MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network
with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan
- URL: http://arxiv.org/abs/2304.01576v1
- Date: Tue, 4 Apr 2023 07:05:15 GMT
- Title: MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network
with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan
- Authors: Muhammad Usman, Azka Rehman, Abdullah Shahid, Siddique Latif, Shi Sub
Byon, Sung Hyun Kim, Tariq Mahmood Khan, and Yeong Gil Shin
- Abstract summary: We propose an efficient end-to-end framework, the multi-encoder-based self-adaptive hard attention network (MESAHA-Net) for precise lung nodule segmentation in CT scans.
MESAHA-Net iteratively performs slice-by-slice 2D segmentation of lung nodules, focusing on the nodule region in each slice to generate 3D segmentation of lung nodules.
The proposed framework has been evaluated on the LIDC-IDRI dataset, the largest publicly available dataset for lung nodule segmentation.
- Score: 6.266053305874546
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Accurate lung nodule segmentation is crucial for early-stage lung cancer
diagnosis, as it can substantially enhance patient survival rates. Computed
tomography (CT) images are widely employed for early diagnosis in lung nodule
analysis. However, the heterogeneity of lung nodules, size diversity, and the
complexity of the surrounding environment pose challenges for developing robust
nodule segmentation methods. In this study, we propose an efficient end-to-end
framework, the multi-encoder-based self-adaptive hard attention network
(MESAHA-Net), for precise lung nodule segmentation in CT scans. MESAHA-Net
comprises three encoding paths, an attention block, and a decoder block,
facilitating the integration of three types of inputs: CT slice patches,
forward and backward maximum intensity projection (MIP) images, and region of
interest (ROI) masks encompassing the nodule. By employing a novel adaptive
hard attention mechanism, MESAHA-Net iteratively performs slice-by-slice 2D
segmentation of lung nodules, focusing on the nodule region in each slice to
generate 3D volumetric segmentation of lung nodules. The proposed framework has
been comprehensively evaluated on the LIDC-IDRI dataset, the largest publicly
available dataset for lung nodule segmentation. The results demonstrate that
our approach is highly robust for various lung nodule types, outperforming
previous state-of-the-art techniques in terms of segmentation accuracy and
computational complexity, rendering it suitable for real-time clinical
implementation.
Related papers
- Enhancing Weakly Supervised 3D Medical Image Segmentation through
Probabilistic-aware Learning [52.249748801637196]
3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning.
Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation.
We propose a novel probabilistic-aware weakly supervised learning pipeline, specifically designed for 3D medical imaging.
arXiv Detail & Related papers (2024-03-05T00:46:53Z) - SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped
Domain Attention [47.44114201293201]
Lung cancer is the leading cause of cancer death worldwide.
Current pulmonary nodule detection methods are usually domain-specific.
We propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks.
arXiv Detail & Related papers (2023-03-07T03:17:49Z) - Lung nodules segmentation from CT with DeepHealth toolkit [6.980270783615686]
The goal of this study was to demonstrate the feasibility of Deephealth toolkit including PyECVL and PyEDDL libraries to precisely segment lung nodules.
The results depict accurate segmentation of lung nodules across a wide diameter range and better accuracy over a traditional detection approach.
arXiv Detail & Related papers (2022-08-01T06:54:12Z) - Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule
Augmentation and Detection [52.93342510469636]
Lung nodule detection in chest X-ray (CXR) images is common to early screening of lung cancers.
Deep-learning-based Computer-Assisted Diagnosis (CAD) systems can support radiologists for nodule screening in CXR.
To alleviate the limited availability of such datasets, lung nodule synthesis methods are proposed for the sake of data augmentation.
arXiv Detail & Related papers (2022-07-19T16:38:48Z) - Improving Classification Model Performance on Chest X-Rays through Lung
Segmentation [63.45024974079371]
We propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations.
Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.
arXiv Detail & Related papers (2022-02-22T15:24:06Z) - Pulmonary Vessel Segmentation based on Orthogonal Fused U-Net++ of Chest
CT Images [1.8692254863855962]
We present an effective framework and refinement process of pulmonary vessel segmentation from chest computed tomographic (CT) images.
The key to our approach is a 2.5D segmentation network applied from three axes, which presents a robust and fully automated pulmonary vessel segmentation result.
Our method outperforms other network structures by a large margin and achieves by far the highest average DICE score of 0.9272 and precision of 0.9310.
arXiv Detail & Related papers (2021-07-03T21:46:29Z) - Accurate Lung Nodules Segmentation with Detailed Representation Transfer
and Soft Mask Supervision [19.64536342490214]
Smallness and variety of lung nodules make accurate lung nodule segmentation difficult.
We introduce a novel segmentation mask named Soft Mask which has richer and more accurate edge details description.
A novel Network with detailed representation transfer and Soft Mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results.
arXiv Detail & Related papers (2020-07-29T02:38:02Z) - Deep Residual 3D U-Net for Joint Segmentation and Texture Classification
of Nodules in Lung [91.3755431537592]
We present a method for lung nodules segmentation, their texture classification and subsequent follow-up recommendation from the CT image of lung.
Our method consists of neural network model based on popular U-Net architecture family but modified for the joint nodule segmentation and its texture classification tasks and an ensemble-based model for the follow-up recommendation.
arXiv Detail & Related papers (2020-06-25T07:20:41Z) - A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced
Cardiac Magnetic Resonance Imaging [90.29017019187282]
" 2018 Left Atrium Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset.
Analyse of the submitted algorithms using technical and biological metrics was performed.
Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm.
arXiv Detail & Related papers (2020-04-26T08:49:17Z) - U-Det: A Modified U-Net architecture with bidirectional feature network
for lung nodule segmentation [0.0]
This article proposes U-Det, a resource-efficient model architecture, which is an end to end deep learning approach to solve the task at hand.
The proposed model is extensively trained and evaluated on the publicly available LUNA-16 dataset consisting of 1186 lung nodules.
The U-Det architecture outperforms the existing U-Net model with the Dice similarity coefficient (DSC) of 82.82% and achieves results comparable to human experts.
arXiv Detail & Related papers (2020-03-20T14:25:22Z) - Volumetric Lung Nodule Segmentation using Adaptive ROI with Multi-View
Residual Learning [2.8145631839076004]
The proposed approach has been rigorously evaluated on the LIDC dataset.
The result suggests that the approach is significantly robust and accurate as compared to the previous state of the art techniques.
arXiv Detail & Related papers (2019-12-31T15:03:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.