DCV: A Taxonomy on Deep Learning Based Lung Cancer Classification

The microarray gene expression data poses a tremendous challenge due to their curse of dimensionality problem. The sheer volume of features far surpasses available samples, leading to overfitting and reduced classification accuracy. Thus the dimensionality of microarray gene expression data must be reduced with efficient feature extraction methods to reduce the volume of data and extract meaningful information to enhance the classification accuracy and interpretability. In this research, we discover the uniqueness of applying STFT (Short Term Fourier Transform), LASSO (Least Absolute Shrinkage and Selection Operator), and EHO (Elephant Herding Optimisation) for extracting significant features from lung cancer and reducing the dimensionality of the microarray gene expression database. The classification of lung cancer is performed using the following classifiers: Gaussian Mixture Model (GMM), Particle Swarm Optimization (PSO) with GMM, Detrended Fluctuation Analysis (DFA), Naive Bayes classifier (NBC), Firefly with GMM, Support Vector Machine with Radial Basis Kernel (SVM-RBF) and Flower Pollination Optimization (FPO) with GMM. The EHO feature extraction with the FPO-GMM classifier attained the highest accuracy in the range of 96.77, with an F1 score of 97.5, MCC of 0.92 and Kappa of 0.92. The reported results underline the significance of utilizing STFT, LASSO, and EHO for feature extraction in reducing the dimensionality of microarray gene expression data. These methodologies also help in improved and early diagnosis of lung cancer with enhanced classification accuracy and interpretability.

Multi-center study on the application potential of Siaα-2,6Gal in early and differential diagnosis of lung cancer.

Precise segmentation of lung nodules is critical for early diagnosis and treatment of lung cancer. However, traditional methods are prone to boundary missegmentation and missed detection owing to the irregular shapes of nodules, blurred edges of small lesions, and vascular adhesion interference in CT images. This study proposes an improved U-Net model, SWAG-Net, which enhances the segmentation accuracy of edge-complex nodules and small-sized nodules through multi-module collaboration. The model designs a bidirectional path aggregation network that fuses cross-level feature pyramids to integrate the deep semantic information from the encoder and shallow details from the decoder, thereby enhancing the feature representation of small lesions. It embeds an adaptive multi-subband wavelet convolution module, utilizing wavelet transforms to explicitly separate multi-scale features and adaptively enhance high-frequency detail subbands, thereby addressing edge blurring and adhesion interference. Additionally, it introduces a dual-domain dynamic gating attention mechanism that combines channel-domain semantic filtering and spatial-domain edge enhancement to dynamically suppress background noise and highlight nodule regions. In the preprocessing stage, coordinate system decoupling and adaptive normalization were employed to reduce data bias. Experiments on the LUNA16 dataset demonstrated that the model achieved a DSC of 93.37% and an IOU of 88.79%, representing improvements of 11.43% and 19.39%, respectively, over the baseline U-Net. These results significantly improved the segmentation performance for irregular and small nodules. The experimental results demonstrate that this model effectively reduces mis-segmentations and missed detections, providing a reliable auxiliary basis for the early diagnosis of lung cancer.

Accurate malignancy level classification of lung nodules can reduce lung cancer mortality rate effectively. In this study, we present a fast and efficient CAD system to improve the performance of nodules malignancy level classification. Firstly, to reduce false positives (FPs), we propose a novel vessel segmentation method which measures vessel likelihood by tubular-like structures discriminating from multiple views. The method can recognize irregular vascular structures robustly and sensitively, and achieve fast vessel segmentation. In addition, a mathematical description for 3D pulmonary entities using neighbor centroids clustering is provided as a fundamental condition for spatial feature extraction. To optimize features extraction, we formulate a gray values cumulative function and a patches selection function based on the mathematical description, to generate axial spatial outline and spatial density distribution samples of the entities, respectively. Then, we use Edge Orientation Histogram (EOH) to extract edge features from the spatial outline and propose a multi-scale path LBP (MSPLBP) to extract the texture feature of the density distribution samples. Finally, the fused EOH and MSPLBP are classified into 6 malignancy levels by three state-of-the-art classifiers. The experimental results show that the vessel segmentation method achieves an average $F1\_Score$ of 78.14% and AUC value under $PR$ curves of 0.8149. Moreover, our system reaches an average $accuracy$ of 95.88% and consumes average 176.26 seconds for evaluating a CT set on malignancy level classification. These results indicate that the system can segment vessels exactly, and classify the malignancy level of nodules efficiently. Our system is the potential to be a powerful tool for early diagnosis of lung cancer.

