One of the main obstacles for the implementation of deep convolutional neural networks (DCNNs) in the clinical pathology workflow is their low capability to overcome variability in slide preparation and scanner configuration, that leads to changes in tissue appearance. Some of these variations may not be not included in the training data, which means that the models have a risk to not generalize well. Addressing such variations and evaluating them in reproducible scenarios allows understanding of when the models generalize better, which is crucial for performance improvements and better DCNN models. Staining normalization techniques (often based on color deconvolution and deep learning) and color augmentation approaches have shown improvements in the generalization of the classification tasks for several tissue types. Domain-invariant training of DCNN's is also a promising technique to address the problem of training a single model for different domains, since it includes the source domain information to guide the training toward domain-invariant features, achieving state-of-the-art results in classification tasks. In this article, deep domain adaptation in convolutional networks (DANN) is applied to computational pathology and compared with widely used staining normalization and color augmentation methods in two challenging classification tasks. The classification tasks rely on two openly accessible datasets, targeting Gleason grading in prostate cancer, and mitosis classification in breast tissue. The benchmark of the different techniques and their combination in two DCNN architectures allows us to assess the generalization abilities and advantages of each method in the considered classification tasks. The code for reproducing our experiments and preprocessing the data is publicly available¹. Quantitative and qualitative results show that the use of DANN helps model generalization to external datasets. The combination of several techniques to manage color heterogeneity suggests that several methods together, such as color augmentation methods with DANN training, can generalize even further. The results do not show a single best technique among the considered methods, even when combining them. However, color augmentation and DANN training obtain most often the best results (alone or combined with color normalization and color augmentation). The statistical significance of the results and the embeddings visualizations provide useful insights to design DCNN that generalizes to unseen staining appearances. Furthermore, in this work, we release for the first time code for DANN evaluation in open access datasets for computational pathology. This work opens the possibility for further research on using DANN models together with techniques that can overcome the tissue preparation differences across datasets to tackle limited generalization.

Screening of lymph node metastases in colorectal cancer (CRC) can be a cumbersome task, but it is amenable to artificial intelligence (AI)-assisted diagnostic solution. Here, we propose a deep learning-based workflow for the evaluation of CRC lymph node metastases from digitized hematoxylin and eosin-stained sections. A segmentation model was trained on 100 whole-slide images (WSIs). It achieved a Matthews correlation coefficient of 0.86 (±0.154) and an acceptable Hausdorff distance of 135.59 μm (±72.14 μm), indicating a high congruence with the ground truth. For metastasis detection, 2 models (Xception and Vision Transformer) were independently trained first on a patch-based breast cancer lymph node data set and were then fine-tuned using the CRC data set. After fine-tuning, the ensemble model showed significant improvements in the F1 score (0.797-0.949; P <.00001) and the area under the receiver operating characteristic curve (0.959-0.978; P <.00001). Four independent cohorts (3 internal and 1 external) of CRC lymph nodes were used for validation in cascading segmentation and metastasis detection models. Our approach showed excellent performance, with high sensitivity (0.995, 1.0) and specificity (0.967, 1.0) in 2 validation cohorts of adenocarcinoma cases (n = 3836 slides) when comparing slide-level labels with the ground truth (pathologist reports). Similarly, an acceptable performance was achieved in a validation cohort (n = 172 slides) with mucinous and signet-ring cell histology (sensitivity, 0.872; specificity, 0.936). The patch-based classification confidence was aggregated to overlay the potential metastatic regions within each lymph node slide for visualization. We also applied our method to a consecutive case series of lymph nodes obtained over the past 6 months at our institution (n = 217 slides). The overlays of prediction within lymph node regions matched 100% when compared with a microscope evaluation by an expert pathologist. Our results provide the basis for a computer-assisted diagnostic tool for easy and efficient lymph node screening in patients with CRC.

