The advent of high-throughput automated imaging technology has enabled us to capture various morphological features of single cells under different perturbations at single-cell resolution. Concurrently, significant advancements in deep learning for computer vision tasks have greatly enhanced our ability to analyze large-scale high-throughput images. These technological advancements have facilitated researchers’ understanding of compound mechanisms of action, drug repurposing, and the characterization of cellular morphological dynamics under perturbations, ultimately contributing to the development of novel therapeutic drugs. In this paper, we first summarize various model learning paradigms in the task of phenotypic drug discovery (PDD), including weakly supervised representation learning and multimodal learning. We then catalog existing image datasets and their processing methods, including the latest multi-channel image processing algorithms. Finally, we summarize the current challenges in PDD tasks and discuss future research directions. The literature statistics for this paper can be found at https://github.com/Boom5426/Awesome-Phenotypic-Drug-Discovery.

Difference-Deformable Convolution With Pseudo Scale Instance Map for Cell Localization Cell localization still faces two unresolved challenges: 1) the dramatic variations in cell morphology, coupled with the heterogeneous intensity distribution of lightly stained cells; 2) existing cell location maps lack scale information, resulting in insufficient supervision for point maps and inaccurate supervision for density maps. 1) To address the first challenges, we introduce a novel gradient-aware and shape-adaptive Difference-Deformable Convolution (DDConv), which enhances the model’s ro- bustness to color by leveraging gradient information while adaptively adjusting the shape of the convolutional ker- nel to tackle the substantial variability in cell morphology. 2) To overcome the issue of unreasonable location maps, we propose the Pseudo-Scale Instance (PSI) map, which can adaptively provide the corresponding scale information for each cell to realize accurate supervision. We analyze and evaluate DDConv and the PSI map in three challenging cell localization tasks. In comparison to existing methods, our proposed approach significantly enhances localization performance, setting a new benchmark for the cell localiza- tion task.

Cell localization constitutes a fundamental research domain within the realm of pathology image analysis, with its core objective being the precise identification of cell spatial coordinates. The task has always involved the challenge of large color variations among cells, uneven distribution, and overlapping borders. Furthermore, in realistic cell localization scenarios, the existing state-of-the-art methods suffer from high computational costs and slow inference times, which severely reduce the efficiency of computer-assisted. To tackle the above issues, a lightweight and efficient cell localization model named Lite-UNet is proposed. Specifically, the Lite-UNet encompasses three pivotal modules. Firstly, we introduce a gradient aggregation module grounded in difference convolution. This module effectively mitigates the challenge posed by extensive color variations among cells by adeptly leveraging gradient information. Secondly, we propose an efficient plug-and-play graph correlation attention module, which optimizes the feature representation capabilities by encoding higher-order feature associations. Finally, we design a lightweight Ghost\_CBAM module that alleviates the difficulty of uneven cell distribution while forming the base module of the Lite-UNet. Extensive experiments show that our Lite-UNet is capable of locating cells in images quickly and accurately, thus further improving the efficiency of computer-assisted medicine.

Cell localization in medical pathology image analysis is a challenging task due to the significant variation in cell shape, size and color shades. Existing localization methods continue to tackle these challenges separately, frequently facing complications where these difficulties intersect and adversely impact model performance. In this paper, these challenges are first reframed as issues of feature misalignment between cell images and location maps, which are then collectively addressed. Specifically, we propose a feature alignment model based on a multi-scale hypergraph attention network. The model considers local regions in the feature map as nodes and utilizes a learnable similarity metric to construct hypergraphs at various scales. We then utilize a hypergraph convolutional network to aggregate the features associated with the nodes and achieve feature alignment between the cell images and location maps. Furthermore, we introduce a stepwise adaptive fusion module to fuse features at different levels effectively and adaptively. The comprehensive experimental results demonstrate the effectiveness of our proposed multi-scale hypergraph attention module in addressing the issue of feature misalignment, and our model achieves state-of-the-art performance across various cell localization datasets.

Cell localization is an important area of medical image analysis, which is dedicated to predicting the precise location of cells in an image. The existing localization paradigm is to predict the density map using a Convolutional Neural Networks (CNN) model based on vanilla convolution and then process the density map using a local maximum search strategy to obtain the cell location and number information. However, there are three main problems in this paradigm: 1) CNN models based on vanilla convolution have difficulty in handling large variations in cell color; 2) The density map is difficult to provide accurate cell location information and ideal gradient information, and the information loss is more obvious in dense regions; 3) The post-processing strategy of density maps is susceptible to background noise and mutual interference between negative and positive cells. To tackle the above issues, we have made a comprehensive update of the existing paradigm, which consists of three parts: 1) A multi-scale gradient aggregation module based on difference convolution to effectively mitigate the challenge of large variations in cell color; 2) A new exponential distance transform map that provides accurate cell location information along with ideal gradient information for model learning; 3) A post-processing strategy named cell center localization strategy based on location maps that can significantly improve the localization performance. Extensive experiments on multiple datasets show that our approach can substantially improve cell localization and counting performance, establishing a new baseline for the cell localization task, and thereby increasing the efficiency of computer-aided diagnosis.