IMCellXMBD: A statistical approach for robust cell identification and quantification from imaging mass cytometry images

ImagingMass Cytometry (IMC) has become a useful tool in biomedical research due to its capability to measure over 100 markers simultaneously. Unfortunately, some protein channels in IMC images can be very noisy, whichmay significantly affect the phenotyping results without proper data processing. We developed IMCellXMBD, a highly effective and generalizable cell identification and quantification method for IMC images. IMCell performs denoising by subtracting an estimated background noise value from pixel values for each individual protein channel, identifies positive cells from negative cells by comparing the distribution between segmented cells and decoy cells, and normalize the protein expression levels of the identified positive cells for downstream data analysis. Experimental results demonstrate that our method significantly improves the reliability of cell phenotyping which is essential for using IMC in biomedical studies.

Automated cone photoreceptor cell identification in confocal adaptive optics scanning laser ophthalmoscope images based on object detection

Cone photoreceptor cell identification is important for the early diagnosis of retinopathy. In this study, an object detection algorithm is used for cone cell identification in confocal adaptive optics scanning laser ophthalmoscope (AOSLO) images. An effectiveness evaluation of identification using the proposed method reveals precision, recall, and [Formula: see text]-score of 95.8%, 96.5%, and 96.1%, respectively, considering manual identification as the ground truth. Various object detection and identification results from images with different cone photoreceptor cell distributions further demonstrate the performance of the proposed method. Overall, the proposed method can accurately identify cone photoreceptor cells on confocal adaptive optics scanning laser ophthalmoscope images, being comparable to manual identification.

DeepLab and Bias Field Correction Based Automatic Cone Photoreceptor Cell Identification with Adaptive Optics Scanning Laser Ophthalmoscope Images

The identification of cone photoreceptor cells is important for early diagnosing of eye diseases. We proposed automatic deep-learning cone photoreceptor cell identification on adaptive optics scanning laser ophthalmoscope images. The proposed algorithm is based on DeepLab and bias field correction. Considering manual identification as reference, our algorithm is highly effective, achieving precision, recall, and F 1 score of 96.7%, 94.6%, and 95.7%, respectively. To illustrate the performance of our algorithm, we present identification results for images with different cone photoreceptor cell distributions. The experimental results show that our algorithm can achieve accurate photoreceptor cell identification on images of human retinas, which is comparable to manual identification.