A statistical evaluation of the preprocessing medical images impact on a deep learning network’s performance

Renato Constantin Ivanescu

Abstract


The aim of this paper is to explore the efficiency of preprocessing medical images before applying a deep learning algorithm to classify the data. The study uses a statistical framework that establishes the fact that depending on the dataset used, image preprocessing indeed decreases the computational time, without having a dropdown in performance. The dataset used in this study regard colon cancer, lung cancer, and fetal brain ultrasound scans. The study proposes a statistical performance that studies the performances of the ResNet50 deep learning network in different preprocessing scenarios.


Full Text:

PDF

References


S. Belciug, Artificial Intelligence in Cancer: diagnostic to tailored treatment, Elsevier, 2020.

S. Belciug and F. Gorunescu, A hybrid genetic algorithm-queuing multi-compartment model for optimizing inpatient bed occupancy and associated costs, Artificial Intelligence in Medicine 68 (2016), 59-69. DOI: 10.1016/j.artmed.2016.03.001

A. Bour, et al., Automatic colon polyp classification using Convolutional Neural Network: A Case Study at Basque Country, IEEE International Symposium on Signal Processing and Information Technology (2019).

K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, arxiv.org/abs/1512.0338 (2015).

F. Koehler and A. Risteski, Representational Power of ReLU Networks and Polynomial Kernels: Beyond Worst-Case Analysis, arXiv:1805.11405 (2018).

F. Gorunescu, et al., A statistical framework for evaluating neural networks to predict recurrent events in breast cancer, International Journal of General Systems 39 (2010), no. 5, 471-488. DOI: 10.10180/03081079.2010.484282

F. Gorunescu,, et al., An evolutionary computational approach to probabilistic neural network with application to hepatic cancer diagnosis, 18th IEEE Symposium on computer-based medical systems (2005), 461-466. DOI: 10.1109/CBMS.2005.24

L. Jitai, et al., PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning, IEEE Trans Med Imaging (2022).

M. Masud, et al., A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classi_cation Framework, Sensors (Basel, Switzerland) 21 (2021), no. 3, 748.

B. Neha, et al., Classification of Histopathology Images of Lung Cancer Using Convolutional Neural Network (CNN), arXiv:2112.13553 (2021).

L. Salomon, et al., A score-based method for quality control of fetal images at routine second trimester ultrasound examination, Prenatal Diagnosis 28 (2016), no. 9, 822-827.

M. Sanidhya, et al., Convolution Neural Networks for diagnosing colon and lung cancer histopathological images, arXiv:2009.03878 (2020).

M. Sheldon and A. Mukul, A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classi_cation, International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (2021).

M. Suganthi and J.G.R. Sathiaseelan, An Exploratory of Hybrid Techniques on Deep Learning for Image Classi_cation, 4th International Conference on Computer, Communication and Signal Processing (2020).

H.N. Xie, et al., Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal, Ulstr. Obstet Gynecol. (2020). DOI: 10.1002/uog.21967

Z.H. Zhang, et al., Variable selection in logistic regression model with genetic algorithm, Annals of Translational Medicine 6 (2018), no. 3. DOI: 10.21037/atm.2018.01.15




DOI: https://doi.org/10.52846/ami.v49i2.1641