Paul Babyn

Mohammad Reza Mohebbian, Khan A. Wahid, Paul Babyn

Wireless Capsule Endoscopy (WCE) helps physicians examine the gastrointestinal (GI) tract noninvasively. There are few studies that address pathological assessment of endoscopy images in multiclass classification and most of them are based on binary anomaly detection or aim to detect a specific type of anomaly. Multiclass anomaly detection is challenging, especially when the dataset is poorly sampled or imbalanced. Many available datasets in endoscopy field, such as KID2, suffer from an imbalance issue, which makes it difficult to train a high-performance model. Additionally, increasing the number of classes makes classification more difficult. We proposed a multiclass classification algorithm that is extensible to any number of classes and can handle an imbalance issue. The proposed method uses multiple autoencoders where each one is trained on one class to extract features with the most discrimination from other classes. The loss function of autoencoders is set based on reconstruction, compactness, distance from other classes, and Kullback-Leibler (KL) divergence. The extracted features are clustered and then classified using an ensemble of support vector data descriptors. A total of 1,778 normal, 227 inflammation, 303 vascular, and 44 polyp images from the KID2 dataset are used for evaluation. The entire algorithm ran 5 times and achieved F1-score of 96.3 +- 0.2% and 85.0 +- 0.4% on the test set for binary and multiclass anomaly detection, respectively. The impact of each step of the algorithm was investigated by various ablation studies and the results were compared with published works. The suggested approach is a competitive option for detecting multiclass anomalies in the GI field.

Mohammad Reza Mohebbian, Khan A. Wahid, Anh Dinh et al.

Conventional Endoscopy (CE) and Wireless Capsule Endoscopy (WCE) are known tools for diagnosing gastrointestinal (GI) tract disorders. Detecting the anatomical location of GI tract can help clinicians to determine a more appropriate treatment plan, can reduce repetitive endoscopy and is important in drug-delivery. There are few research that address detecting anatomical location of WCE and CE images using classification, mainly because of difficulty in collecting data and anotating them. In this study, we present a few-shot learning method based on distance metric learning which combines transfer-learning and manifold mixup scheme for localizing endoscopy frames and can be trained on few samples. The manifold mixup process improves few-shot learning by increasing the number of training epochs while reducing overfitting, as well as providing more accurate decision boundaries. A dataset is collected from 10 different anatomical positions of human GI tract. Two models were trained using only 78 CE and 27 WCE annotated frames to predict the location of 25700 and 1825 video frames from CE and WCE, respectively. In addition, we performed subjective evaluation using nine gastroenterologists to show the necessaity of having an AI system for localization. Various ablation studies and interpretations are performed to show the importance of each step, such effect of transfer-learning approach, and impact of manifold mixup on performance. The proposed method is also compared with various methods trained on categorical cross-entropy loss and produced better results which show that proposed method has potential to be used for endoscopy image classification.

Robert D. E. Henderson, Xin Yi, Scott J. Adams et al.

We develop and evaluate a deep learning algorithm to classify multiple catheters on neonatal chest and abdominal radiographs. A convolutional neural network (CNN) was trained using a dataset of 777 neonatal chest and abdominal radiographs, with a split of 81%-9%-10% for training-validation-testing, respectively. We employed ResNet-50 (a CNN), pre-trained on ImageNet. Ground truth labelling was limited to tagging each image to indicate the presence or absence of endotracheal tubes (ETTs), nasogastric tubes (NGTs), and umbilical arterial and venous catheters (UACs, UVCs). The data set included 561 images containing 2 or more catheters, 167 images with only one, and 49 with none. Performance was measured with average precision (AP), calculated from the area under the precision-recall curve. On our test data, the algorithm achieved an overall AP (95% confidence interval) of 0.977 (0.679-0.999) for NGTs, 0.989 (0.751-1.000) for ETTs, 0.979 (0.873-0.997) for UACs, and 0.937 (0.785-0.984) for UVCs. Performance was similar for the set of 58 test images consisting of 2 or more catheters, with an AP of 0.975 (0.255-1.000) for NGTs, 0.997 (0.009-1.000) for ETTs, 0.981 (0.797-0.998) for UACs, and 0.937 (0.689-0.990) for UVCs. Our network thus achieves strong performance in the simultaneous detection of these four catheter types. Radiologists may use such an algorithm as a time-saving mechanism to automate reporting of catheters on radiographs.

Sepehr Ataei, Javad Alirezaie, Paul Babyn

Low Dose CT Denoising research aims to reduce the risks of radiation exposure to patients. Recently researchers have used deep learning to denoise low dose CT images with promising results. However, approaches that use mean-squared-error (MSE) tend to over smooth the image resulting in loss of fine structural details in low contrast regions of the image. These regions are often crucial for diagnosis and must be preserved in order for Low dose CT to be used effectively in practice. In this work we use a cascade of two neural networks, the first of which aims to reconstruct normal dose CT from low dose CT by minimizing perceptual loss, and the second which predicts the difference between the ground truth and prediction from the perceptual loss network. We show that our method outperforms related works and more effectively reconstructs fine structural details in low contrast regions of the image.

