Cytology screening from Papanicolaou (Pap) smears is a common and effective tool for the preventive clinical management of cervical cancer, where abnormal cell detection from whole slide images serves as the foundation for reporting cervical cytology. However, cervical cell detection remains challenging due to 1) hazily-defined cell types (e.g., ASC-US) with subtle morphological discrepancies caused by the dynamic cancerization process, i.e., cell class ambiguity, and 2) imbalanced class distributions of clinical data may cause missed detection, especially for minor categories, i.e., cell class imbalance. To this end, we propose a holistic and historical instance comparison approach for cervical cell detection. Specifically, we first develop a holistic instance comparison scheme enforcing both RoI-level and class-level cell discrimination. This coarse-to-fine cell comparison encourages the model to learn foreground-distinguishable and class-wise representations. To emphatically improve the distinguishability of minor classes, we then introduce a historical instance comparison scheme with a confident sample selection-based memory bank, which involves comparing current embeddings with historical embeddings for better cell instance discrimination. Extensive experiments and analysis on two large-scale cytology datasets including 42,592 and 114,513 cervical cells demonstrate the effectiveness of our method. The code is available at https://github.com/hjiangaz/HERO.

Instance segmentation plays a vital role in the morphological quantification of biomedical entities such as tissues and cells, enabling precise identification and delineation of different structures. Current methods often address the challenges of touching, overlapping or crossing instances through individual modeling, while neglecting the intrinsic interrelation between these conditions. In this work, we propose a Gradient Anomaly-aware Biomedical Instance Segmentation approach (GAInS), which leverages instance gradient information to perceive local gradient anomaly regions, thus modeling the spatial relationship between instances and refining local region segmentation. Specifically, GAInS is firstly built on a Gradient Anomaly Mapping Module (GAMM), which encodes the radial fields of instances through window sliding to obtain instance gradient anomaly maps. To efficiently refine boundaries and regions with gradient anomaly attention, we propose an Adaptive Local Refinement Module (ALRM) with a gradient anomaly-aware loss function. Extensive comparisons and ablation experiments in three biomedical scenarios demonstrate that our proposed GAInS outperforms other state-of-the-art (SOTA) instance segmentation methods. The code is available at https://github.com/DeepGAInS/GAInS.

Cell instance segmentation in cytology images has significant importance for biology analysis and cancer screening, while remains challenging due to 1) the extensive over-lapping translucent cell clusters that cause the ambigu-ous boundaries, and 2) the confusion of mimics and de-bris as nuclei. In this work, we proposed a De-overlapping Network (DoNet) in a decompose-and-recombined strategy. A Dual-path Region Segmentation Module (DRM) explicitly decomposes the cell clusters into intersection and complement regions, followed by a Semantic Consistency-guided Recombination Module (CRM) for integration. To further introduce the containment relationship of the nu-cleus in the cytoplasm, we design a Mask-guided Region Proposal Strategy (MRP) that integrates the cell attention maps for inner-cell instance prediction. We validate the proposed approach on ISBI2014 and CPS datasets. Ex-periments show that our proposed DoNet significantly outperforms other state-of-the-art (SOTA) cell instance segmentation methods. The code is available at https://github.com/DeepDoNet/DoNet.

A common shortfall of supervised learning for medical imaging is the greedy need for human annotations, which is often expensive and time-consuming to obtain. This paper proposes a semi-supervised classification method for three kinds of apicomplexan parasites and non-infected host cells microscopic images, which uses a small number of labeled data and a large number of unlabeled data for training. There are two challenges in microscopic image recognition. The first is that salient structures of the microscopic images are more fuzzy and intricate than natural images’ on a real-world scale. The second is that insignificant textures, like background staining, lightness, and contrast level, vary a lot in samples from different clinical scenarios. To address these challenges, we aim to learn a distinguishable and appearance-invariant representation by contrastive learning strategy. On one hand, macroscopic images, which share similar shape characteristics in morphology, are introduced to contrast for structure enhancement. On the other hand, different appearance transformations, including color distortion and flittering, are utilized to contrast for texture elimination. In the case where only 1% of microscopic images are labeled, the proposed method reaches an accuracy of 94.90% in a generalized testing set.

MOTIVATION: Apicomplexan parasites, including Toxoplasma, Plasmodium and Babesia, are important pathogens that affect billions of humans and animals worldwide. Usually a microscope is used to detect these parasites, but it is difficult to use microscopes and clinician requires to be trained. Finding a cost-effective solution to detect these parasites is of particular interest in developing countries, in which infection is more common. RESULTS: Here, we propose an alternative method, deep cycle transfer learning (DCTL), to detect apicomplexan parasites, by utilizing deep learning-based microscopic image analysis. DCTL is based on observations of parasitologists that Toxoplasma is banana-shaped, Plasmodium is generally ring-shaped, and Babesia is typically pear-shaped. Our approach aims to connect those microscopic objects (Toxoplasma, Plasmodium, Babesia and erythrocyte) with their morphological similar macro ones (banana, ring, pear and apple) through a cycle transfer of knowledge. In the experiments, we conduct DCTL on 24 358 microscopic images of parasites. Results demonstrate high accuracy and effectiveness of DCTL, with an average accuracy of 95.7% and an area under the curve of 0.995 for all parasites types. This article is the first work to apply knowledge from parasitologists to apicomplexan parasite recognition, and it opens new ground for developing AI-powered microscopy image diagnostic systems. AVAILABILITY AND IMPLEMENTATION: Code and dataset available at https://github.com/senli2018/DCTL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.