Colonoscopy is a vital tool for the early diagnosis of colorectal cancer, which is one of the main causes of cancer-related mortality globally, hence it is deemed an essential technique for the prevention and early detection of colorectal cancer. The research introduces a unique multidirectional architectural framework to automate polyp detection within colonoscopy images while helping resolve limited healthcare dataset sizes and annotation complexities. The research implements a comprehensive system that delivers synthetic data generation through Stable Diffusion enhancements together with detection and segmentation algorithms. This detection approach combines Faster R-CNN for initial object localization while the Segment Anything Model (SAM) refines the segmentation masks. The faster R-CNN detection algorithm achieved a recall of 93.08% combined with a precision of 88.97% and an F1 score of 90.98%.SAM is then used to generate the image mask. The research evaluated five state-of-the-art segmentation models that included U-Net, PSPNet, FPN, LinkNet, and MANet using ResNet34 as a base model. The results demonstrate the superior performance of FPN with the highest scores of PSNR (7.205893) and SSIM (0.492381), while UNet excels in recall (84.85%) and LinkNet shows balanced performance in IoU (64.20%) and Dice score (77.53%). This framework achieves its primary breakthrough through a synthetic data system and an automatic ground truth generator, as these methods combat data limitations without sacrificing medical accuracy. The framework unites multiple architectures together with extensive evaluation metrics to set new benchmarks, which should speed up medical image segmentation tools across different medical specialties.

The paper proposes to learn graph representations from visual data via graph convolutional unit (GCU). It transforms a 2D feature maps extracted from a neural network to a sample-dependent graph, where pixels with similar features form a vertex and edges measure affinity of vertices in a feature space. Then graph convolutions are applied to pass information along the edges of the graph and update the vertex features. Finally, the updated vertex features are projected back to 2D grids based on the pixel-to-vertex assignment. GCU can be integrated into existing networks allowing end-to-end training and capturing long-range dependencies among regions (vertices).

Safety measures need to be systemically investigated to what extent they evaluate the intended performance of Deep Neural Networks (DNNs) for critical applications. Due to a lack of verification methods for high-dimensional DNNs, a trade-off is needed between accepted performance and handling of out-of-distribution (OOD) samples. This work evaluates rejecting outputs from semantic segmentation DNNs by applying a Mahalanobis distance (MD) based on the most probable class-conditional Gaussian distribution for the predicted class as an OOD score. The evaluation follows three DNNs trained on the Cityscapes dataset and tested on four automotive datasets and finds that classification risk can drastically be reduced at the cost of pixel coverage, even when applied on unseen datasets. The applicability of our findings will support legitimizing safety measures and motivate their usage when arguing for safe usage of DNNs in automotive perception.

Estimating the traversability of terrain should be reliable and accurate in diverse conditions for autonomous driving in off-road environments. However, learning-based approaches often yield unreliable results when confronted with unfamiliar contexts, and it is challenging to obtain manual annotations frequently for new circumstances. In this paper, we introduce a method for learning traversability from images that utilizes only self-supervision and no manual labels, enabling it to easily learn traversability in new circumstances. To this end, we first generate self-supervised traversability labels from past driving trajectories by labeling regions traversed by the vehicle as highly traversable. Using the self-supervised labels, we then train a neural network that identifies terrains that are safe to traverse from an image using a one-class classification algorithm. Additionally, we supplement the limitations of self-supervised labels by incorporating methods of self-supervised learning of visual representations. To conduct a comprehensive evaluation, we collect data in a variety of driving environments and perceptual conditions and show that our method produces reliable estimations in various environments. In addition, the experimental results validate that our method outperforms other self-supervised traversability estimation methods and achieves comparable performances with supervised learning methods trained on manually labeled data.

