A Preliminary Study on Breast Cancer Risk Analysis Using Deep Neural Network

Can a Computer-Aided Mass Diagnosis Model Based on Perceptive Features Learned From Quantitative Mammography Radiology Reports Improve Junior Radiologists' Diagnosis Performance? An Observer Study

Radiologists' diagnostic capabilities for breast mass lesions depend on their experience. Junior radiologists may underestimate or overestimate Breast Imaging Reporting and Data System (BI-RADS) categories of mass lesions owing to a lack of diagnostic experience. The computer-aided diagnosis (CAD) method assists in improving diagnostic performance by providing a breast mass classification reference to radiologists. This study aims to evaluate the impact of a CAD method based on perceptive features learned from quantitative BI-RADS descriptions on breast mass diagnosis performance. We conducted a retrospective multi-reader multi-case (MRMC) study to assess the perceptive feature-based CAD method. A total of 416 digital mammograms of patients with breast masses were obtained from 2014 through 2017, including 231 benign and 185 malignant masses, from which we randomly selected 214 cases (109 benign, 105 malignant) to train the CAD model for perceptive feature extraction and classification. The remaining 202 cases were enrolled as the test set for evaluation, of which 51 patients (29 benign and 22 malignant) participated in the MRMC study. In the MRMC study, we categorized six radiologists into three groups: junior, middle-senior, and senior. They diagnosed 51 patients with and without support from the CAD model. The BI-RADS category, benign or malignant diagnosis, malignancy probability, and diagnosis time during the two evaluation sessions were recorded. In the MRMC evaluation, the average area under the curve (AUC) of the six radiologists with CAD support was slightly higher than that without support (0.896 vs. 0.850, p = 0.0209). Both average sensitivity and specificity increased (p = 0.0253). Under CAD assistance, junior and middle-senior radiologists adjusted the assessment categories of more BI-RADS 4 cases. The diagnosis time with and without CAD support was comparable for five radiologists. The CAD model improved the radiologists' diagnostic performance for breast masses without prolonging the diagnosis time and assisted in a better BI-RADS assessment, especially for junior radiologists.

Convolutional neural network for automated mass segmentation in mammography

BACKGROUND

Automatic segmentation and localization of lesions in mammogram (MG) images are challenging even with employing advanced methods such as deep learning (DL) methods. We developed a new model based on the architecture of the semantic segmentation U-Net model to precisely segment mass lesions in MG images. The proposed end-to-end convolutional neural network (CNN) based model extracts contextual information by combining low-level and high-level features. We trained the proposed model using huge publicly available databases, (CBIS-DDSM, BCDR-01, and INbreast), and a private database from the University of Connecticut Health Center (UCHC).

RESULTS

We compared the performance of the proposed model with those of the state-of-the-art DL models including the fully convolutional network (FCN), SegNet, Dilated-Net, original U-Net, and Faster R-CNN models and the conventional region growing (RG) method. The proposed Vanilla U-Net model outperforms the Faster R-CNN model significantly in terms of the runtime and the Intersection over Union metric (IOU). Training with digitized film-based and fully digitized MG images, the proposed Vanilla U-Net model achieves a mean test accuracy of 92.6%. The proposed model achieves a mean Dice coefficient index (DI) of 0.951 and a mean IOU of 0.909 that show how close the output segments are to the corresponding lesions in the ground truth maps. Data augmentation has been very effective in our experiments resulting in an increase in the mean DI and the mean IOU from 0.922 to 0.951 and 0.856 to 0.909, respectively.

CONCLUSIONS

The proposed Vanilla U-Net based model can be used for precise segmentation of masses in MG images. This is because the segmentation process incorporates more multi-scale spatial context, and captures more local and global context to predict a precise pixel-wise segmentation map of an input full MG image. These detected maps can help radiologists in differentiating benign and malignant lesions depend on the lesion shapes. We show that using transfer learning, introducing augmentation, and modifying the architecture of the original model results in better performance in terms of the mean accuracy, the mean DI, and the mean IOU in detecting mass lesion compared to the other DL and the conventional models.

Deep convolutional neural networks for mammography: advances, challenges and applications

BACKGROUND

The limitations of traditional computer-aided detection (CAD) systems for mammography, the extreme importance of early detection of breast cancer and the high impact of the false diagnosis of patients drive researchers to investigate deep learning (DL) methods for mammograms (MGs). Recent breakthroughs in DL, in particular, convolutional neural networks (CNNs) have achieved remarkable advances in the medical fields. Specifically, CNNs are used in mammography for lesion localization and detection, risk assessment, image retrieval, and classification tasks. CNNs also help radiologists providing more accurate diagnosis by delivering precise quantitative analysis of suspicious lesions.

RESULTS

In this survey, we conducted a detailed review of the strengths, limitations, and performance of the most recent CNNs applications in analyzing MG images. It summarizes 83 research studies for applying CNNs on various tasks in mammography. It focuses on finding the best practices used in these research studies to improve the diagnosis accuracy. This survey also provides a deep insight into the architecture of CNNs used for various tasks. Furthermore, it describes the most common publicly available MG repositories and highlights their main features and strengths.

CONCLUSIONS

The mammography research community can utilize this survey as a basis for their current and future studies. The given comparison among common publicly available MG repositories guides the community to select the most appropriate database for their application(s). Moreover, this survey lists the best practices that improve the performance of CNNs including the pre-processing of images and the use of multi-view images. In addition, other listed techniques like transfer learning (TL), data augmentation, batch normalization, and dropout are appealing solutions to reduce overfitting and increase the generalization of the CNN models. Finally, this survey identifies the research challenges and directions that require further investigations by the community.

Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis

This study aimed to analyze the ability of extracting automatically generated features using deep structured algorithms in lung nodule CT image diagnosis, and compare its performance with traditional computer aided diagnosis (CADx) systems using hand-crafted features. All of the 1018 cases were acquired from Lung Image Database Consortium (LIDC) public lung cancer database. The nodules were segmented according to four radiologists' markings, and 13,668 samples were generated by rotating every slice of nodule images. Three multichannel ROI based deep structured algorithms were designed and implemented in this study: convolutional neural network (CNN), deep belief network (DBN), and stacked denoising autoencoder (SDAE). For the comparison purpose, we also implemented a CADx system using hand-crafted features including density features, texture features and morphological features. The performance of every scheme was evaluated by using a 10-fold cross-validation method and an assessment index of the area under the receiver operating characteristic curve (AUC). The observed highest area under the curve (AUC) was 0.899±0.018 achieved by CNN, which was significantly higher than traditional CADx with the AUC=0.848±0.026. The results from DBN was also slightly higher than CADx, while SDAE was slightly lower. By visualizing the automatic generated features, we found some meaningful detectors like curvy stroke detectors from deep structured schemes. The study results showed the deep structured algorithms with automatically generated features can achieve desirable performance in lung nodule diagnosis. With well-tuned parameters and large enough dataset, the deep learning algorithms can have better performance than current popular CADx. We believe the deep learning algorithms with similar data preprocessing procedure can be used in other medical image analysis areas as well.