Possible Bias in Supervised Deep Learning Algorithms for CT Lung Nodule Detection and Classification

Lung Cancer is one of the most dangerous threats for human life since many decades. When compared to other types of cancers, Lung cancer is very prevalent with less survival rate. Computed-Tomography-images are the main source of lung nodule detection as it provides detailed information about the nodules. Though there are many advanced techniques available in the present scenario like CNN, deep Neural Networks etc. For training purposes, all these existing methods use raw chest CT images which contain more complicated information like Blood vessels, muscles, lymph nodes, air ways, bones etc. Hence if the nodule is segmented effectively and that in turn used to train the system to classify cancerous and non-cancerous, then the results will be extraordinarily efficient. This paper presents the simple and efficient segmentation of Lung nodules and automatic classification of Nodules into Benign or Malignant using novel algorithms. The techniques used includes thresholding, morphological operations, pixels closures and mathematical model, for effective detection and classification of Nodules. The proposed algorithm is evaluated on axial plane CT Scans from LIDC-IDRI database, and the comparative study proved the effectiveness of segmentation and classification. The experimental result achieved the specificity of 98.67%, Accuracy of 97.98% and F-score of 1.0859 for β = 0.5.KeywordsComputed TomographyBenignMalignantSegmentationClassificationThresholdingMorphologyImage Processing

India is experiencing a rapid rise in lung cancer cases, with more than 1 lakh new cases forecast in the next five years. 90% of patients who are not discovered early live for five years, however, only 10-15% of patients who are discovered late live for five years. Lung cancer can be discovered early with computed tomography (CT) imaging. To detect and classify lung nodules and their malignancy levels, Computer Tomography (CT) scans were used on lung patients. Since nodules vary widely in size, shape, and texture, detecting them is a difficult task. Moreover, there are other structures in the lungs that are considered to be non-nodules, for example vessels, fibrosis, diffusive diseases, which often resemble nodules in appearance. Therefore, proposed an end-to-end architecture to recognize nodules from three-dimensional CT volume by modified UNet segmentation and CNN based classification on readily available Lung Image Database Consortium – Image Database Resource Initiative (LIDC-IDRI), virtuously self-governing Indian Lung CT Image Database (ILCID) and LNDb Challenge Dataset. According to the results obtained with the proposed method, nodules can be reliably detected and segmented in contrast to the existing lung segmentation, classification and detection algorithms. For nodule segmentation, attained a Dice Similarity Coefficient (DSC) value is about 0.89 and for nodule detection, achieved the Sensitivity of 98.53%.

Lung cancer is one of the major causes of cancer-related deaths due to its aggressive nature and delayed detections at advanced stages. Early detection of lung cancer is very important for the survival of an individual, and is a significant challenging problem. Generally, chest radiographs (X-ray) and computed tomography (CT) scans are used initially for the diagnosis of the malignant nodules; however, the possible existence of benign nodules leads to erroneous decisions. At early stages, the benign and the malignant nodules show very close resemblance to each other. In this paper, a novel deep learning-based model with multiple strategies is proposed for the precise diagnosis of the malignant nodules. Due to the recent achievements of deep convolutional neural networks (CNN) in image analysis, we have used two deep three-dimensional (3D) customized mixed link network (CMixNet) architectures for lung nodule detection and classification, respectively. Nodule detections were performed through faster R-CNN on efficiently-learned features from CMixNet and U-Net like encoder–decoder architecture. Classification of the nodules was performed through a gradient boosting machine (GBM) on the learned features from the designed 3D CMixNet structure. To reduce false positives and misdiagnosis results due to different types of errors, the final decision was performed in connection with physiological symptoms and clinical biomarkers. With the advent of the internet of things (IoT) and electro-medical technology, wireless body area networks (WBANs) provide continuous monitoring of patients, which helps in diagnosis of chronic diseases—especially metastatic cancers. The deep learning model for nodules’ detection and classification, combined with clinical factors, helps in the reduction of misdiagnosis and false positive (FP) results in early-stage lung cancer diagnosis. The proposed system was evaluated on LIDC-IDRI datasets in the form of sensitivity (94%) and specificity (91%), and better results were obatined compared to the existing methods.