Xin Yi, Scott J. Adams, Robert D. E. Henderson et al.

Catheters are the second most common abnormal finding on radiographs. The position of catheters must be assessed on all radiographs, as serious complications can arise if catheters are malpositioned. However, due to the large number of radiographs performed each day, there can be substantial delays between the time a radiograph is performed and when it is interpreted by a radiologist. Computer-aided approaches hold the potential to assist in prioritizing radiographs with potentially malpositioned catheters for interpretation and automatically insert text indicating the placement of catheters in radiology reports, thereby improving radiologists' efficiency. After 50 years of research in computer-aided diagnosis, there is still a paucity of study in this area. With the development of deep learning approaches, the problem of catheter assessment is far more solvable. Therefore, we have performed a review of current algorithms and identified key challenges in building a reliable computer-aided diagnosis system for assessment of catheters on radiographs. This review may serve to further the development of machine learning approaches for this important use case.

Maryam Gholizadeh-Ansari, Javad Alirezaie, Paul Babyn

Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep neural network that uses dilated convolutions with different dilation rates instead of standard convolution helping to capture more contextual information in fewer layers. Also, we have employed residual learning by creating shortcut connections to transmit image information from the early layers to later ones. To further improve the performance of the network, we have introduced a non-trainable edge detection layer that extracts edges in horizontal, vertical, and diagonal directions. Finally, we demonstrate that optimizing the network by a combination of mean-square error loss and perceptual loss preserves many structural details in the CT image. This objective function does not suffer from over smoothing and blurring effects caused by per-pixel loss and grid-like artifacts resulting from perceptual loss. The experiments show that each modification to the network improves the outcome while only minimally changing the complexity of the network.

Xin Yi, Ekta Walia, Paul Babyn

Generative adversarial networks have gained a lot of attention in the computer vision community due to their capability of data generation without explicitly modelling the probability density function. The adversarial loss brought by the discriminator provides a clever way of incorporating unlabeled samples into training and imposing higher order consistency. This has proven to be useful in many cases, such as domain adaptation, data augmentation, and image-to-image translation. These properties have attracted researchers in the medical imaging community, and we have seen rapid adoption in many traditional and novel applications, such as image reconstruction, segmentation, detection, classification, and cross-modality synthesis. Based on our observations, this trend will continue and we therefore conducted a review of recent advances in medical imaging using the adversarial training scheme with the hope of benefiting researchers interested in this technique.

Xin Yi, Scott Adams, Paul Babyn et al.

Catheters are commonly inserted life supporting devices. X-ray images are used to assess the position of a catheter immediately after placement as serious complications can arise from malpositioned catheters. Previous computer vision approaches to detect catheters on X-ray images either relied on low-level cues that are not sufficiently robust or only capable of processing a limited number or type of catheters. With the resurgence of deep learning, supervised training approaches are begining to showing promising results. However, dense annotation maps are required, and the work of a human annotator is hard to scale. In this work, we proposed a simple way of synthesizing catheters on X-ray images and a scale recurrent network for catheter detection. By training on adult chest X-rays, the proposed network exhibits promising detection results on pediatric chest/abdomen X-rays in terms of both precision and recall.

Xin Yi, Ekta Walia, Paul Babyn

Melanoma is a curable aggressive skin cancer if detected early. Typically, the diagnosis involves initial screening with subsequent biopsy and histopathological examination if necessary. Computer aided diagnosis offers an objective score that is independent of clinical experience and the potential to lower the workload of a dermatologist. In the recent past, success of deep learning algorithms in the field of general computer vision has motivated successful application of supervised deep learning methods in computer aided melanoma recognition. However, large quantities of labeled images are required to make further improvements on the supervised method. A good annotation generally requires clinical and histological confirmation, which requires significant effort. In an attempt to alleviate this constraint, we propose to use categorical generative adversarial network to automatically learn the feature representation of dermoscopy images in an unsupervised and semi-supervised manner. Thorough experiments on ISIC 2016 skin lesion chal- lenge demonstrate that the proposed feature learning method has achieved an average precision score of 0.424 with only 140 labeled images. Moreover, the proposed method is also capable of generating real-world like dermoscopy images.

Xin Yi, Paul Babyn

Low Dose Computed Tomography (LDCT) has offered tremendous benefits in radiation restricted applications, but the quantum noise as resulted by the insufficient number of photons could potentially harm the diagnostic performance. Current image-based denoising methods tend to produce a blur effect on the final reconstructed results especially in high noise levels. In this paper, a deep learning based approach was proposed to mitigate this problem. An adversarially trained network and a sharpness detection network were trained to guide the training process. Experiments on both simulated and real dataset shows that the results of the proposed method have very small resolution loss and achieves better performance relative to the-state-of-art methods both quantitatively and visually.