A Technique for Lung Nodule Candidate Detection in CT Using Global Minimization Methods

Duggan, Nóirín; Bae, Egil; Shen, Shiwen; Hsu, William; Bui, Alex A. T.; Jones, Edward; Glavin, Martin; Vese, Luminita A.

doi:10.1007/978-3-319-14612-6_35

Cited by 12 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows examples of malignant and benign nodules, helping to illustrate the challenges of differentiating between the two groups. In response, computer-aided diagnosis (CADx) systems [6,7,8,9,10,11] have been explored to assist radiologists in the interpretation process; these help to separate malignant from benign nodules and show promise in increasing the positive predictive value and reducing the false positive rates in characterizing small nodules [11]. Broadly, a contemporary lung nodule CADx system comprises three components: 1) nodule segmentation; 2) feature extraction from nodule candidates; and 3) classification of the candidate as benign or malignant based on its extracted features.…”

Section: Introductionmentioning

confidence: 99%

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

Shen

Han

Aberle

et al. 2019

Expert Systems with Applications

Self Cite

219

141

View full text Add to dashboard Cite

While deep learning methods are increasingly being applied to tasks such as computer-aided diagnosis, these models are difficult to interpret, do not incorporate prior domain knowledge, and are often considered as a "black-box." The lack of model interpretability hinders them from being fully understood by target users such as radiologists. In this paper, we present a novel interpretable deep hierarchical semantic convolutional neural network (HSCNN) to predict whether a given pulmonary nodule observed on a computed tomography (CT) scan is malignant. Our network provides two levels of output: 1) low-level radiologist semantic features; and 2) a high-level malignancy prediction score. The low-level semantic outputs quantify the diagnostic features used by radiologists and serve to explain how the model interprets the images in an expert-driven manner. The information from these low-level tasks, along with the representations learned by the convolutional layers, are then combined and used to infer the high-level task of predicting nodule malignancy. This unified architecture is trained by optimizing a global loss function including both low-and high-level tasks, thereby learning all the parameters within a joint framework. Our experimental results using the Lung Image Database Consortium (LIDC) show that the proposed method not only produces interpretable lung cancer predictions but also achieves significantly better results compared to common 3D CNN approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

Shen

Han

Aberle

et al. 2019

Expert Systems with Applications

Self Cite

219

141

View full text Add to dashboard Cite

show abstract

“…We generated false-positive (or non-nodule) candidates that did not overlap with true nodules and were within the segmented lungs, using multilevel thresholding and morphological operations, developed to accentuate nodules close to lung boundaries and vascular tissue. 6,26,27 The Hounsfield unit (HU) values of the CT scans were clipped to the range from À1000 to 500, encompassing air and tissue in the lungs. This range was compressed to values between 0 and 1 in subsequent analysis.…”

Section: B Data Preprocessingmentioning

confidence: 99%

The effects of physics‐based data augmentation on the generalizability of deep neural networks: Demonstration on nodule false‐positive reduction

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose An important challenge for deep learning models is generalizing to new datasets that may be acquired with acquisition protocols different from the training set. It is not always feasible to expand training data to the range encountered in clinical practice. We introduce a new technique, physics‐based data augmentation (PBDA), that can emulate new computed tomography (CT) data acquisition protocols. We demonstrate two forms of PBDA, emulating increases in slice thickness and reductions of dose, on the specific problem of false‐positive reduction in the automatic detection of lung nodules. Methods We worked with CT images from the lung image database consortium (LIDC) collection. We employed a hybrid ensemble convolutional neural network (CNN), which consists of multiple CNN modules (VGG, DenseNet, ResNet), for a classification task of determining whether an image patch was a suspicious nodule or a false positive. To emulate a reduction in tube current, we injected noise by simulating forward projection, noise addition, and backprojection corresponding to 1.5 mAs (a “chest x‐ray” dose). To simulate thick slice CT scans from thin slice CT scans, we grouped and averaged spatially contiguous CT within thin slice data. The neural network was trained with 10% of the LIDC dataset that was selected to have either the highest tube current or the thinnest slices. The network was tested on the remaining data. We compared PBDA to a baseline with standard geometric augmentations (such as shifts and rotations) and Gaussian noise addition. Results PBDA improved the performance of the networks when generalizing to the test dataset in a limited number of cases. We found that the best performance was obtained by applying augmentation at very low doses (1.5 mAs), about an order of magnitude less than most screening protocols. In the baseline augmentation, a comparable level of Gaussian noise was injected. For dose reduction PBDA, the average sensitivity of 0.931 for the hybrid ensemble network was not statistically different from the average sensitivity of 0.935 without PBDA. Similarly for slice thickness PBDA, the average sensitivity of 0.900 when augmenting with doubled simulated slice thicknesses was not statistically different from the average sensitivity of 0.895 without PBDA. While there were cases detailed in this paper in which we observed improvements, the overall picture was one that suggests PBDA may not be an effective data enrichment tool. Conclusions PBDA is a newly proposed strategy for mitigating the performance loss of neural networks related to the variation of acquisition protocol between the training dataset and the data that is encountered in deployment or testing. We found that PBDA does not provide robust improvements with the four neural networks (three modules and the ensemble) tested and for the specific task of false‐positive reduction in nodule detection.

show abstract

“…CAD systems designed for automated lung cancer diagnosis can be divided into two main stages: 1) Lung nodule detection and segmentation; and 2) malignancy classification of segmented nodules. The first stage consists of processing CT images to isolate the lung region [16] and search for potential pulmonary nodule candidates [17], [18]. The process involves finding FIGURE 2.…”

Section: Introductionmentioning

confidence: 99%

SISC: End-to-End Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells

et al. 2019

View full text Add to dashboard Cite

Lung cancer is the leading cause of cancer-related death worldwide. Computer-aided diagnosis (CAD) systems have shown significant promise in recent years for facilitating the effective detection and classification of abnormal lung nodules in computed tomography (CT) scans. While hand-engineered radiomic features have been traditionally used for lung cancer prediction, there have been significant recent successes achieving state-of-the-art results in the area of discovery radiomics. Here, radiomic sequencers comprising of highly discriminative radiomic features are discovered directly from archival medical data. However, the interpretation of predictions made using such radiomic sequencers remains a challenge. A novel end-to-end interpretable discovery radiomics-driven lung cancer prediction pipeline has been designed, build, and tested. The radiomic sequencer being discovered possesses a deep architecture comprised of stacked interpretable sequencing cells (SISC). The SISC architecture is shown to outperform previous approaches while providing more insight in to its decision making process. The SISC radiomic sequencer is able to achieve state-of-the-art results in lung cancer prediction, and also offers prediction interpretability in the form of critical response maps. The critical response maps are useful for not only validating the predictions of the proposed SISC radiomic sequencer, but also provide improved radiologist-machine collaboration for effective diagnosis.

show abstract

A Technique for Lung Nodule Candidate Detection in CT Using Global Minimization Methods

Cited by 12 publications

References 31 publications

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

The effects of physics‐based data augmentation on the generalizability of deep neural networks: Demonstration on nodule false‐positive reduction

SISC: End-to-End Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells

Contact Info

Product

Resources

About