Recent advances in deep learning technology have triggered radical progress in the autonomy of ground vehicles. Marine coastal Autonomous Surface Vehicles (ASVs) that are regularly used for surveillance, monitoring and other routine tasks can benefit from this autonomy. Long haul deep sea transportation activities are additional opportunities. These two use cases present very different terrains -- the first being coastal waters -- with many obstacles, structures and human presence while the latter is mostly devoid of such obstacles. Variations in environmental conditions are common to both terrains. Robust labeled datasets mapping such terrains are crucial in improving the situational awareness that can drive autonomy. However, there are only limited such maritime datasets available and these primarily consist of optical images. Although, Long Wave Infrared (LWIR) is a strong complement to the optical spectrum that helps in extreme light conditions, a labeled public dataset with LWIR images does not currently exist. In this paper, we fill this gap by presenting a labeled dataset of over 2,900 LWIR segmented images captured in coastal maritime environment under diverse conditions. The images are labeled using instance segmentation and classified in seven categories -- sky, water, obstacle, living obstacle, bridge, self and background. We also evaluate this dataset across three deep learning architectures (UNet, PSPNet, DeepLabv3) and provide detailed analysis of its efficacy. While the dataset focuses on the coastal terrain it can equally help deep sea use cases. Such terrain would have less traffic, and the classifier trained on cluttered environment would be able to handle sparse scenes effectively. We share this dataset with the research community with the hope that it spurs new scene understanding capabilities in the maritime environment.

To mitigate the radiologist's workload, computer-aided diagnosis with the capability to review and analyze medical images is gradually deployed. Deep learning-based region of interest segmentation is among the most exciting use cases. However, this paradigm is restricted in real-world clinical applications due to poor robustness and generalization. The issue is more sinister with a lack of training data. In this paper, we address the challenge from the representation learning point of view. We investigate that the collapsed representations, as one of the main reasons which caused poor robustness and generalization, could be avoided through transfer learning. Therefore, we propose a novel two-stage framework for robust generalized segmentation. In particular, an unsupervised Tile-wise AutoEncoder (T-AE) pretraining architecture is coined to learn meaningful representation for improving the generalization and robustness of the downstream tasks. Furthermore, the learned knowledge is transferred to the segmentation benchmark. Coupled with an image reconstruction network, the representation keeps to be decoded, encouraging the model to capture more semantic features. Experiments of lung segmentation on multi chest X-ray datasets are conducted. Empirically, the related experimental results demonstrate the superior generalization capability of the proposed framework on unseen domains in terms of high performance and robustness to corruption, especially under the scenario of the limited training data.

Cancer is one of the deadliest diseases faced by mankind since ancient times. If the tumour is detected in early stages, the chances of survival increase drastically. Deep Learning (CNN) has transformed computer vision including diagnosis on medical images. In this post we will harness the power of CNNs to detect and segment tumours from Brain MRI images. See example of Brain MRI image with tumour below and the result of segmentation on it.

We present a fully convolutional neural network for segmenting ischemic stroke lesions in CT perfusion images for the ISLES 2018 challenge. Treatment of stroke is time sensitive and current standards for lesion identification require manual segmentation, a time consuming and challenging process. Automatic segmentation methods present the possibility of accurately identifying lesions and improving treatment planning. Our model is based on the PSPNet, a network architecture that makes use of pyramid pooling to provide global and local contextual information. To learn the varying shapes of the lesions, we train our network using focal loss, a loss function designed for the network to focus on learning the more difficult samples. We compare our model to networks trained using the U-Net and V-Net architectures. Our approach demonstrates effective performance in lesion segmentation and ranked among the top performers at the challenge conclusion.

The field of semantic segmentation has many popular networks, including U-Net (2015), FCN (2015), PSPNet (2017), and others. In this study, we used an AMD Radeon GPU to run these networks. We used ROCm-TensorFlow 1.3 and ROCm 1.7.137 as our operating framework. HIP-TensorFLow 1.0.1 was recently updated to TensorFlow 1.3, with HIP being removed and made into its own repository at the same time. As a result, the old HIP-TensorFlow repository is no longer viewable.