Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans

@article{Cheng2016ComputerAidedDW,
  title={Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans},
  author={Jie-Zhi Cheng and Dong Ni and Yi-Hong Chou and Jing Qin and Chui-Mei Tiu and Yeun-Chung Chang and Chiun-Sheng Huang and Dinggang Shen and Chung-Ming Chen},
  journal={Scientific Reports},
  year={2016},
  volume={6}
}
This paper performs a comprehensive study on the deep-learning-based computer-aided diagnosis (CADx) for the differential diagnosis of benign and malignant nodules/lesions by avoiding the potential errors caused by inaccurate image processing results (e.g., boundary segmentation), as well as the classification bias resulting from a less robust feature set, as involved in most conventional CADx algorithms. Specifically, the stacked denoising auto-encoder (SDAE) is exploited on the two CADx… 
Computer-Aided Detection of mass-like abnormalities in dedicated breast CT images using deep learning : a preliminary study
TLDR
A computer-aided detection system to detect mass-like abnormalities in dedicated breast CT images and a multi-scale candidate selection system based on image secondorder features and distance maps to discretize the search space is developed.
A deep learning framework for supporting the classification of breast lesions in ultrasound images.
TLDR
The proposed method can work in tandem with human radiologists to improve performance, which is a fundamental purpose of computer-aided diagnosis.
Effect of a Deep Learning Framework-Based Computer-Aided Diagnosis System on the Diagnostic Performance of Radiologists in Differentiating between Malignant and Benign Masses on Breast Ultrasonography
TLDR
Deep learning-based CAD could improve radiologists' diagnostic performance by increasing their specificity, accuracy, and PPV in differentiating between malignant and benign masses on breast US.
Mammogram Classification and Segmentation Through Deep Learning
TLDR
This work proposes the use of sophisticated Convolutional Neural Networks (CNNs) for classification and segmentation of mass and Micro-Calcification lesions on the publicly available INbreast dataset and shows competitive results regarding the State of the Art in fully-automated classification of breast screening exams.
Nodular-Deep: Classification of Pulmonary Nodules using Deep Neural Network
TLDR
Results demonstrate that the new CADe system implemented through the integration of variants of advanced deep learning algorithms known as Nodular-Deep outperforms compared to manual segmentation by a radiologist.
Do pre-trained deep learning models improve computer-aided classification of digital mammograms?
TLDR
This study evaluated the effect of pre-training deep learning models with other imaging datasets in order to boost classification performance on a digital mammography dataset, with the very large non-medical dataset performing the best in improving the classification accuracy.
A Practical Implementation of Deep Learning Method for Supporting the Classification of Breast Lesions in Ultrasound Images
TLDR
The suggested framework to differentiate the lesions and nodules in breast acquired with ultrasound imaging showed promising results and supports human radiologist to give successful performance and helps to create a fluent diagnostic workflow that meets the fundamental purpose of CADx.
COMPUTER AIDED DIAGNOSIS OF BREAST CANCER FROM HISTOPATHOLOGICAL IMAGES USING DEEP LEARNING TECHNIQUES
TLDR
The use of deep transfer learning to automate diagnosis of invasive ductal carcinoma (IDC), the most frequent subtype of breast cancer, is proposed in this work.
Lung Nodule Classification on Computed Tomography Images Using Deep Learning
TLDR
Variation applied on deep learning architecture to improve the accuracy of the classification system and a comprehensive comparison between various deep learning methods used so far for lung nodule classification are discussed.
Automatic Breast Lesion Classification by Joint Neural Analysis of Mammography and Ultrasound
TLDR
A deep-learning based method for classifying breast cancer lesions from their respective mammography and ultrasound images, based on a GoogleNet architecture, outperforming state-of-the-art models trained over a single modality.
...
...

References

SHOWING 1-10 OF 49 REFERENCES
Computer-aided diagnosis of pulmonary nodules on CT scans: improvement of classification performance with nodule surface features.
TLDR
It is demonstrated that the authors' proposed segmentation and feature extraction techniques are promising for classifying lung nodules on CT images and if a support vector machine (SVM) classifier can achieve improved performance over the LDA classifier.
Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features
TLDR
The developed CAD algorithm has the potential to increase the specificity of US for characterization of breast lesions by identifying breast nodule malignancy using multiple ultrasonography features and artificial neural network (ANN) classifier.
Computer-aided diagnosis in high resolution CT of the lungs.
TLDR
A computer-aided diagnosis system is presented to automatically distinguish normal from abnormal tissue in high-resolution CT chest scans acquired during daily clinical practice, and performance is shown to approach that of two expert radiologists in diagnosing the local regions of interest.
Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks.
TLDR
The proposed CAD algorithm could effectively and reliably differentiate benign and malignant lesions and was shown to be extendible from one set of US images to the other set and robust for both small and large sample sizes.
Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours.
TLDR
Preliminary results indicate that use of the 3D AC model and the3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD.
Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy.
TLDR
Use of a computer algorithm may improve radiologists' accuracy in distinguishing malignant from benign breast masses on 3D US volumetric images.
Robust Texture Analysis Using Multi-Resolution Gray-Scale Invariant Features for Breast Sonographic Tumor Diagnosis
TLDR
The experiments suggest that the texture analysis using multi-resolution gray-scale invariant features via ranklet transform is useful for designing a robust CAD system.
Computer-aided US diagnosis of breast lesions by using cell-based contour grouping.
TLDR
The newly developed computer-aided diagnostic algorithm that used a cell-based contour grouping segmentation method to measure boundaries achieved a high differentiation performance.
Computer-Aided Diagnosis for Early-Stage Lung Cancer Based on Longitudinal and Balanced Data
TLDR
Computer-aided diagnosis was used to facilitate the prediction of characteristics of solitary pulmonary nodules in CT of lungs to diagnose early-stage lung cancer and a sensitive support vector machine prediction model can increase the rate of diagnosis.
...
...