Robust Computer-aided Diagnosis System Research Articles

Fully Automated Neural Network Framework for Pulmonary Nodules Detection and Segmentation

Lung cancer is the leading cause of cancer death worldwide, and most patients are diagnosed with advanced stages for lack of symptoms in the early stages of the disease, leading to poor prognosis. It is thus of great importance to detect lung cancer in the early stages which can reduce mortality and improve patient survival significantly. Although there are many computer aided diagnosis (CAD) systems used for detecting pulmonary nodules, there are still few CAD systems for detection and segmentation, and their performance on small nodules is not ideal. Thus, in this paper, we propose a deep cascaded multitask framework called mobilenet split-attention Yolo unet, the mobilenet split-attention Yolo(Msa-yolo) greatly enhance the feature of small nodules and boost up their performance, the overall result shows that the mean accuracy precision (mAP) of our Msa-Yolo compared to Yolox has increased from 85.10% to 86.64% on LUNA16 dataset, and from 90.13% to 94.15% on LCS dataset compared to YoloX. Besides, we get only 8.35 average number of candidates per scan with 96.32% sensitivity on LUNA16 dataset, which greatly outperforms other existing systems. At the segmentation stage, the mean intersection over union (mIOU) of our CAD system has increased from 71.66% to 76.84% on LCS dataset comparing to baseline. Conclusion: A fast, accurate and robust CAD system for nodule detection, segmentation and classification is proposed in this paper. And it is confirmed by the experimental results that the proposed system possesses the ability to detect and segment small nodules.

Developing breast lesion detection algorithms for digital breast tomosynthesis: Leveraging false positive findings.

Due to the complex nature of digital breast tomosynthesis (DBT) in imaging techniques, reading times are longer than 2D mammograms. A robust computer-aided diagnosis system in DBT could help radiologists reduce their workload and reading times. The purpose of this study was to develop algorithms for detecting biopsy-proven breast lesions on DBT using multi-depth level convolutional models and leveraging non-biopsied samples. As biopsied positive samples in a lesion dataset are limited, we hypothesized that false positive (FP) findings by detection algorithms from non-biopsied benign lesions could improve detection algorithms by using them as data augmentation. We first extracted 2D slices from DBT volumes with biopsy-proven breast lesions (cancer and benign), with non-biopsied benign lesions (actionable), and for controls. Then, to provide lesion continuity along the z-direction, we combined a lesion slice with its immediate adjacent slices to synthesize 2.5-dimensional (2.5D) images of the lesion by assigning them into R, G, and B color channels. We used 224 biopsy-proven lesions from 39 cancer and 62 benign patients from a DBTex challenge dataset of 1000 scans. We included the 2.5D images of immediate neighboring slices from the lesion's center to increase the number of training samples. For lesion detection, we used the YOLOv5 algorithm as our base network. We trained a baseline algorithm (medium-depth level) using biopsied samples to detect actionable FPs in non-biopsied images. Afterward, we fine-tuned the baseline model on the augmented image set (actionable FPs added). For lesion inferencing, we processed the DBT volume slice-by-slice to estimate bounding boxes in each slice, and then combined them by connecting bounding boxes along the depth via volumetric morphological closing. We trained an additional model (large) with deeper-depth levels by repeating the above process. Finally, we developed an ensemble algorithm by combining the medium and large detection models. We used the free-response operating characteristic curve to evaluate our algorithms. We reported mean sensitivity per FPs per DBT volume only for biopsied views and sensitivity at 2-false positives per image (2FPI) for all views. However, due to the limited accessibility to the truth of the challenge validation and test datasets, we used sensitivity at 2FPI for statistical evaluation. For the DBTex independent validation set, the medium baseline model achieved a mean sensitivity of 0.627 FPs per DBT volume, and a sensitivity of 0.640 at 2FPI. After adding actionable FP lesions, the model had an improved 2FPI of 0.769 over the baseline (p-value=0.013). Our ensemble algorithm with multi-depth levels (medium + large) achieved a mean sensitivity of 0.815 FPs per DBT volume and an improved sensitivity at 2FPI of 0.80 over the baseline (p-value<0.001) on the validation set. Finally, our ensemble model achieved a mean sensitivity of 0.786 FPs per DBT volume and a sensitivity of 0.743 at 2FPI on the DBTex independent test set. Our results show that actionable FP findings hold useful information for lesion detection algorithms, and our ensemble detection model with multi-depth levels improves lesion detection performance.

A Hybrid Approach of Texture Feature and Gradient Orientation for Computer Aided Diagnosis System Based on Breast Density Classification

A Computer-Aided Diagnosis (CAD) system can perform an accurate diagnosis and help radiologists by presenting a second opinion about breast density. However, the development of a robust CAD system for breast density classification is still an open problem. In this study, we proposed a CAD system based on hybrid intelligent machine learning technique for automatic classification of breast density on mammogram images. The proposed technique employs gradient orientation pattern HOG and texture descriptor CLBP-HF as features and K Nearest Neighbor (KNN) as classifier. The experiments were carried out on benchmarks public domain MIAS and DDSM datasets. The classification accuracy is 96.4% whereas recall and precision are 96.59 and 96.75% on MIAS dataset. Moreover, the comparison with the state-of-the-art breast density classification methods shows that the proposed method outperforms the existing methods on both MIAS and DDSM datasets, the improvement is significant on both datasets. The proposed method will help radiologists in assessing the breast density, which is important for breast cancer diagnosis.

