iW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network

Aresta, Guilherme; Jacobs, Colin; Araújo, Teresa; Cunha, António; Ramos, Isabel; Ginneken, Bram van; Campilho, Aurélio

doi:10.1038/s41598-019-48004-8

Cited by 63 publications

(46 citation statements)

References 16 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…DL has shown excellent performance in image segmentation and image classification (93,94). The excellent performance of DL algorithms has been reported in the segmentation of various anatomic structures in chest CTs, including the lung parenchyma (95,96), pulmonary lobes (97), airways (98), and lung nodules (99,100).…”

Section: Applications Of Ai In Quantitative Imaging Analyses Segmentamentioning

confidence: 95%

Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges

Hwang

Park

2020

Korean J Radiol

View full text Add to dashboard Cite

Chest X-ray radiography and computed tomography, the two mainstay modalities in thoracic radiology, are under active investigation with deep learning technology, which has shown promising performance in various tasks, including detection, classification, segmentation, and image synthesis, outperforming conventional methods and suggesting its potential for clinical implementation. However, the implementation of deep learning in daily clinical practice is in its infancy and facing several challenges, such as its limited ability to explain the output results, uncertain benefits regarding patient outcomes, and incomplete integration in daily workflow. In this review article, we will introduce the potential clinical applications of deep learning technology in thoracic radiology and discuss several challenges for its implementation in daily clinical practice.

show abstract

Section: Applications Of Ai In Quantitative Imaging Analyses Segmentamentioning

confidence: 95%

Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges

Hwang

Park

2020

Korean J Radiol

View full text Add to dashboard Cite

show abstract

“…We consider nodules annotated by at least 3 out of 4 radiologists the ground truth, resulting in a total number of 586 CT scans with 1131 nodules. Note that the number of CT scans and nodules included in this work may be different from previous work [17,18,1], due to different inclusion criteria.…”

Section: Resultsmentioning

confidence: 99%

“…Also, this work focuses on the joint learning of nodule detection and segmentation, whereas the LUNA16 focuses only on nodule detection. Nodule segmentation performance In Table 2, we compared the segmentation performance of NoduleNet to other deep learning based methods trained and tested on LIDC dataset [17,18,1]. NoduleNet outperformed previous stateof-the-art deep learning based method by 0.95% on DSC, without the need to train a separate and dedicated 3D DCNN for nodule segmentation.…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, the refinement provided by the extra classifiers may correct some errors made by the detectors. In terms of nodule segmentation, U-Net [13] and V-Net [11] like structure is predominantly used [17,18,1]. In practice, a computer aided diagnosis (CAD) system for pulmonary nodule detection and segmentation often consists of several independent subsystems, optimized separately.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation

Tang¹,

Zhang²,

Xie³

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Pulmonary nodule detection, false positive reduction and segmentation represent three of the most common tasks in the computer aided analysis of chest CT images. Methods have been proposed for each task with deep learning based methods heavily favored recently. However training deep learning models to solve each task separately may be sub-optimal -resource intensive and without the benefit of feature sharing. Here, we propose a new end-to-end 3D deep convolutional neural net (DCNN), called NoduleNet, to solve nodule detection, false positive reduction and nodule segmentation jointly in a multi-task fashion. To avoid friction between different tasks and encourage feature diversification, we incorporate two major design tricks: 1) decoupled feature maps for nodule detection and false positive reduction, and 2) a segmentation refinement subnet for increasing the precision of nodule segmentation. Extensive experiments on the large-scale LIDC dataset demonstrate that the multi-task training is highly beneficial, improving the nodule detection accuracy by 10.27%, compared to the baseline model trained to only solve the nodule detection task. We also carry out systematic ablation studies to highlight contributions from each of the added components. Code is available at https://github.com/uci-cbcl/NoduleNet.

show abstract

“…Based on the encoder-decoder structure of U-Net, some approaches apply it to the organ segmentation task in a cascaded fashion [5], [27], [33], [35]- [37]. Cascading networks is a classic and effective way to improve the performance.…”

Section: Introductionmentioning

confidence: 99%

Block Level Skip Connections Across Cascaded V-Net for Multi-Organ Segmentation

Zhang

Shen

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Multi-organ segmentation is a challenging task due to the label imbalance and structural differences between different organs. In this work, we propose an efficient cascaded V-Net model to improve the performance of multi-organ segmentation by establishing dense Block Level Skip Connections (BLSC) across cascaded V-Net. Our model can take full advantage of features from the first stage network and make the cascaded structure more efficient. We also combine stacked small and large kernels with an inception-like structure to help our model to learn more patterns, which produces superior results for multi-organ segmentation. In addition, some small organs are commonly occluded by large organs and have unclear boundaries with other surrounding tissues, which makes them hard to be segmented. We therefore first locate the small organs through a multi-class network and crop them randomly with the surrounding region, then segment them with a single-class network. We evaluated our model on SegTHOR 2019 challenge unseen testing set and Multi-Atlas Labeling Beyond the Cranial Vault challenge validation set. Our model has achieved an average dice score gain of 1.62 percents and 3.90 percents compared to traditional cascaded networks on these two datasets, respectively. For hard-to-segment small organs, such as the esophagus in SegTHOR 2019 challenge, our technique has achieved a gain of 5.

show abstract

iW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network

Cited by 63 publications

References 16 publications

Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges

Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges

NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation

Block Level Skip Connections Across Cascaded V-Net for Multi-Organ Segmentation

Contact Info

Product

Resources

About