A Framework for Lung and Colon Cancer Diagnosis via Lightweight Deep Learning Models and Transformation Methods

Abstract

Among the leading causes of mortality and morbidity in people are lung and colon cancers. They may develop concurrently in organs and negatively impact human life. If cancer is not diagnosed in its early stages, there is a great likelihood that it will spread to the two organs. The histopathological detection of such malignancies is one of the most crucial components of effective treatment. Although the process is lengthy and complex, deep learning (DL) techniques have made it feasible to complete it more quickly and accurately, enabling researchers to study a lot more patients in a short time period and for a lot less cost. Earlier studies relied on DL models that require great computational ability and resources. Most of them depended on individual DL models to extract features of high dimension or to perform diagnoses. However, in this study, a framework based on multiple lightweight DL models is proposed for the early detection of lung and colon cancers. The framework utilizes several transformation methods that perform feature reduction and provide a better representation of the data. In this context, histopathology scans are fed into the ShuffleNet, MobileNet, and SqueezeNet models. The number of deep features acquired from these models is subsequently reduced using principal component analysis (PCA) and fast Walsh–Hadamard transform (FHWT) techniques. Following that, discrete wavelet transform (DWT) is used to fuse the FWHT’s reduced features obtained from the three DL models. Additionally, the three DL models’ PCA features are concatenated. Finally, the diminished features as a result of PCA and FHWT-DWT reduction and fusion processes are fed to four distinct machine learning algorithms, reaching the highest accuracy of 99.6%. The results obtained using the proposed framework based on lightweight DL models show that it can distinguish lung and colon cancer variants with a lower number of features and less computational complexity compared to existing methods. They also prove that utilizing transformation methods to reduce features can offer a superior interpretation of the data, thus improving the diagnosis procedure.

An Explainable Classification Method Based on Complex Scaling in Histopathology Images for Lung and Colon Cancer

“…Hence, the models may essentially replace the pathologist and make the classification of lung and colon cancer fully automatic. Furthermore, our framework is end-to-end, requiring neither any pre-processing methods nor any dimensionality reduction strategies as employed in some previous studies to achieve accuracies above 99.5% [26,31]. For instance, the method in [27] used histogram equalization for colon cancer images to boost the overall accuracy from 89% to 98.4%, and we believe that extensive pre-processing may hamper the generalizable ability of the model to unseen data.…”

“…Integration of deep feature extraction and ensemble learning with high-performance filtering was found to be effective in a recent work [30] with an accuracy of 99.3% using LC25000 data. Lastly, a custom CNN model from the same dataset followed by several dimensionality reduction methods, such as PCA, discrete Fourier transform, and fast Walsh-Hadamard transform, was employed to obtain 99.6% accuracy for the five-class classification [31].…”

RADIC:A tool for diagnosing COVID-19 from chest CT and X-ray scans using deep learning and quad-radiomics

“…In recent years, AI has been successfully used in digital health along with assistive technology to enhance the quality of life [ 10 , 11 ]. , AI methods have been extensively employed along with computer-assisted diagnosis tools (CAD) to support doctors in diagnosing many diseases accurately including heart complications [ 12 , 13 ], cancer [ [14] , [15] , [16] , [17] , [18] ], stomach diseases [ 19 ], lung diseases [ [20] , [21] , [22] ], visual disorders [ 23 ], and genetic abnormalities [ 24 ]. For the purpose of detecting coronavirus disease, the AI research community has lately committed a lot of time and funds to create deep learning models (DL) based on chest radiographs.…”

Dynamic learning for imbalanced data in learning chest X-ray and CT images

“…Artificial neural networks are used in deep learning, a kind of machine learning that may aid in the early identification, diagnosis, and treatment of lung disorders [13] , [14] . In the field of medical imaging, deep learning algorithms can be used to analyze chest X-rays and other imaging modalities to identify abnormalities can facilitate the identification of lung disorders such as pneumonia, lung cancer, and COPD.…”