This paper examines the effectiveness of geometric feature descriptors, common in computer vision, for false positive reduction and for classification of lung nodules in low dose CT (LDCT) scans. A data-driven lung nodule modeling approach creates templates for common nodule types, using active appearance models (AAM); which are then used to detect candidate nodules based on optimum similarity measured by the normalized cross-correlation (NCC). Geometric feature descriptors (e.g., SIFT, LBP and SURF) are applied to the output of the detection step, in order to extract features from the nodule candidates, for further enhancement of output and possible reduction of false positives. Results on the clinical ELCAP database showed that the descriptors provide 2% enhancements in the specificity of the detected nodule above the NCC results when used in a k-NN classifier. Thus quantitative measures of enhancements of the performance of CAD models based on LDCT are now possible and are entirely model-based. Most importantly, our approach is applicable for classification of nodules into categories and pathologies.

The main objective of the proposed work is to develop an automated CAD system for classification of lung nodules using various classifiers from CT images. The classification of nodule and non-nodule patterns in CT is one of the most significant processes during the detection of lung nodule. This helps in detecting the disease at early stage thereby decrease the mortality rate. The developed CAD systems consist of segmentation, feature extraction and classification. For Segmentation we used Fuzzy C Means (FCM) for effective extraction infected region. Later, we extracted features through First order statistics (FOS) and Second order statistics (SOS) and fed into classifiers like DS, RF and BPNN. The experimentation is conducted on LIDC-IDRI dataset and results outperforms well with BPNN when compare to other classifiers.KeywordsSegmentationClassificationCADFeature extraction

Objectives: To propose a new hybrid deep learning model to boost lung nodule detection and classification in combination with a bioinspired method for efficient hyper-parameter optimization to maximize true positive and nodule discrimination rates. Methods: In order to extract the intrinsic and complex features from different lung nodules, deep learning-based enhanced CNN (ECNN) is used. Segmentation masks are generated using Mask-RCNN to isolate and capture the ROIs, which serve as input to CNN. Prior to segmentation and extraction, data cleaning, transformation, and augmentation is done. Hyper-parameter optimization is done using a bio-inspired differential evolution method, which helps to identify the learning rate and number of layers to achieve optimal performance. We utilize BCE to quantify the performance of classification tasks. A large-scale CT-DICOM image dataset with 25,1135 images is used for this research work, collected from the cancer imaging archive, which has a clinically proven record of 355 instances with detailed image analysis, tumor location, and bounding boxes with a resolution of 512x512 pixels. 175794 images are used for training, and 75341 images are used for testing and validation. The performance of the new system is assessed using MATLAB, where results are compared with existing models such as SVM-WSS, GCPSO-PNN, and 3D-DLCNN models. Findings: The newly suggested ECNN with DE Bio-inspired model boosts the performance of lung nodule detection and classification with 94.7% accuracy, 93.8% sensitivity, 94.5% specificity, 93.4% F1 score, 92.4% dice coefficient, 0.1 Log Loss and AUC-ROC with 0.93 TPR and 0.07 FPR. Novelty: The novel method presents an advanced computational model using deep learning and bio-inspired algorithms for robust classification of lung nodules, which significantly improves the early diagnosis. This CAD model overcomes the limitations of the existing approaches SVM-WSS, GCPSO-PNN, and 3D-DLCNN in terms of segmentation, classification, error detection, and hyper-parameter tuning. Keywords: Lung Nodules, Deep Learning, Disease Classification, Image Processing, ECNN- DE Classifier, CT-DICOM Dataset

