Colonoscopic image synthesis with generative adversarial network for enhanced detection of sessile serrated lesions using convolutional neural network

Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.

COVID-CLNet; COVID-19 Detection with Compressive Deep Learning Approaches

One of the most serious global health threats is COVID-19 pandemic. The emphasis on increasing the diagnostic capability helps stopping its spread significantly. Therefore, to assist the radiologist or other medical professional to detect and identify the COVID-19 cases in the shortest possible time, we propose a computer-aided detection (CADe) system that uses the computed tomography (CT) scan images. This proposed boosted deep learning network (CLNet) is based on the implementation of Deep Learning (DL) networks as a complementary to the Compressive Learning (CL). We utilize our inception feature extraction technique in the measurement domain using CL to represent the data features into a new space with less dimensionality before accessing the Convolutional Neural Network. All original features have been contributed equally to the new space using a sensing matrix. Experiments performed on different compressed methods show promising results for COVID-19 detection.

Detection Accuracy and Latency of Colorectal Lesions with Computer-Aided Detection System Based on Low-Bias Evaluation

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for 69 colorectal lesions at the Jikei University Hospital between June 2017 and February 2018. First, we evaluated the diagnostic performances using still images randomly and automatically extracted from video recordings of the entire endoscopic procedure at intervals of 5 s, without eliminating poor quality images. Second, the latency of lesion detection by the CADe system from the initial appearance of lesions was investigated by reviewing the videos. A total of 6531 images, including 662 images with a lesion, were studied in the image-based analysis. The AUC, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.983, 94.6%, 95.2%, 68.8%, 99.4%, and 95.1%, respectively. The median time for detecting colorectal lesions measured in the lesion-based analysis was 0.67 s. In conclusion, we proved that the originally developed CADe system based on YOLO v3 could accurately and instantaneously detect colorectal lesions using the test dataset obtained from videos, mitigating operator selection biases.

Computer-Aided Detection (CADe) System with Optical Coherent Tomography for Melanin Morphology Quantification in Melasma Patients

Dark skin-type individuals have a greater tendency to have pigmentary disorders, among which melasma is especially refractory to treat and often recurs. Objective measurement of melanin amount helps evaluate the treatment response of pigmentary disorders. However, naked-eye evaluation is subjective to weariness and bias. We used a cellular resolution full-field optical coherence tomography (FF-OCT) to assess melanin features of melasma lesions and perilesional skin on the cheeks of eight Asian patients. A computer-aided detection (CADe) system is proposed to mark and quantify melanin. This system combines spatial compounding-based denoising convolutional neural networks (SC-DnCNN), and through image processing techniques, various types of melanin features, including area, distribution, intensity, and shape, can be extracted. Through evaluations of the image differences between the lesion and perilesional skin, a distribution-based feature of confetti melanin without layering, two distribution-based features of confetti melanin in stratum spinosum, and a distribution-based feature of grain melanin at the dermal–epidermal junction, statistically significant findings were achieved (p-values = 0.0402, 0.0032, 0.0312, and 0.0426, respectively). FF-OCT enables the real-time observation of melanin features, and the CADe system with SC-DnCNN was a precise and objective tool with which to interpret the area, distribution, intensity, and shape of melanin on FF-OCT images.

Computer-Aided Detection False Positives in Colonoscopy

Randomized control trials and meta-analyses comparing colonoscopies with and without computer-aided detection (CADe) assistance showed significant increases in adenoma detection rates (ADRs) with CADe. A major limitation of CADe is its false positives (FPs), ranked 3rd in importance among 59 research questions in a modified Delphi consensus review. The definition of FPs varies. One commonly used definition defines an FP as an activation of the CADe system, irrespective of the number of frames or duration of time, not due to any polypoid or nonpolypoid lesions. Although only 0.07 to 0.2 FPs were observed per colonoscopy, video analysis studies using FPs as the primary outcome showed much higher numbers of 26 to 27 per colonoscopy. Most FPs were of short duration (91% < 0.5 s). A higher number of FPs was also associated with suboptimal bowel preparation. The appearance of FPs can lead to user fatigue. The polypectomy of FPs results in increased procedure time and added use of resources. Re-training the CADe algorithms is one way to reduce FPs but is not practical in the clinical setting during colonoscopy. Water exchange (WE) is an emerging method that the colonoscopist can use to provide salvage cleaning during insertion. We discuss the potential of WE for reducing FPs as well as the augmentation of ADRs through CADe.

