A soft computing automatic based in deep learning with use of fine-tuning for pulmonary segmentation in computed tomography images

Abstract The segmentation of medical images is a significant challenge for computer vision and medical techniques. In the lungs, the difficulty is mainly due to the presence of lung diseases, different dimensions of the lung, and different types and configurations of medical imaging devices. Computed tomography (CT) is a tool to aid clinical diagnosis; several systems based on computer-aided diagnostics (CAD) are developed or enhanced from CT images combined with computational methods. This study proposes an innovative approach based on the generalization of models for pulmonary segmentation in CT images, using the Convolutional Neural Network Based on Mask Regions (Mask R-CNN) combined with image processing techniques, K-means clustering, region growing and Parzen window through fine-tunning. Our models achieved satisfactory results with 97% Accuracy and 98% Dice, 99% Sensitivity, and 97% Positive Predictive Value (PPV) in our best MPK model. The method was able to generalize its learning to solve different pulmonary segmentation problems in different lung CT databases. A second set of data was used, obtaining even better results. The results obtained for this second data set were: 98% Accuracy, 99% Dice, 100% Sensitivity, and 98% PPV, demonstrating the effectiveness of our method.

[1]  Timo Kohlberger,et al.  Evaluating Segmentation Error without Ground Truth , 2012, MICCAI.

[2]  Adriano Bessa Albuquerque,et al.  Automatic detection of COVID-19 infection using chest X-ray images through transfer learning , 2021, IEEE/CAA Journal of Automatica Sinica.

[3]  J. M. Cortina,et al.  What Is Coefficient Alpha? An Examination of Theory and Applications , 1993 .

[4]  Joseph M. Reinhardt,et al.  Transfer Learning for Segmentation of Injured Lungs Using Coarse-to-Fine Convolutional Neural Networks , 2018, RAMBO+BIA+TIA@MICCAI.

[5]  W. Neufeld-Kaiser,et al.  Positive predictive value of non-invasive prenatal screening for fetal chromosome disorders using cell-free DNA in maternal serum: independent clinical experience of a tertiary referral center , 2015, BMC Medicine.

[6]  Lauge Sørensen,et al.  A Texton-Based Approach for the Classification of Lung Parenchyma in CT Images , 2010, MICCAI.

[7]  Victor Hugo C. de Albuquerque,et al.  Brazilian vehicle identification using a new embedded plate recognition system , 2015 .

[8]  H. Zar,et al.  Burden of asthma and chronic obstructive pulmonary disease and access to essential medicines in low-income and middle-income countries. , 2015, The Lancet. Respiratory medicine.

[9]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  R. Bergmann,et al.  Different Outcomes of the Wilcoxon—Mann—Whitney Test from Different Statistics Packages , 2000 .

[11]  M. L. Dewal,et al.  An integrated method for hemorrhage segmentation from brain CT Imaging , 2013, Comput. Electr. Eng..

[12]  A. Huisman,et al.  Automatic Nuclei Segmentation in H&E Stained Breast Cancer Histopathology Images , 2013, PloS one.

[13]  Wen Li,et al.  A Fast Automatic Method of Lung Segmentation in CT Images Using Mathematical Morphology , 2007 .

[14]  Joel J. P. C. Rodrigues,et al.  Enabling Technologies on Cloud of Things for Smart Healthcare , 2018, IEEE Access.

[15]  Daniel Rueckert,et al.  Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy , 2009, NeuroImage.

[16]  Ashish Khanna,et al.  Evolutionary algorithms for automatic lung disease detection , 2019, Measurement.

[17]  Victor Hugo C. de Albuquerque,et al.  Artificial intelligence techniques empowered edge-cloud architecture for brain CT image analysis , 2020, Eng. Appl. Artif. Intell..

[18]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[19]  Suane Pires P. da Silva,et al.  Lung Nodule Classification via Deep Transfer Learning in CT Lung Images , 2018, 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS).

[20]  Pedro Pedrosa Rebouças Filho,et al.  Automatic lung segmentation in CT images using mask R-CNN for mapping the feature extraction in supervised methods of machine learning using transfer learning , 2020, Int. J. Hybrid Intell. Syst..

[21]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[22]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

[23]  João Manuel R. S. Tavares,et al.  Analysis of human tissue densities: A new approach to extract features from medical images , 2017, Pattern Recognit. Lett..

[24]  Victor Hugo C. De Albuquerque,et al.  Health of Things Algorithms for Malignancy Level Classification of Lung Nodules , 2018, IEEE Access.

[25]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[26]  Javier Del Ser,et al.  Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Victor Hugo C. de Albuquerque,et al.  An IoT platform for the analysis of brain CT images based on Parzen analysis , 2020, Future Gener. Comput. Syst..

[28]  Victor Hugo C. de Albuquerque,et al.  An Open IoHT-Based Deep Learning Framework for Online Medical Image Recognition , 2021, IEEE Journal on Selected Areas in Communications.

[29]  D. Mollura,et al.  Computer-aided diagnosis of pulmonary infections using texture analysis and support vector machine classification. , 2011, Academic radiology.

[30]  Matheus T. Guimarães,et al.  A new fast morphological geodesic active contour method for lung CT image segmentation , 2019 .

[31]  Azael M Sousa,et al.  ALTIS: A Fast and Automatic Lung and Trachea CT-Image Segmentation Method. , 2019, Medical physics.

[32]  Jayaram K. Udupa,et al.  A framework for evaluating image segmentation algorithms , 2006, Comput. Medical Imaging Graph..

[33]  Tao Han,et al.  An effective approach for CT lung segmentation using mask region-based convolutional neural networks , 2020, Artif. Intell. Medicine.

[34]  E A Hoffman,et al.  Assessment of methacholine-induced airway constriction by ultrafast high-resolution computed tomography. , 1993, Journal of applied physiology.

[35]  Javad Alirezaie,et al.  Lung Segmentation in Pulmonary CT Images using Wavelet Transform , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[36]  Tao Han,et al.  Internet of Medical Things—Based on Deep Learning Techniques for Segmentation of Lung and Stroke Regions in CT Scans , 2020, IEEE Access.

[37]  span,et al.  Intelligent Incipient Fault Detection in Wind Turbines based on Industrial IoT Environment , 2019, Journal of Artificial Intelligence and Systems.

[38]  Nikos A. Vlassis,et al.  The global k-means clustering algorithm , 2003, Pattern Recognit..

[39]  M. L. Dewal,et al.  Intracranial hemorrhage detection using spatial fuzzy c-mean and region-based active contour on brain CT imaging , 2012, Signal, Image and Video Processing.

[40]  Korris Fu-Lai Chung,et al.  A novel image thresholding method based on Parzen window estimate , 2008, Pattern Recognit..

[41]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[42]  E. Hoffman,et al.  Assessment of the pulmonary structure-function relationship and clinical outcomes measures: quantitative volumetric CT of the lung. , 1997, Academic radiology.

[43]  T. King.  Clinical advances in the diagnosis and therapy of the interstitial lung diseases. , 2005, American journal of respiratory and critical care medicine.

[44]  Javier Del Ser,et al.  Online heart monitoring systems on the internet of health things environments: A survey, a reference model and an outlook , 2020, Inf. Fusion.

[45]  Victor Hugo C. de Albuquerque,et al.  Novel Adaptive Balloon Active Contour Method based on internal force for image segmentation - A systematic evaluation on synthetic and real images , 2014, Expert Syst. Appl..

[46]  A. Piquero,et al.  USING THE CORRECT STATISTICAL TEST FOR THE EQUALITY OF REGRESSION COEFFICIENTS , 1998 .