PaperlayerView exact revision on arXiv

Source-linked AI summary

MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation

Yu Qiu, Yun Liu, Shijie Li, Jing Xu

arXiv:2004.09750v3cs.CV

TL;DR

Limited COVID-19 training data and the computational demands of traditional segmentation hinder efficient CT-based screening. The paper proposes MiniSeg, an 83K-parameter lightweight network using AHSP multi-scale learning, and builds a benchmark for comparison. MiniSeg achieves favorable performance against previous state-of-the-art methods with high efficiency, while showing DSC above 0.7 for most slices and median DSC above 0.8 across lesion counts on COVID-19-P20.

  • Problem

    Limited COVID-19 training data can cause overfitting in traditional data-hungry models, while computationally intensive methods hinder fast training, testing, and deployment.

    Source: Introduction · p. 1

  • Method

    MiniSeg is an 83K-parameter lightweight segmentation network incorporating the AHSP module for multi-scale learning and accompanied by a comprehensive COVID-19 segmentation benchmark.

    Source: Introduction · p. 2

  • Results

    MiniSeg performs favorably against previous state-of-the-art segmentation methods with high efficiency; on COVID-19-P20, DSC exceeds 0.7 for most slices and median DSC exceeds 0.8 regardless of lesion counts.

    Source: Quantitative Evaluation · p. 6, Qualitative Comparison · p. 7, Statistical Analysis · p. 7

  • Takeaways & Limitations

    MiniSeg provides an efficient COVID-19 infected-area segmentation approach designed for limited training data and practical screening-system deployment.

    Source: Introduction · p. 2, Conclusion · p. 7

Abstract

from arXiv · show

The rapid spread of the new pandemic, i.e., COVID-19, has severely threatened global health. Deep-learning-based computer-aided screening, e.g., COVID-19 infected CT area segmentation, has attracted much attention. However, the publicly available COVID-19 training data are limited, easily causing overfitting for traditional deep learning methods that are usually data-hungry with millions of parameters. On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional deep learning methods are usually computationally intensive. To address the above problems, we propose MiniSeg, a lightweight deep learning model for efficient COVID-19 segmentation. Compared with traditional segmentation methods, MiniSeg has several significant strengths: i) it only has 83K parameters and is thus not easy to overfit; ii) it has high computational efficiency and is thus convenient for practical deployment; iii) it can be fast retrained by other users using their private COVID-19 data for further improving performance. In addition, we build a comprehensive COVID-19 segmentation benchmark for comparing MiniSeg to traditional methods.

Introduction

COVID-19 screening needs computer-aided CT interpretation because RT-PCR sensitivity is limited and experienced radiologists are scarce. MiniSeg addresses limited training data and deployment constraints through lightweight multi-scale learning, an 83K-parameter network, and a benchmark for comparison.

Motivation

  • Limited COVID-19 data can cause overfitting in traditional deep-learning models with millions of parameters.Traditional segmentation methods are also computationally intensive, making fast training/testing and low computational load important for screening-system deployment.Source: Introduction · p. 1
  • Lightweight networks are proposed to reduce overfitting risk and computational cost while preserving accurate segmentation through multi-scale learning.The paper identifies effective multi-scale learning as a way to improve segmentation accuracy under parameter and efficiency constraints.Source: Introduction · p. 1

Method

  • AHSP performs lightweight multi-scale learning using dilated depthwise separable convolutions, feature pooling, hierarchical fusion, and attention-guided feature merging.The attention mechanism highlights essential information and filters noisy information in radiography images.Source: Introduction · p. 1

Contributions

  • 83K parameters make MiniSeg two orders of magnitude smaller than traditional image segmentation methods.The authors state that the limited COVID-19 data can therefore be sufficient for training MiniSeg.Source: Introduction · p. 2
  • The paper builds a comprehensive COVID-19 segmentation benchmark to compare MiniSeg extensively with previous methods.The benchmark is presented as a resource for evaluating segmentation approaches under the paper’s target setting.Source: Introduction · p. 2

Related Work

Prior segmentation methods emphasize multi-scale representation and accuracy but often overlook model size and inference speed. Lightweight architectures reduce computational complexity, motivating COVID-19 segmentation methods that improve accuracy and speed within a lightweight setting.

Multi-scale segmentation

  • Encoder-decoder networks, dilated-convolution ASPP modules, pyramid pooling, context encoding, and non-local operations are used to learn multi-scale or global-context representations.These approaches primarily target segmentation accuracy without considering model size and inference speed.Source: Related Work · p. 2

Lightweight networks

  • Lightweight networks reduce parameters and improve efficiency through convolutional factorization, including depthwise separable, grouped, and channel-shuffle operations.Examples include Flattened Model, Inception, Xception, MobileNets, and ShuffleNets.Source: Related Work · p. 2

Lightweight segmentation

  • Efficient semantic-segmentation research provides relevant designs for reducing computational cost in segmentation networks.The paper positions its COVID-19 goal as achieving higher accuracy and faster speed by enhancing multi-scale learning in a lightweight setting.Source: Related Work · p. 2

COVID-19 screening

  • COVID-19 screening studies commonly classify chest X-rays or CT slices, while Fan et al. proposed CT infected-area segmentation but remained within the category of previous segmentation methods.The paper presents this prior segmentation approach as suboptimal relative to its lightweight objective.Source: Related Work · p. 2

Methodology

MiniSeg combines the AHSP module with an encoder-decoder architecture to learn multi-scale features efficiently for COVID-19 CT segmentation. Its design uses dilated depthwise separable convolutions, hierarchical aggregation, spatial attention, and lightweight feature fusion.