Correction to: Computer-aided diagnosis (CAD) system based on multi-layer feature fusion network for skin lesion recognition in dermoscopy images

Skin lesion recognition is one of the most important tasks in dermoscopic image analysis. Current Convolutional Neural Network (CNN) algorithms based recognition methods tend to become a standard methodology to fix a large array of Computer-Aided Diagnosis (CAD) and interpretation problems. Besides significant practical and theoretical improvements in their architecture, their effectiveness is built on the existence of the flexible pre-trained models which generalize well to novel tasks and handle the problem of having small set of dermoscopic data. However, existing works pay little attention to exploring the benefits of hierarchical multi-feature fusion for classifying the skin lesions in digital dermoscopic images. Practically, it has been found that integrating multi-layer features has significant potential for improving performance of any pattern recognition task. In this paper, we developed a robust CAD system based on transfer learning and multi-layer feature fusion network to diagnose complex skin diseases. It is a convenient approach in terms of overfitting prevention, convergence speed and high morphological feature similarity processing. Our research focuses exclusively on obtaining optimal performance with addressing the various gaps in the skin pattern recognition area. For validation and comparison purposes, the proposed approach was evaluated on publicly dermoscopic dataset, and achieved the high recognition precision compared with fully trained CNN models, fine-tuning process, single CNN model and other related works. Therefore, the study demonstrates that our proposed approach can dramatically improve the performance of CAD systems which are based on the conventional recognition and classification algorithms for skin lesion recognition in dermoscopic data.

Multi class disorder detection of magnetic resonance brain images using composite features and neural network.

Brain disorder recognition has becoming a promising area of study. In reality, somedisorders share similar features and signs, making the task ofdiagnosis and treatment challenging. This paper presents a rigorous and robust computer aided diagnosis system for the detection of multiple brain abnormalities which can assist physicians in the diagnosis and treatment of brain diseases. In this system, we used energy of wavelet sub bands, textural features of gray level co-occurrence matrix and intensity feature of MR brain images. These features are ranked using Wilcoxon test. The composite features are classified using back propagation neural network. Bayesian regulation is adopted to find the optimal weights of neural network. The experimentation is carried out on datasets DS-90 and DS-310 of Harvard Medical School. To enhance the generalization capability of the network, fivefold stratified cross validation technique is used. The proposed system yields multi class disease classification accuracy of 100% in differentiating 90 MR brain images into 18 classes and 97.81% in differentiating 310 MR brain images into 6 classes. The experimental results reveal that the composite features along with BPNN classifier create a competent and reliable system for the identification of multiple brain disorders which can be used in clinical applications. The Wilcoxon test outcome demonstrates that standard deviation feature along with energies of approximate and vertical sub bands of level 7 contribute the most in achieving enhanced multi class classification performance results.

Robust Texture Analysis Using Multi-Resolution Gray-Scale Invariant Features for Breast Sonographic Tumor Diagnosis

Computer-aided diagnosis (CAD) systems in gray-scale breast ultrasound images have the potential to reduce unnecessary biopsy of breast masses. The purpose of our study is to develop a robust CAD system based on the texture analysis. First, gray-scale invariant features are extracted from ultrasound images via multi-resolution ranklet transform. Thus, one can apply linear support vector machines (SVMs) on the resulting gray-level co-occurrence matrix (GLCM)-based texture features for discriminating the benign and malignant masses. To verify the effectiveness and robustness of the proposed texture analysis, breast ultrasound images obtained from three different platforms are evaluated based on cross-platform training/testing and leave-one-out cross-validation (LOO-CV) schemes. We compare our proposed features with those extracted by wavelet transform in terms of receiver operating characteristic (ROC) analysis. The AUC values derived from the area under the curve for the three databases via ranklet transform are 0.918 (95% confidence interval [CI], 0.848 to 0.961), 0.943 (95% CI, 0.906 to 0.968), and 0.934 (95% CI, 0.883 to 0.961), respectively, while those via wavelet transform are 0.847 (95% CI, 0.762 to 0.910), 0.922 (95% CI, 0.878 to 0.958), and 0.867 (95% CI, 0.798 to 0.914), respectively. Experiments with cross-platform training/testing scheme between each database reveal that the diagnostic performance of our texture analysis using ranklet transform is less sensitive to the sonographic ultrasound platforms. Also, we adopt several co-occurrence statistics in terms of quantization levels and orientations (i.e., descriptor settings) for computing the co-occurrence matrices with 0.632+ bootstrap estimators to verify the use of the proposed texture analysis. These experiments suggest that the texture analysis using multi-resolution gray-scale invariant features via ranklet transform is useful for designing a robust CAD system.