A Novel Heteromorphous Convolutional Neural Network for Automated Assessment of Tumors in Colon and Lung Histopathology Images

Abstract

The automated assessment of tumors in medical image analysis encounters challenges due to the resemblance of colon and lung tumors to non-mitotic nuclei and their heteromorphic characteristics. An accurate assessment of tumor nuclei presence is crucial for determining tumor aggressiveness and grading. This paper proposes a new method called ColonNet, a heteromorphous convolutional neural network (CNN) with a feature grafting methodology categorically configured for analyzing mitotic nuclei in colon and lung histopathology images. The ColonNet model consists of two stages: first, identifying potential mitotic patches within the histopathological imaging areas, and second, categorizing these patches into squamous cell carcinomas, adenocarcinomas (lung), benign (lung), benign (colon), and adenocarcinomas (colon) based on the model’s guidelines. We develop and employ our deep CNNs, each capturing distinct structural, textural, and morphological properties of tumor nuclei, to construct the heteromorphous deep CNN. The execution of the proposed ColonNet model is analyzed by its comparison with state-of-the-art CNNs. The results demonstrate that our model surpasses others on the test set, achieving an impressive F1 score of 0.96, sensitivity and specificity of 0.95, and an area under the accuracy curve of 0.95. These outcomes underscore our hybrid model’s superior performance, excellent generalization, and accuracy, highlighting its potential as a valuable tool to support pathologists in diagnostic activities.

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures

“… Rajput and Subasi [ 11 ] used ResNet50 and achieved a remarkable accuracy of 99.8 % for colon cancer classification, although they did not report AUC metrics. Iqbal et al [ 15 ] introduced ColonNet for colon cancer classification, achieving an accuracy of 96.31 % along with an AUC of 0.95 using histopathology images as the dataset. …”

“…Iqbal et al [ 15 ] introduced ColonNet for colon cancer classification, achieving an accuracy of 96.31 % along with an AUC of 0.95 using histopathology images as the dataset.…”

“…Iqbal et al [ 15 ] introduced a new approach called ColonNet. They compared their proposed ColonNet model to state-of-the-art CNNs, showing that it outperformed others on the test set with an impressive F1-score of 0.96, sensitivity and specificity of 0.95, and an area under the accuracy curve of 0.95.…”

“…Methods encompassed a wide range, from hybrid networks to image enhancements using VGG16 and CLAHE, as seen in the work of Hadiyoso et al [ 13 ]. Other researchers, such as Iqbal et al [ 15 ], focused on achieving higher F1-scores, while others emphasized transfer learning, as exemplified by the studies conducted by Kumar et al [ 18 ] and Al Ghamdi et al [ 16 ]. Neural architecture searches were employed by Stephen and Sain [ 17 ].…”

“…Tested only on one dataset. Hadiyoso et al [ 13 ] VGG16 with CLAHE LC25000 Image enhancement 98.96 Wahid et al [ 14 ] Various CNNs LC25000 Multiple models Up to 99.87 Iqbal et al [ 15 ] ColonNet LC25000 High F1-score 96.31 Al Ghamdi et al [ 16 ] ShuffleNet, DCRNN LC25000 Transfer learning 98.99 Stephen and Sain [ 17 ] Neural Arch Search LC25000 Neural net search 93.91 Kumar et al [ 18 ] Transfer Learning LC25000 Feature extraction 98.60 Hage Chehade et al [ 19 ] Various ML models LC25000 Multiple models Up to 99 Mridha et al [ 20 ] DL Framework LC25000 5 types of cells 98.30 Mehmood et al [ 21 ] Modified AlexNet LC25000 Fine-tuned model 98.40 Provat et al [ 22 ] Custom CNN LC25000 Cyclic learning rates ...…”