that is built upon a pretrained pyramid vision transformer (PVT v2) combined with advanced residual upsampling and decoder block. By integrating a refined feature channel approach with a hierarchical decoding strategy, PVTFormer generates high quality segmentation masks by enhancing semantic features. Rigorous evaluation of the proposed method on Liver Tumor Segmentation Benchmark (LiTS) 2017 demonstrates that our proposed architecture not only achieves a high dice coefficient of 86.78\%, mIoU of 78.46\%, but also obtains a low HD of 3.50. The results underscore PVTFormer's efficacy in setting a new benchmark for state-of-the-art liver segmentation methods. The source code of the proposed PVTFormer is available at \url{https://github.com/DebeshJha/PVTFormer}.