Pulmonary cancer is one of the major causes of deaths caused by cancer around the globe. Early stage lung cancer detection can prove to be essential for the patients, for which the computed tomography (CT) images are analyzed by the radiologists to determine the presence of nodules and diagnose the disease. Conventional techniques used by the radiologists for nodule detection in CT images is time-consuming and inefficient; to assist in the diagnosis process and further enhance its efficiency and accuracy, decision support systems have been developed in the past few years. In our paper, we proposed a Multi-Dimension Region-based Fully Convolutional Network based decision support system for detection and classification of lung nodule. The Multi-Dimension RFCN serves as an image classifier backbone for our feature extraction step in addition to the proposed Tri-Level Region Proposal Network (3L-RPN) along with the position-sensitive score maps (PSSM) being explored. A novel median intensity projection method is used to leverage the multi-dimensional information from CT images and introduced an additional deconvolutional layer to adopt the proposed Tri-Level Region Proposal Network in our architecture to automatically identify the potential Region of Interest. We trained and evaluated our proposed decision support system using LIDC-IDRI dataset. The evaluation results demonstrated the high level performance of our proposed model in comparison to the state-of-the-art nodule detection and classification methods by attaining classification accuracy of 97.61% and sensitivity of 97.4%.

The main objective of the proposed work is to develop an automated computer-aided detection (CAD) system to classify lung nodules using various classifiers from computed tomography (CT) images. One of the most important steps in lung nodule detection is the classification of nodule and non-nodule patterns in CT. The early detection of the condition helps lower the mortality rate. The developed CAD systems consist of segmentation, feature extraction, and classification. In this work, a filter method is used to segment the infected region. Later, we extracted features through and fed into classifiers such as Decision Stump (DS), Random Forest (RF), and Back Propagation Neural Network (BPNN). The experimentation was conducted on LIDC-IDRI dataset, and the results with BPNN outperformed those with DS and RF classifiers.

Automatic detection of lung nodules in CT datasets based on stable 3D mass–spring models

A survey and taxonomy of 2.5D approaches for lung segmentation and nodule detection in CT images

The classification process of lung nodule detection in a traditional computer-aided detection (CAD) system is complex, and the classification result is heavily dependent on the performance of each step in lung nodule detection, causing low classification accuracy and high false positive rate. In order to alleviate these issues, a lung nodule classification method based on a deep residual network is proposed. Abandoning traditional image processing methods and taking the 50-layer ResNet network structure as the initial model, the deep residual network is constructed by combining residual learning and migration learning. The proposed approach is verified by conducting experiments on the lung computed tomography (CT) images from the publicly available LIDC-IDRI database. An average accuracy of 98.23% and a false positive rate of 1.65% are obtained based on the ten-fold cross-validation method. Compared with the conventional support vector machine (SVM)-based CAD system, the accuracy of our method improved by 9.96% and the false positive rate decreased by 6.95%, while the accuracy improved by 1.75% and 2.42%, respectively, and the false positive rate decreased by 2.07% and 2.22%, respectively, in contrast to the VGG19 model and InceptionV3 convolutional neural networks. The experimental results demonstrate the effectiveness of our proposed method in lung nodule classification for CT images.

A critical step to ameliorate diagnosis and extend patient survival is Benign-malignant Pulmonary Nodule (PN) classification at earlier detection. On account of the noise of Computed Tomography (CT) images, the prevailing Lung Nodule (LN) detection techniques exhibit broad variation in accurate prediction. Thus, a novel Nodule Detection along with Classification algorithm for early diagnosis of Lung Cancer (LC) has been proposed. Initially, employing the Adaptive Mode Ostu Binarization (AMOB) technique, the Lung Volumes (LVs) isextortedas of the image together with the extracted lung regions is pre-processed. Then, detection of LNs takes place, and utilizing Geodesic Fuzzy C-Means Clustering (GFCM) Segmentation Algorithm, it is segmented.Next, the vital features are extracted, and the Nodules are classified by utilizing Logarithmic Layer Xception Neural Network (LLXcepNN) Classifier grounded on the extracted feature. The nodules are classified as Benign Nodules (BN) and Malignant Nodules (MN) by the proposed classifier. Lastly, the Lung CT images are scrutinized. Thus, when weighed against the prevailing techniques, the proposed systems' acquired outcomes exhibit that the rate of accuracy of classification is enhanced.

