Planktonic organisms including phyto-, zoo-, and mixoplankton are key components of aquatic ecosystems and respond quickly to changes in the environment, therefore their monitoring is vital to follow and understand these changes. Advances in imaging technology have enabled novel possibilities to study plankton populations, but the manual classification of images is time consuming and expert-based, making such an approach unsuitable for large-scale application and urging for automatic solutions for the analysis, especially recognizing the plankton species from images. Despite the extensive research done on automatic plankton recognition, the latest cutting-edge methods have not been widely adopted for operational use. In this paper, a comprehensive survey on existing solutions for automatic plankton recognition is presented. First, we identify the most notable challenges that make the development of plankton recognition systems difficult and restrict the deployment of these systems for operational use. Then, we provide a detailed description of solutions found in plankton recognition literature. Finally, we propose a workflow to identify the specific challenges in new datasets and the recommended approaches to address them. Many important challenges remain unsolved including the following: (1) the domain shift between the datasets hindering the development of an imaging instrument independent plankton recognition system, (2) the difficulty to identify and process the images of previously unseen classes and non-plankton particles, and (3) the uncertainty in expert annotations that affects the training of the machine learning models. To build harmonized instrument and location agnostic methods for operational purposes these challenges should be addressed in future research.

Early diagnosis of retinopathy is essential for preventing retinal complications and visual impairment due to diabetes. For the detection of retinopathy lesions from retinal images, several automatic approaches based on deep neural networks have been developed in the recent years. Most of the proposed methods produce point estimates of pixels belonging to the lesion areas and give no or little information on the uncertainty of method predictions. However, the latter can be essential in the examination of the medical condition of the patient when the goal is early detection of abnormalities. This work extends the recent research with a Bayesian framework by considering the parameters of a convolutional neural network as random variables and utilizing stochastic variational dropout based approximation for uncertainty quantification. The framework includes an extended validation procedure and it allows analyzing lesion segmentation distributions, model calibration and prediction uncertainties. Also the challenges related to the deep probabilistic model and uncertainty quantification are presented. The proposed method achieves area under precision-recall curve of 0.84 for hard exudates, 0.641 for soft exudates, 0.593 for haemorrhages, and 0.484 for microaneurysms on IDRiD dataset.

We address the performance evaluation practices for developing medical image analysis methods, in particular, how to establish and share databases of medical images with verified ground truth and solid evaluation protocols. Such databases support the development of better algorithms, execution of profound method comparisons, and, consequently, technology transfer from research laboratories to clinical practice. For this purpose, we propose a framework consisting of reusable methods and tools for the laborious task of constructing a benchmark database. We provide a software tool for medical image annotation helping to collect class label, spatial span, and expert's confidence on lesions and a method to appropriately combine the manual segmentations from multiple experts. The tool and all necessary functionality for method evaluation are provided as public software packages. As a case study, we utilized the framework and tools to establish the DiaRetDB1 V2.1 database for benchmarking diabetic retinopathy detection algorithms. The database contains a set of retinal images, ground truth based on information from multiple experts, and a baseline algorithm for the detection of retinopathy lesions.