Learning Deep Spatial Lung Features by 3D Convolutional Neural Network for Early Cancer Detection

Jin, Taolin; Cui, Hui; Zeng, Shan; Wang, Xiuying

doi:10.1109/dicta.2017.8227454

Cited by 22 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They obtained a 28% relative improvement on the COCO object detection dataset, and they won the ImageNet Large Scale Visual Recognition Competition (ILSVR). Jin et al [15] used the 3D-AlexNet to classify the images of the DSB Kaggle lung CT scan. They compared the 3D-AlexNet architecture with various input sizes and a different number of epochs.…”

Section: Related Workmentioning

confidence: 99%

A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

2020

View full text Add to dashboard Cite

This research is concerned with malignant pulmonary nodule detection (PND) in low-dose CT scans. Due to its crucial role in the early diagnosis of lung cancer, PND has considerable potential in improving the survival rate of patients. We propose a two-stage framework that exploits the ever-growing advances in deep neural network models, and that is comprised of a semantic segmentation stage followed by localization and classification. We employ the recently published DeepLab model for semantic segmentation, and we show that it significantly improves the accuracy of nodule detection compared to the classical U-Net model and its most recent variants. Using the widely adopted Lung Nodule Analysis dataset (LUNA16), we evaluate the performance of the semantic segmentation stage by adopting two network backbones, namely, MobileNet-V2 and Xception. We present the impact of various model training parameters and the computational time on the detection accuracy, featuring a 79.1% mean intersection-over-union (mIoU) and an 88.34% dice coefficient. This represents a mIoU increase of 60% and a dice coefficient increase of 30% compared to U-Net. The second stage involves feeding the output of the DeepLab-based semantic segmentation to a localization-then-classification stage. The second stage is realized using Faster RCNN and SSD, with an Inception-V2 as a backbone. On LUNA16, the two-stage framework attained a sensitivity of 96.4%, outperforming other recent models in the literature, including deep models. Finally, we show that adopting a transfer learning approach, particularly, the DeepLab model weights of the first stage of the framework, to infer binary (malignant-benign) labels on the Kaggle dataset for pulmonary nodules achieves a classification accuracy of 95.66%, which represents approximately 4% improvement over the recent literature.

show abstract

Section: Related Workmentioning

confidence: 99%

A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

2020

View full text Add to dashboard Cite

show abstract

“…Multidimensional Attention Mechanism. 3D CNNs [24] were used for early cancer detection to preserve the spatial relationship between neighboring CT slices [25,26]. DenseNet [27] has been applied to numerous problems within the medical field [28,29] because of its connectivity pattern and the small number of parameters needed.…”

Section: Fine-grained Feature Extraction Network Based Onmentioning

confidence: 99%

Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism

et al. 2020

View full text Add to dashboard Cite

Lung cancer ranks among the most common types of cancer. Noninvasive computer-aided diagnosis can enable large-scale rapid screening of potential patients with lung cancer. Deep learning methods have already been applied for the automatic diagnosis of lung cancer in the past. Due to restrictions caused by single modality images of dataset as well as the lack of approaches that allow for a reliable extraction of fine-grained features from different imaging modalities, research regarding the automated diagnosis of lung cancer based on noninvasive clinical images requires further study. In this paper, we present a deep learning architecture that combines the fine-grained feature from PET and CT images that allow for the noninvasive diagnosis of lung cancer. The multidimensional (regarding the channel as well as spatial dimensions) attention mechanism is used to effectively reduce feature noise when extracting fine-grained features from each imaging modality. We conduct a comparative analysis of the two aspects of feature fusion and attention mechanism through quantitative evaluation metrics and the visualization of deep learning process. In our experiments, we obtained an area under the ROC curve of 0.92 (balanced accuracy = 0.72) and a more focused network attention which shows the effective extraction of the fine-grained feature from each imaging modality.

show abstract

“…As the authors used images of size 224×224 as their input, we also performed the same resizing of the data in a pre-processing step. We also implemented the method used in the classification of 3D lung images introduced in Jin et al (2017). They used thresholds based on the Hounsfield unit (HU) to extract an initial mask from CT images and used morphological operations to fill holes in this mask.…”

Section: Databasesmentioning

confidence: 99%

“…Finally, we extracted the organ from the background using this mask and used this as the input to the DCNN. Jin et al (2017) observed that an input image size of 128 × 128 × 20 provided the best performance, and therefore, we also resized the input images to this size.…”

Section: Databasesmentioning

confidence: 99%

“…They performed two classifications: binary (benign or malignant) and ternary (benign, primary malignant, or metastatic malignant). Jin et al (2017) modified the AlexNet (Krizhevsky, Sutskever & Hinton, 2012) architecture to make it suitable for the classification of 3D CT images of lungs. They segmented the lungs from the CT image using a pre-processing step and performed a binary classification (cancer or not) on the resulting image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A rotation and translation invariant method for 3D organ image classification using deep convolutional neural networks

Islam

Wijewickrema

O’Leary

2019

PeerJ Computer Science

View full text Add to dashboard Cite

Three-dimensional (3D) medical image classification is useful in applications such as disease diagnosis and content-based medical image retrieval. It is a challenging task due to several reasons. First, image intensity values are vastly different depending on the image modality. Second, intensity values within the same image modality may vary depending on the imaging machine and artifacts may also be introduced in the imaging process. Third, processing 3D data requires high computational power. In recent years, significant research has been conducted in the field of 3D medical image classification. However, most of these make assumptions about patient orientation and imaging direction to simplify the problem and/or work with the full 3D images. As such, they perform poorly when these assumptions are not met. In this paper, we propose a method of classification for 3D organ images that is rotation and translation invariant. To this end, we extract a representative two-dimensional (2D) slice along the plane of best symmetry from the 3D image. We then use this slice to represent the 3D image and use a 20-layer deep convolutional neural network (DCNN) to perform the classification task. We show experimentally, using multi-modal data, that our method is comparable to existing methods when the assumptions of patient orientation and viewing direction are met. Notably, it shows similarly high accuracy even when these assumptions are violated, where other methods fail. We also explore how this method can be used with other DCNN models as well as conventional classification approaches.

show abstract

Learning Deep Spatial Lung Features by 3D Convolutional Neural Network for Early Cancer Detection

Cited by 22 publications

References 5 publications

A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism

A rotation and translation invariant method for 3D organ image classification using deep convolutional neural networks

Contact Info

Product

Resources

About