BackgroundAccurate segmentation of lung nodules can help doctors get more accurate results and protocols in early lung cancer diagnosis and treatment planning, so that patients can be better detected and treated at an early stage, and the mortality rate of lung cancer can be reduced.PurposeCurrently, the improvement of lung nodule segmentation accuracy has been limited by his heterogeneous performance in the lungs, the imbalance between segmentation targets and background pixels, and other factors. We propose a new 2.5D lung nodule segmentation network model for lung nodule segmentation. This network model can well improve the extraction of edge information of lung nodules, and fuses intra‐slice and inter‐slice features, which makes good use of the three‐dimensional structural information of lung nodules and can more effectively improve the accuracy of lung nodule segmentation.MethodsOur approach is based on a typical encoding‐decoding network structure for improvement. The improved model captures the features of multiple nodules in both 3‐D and 2‐D CT images, complements the information of the segmentation target's features and enhances the texture features at the edges of the pulmonary nodules through the dual‐branch feature fusion module (DFFM) and the reverse attention context module (RACM), and employs central pooling instead of the maximal pooling operation, which is used to preserve the features around the target and to eliminate the edge‐irrelevant features, to further improve the performance of the segmentation of the pulmonary nodules.ResultsWe evaluated this method on a wide range of 1186 nodules from the LUNA16 dataset, and averaging the results of ten cross‐validated, the proposed method achieved the mean dice similarity coefficient (mDSC) of 84.57%, the mean overlapping error (mOE) of 18.73% and average processing of a case is about 2.07 s. Moreover, our results were compared with inter‐radiologist agreement on the LUNA16 dataset, and the average difference was 0.74%.ConclusionThe experimental results show that our method improves the accuracy of pulmonary nodules segmentation and also takes less time than more 3‐D segmentation methods in terms of time.

Microsatellite alterations in bronchial and sputum specimens of lung cancer patients: Miozzo M, Sozzi G, Musso K et al. Division of Experimental Oncology A, Istituto Nazionale Tumori, Via G, Venezian 1, 20133 Milano. Cancer Res 1996;56:2285–2288

Lungs are the most crucial organs in a human body. Since the cancer detection began, lung cancer has been the most common terminal disease amongst all type of cancers. The contribution of deep learning, especially the convolution neural networks has widely reduced the mortality rates resulting from lung cancer. The classification of Computed Tomography (CT) images has enhanced the early diagnosis of lung cancer that has enabled victims to undergo treatment at an early stage. The resolution of the CT images have been variedly used for the accuracy of the model. Besides, the detection of lumps or anomalies in the images has greatly supported early diagnosis. Classification plays a vital role in the deep learning models to sort out the input images as positive and negative based on the attribute of the model built. However, the generalisation of classifiers has reduced the accuracy of the corresponding models built. To increase the accuracy and efficiency of the deep learning model, an optimised classification technique is used to predict lung cancer from the CT images. The purpose of optimisation here will enable the model to adapt stipulated feature extraction process according to the input images fed into the network. The model will be trained for predicting purpose given any resolution of the images. KEYWORDS: Lung cancer, CT images, Classification techniques, Optimised Classification, Prediction

For real-time target classification, a study was conducted to improve the AI-based target classification performance using RCS measurements that are vulnerable to noise, but can be obtained quickly. To compensate for the shortcomings of the RCS, a 1D CNN–GRU network with strengths in feature extraction and time-series processing was considered. The 1D CNN–GRU was experimentally changed and designed to fit the RCS characteristics. The performance of the proposed 1D CNN–GRU was compared and analyzed using the 1D CNN and 1D CNN–LSTM. The designed 1D CNN–GRU had the best classification performance with a high accuracy of 99.50% in complex situations, such as with different missile shapes with the same trajectory and with the same missile shapes that had the same trajectory. In addition, to confirm the general target classification performance for the RCS, a new class was verified. The 1D CNN–GRU had the highest classification performance at 99.40%. Finally, as a result of comparing three networks by adding noise to compensate for the shortcomings of the RCS, the 1D CNN–GRU, which was optimized for both the data set used in this paper and the newly constructed data set, was the most robust to noise.

It is well known that breast density in mammograms may hinder the accuracy of diagnosis of breast cancer. Although the dense breasts should be processed in a special manner, most of the research has treated dense breast almost the same as fatty. Consequently, the dense tissues in the breast are diagnosed as a developed cancer. In contrast, dense-fatty should be clearly distinguished before the diagnosis of cancerous or not cancerous breast. In this paper, we develop such a system that will automatically analyze mammograms and identify significant features. For feature extraction, we develop a novel system by combining a two-dimensional discrete cosine transform (2D-DCT) and a principal component analysis (PCA) to extract a minimal feature set of mammograms to differentiate breast density. These features are fed to three classifiers: Backpropagation Multilayer Perceptron (MLP), Support Vector Machine (SVM) and K Nearest Neighbour (KNN). A majority voting on the outputs of different machine learning tools is also investigated to enhance the classification performance. The results show that features extracted using a combination of DCT-PCA provide a very high classification performance while using a majority voting of classifiers outputs from MLP, SVM, and KNN.

