Cell nuclei classification in histopathological images using hybrid OLConvNet

TL;DR

This paper introduces OLConvNet, a hybrid deep learning model combining traditional object-level features with CNNs for more flexible and interpretable nuclei classification in histopathological images, outperforming existing models.

Contribution

The study proposes a novel hybrid architecture OLConvNet that integrates interpretability and generalization, using a shallow CNN to reduce training time and improve performance.

Findings

OLConvNet outperforms state-of-the-art deep learning models.

The shallow CNN reduces training time and complexity.

Hybrid approach enhances interpretability and accuracy.

Abstract

Computer-aided histopathological image analysis for cancer detection is a major research challenge in the medical domain. Automatic detection and classification of nuclei for cancer diagnosis impose a lot of challenges in developing state of the art algorithms due to the heterogeneity of cell nuclei and data set variability. Recently, a multitude of classification algorithms has used complex deep learning models for their dataset. However, most of these methods are rigid and their architectural arrangement suffers from inflexibility and non-interpretability. In this research article, we have proposed a hybrid and flexible deep learning architecture OLConvNet that integrates the interpretability of traditional object-level features and generalization of deep learning features by using a shallower Convolutional Neural Network (CNN) named as $CNN_{3L}$. $CNN_{3L}$ reduces the training time by training fewer parameters and hence eliminating space constraints imposed by deeper algorithms. We used F1-score and multiclass Area Under the Curve (AUC) performance parameters to compare the results. To further strengthen the viability of our architectural approach, we tested our proposed methodology with state of the art deep learning architectures AlexNet, VGG16, VGG19, ResNet50, InceptionV3, and DenseNet121 as backbone networks. After a comprehensive analysis of classification results from all four architectures, we observed that our proposed model works well and perform better than contemporary complex algorithms.