Characterization of liver Disease Based on Ultrasound Imaging System

Computer-Aided Detection (CAD) systems are one of the most effected tools nowadays in aiding physicians in the detection of liver tumors at early stage. In this paper, the CADe system will be built which has the ability to detect the abnormal tumor inside the liver. In order to create that system, different types of classifiers must be implemented. In our CADe system, a support vector machine (SVM) and K-Nearest Neighbor (KNN) will be used as classifiers. A total number of 120 images including the normal and abnormal cases were collected. Initially, the features will be extracted from database images in order to distinguish between the classes of those liver tumors. Then, by using SVM and KNN the images will be classified into two classes normal and abnormal cases. The paper reveals that SVM and KNN, which demonstrated 100 percent precision, 100 percent sensitivity, and 100 percent specificity, were the best classifiers.

Nipple Localization in Automated Whole Breast Ultrasound Coronal Scans Using Ensemble Learning

Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-aided detection (CADe) systems for nipple detection in breast mediolateral oblique (MLO) views of mammogram images, few academic works address the coronal views of breast ultrasound (BUS) images. This paper addresses a novel CADe system to locate the Nipple Shadow Area (NSA) in ultrasound images. Here the Hu Moments and Gray-level Co-occurrence Matrix (GLCM) were calculated through an iterative sliding window for the extraction of shape and texture features. These features are then concatenated and fed into an Artificial Neural Network (ANN) to obtain probable NSA’s. Later, contour features, such as shape complexity through fractal dimension, edge distance from the periphery and contour area, were computed and passed into a Support Vector Machine (SVM) to identify the accurate NSA in each case. The coronal plane BUS dataset is built upon our own, which consists of 64 images from 13 patients. The test results show that the proposed CADe system achieves 91.99% accuracy, 97.55% specificity, 82.46% sensitivity and 88% F-score on our dataset.

Benchmarking False Positive Definitions for Computer Aided Polyp Detection in Colonoscopy

Introduction The occurrence of false positive (FP) alarms is an important outcome measure in computer-aided colon polyp detection (CADe) studies. However, there is no consensus definition for FPs in clinical trials evaluating CADe in colonoscopy. We aimed to study the diagnostic performance of CADe based on different threshold definitions for FP alarms. Methods A previously validated CADe system was applied to screening/surveillance colonoscopy videos. Different thresholds for FP alerts were defined based on the time an alarm box was continuously traced by the system. Primary outcomes were FP results and specificity using differing FP thresholds. Results 62 colonoscopies were analyzed. CADe specificity and accuracy were 93.2% and 97.8% respectively for a FP threshold definition of > 0.5 seconds, 98.6 % and 99.5% for a FP threshold > 1 second, and 99.8% and 99.9% for a FP threshold > 2 seconds. Conclusion Our analysis demonstrates how different threshold definitions for false positives can impact the reported diagnostic performance of CADe for colon polyp detection.

Multi-level 3D Densenets for False-positive Reduction in Lung Nodule Detection Based on Chest Computed Tomography

Objective: False-positive nodule reduction is a crucial part of a computer-aided detection (CADe) system, which assists radiologists in accurate lung nodule detection. In this research, a novel scheme using multi-level 3D DenseNet framework is proposed to implement false-positive nodule reduction task. Methods: Multi-level 3D DenseNet models were extended to differentiate lung nodules from falsepositive nodules. First, different models were fed with 3D cubes with different sizes for encoding multi-level contextual information to meet the challenges of the large variations of lung nodules. In addition, image rotation and flipping were utilized to upsample positive samples which consisted of a positive sample set. Furthermore, the 3D DenseNets were designed to keep low-level information of nodules, as densely connected structures in DenseNet can reuse features of lung nodules and then boost feature propagation. Finally, the optimal weighted linear combination of all model scores obtained the best classification result in this research. Results: The proposed method was evaluated with LUNA16 dataset which contained 888 thin-slice CT scans. The performance was validated via 10-fold cross-validation. Both the Free-response Receiver Operating Characteristic (FROC) curve and the Competition Performance Metric (CPM) score show that the proposed scheme can achieve a satisfactory detection performance in the falsepositive reduction track of the LUNA16 challenge. Conclusion: The result shows that the proposed scheme can be significant for false-positive nodule reduction task.