Feature extraction and classification is a subject of broad and current interest in the brain-computer interfaces (BCIs) community, and remains a challenging task when working with Electroencephalogram (EEG) data, with no agreed upon optimum features set and classifier algorithm. In this 75-participant lab study, we compare different feature extraction methods and classifiers as we investigate the relationship between users' perceptions of the memorability of a number of passwords and the users' EEG data collected using BCIs when presented with these passwords. We asked the participants to rank the comparative memorability of 15 blocks of 5 passwords each, while recording their EEG data. Features from the EEG signals are extracted in three domains, power spectrum from the frequency domain, statistics from the time domain, and wavelet coefficients from the time-frequency domain. The feature subsets are submitted for classification with two classes, most memorable and least memorable, based on the user's perceived memorability of the passwords. Classification performance of Neural Networks and Support Vector Machine algorithms are compared. Results show distinctive features of EEG signals in the two different classes, achieving a classification accuracy of 89%. Our results indicate that features extracted in the time-frequency domain using wavelet transform, and classified using neural networks, resulted in the highest classification performance.

To retrospectively develop and evaluate computer-aided diagnosis (CAD) models that include both mammographic and sonographic descriptors. Institutional review board approval was obtained for this HIPAA-compliant study. A waiver of informed consent was obtained. Mammographic and sonographic examinations were performed in 737 patients (age range, 17-87 years), which yielded 803 breast mass lesions (296 malignant, 507 benign). Radiologist-interpreted features from mammograms and sonograms were used as input features for linear discriminant analysis (LDA) and artificial neural network (ANN) models to differentiate benign from malignant lesions. An LDA with all the features was compared with an LDA with only stepwise-selected features. Classification performances were quantified by using receiver operating characteristic (ROC) analysis and were evaluated in a train, validate, and retest scheme. On the retest set, both LDAs were compared with radiologist assessment score of malignancy. Both the LDA and ANN achieved high classification performance with cross validation (area under the ROC curve [A(z)] = 0.92 +/- 0.01 [standard deviation] and (0.90)A(z) = 0.54 +/- 0.08 for LDA, A(z) = 0.92 +/- 0.01 and (0.90)A(z) = 0.55 +/- 0.08 for ANN). Results of both models generalized well to the retest set, with no significant performance differences between the validate and retest sets (P > .1). On the retest set, there were no significant performance differences between LDA with all features and LDA with only the stepwise-selected features (P > .3) and between either LDA and radiologist assessment score (P > .2). Results showed that combining mammographic and sonographic descriptors in a CAD model can result in high classification and generalization performance. On the retest set, LDA performance matched radiologist classification performance.

Lung cancer is one of the most prevalent causes of mortality worldwide, making early detection essential for improving patient survival rates. Computed tomography (CT) imaging serves as a crucial diagnostic tool; however, the large volume of generated images poses challenges in precise interpretation by radiologists. This study evaluates the effectiveness of lung cancer classification by utilizing various feature extraction techniques in combination with support vector machine (SVM) and k-nearest neighbours (KNN) classifiers. By analysing different feature sets, the research aims to identify the most effective combination for enhanced classification accuracy. The findings indicate notable improvements in classification performance, facilitating more reliable lung cancer detection.

The Deep Learning approach provides a high performance of classification, especially when invoking image classification problems. However, a shortcoming of the traditional Deep Learning method is the large time scale of training. The hierarchical extreme learning machine (H-ELM) framework was based on the hierarchical learning architecture of multilayer perceptron to address the problem. H-ELM is composed of two parts; the first entails unsupervised multilayer encoding, and the second is the supervised feature classification. H-ELM can give a higher accuracy rate than the traditional ELM. However, there still remains room to enhance its classification performance. This paper therefore proposes a new method termed the extending hierarchical extreme learning machine (EH-ELM), which extends the number of layers in the supervised portion of the H-ELM from a single layer to multiple layers. To evaluate the performance of the EH-ELM, the various classification datasets were studied and compared with the H-ELM and the multilayer ELM, as well as various state-of-the-art such deep architecture methods. The experimental results show that the EH-ELM improved the accuracy rates over most other methods.

Although CT and MRI are standard procedures in cirrhosis diagnosis, differentiation of etiology based on imaging is not established. This proof-of-concept study explores the potential of deep learning (DL) to support imaging-based differentiation of the etiology of liver cirrhosis. This retrospective, monocentric study included 465 patients with confirmed diagnosis of (a) alcoholic (n = 221) and (b) other-than-alcoholic (n = 244) cirrhosis. Standard T2-weighted single-slice images at the caudate lobe level were randomly split for training with fivefold cross-validation (85%) and testing (15%), balanced for (a) and (b). After automated upstream liver segmentation, two different ImageNet pre-trained convolutional neural network (CNN) architectures (ResNet50, DenseNet121) were evaluated for classification of alcohol-related versus non-alcohol-related cirrhosis. The highest classification performance on test data was observed for ResNet50 with unfrozen pre-trained parameters, yielding an area under the receiver operating characteristic curve of 0.82 (95% confidence interval (CI) 0.71–0.91) and an accuracy of 0.75 (95% CI 0.64–0.85). An ensemble of both models did not lead to significant improvement in classification performance. This proof-of-principle study shows that deep-learning classifiers have the potential to aid in discriminating liver cirrhosis etiology based on standard MRI.

CCSA-RF enhanced lightweight multi-scale CNN framework for robust lung cancer classification