Attentive Hierarchical Spatial Pyramid Module

  • AHSP builds multi-scale features with parallel dilated depthwise separable convolutions and pooling, then aggregates them hierarchically.Large and small dilation rates capture contextual and local information, respectively.Source: Attentive Hierarchical Spatial Pyramid… · p. 3
  • Spatial attention weights each scale to emphasize target structures and suppress irrelevant information during multi-scale learning.The attention map is generated by a pointwise convolution and sigmoid activation before element-wise multiplication with each feature map.Source: Attentive Hierarchical Spatial Pyramid… · p. 3
  • AHSP uses grouped pointwise convolution to fuse hierarchical feature maps, reducing Eqn. 8 parameters from C′2 to C′2/K.This design separately fuses feature branches and reduces the number of convolution parameters by K times compared with vanilla pointwise convolution.Source: Attentive Hierarchical Spatial Pyramid… · p. 3

MiniSeg Network Architecture

  • MiniSeg uses an encoder-decoder structure in which the encoder learns multi-scale representations and the decoder aggregates representations across levels.The decoder combines high-level semantic features with low-level fine details for infected-area prediction.Source: Network Architecture · p. 3
  • The encoder uses AHSP blocks, nested skip pathways, and four downsampled scales, while the decoder produces dense two-class predictions with deep supervision.The four encoder scales are 1/2, 1/4, 1/8, and 1/16; the prediction classes are background and COVID-19.Source: Network Architecture · pp. 4–5

Experimental Setup

MiniSeg is evaluated on four open-access COVID-19 CT segmentation datasets using standardized training, augmentation, cross-validation, and medical-imaging metrics.

Training

  • All methods use PyTorch, Adam optimization, 80 training epochs, batch size 5, and identical training settings for fair comparison.The initial learning rate is 1e-3 with weight decay of 1e-4 and a poly learning-rate policy.Source: Implementation details · p. 5

Datasets

  • Four open-access COVID-19 CT segmentation datasets are used to evaluate MiniSeg and the baselines.The datasets are renamed COVID-19-CT100, COVID-19-P9, COVID-19-P20, and COVID-19-P1110.Source: Dataset · p. 5

Evaluation Protocol

  • Standard cropping and random flipping augment the training data, while 5-fold cross-validation reduces statistically significant differences in performance evaluation.Source: Dataset · p. 5

Metrics

  • Performance is measured using mIoU, SEN, SPC, DSC, and HD, where higher values are better except for HD.mIoU, SEN, SPC, and DSC range from 0 to 1, whereas lower HD indicates better segmentation accuracy.Source: Evaluation metrics · p. 5

Ablation Studies

Ablation experiments evaluate MiniSeg’s main components and design choices, with results supporting the effectiveness of its complete architecture.

Main Components

  • Adding multi-scale branches, attentive hierarchical fusion, the two-path encoder, and channel splitting produces the final MiniSeg configuration.The ablation sequence begins with a single-branch module and progressively adds the main architectural components.Source: Effect of main components · pp. 5–6
  • The ablation studies conclude that MiniSeg’s main components are all effective for COVID-19 segmentation.Source: Effect of main components · p. 6

Design Choices

  • The default setting achieves the best overall performance across tested activation, decoder, supervision, convolution, and feature-fusion alternatives.The evaluated choices include PReLU versus ReLU, decoder removal, deep-supervision removal, AHSP substitutions, kernel-size changes, and FFM replacements.Source: Effect of some design choices · p. 6

Comparison with State-of-the-art Methods

MiniSeg is compared with 31 previous state-of-the-art segmentation methods through computational, numerical, qualitative, and statistical analyses across COVID-19 datasets.

Benchmark

  • The benchmark contains 31 previous state-of-the-art image segmentation methods for extensive comparison with MiniSeg.Source: Quantitative Evaluation · p. 6

Efficiency

  • MiniSeg has extremely small parameter and FLOP counts and is much faster than competing methods.The comparison covers parameters, FLOPs, and speed.Source: Quantitative Evaluation · p. 6

Quantitative Results

  • MiniSeg achieves the best or close-to-best performance across all metrics and datasets, with limited exceptions for SPC and SEN.It is slightly below the best SPC method on COVID-19-CT100 and COVID-19-P9, and does not achieve the best SEN on COVID-19-P1110.Source: Quantitative Evaluation · p. 6

Qualitative Results

  • Visual comparisons against eight state-of-the-art methods further indicate that MiniSeg outperforms the baseline methods.Figure 4 encodes true positives in red, false negatives in green, and false positives in blue.Source: Qualitative Comparison · p. 7, Figure 4 · p. 7

Statistical Analysis

  • On COVID-19-P20, most CT slices have DSC above 0.7 regardless of infected area, while median DSC exceeds 0.8 regardless of lesion count.Source: Statistical Analysis · p. 7

Conclusion

MiniSeg addresses limited COVID-19 training data and deployment efficiency through an extremely small network with AHSP-based multi-scale learning and a comprehensive benchmark.

Conclusion

  • MiniSeg uses the AHSP module to support accurate and efficient COVID-19 infected-area segmentation under an extremely small network-size constraint.Source: Conclusion · p. 7
  • The benchmark compares MiniSeg extensively with previous state-of-the-art methods and is intended to support future COVID-19 segmentation research.Source: Conclusion · p. 7
  • Comparison with state-of-the-art methods demonstrates that MiniSeg combines best performance with high efficiency for practical deployment.Source: Conclusion · p. 7

Related papers

Loading 2004.09750v3…