This paper presents the culmination of our research in designing a system for computer-aided detection (CAD) of polyps in colonoscopy videos. Our system is based on a hybrid context-shape approach, ...which utilizes context information to remove non-polyp structures and shape information to reliably localize polyps. Specifically, given a colonoscopy image, we first obtain a crude edge map. Second, we remove non-polyp edges from the edge map using our unique feature extraction and edge classification scheme. Third, we localize polyp candidates with probabilistic confidence scores in the refined edge maps using our novel voting scheme. The suggested CAD system has been tested using two public polyp databases, CVC-ColonDB, containing 300 colonoscopy images with a total of 300 polyp instances from 15 unique polyps, and ASU-Mayo database, which is our collection of colonoscopy videos containing 19,400 frames and a total of 5,200 polyp instances from 10 unique polyps. We have evaluated our system using free-response receiver operating characteristic (FROC) analysis. At 0.1 false positives per frame, our system achieves a sensitivity of 88.0% for CVC-ColonDB and a sensitivity of 48% for the ASU-Mayo database. In addition, we have evaluated our system using a new detection latency analysis where latency is defined as the time from the first appearance of a polyp in the colonoscopy video to the time of its first detection by our system. At 0.05 false positives per frame, our system yields a polyp detection latency of 0.3 seconds.
End-to-end learning machines enable a direct mapping from the raw input data to the desired outputs, eliminating the need for hand-crafted features. Despite less engineering effort than the ...hand-crafted counterparts, these learning machines achieve extremely good results for many computer vision and medical image analysis tasks. Two dominant classes of end-to-end learning machines are massive-training artificial neural networks (MTANNs) and convolutional neural networks (CNNs). Although MTANNs have been actively used for a number of medical image analysis tasks over the past two decades, CNNs have recently gained popularity in the field of medical imaging. In this study, we have compared these two successful learning machines both experimentally and theoretically. For that purpose, we considered two well-studied topics in the field of medical image analysis: detection of lung nodules and distinction between benign and malignant lung nodules in computed tomography (CT). For a thorough analysis, we used 2 optimized MTANN architectures and 4 distinct CNN architectures that have different depths. Our experiments demonstrated that the performance of MTANNs was substantially higher than that of CNN when using only limited training data. With a larger training dataset, the performance gap became less evident even though the margin was still significant. Specifically, for nodule detection, MTANNs generated 2.7 false positives per patient at 100% sensitivity, which was significantly (p<0.05) lower than the best performing CNN model with 22.7 false positives per patient at the same level of sensitivity. For nodule classification, MTANNs yielded an area under the receiver-operating-characteristic curve (AUC) of 0.8806 (95% CI: 0.8389–0.9223), which was significantly (p<0.05) greater than the best performing CNN model with an AUC of 0.7755 (95% CI: 0.7120–0.8270). Thus, with limited training data, MTANNs would be a suitable end-to-end machine-learning model for detection and classification of focal lesions that do not require high-level semantic features.
•MTANNs yielded higher performance than CNNs for nodule detection and classification.•Deep CNN architectures achieved higher performance than shallow architectures for nodule detection.•CNN architectures with varying depths performed comparably for nodule classification.•MTANNs can achieve desired performance with a smaller training dataset than do the CNNs.•MTANNs tend to learn the appearance of lesion parts, whereas CNNs attempt to learn the lesion appearance as a whole.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
•Medical image segmentation typically faces limited datasets.•Dataset limitations are broadly grouped into scarce and weak annotations.•Scarce annotations can be addressed proactively via ...cost-effective annotation or by leveraging external labeled or unlabeled datasets.•Scarce annotations can be addressed reactively via various forms of conditional random fields as post processing.•Weak annotations may manifest as sparse, noisy, or only image-level labels.•Sparse and noisy annotations can leveraged via selective and noise-resilient loss functions, respectively.•Image-level labels can leveraged via various forms of class activation maps.•Recommended solutions based on a cost-gain trade-off are provided.
