Bridging Computational Features Toward Multiple Semantic Features with Multi-task Regression: A Study of CT Pulmonary Nodules

Chen, Sihong; Ni, Dong; Qin, Jing; Lei, Bai Ying; Wang, Tianfu; Cheng, Jie-Zhi

doi:10.1007/978-3-319-46723-8_7

Cited by 19 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pulmonary nodules with different malignant phenotypes exhibited a number of morphological characteristics. In the LIDC-IDRI dataset, the malignant phenotype of the lung nodules was quantified by the physician using specific numbers and the quantification range was set to 1-5, according to the definition of dataset (14,16). The probability of malignancy was indicated as follows: i) Malignancy 1, high probability of being benign; ii) malignancy 2, moderate probability of being benign; iii) malignancy 3, indeterminate probability being benign; iv) malignancy 4, moderate probability of being malignant; and v) malignancy 5, high probability of being malignant.…”

Section: Methodsmentioning

confidence: 99%

“…Concomitantly, physical examination and imaging of lung nodules is becoming increasingly onerous and presents a major challenge for physicians, affecting the diagnostic classification accuracy (Acc) of lung nodules. The continuous development of machine learning has enabled the application of advanced learning techniques in the research and diagnosis of a number of diseases (8)(9)(10)(11)(12)(13)(14)(15)(16)(17). The information derived from lung nodule image data can be combined with machine learning in order to investigate the association between lung cancer incidence and clinicopathological features (18).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images

et al. 2020

View full text Add to dashboard Cite

Early identification and classification of pulmonary nodules are essential for improving the survival rates of individuals with lung cancer and are considered to be key requirements for computer-assisted diagnosis. To address this topic, the present study proposed a method for predicting the malignant phenotype of pulmonary nodules based on weighted voting rules. This method used the pulmonary nodule regions of interest as the input data and extracted the features of the pulmonary nodules using the Denoising Auto Encoder, ResNet-18. Moreover, the software also modifies texture and shape features to assess the malignant phenotype of the pulmonary nodules. Based on their classification accuracy (Acc), the different classifiers were assigned to different weights. Finally, an integrated classifier was obtained to score the malignant phenotype of the pulmonary nodules. The present study included training and testing experiments conducted by extracting the corresponding lung nodule image data from the Lung Image Database Consortium-Image Database Resource Initiative. The results of the present study indicated a final classification Acc of 93.10±2.4%, demonstrating the feasibility and effectiveness of the proposed method. This method includes the powerful feature extraction ability of deep learning combined with the ability to use traditional features in image representation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Recently, Buty et al [12] combined spherical harmonics along with deep CNN features and then classified them using RF. However, the use of CNN for lung nodule classification has been confined to 2D image analysis [13], thus falling short of utilizing the important volumetric and contextual information.…”

Section: D Cnn For Attribute 'M'mentioning

confidence: 99%

Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning

Hussein

Cao²,

Song³

et al. 2017

Lecture Notes in Computer Science

125

View full text Add to dashboard Cite

Abstract. Risk stratification of lung nodules is a task of primary importance in lung cancer diagnosis. Any improvement in robust and accurate nodule characterization can assist in identifying cancer stage, prognosis, and improving treatment planning. In this study, we propose a 3D Convolutional Neural Network (CNN) based nodule characterization strategy. With a completely 3D approach, we utilize the volumetric information from a CT scan which would be otherwise lost in the conventional 2D CNN based approaches. In order to address the need for a large amount for training data for CNN, we resort to transfer learning to obtain highly discriminative features. Moreover, we also acquire the task dependent feature representation for six high-level nodule attributes and fuse this complementary information via a Multi-task learning (MTL) framework. Finally, we propose to incorporate potential disagreement among radiologists while scoring different nodule attributes in a graph regularized sparse multi-task learning. We evaluated our proposed approach on one of the largest publicly available lung nodule datasets comprising 1018 scans and obtained state-of-the-art results in regressing the malignancy scores.

show abstract

“…In the past few years, discriminative deep‐learning approaches demonstrated substantial improvement over traditional machine learning approaches in different tasks including image classification and segmentation . Similarly, such approaches were applied successfully for abnormality detection in medical images . For a general review of deep‐learning approaches for computer‐aided detection of abnormalities in medical images we refer the reader to the review by Hoo‐Chang et al …”

Section: Introductionmentioning

confidence: 99%

“…11 Similarly, such approaches were applied successfully for abnormality detection in medical images. 10,12,13 For a general review of deep-learning approaches for computer-aided detection of abnormalities in medical images we refer the reader to the review by Hoo-Chang et al 14 However, these discriminative deep-learning approaches rely heavily upon the availability of vast amounts of both normal and abnormal samples with explicit annotation by experts which is very challenging to collect. Moreover, due to the large variability in abnormal samples, these models usually require specific training tuned to detect each abnormality.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised abnormality detection through mixed structure regularization (MSR) in deep sparse autoencoders

2019

View full text Add to dashboard Cite

Purpose The purpose of this study is to introduce and evaluate the mixed structure regularization (MSR) approach for a deep sparse autoencoder aimed at unsupervised abnormality detection in medical images. Unsupervised abnormality detection based on identifying outliers using deep sparse autoencoders is a very appealing approach for computer‐aided detection systems as it requires only healthy data for training rather than expert annotated abnormality. However, regularization is required to avoid overfitting of the network to the training data. Methods We used coronary computed tomography angiography (CCTA) datasets of 90 subjects with expert annotated centerlines. We segmented coronary lumen and wall using an automatic algorithm with manual corrections where required. We defined normal coronary cross section as cross sections with a ratio between lumen and wall areas larger than 0.8. We divided the datasets into training, validation, and testing groups in a tenfold cross‐validation scheme. We trained a deep sparse overcomplete autoencoder model for normality modeling with random structure and noise augmentation. We assessed the performance of our deep sparse autoencoder with MSR without denoising (SAE‐MSR) and with denoising (SDAE‐MSR) in comparison to deep sparse autoencoder (SAE), and deep sparse denoising autoencoder (SDAE) models in the task of detecting coronary artery disease from CCTA data on the test group. Results The SDAE‐MSR achieved the best aggregated area under the curve (AUC) with a 20% improvement and the best aggregated Average Precision (AP) with a 30% improvement upon the SAE and SDAE (AUC: 0.78 to 0.94, AP: 0.66 to 0.86) in distinguishing between coronary cross sections with mild stenosis (stenosis grade < 0.3) and coronary cross sections with severe stenosis (stenosis grade > 0.7). The improvements were statistically significant (Mann–Whitney U‐test, P < 0.001). Similarly, The SDAE‐MSR achieved the best aggregated AUC (AP) with an 18% (18%) improvement upon the SAE and SDAE (AUC: 0.71 to 0.84, AP: 0.68 to 0.80). The improvements were statistically significant (Mann–Whitney U‐test, P < 0.05). Conclusion Deep sparse autoencoders with MSR in addition to explicit sparsity regularization term and stochastic corruption of the input data with Gaussian noise have the potential to improve unsupervised abnormality detection using deep‐learning compared to common deep autoencoders.

show abstract

Bridging Computational Features Toward Multiple Semantic Features with Multi-task Regression: A Study of CT Pulmonary Nodules

Cited by 19 publications

References 11 publications

Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images

Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images

Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning

Unsupervised abnormality detection through mixed structure regularization (MSR) in deep sparse autoencoders

Contact Info

Product

Resources

About