Accurate Segmentation of Nuclear Regions with Multi-Organ Histopathology Images Using Artificial Intelligence for Cancer Diagnosis in Personalized Medicine

Abstract

Accurate nuclear segmentation in histopathology images plays a key role in digital pathology. It is considered a prerequisite for the determination of cell phenotype, nuclear morphometrics, cell classification, and the grading and prognosis of cancer. However, it is a very challenging task because of the different types of nuclei, large intraclass variations, and diverse cell morphologies. Consequently, the manual inspection of such images under high-resolution microscopes is tedious and time-consuming. Alternatively, artificial intelligence (AI)-based automated techniques, which are fast and robust, and require less human effort, can be used. Recently, several AI-based nuclear segmentation techniques have been proposed. They have shown a significant performance improvement for this task, but there is room for further improvement. Thus, we propose an AI-based nuclear segmentation technique in which we adopt a new nuclear segmentation network empowered by residual skip connections to address this issue. Experiments were performed on two publicly available datasets: (1) The Cancer Genome Atlas (TCGA), and (2) Triple-Negative Breast Cancer (TNBC). The results show that our proposed technique achieves an aggregated Jaccard index (AJI) of 0.6794, Dice coefficient of 0.8084, and F1-measure of 0.8547 on TCGA dataset, and an AJI of 0.7332, Dice coefficient of 0.8441, precision of 0.8352, recall of 0.8306, and F1-measure of 0.8329 on the TNBC dataset. These values are higher than those of the state-of-the-art methods.

Artificial Intelligence-Based Solution in Personalized Computer-Aided Arthroscopy of Shoulder Prostheses

“…After the successful application of the DL models in object detection, classification, and localization, various DL algorithms have been successfully used to design classification [36,37] and segmentation frameworks [38][39][40] to diagnose different diseases. However, the use and potential advantages of DL-based models in arthroplasty are limited.…”

Domain-Adaptive Artificial Intelligence-Based Model for Personalized Diagnosis of Trivial Lesions Related to COVID-19 in Chest Computed Tomography Scans

“…Our proposed segmentation model was implemented in the MATLAB R2020b (Math-Works, Inc., Natick, MA, USA) coding framework using a stand-alone desktop computer with the following specifications: Intel Corei7 CPU, 16 GB RAM, NVIDIA GeForce GPU (GTX 1070), and Windows 10 operating system. In our selected optimization scheme, we used the SGD optimizer with a small learning rate value of 0.001, as used in most of the existing studies [37][38][39][40][41]. Generally, with a small learning rate, the minimum may eventually be approached; nonetheless, it will take many epochs to get there [42].…”

A survey on recent trends in deep learning for nucleus segmentation from histopathology images

“…But the size of the dataset was carefully considered when deciding on the analytical pipeline. This was the main reason why more traditional methods were used Year: 2021 Mahmood et al ( 2021 ) proposed AI-based nuclear segmentation technique and Residual Skip Connections-based segmentation Network for Nuclei (R-SNN) of Nuclear Regions with Multi-Organ Histopathology Image Features: Backbone: Not mentioned Loss: Cross-entropy Adam optimizer was employed, and R-SNN comprised 15,279,174 trainable parameters. The proposed method based on R-SNN used the stain normalization technique to come up with images with standard appearances and reduce the image’s color variants and intensity.…”

“…Mahmood et al ( 2021 ) proposed AI-based nuclear segmentation technique and Residual Skip Connections-based segmentation Network for Nuclei (R-SNN) of Nuclear Regions with Multi-Organ Histopathology Image…”