The image captured in water is hazy due to the several effects of the underwater medium. These effects are governed by the suspended particles that lead to absorption and scattering of light during image formation process. The underwater medium is not friendly for imaging data and brings low contrast and fade color issues. Therefore, during any image based exploration and inspection activity, it is essential to enhance the imaging data before going for further processing. This paper presents a wavelet-based fusion method to enhance the hazy underwater images by addressing the low contrast and color alteration issues. The publicly available hazy underwater images are enhanced and analyzed qualitatively with some state of the art methods. The quantitative study of image quality depicts promising results.

Subsea pipeline corrosion is considered as a severe problem in offshore oil and gas industry. It directly affects the integrity of the pipeline which further leads to cracks and leakages. At present, subsea visual inspection and monitoring is performed by trained human divers; however, offshore infrastructures are moving from shallow to deep waters due to exhaustion of fossil fuels. Therefore, inhospitable underwater environmental conditions for human diver demand imaging-based robotic solution as an alternate for visual inspection and monitoring of subsea pipelines. However, an unfriendly medium is a challenge for underwater imaging-based inspection and monitoring activities due to absorption and scattering of light that further leads to blur, color attenuation, and low contrast. This paper presents a new method for subsea pipeline corrosion estimation by using color information of corroded pipe. As precursor steps, an image restoration and enhancement algorithm are developed for degraded underwater images. The developed algorithm minimizes blurring effects and enhances color and contrast of the images. The enhanced colors in the imaging data help in corrosion estimation process. The image restoration and enhancement algorithm are tested on both experimentally collected as well as publicly available hazy underwater images. A reasonable accuracy is achieved in corrosion estimation that helped to distinguish between corroded and non-corroded surface areas of corroded pipes. The qualitative and quantitative analyses show promising results that encourage to integrate the proposed method into a robotic system that can be used for real-time underwater pipeline corrosion inspection activity.

Commercial RGB-D cameras provide the possibility of fast, accurate, and cost-effective 3-D scanning solution in a single package. These economical depth cameras provide several advantages over conventional depth sensors, such as sonars and lidars, in specific usage scenarios. In this paper, we analyze the performance of Kinect v2 time-of-flight camera while operating fully submerged underwater in a customized waterproof housing. Camera calibration has been performed for Kinect's RGB and NIR cameras, and the effect of calibration on the generated 3-D mesh is discussed in detail. To overcome the effect of refraction of light due to the sensor housing and water, we propose a time-of-flight correction method and a fast, accurate and intuitive refraction correction method that can be applied to the acquired depth images, during 3-D mesh generation. Experimental results show that the Kinect v2 can acquire point cloud data up to 650 mm. The reconstruction results have been analyzed qualitatively and quantitatively, and confirm that the 3-D reconstruction of submerged objects at small distances is possible without the requirement of any external NIR light source. The proposed algorithms successfully generated 3-D mesh with a mean error of ±6 mm at a frame rate of nearly 10 fps. We acquired a large data set of RGB, IR and depth data from a submerged Kinect v2. The data set covers a large variety of objects scanned underwater and is publicly available for further use, along with the Kinect waterproof housing design and correction filter codes. The research is aimed toward small-scale research activities and economical solution for 3-D scanning underwater. Applications such as coral reef mapping and underwater SLAM in shallow waters for ROV's can be a viable application area that can benefit from results achieved.

Underwater robotics and imaging have emerged as an attractive field due to complications for human divers in a deepwater environment. Inspection of various installations in an underwater environment is carried out by underwater vehicles. The equipment that is used at present requires high computational cost and dedicated only to single task. This results in an expensive hardware and application-oriented technology, hence restricting the versatility of the underwater vehicle. This article proposes a visual feedback–based heading control and tracking method for the autonomous underwater vehicle to provide a versatile solution. The proposed method is used for subsea pipeline corrosion inspection subjected to hydrodynamic disturbances. There are two parts of this study: the first part includes the heading control of the underwater vehicle using visual feedback to follow the pipeline, whereas the second part involves underwater image enhancement and dehazing using wavelet-based fusion for corrosion estimation. The visual feedback and corrosion estimation rely on the same image data during the inspection of the pipeline, hence, reducing the complexity of the overall algorithm. The performance of the proposed method is evaluated on image dataset acquired in an underwater environment where the camera is mounted on the underwater vehicle.