Display omitted
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large, representative, and high quality annotated datasets. However, rarely do we have a perfect training dataset, particularly in the field of medical imaging, where data and annotations are both expensive to acquire. Recently, a large body of research has studied the problem of medical image segmentation with imperfect datasets, tackling two major dataset limitations: scarce annotations where only limited annotated data is available for training, and weak annotations where the training data has only sparse annotations, noisy annotations, or image-level annotations. In this article, we provide a detailed review of the solutions above, summarizing both the technical novelties and empirical results. We further compare the benefits and requirements of the surveyed methodologies and provide our recommended solutions. We hope this survey article increases the community awareness of the techniques that are available to handle imperfect medical image segmentation datasets.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A ...promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.
Computer-aided polyp detection in colonoscopy videos has been the subject of research for over the past decade. However, despite significant advances, automatic polyp detection is still an unsolved ...problem. In this paper, we propose a new polyp detection method based on a unique 3-way image presentation and convolutional neural networks. Our method learns a variety of polyp features such as color, texture, shape, and temporal information in multiple scales, enabling a more accurate polyp localization. Given a polyp candidate, a set of convolution neural networks - each specialized in one type of features - are applied in the vicinity of the candidate and then their results are aggregated to either accept or reject the candidate. Our experimental results based on our collection of videos, which to our knowledge is the largest annotated polyp database, shows a remarkable performance improvement over the state-of-the-art, significantly reducing the number of false positives in nearly all operating points. In addition, we propose a new performance curve, demonstrating that our new method significantly decreases polyp detection latency, which is defined as the time from the first appearance of a polyp in the video to the time of its first detection by our method.
This paper presents a new method for detecting polyps in colonoscopy. Its novelty lies in integrating the global geometric constraints of polyps with the local patterns of intensity variation across ...polyp boundaries: the former drives the detector towards the objects with curvy boundaries, while the latter minimizes the misleading effects of polyp-like structures. This paper makes three original contributions: (1) a fast and discriminative patch descriptor for precisely characterizing patterns of intensity variation across boundaries, (2) a new 2-stage classification scheme for accurately excluding non-polyp edges from an overcomplete edge map, and (3) a novel voting scheme for robustly localizing polyps from the retained edges. Evaluations on a public database and our own videos demonstrate that our method is promising and outperforms the state-of-the-art methods.
The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal ...depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths; and (2) their skip connections impose an unnecessarily restrictive fusion scheme, forcing aggregation only at the same-scale feature maps of the encoder and decoder sub-networks. To overcome these two limitations, we propose UNet++, a new neural architecture for semantic and instance segmentation, by (1) alleviating the unknown network depth with an efficient ensemble of U-Nets of varying depths, which partially share an encoder and co-learn simultaneously using deep supervision; (2) redesigning skip connections to aggregate features of varying semantic scales at the decoder sub-networks, leading to a highly flexible feature fusion scheme; and (3) devising a pruning scheme to accelerate the inference speed of UNet++. We have evaluated UNet++ using six different medical image segmentation datasets, covering multiple imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and electron microscopy (EM), and demonstrating that (1) UNet++ consistently outperforms the baseline models for the task of semantic segmentation across different datasets and backbone architectures; (2) UNet++ enhances segmentation quality of varying-size objects-an improvement over the fixed-depth U-Net; (3) Mask RCNN++ (Mask R-CNN with UNet++ design) outperforms the original Mask R-CNN for the task of instance segmentation; and (4) pruned UNet++ models achieve significant speedup while showing only modest performance degradation. Our implementation and pre-trained models are available at https://github.com/MrGiovanni/UNetPlusPlus.
Annotation-efficient deep learning refers to methods and practices that yield high-performance deep learning models without the use of massive carefully labeled training datasets. This paradigm has ...recently attracted attention from the medical imaging research community because (1) it is difficult to collect large, representative medical imaging datasets given the diversity of imaging protocols, imaging devices, and patient populations, (2) it is expensive to acquire accurate annotations from medical experts even for moderately sized medical imaging datasets, and (3) it is infeasible to adapt data-hungry deep learning models to detect and diagnose rare diseases whose low prevalence hinders data collection.