Lung cancer has become a major cause of cancer-related deaths. Detection of potentially malignant lung nodules is essential for the early diagnosis and clinical management of lung cancer. In clinical practice, the interpretation of Computed Tomography (CT) images is challenging for radiologists due to a large number of cases. There is a high rate of false positives in the manual findings. Computer aided detection system (CAD) and computer aided diagnosis systems (CADx) enhance the radiologists in accurately delineating the lung nodules. The objective is to analyze CAD and CADx systems for lung nodule detection. It is necessary to review the various techniques followed in CAD and CADx systems proposed and implemented by various research persons. This study aims at analyzing the recent application of various concepts in computer science to each stage of CAD and CADx. This review paper is special in its own kind because it analyses the various techniques proposed by different eminent researchers in noise removal, contrast enhancement, thorax removal, lung segmentation, bone suppression, segmentation of trachea, classification of nodule and nonnodule and final classification of benign and malignant nodules. A comparison of the performance of different techniques implemented by various researchers for the classification of nodule and non-nodule has been tabulated in the paper. The findings of this review paper will definitely prove to be useful to the research community working on automation of lung nodule detection.

Deep learning-based methods have achieved promising performance in early\ndetection and classification of lung nodules, most of which discard unsure\nnodules and simply deal with a binary classification -- malignant vs benign.\nRecently, an unsure data model (UDM) was proposed to incorporate those unsure\nnodules by formulating this problem as an ordinal regression, showing better\nperformance over traditional binary classification. To further explore the\nordinal relationship for lung nodule classification, this paper proposes a meta\nordinal regression forest (MORF), which improves upon the state-of-the-art\nordinal regression method, deep ordinal regression forest (DORF), in three\nmajor ways. First, MORF can alleviate the biases of the predictions by making\nfull use of deep features while DORF needs to fix the composition of decision\ntrees before training. Second, MORF has a novel grouped feature selection (GFS)\nmodule to re-sample the split nodes of decision trees. Last, combined with GFS,\nMORF is equipped with a meta learning-based weighting scheme to map the\nfeatures selected by GFS to tree-wise weights while DORF assigns equal weights\nfor all trees. Experimental results on the LIDC-IDRI dataset demonstrate\nsuperior performance over existing methods, including the state-of-the-art\nDORF.\n

Accurate pulmonary nodule detection is a crucial step in lung cancer screening. Computer-aided detection (CAD) systems are not routinely used by radiologists for pulmonary nodule detection in clinical practice despite their potential benefits. Maximum intensity projection (MIP) images improve the detection of pulmonary nodules in radiological evaluation with computed tomography (CT) scans. Inspired by the clinical methodology of radiologists, we aim to explore the feasibility of applying MIP images to improve the effectiveness of automatic lung nodule detection using convolutional neural networks (CNNs). We propose a CNN-based approach that takes MIP images of different slab thicknesses (5 mm, 10 mm, 15 mm) and 1 mm axial section slices as input. Such an approach augments the two-dimensional (2-D) CT slice images with more representative spatial information that helps discriminate nodules from vessels through their morphologies. Our proposed method achieves sensitivity of 92.7% with 1 false positive per scan and sensitivity of 94.2% with 2 false positives per scan for lung nodule detection on 888 scans in the LIDC-IDRI dataset. The use of thick MIP images helps the detection of small pulmonary nodules (3 mm-10 mm) and results in fewer false positives. Experimental results show that utilizing MIP images can increase the sensitivity and lower the number of false positives, which demonstrates the effectiveness and significance of the proposed MIP-based CNNs framework for automatic pulmonary nodule detection in CT scans. The proposed method also shows the potential that CNNs could gain benefits for nodule detection by combining the clinical procedure.