Lung Nodule Detection from Feature Engineering to Deep Learning in Thoracic CT Images: a Comprehensive Review.

This paper presents a systematic review of the literature focused on the lung nodule detection in chest computed tomography (CT) images. Manual detection of lung nodules by the radiologist is a sequential and time-consuming process. The detection is subjective and depends on the radiologist's experiences. Owing to the variation in shapes and appearances of a lung nodule, it is very difficult to identify the proper location of the nodule from a huge number of slices generated by the CT scanner. Small nodules (< 10 mm in diameter) may be missed by this manual detection process. Therefore, computer-aided diagnosis (CAD) system acts as a "second opinion" for the radiologists, by making final decision quickly with higher accuracy and greater confidence. The goal of this survey work is to present the current state of the artworks and their progress towards lung nodule detection to the researchers and readers in this domain. This review paper has covered the published works from 2009 to April 2018. Different nodule detection approaches are described elaborately in this work. Recently, it is observed that deep learning (DL)-based approaches are applied extensively for nodule detection and characterization. Therefore, emphasis has been given to convolutional neural network (CNN)-based DL approaches by describing different CNN-based networks.

An adaptive morphology based segmentation technique for lung nodule detection in thoracic CT image.

Lung cancer is one of the most life-threatening cancers mostly indicated by the presence of nodules in the lung. Doctors and radiological experts use High-Resolution Computed Tomography (HRCT) images for nodule detection and further decision making from visual inspection. Manual detection of lung nodules is a time-consuming process. Therefore, Computer-aided detection (CADe) systems have been developed for accurate nodule detection and segmentation. CADe-based systems assist radiologists to detect lung nodules with greater confidence and a lesser amount of time and have a significant impact on the accurate, uniform, and early-stage diagnosis of lung cancer. In this research work, an adaptive morphology-based segmentation technique (AMST) has been introduced by designing an adaptive morphological filter for improved segmentation of the lung nodule region. The adaptive morphological filter detects candidate nodule regions by employing adaptive structuring element (ASE) and at the same time improves nodule detection accuracy by reducing false positives (FPs) from the Computed Tomography (CT) slices. The detected nodule candidate regions are then processed for feature extraction. In this study, morphological, texture and intensity-based features have been used with support vector machine (SVM) classifier for lung nodule detection. The performance of the proposed framework has been evaluated by incorporating a 10-fold cross-validation technique on Lung Image Database Consortium-Image Database Resource Initiative (LIDC/IDRI) dataset and on a private dataset, collected from a consultant radiologist. It has been observed that the proposed automated computer-aided detection system has achieved overall classification performance indices with 94.88% sensitivity, 93.45% specificity and 94.27% detection accuracy with 1.8 FPs/scan on LIDC/IDRI dataset and 91.43% sensitivity, 90.45% specificity, 92.83% accuracy with 3.2 FPs/scan on a private dataset. The results show that the proposed CADe system presented in this paper outperforms the other state-of-the-art methods for automatic nodule detection from the HRCT image.

Integration of morphological preprocessing and fractal based feature extraction with recursive feature elimination for skin lesion types classification.

BACKGROUND AND OBJECTIVE: Skin cancer is the commonest form of cancer in the worldwide population. Non-invasive and non-contact imaging modalities are being used for the screening of melanoma and other cutaneous malignancies to endorse early detection and prevention of the disease. Traditionally it has been a problem for medical personnel to differentiate melanoma, dysplastic nevi and basal cell carcinoma (BCC) diseases from one another due to the confusing appearance and similarity in the characteristics of the pigmented lesions. The paper reports an integrated method developed for identifying these skin diseases from the dermoscopic images. METHODS: The proposed integrated computer-aided method has been employed for the identification of each of these diseases using recursive feature elimination (RFE) based layered structured multiclass image classification technique. Prior to the classification, different quantitative features have been extracted by analyzing the shape, the border irregularity, the texture and the color of the skin lesions, using different image processing tools. Primarily, a combination of gray level co-occurrence matrix (GLCM) and a proposed fractal-based regional texture analysis (FRTA) algorithm has been used for the quantification of textural information. The performance of the framework has been evaluated using a layered structure classification model using support vector machine (SVM) classifier with radial basis function (RBF). RESULTS: The performance of the morphological skin lesion segmentation algorithm has been evaluated by estimating the pixel level sensitivity (Sen) of 0.9172, 0.9788 specificity (Spec), 0.9521 accuracy (ACU), along with the image similarity measuring indices as Jaccard similarity index (JSI) of 0.8562 and Dice similarity coefficient (DSC) of 0.9142 with respect to the corresponding ground truth (GT) images. The quantitative features extracted from the proposed feature extraction algorithms have been employed for the proposed multi-class skin disease identification. The proposed layered structure identifies all the three classes of skin diseases with a highly acceptable classification accuracy of 98.99%, 97.54% and 99.65% for melanoma, dysplastic nevi and BCC respectively. CONCLUSION: To overcome the difficulties of proper diagnosis of diseases based on visual evaluation, the proposed integrated system plays an important role by quantifying the effective features and identifying the diseases with higher degree of accuracy. This combined approach of quantitative and qualitative analysis not only increases the diagnostic accuracy, but also provides some important information not obtainable from qualitative assessment alone.

Obstructive sleep apnoea detection using convolutional neural network based deep learning framework.

This letter presents an automated obstructive sleep apnoea (OSA) detection method with high accuracy, based on a deep learning framework employing convolutional neural network. The proposed work develops a system that takes single lead electrocardiography signals from patients for analysis and detects the OSA condition of the patient. The results show that the proposed method has some advantages in solving such problems and it outperforms the existing methods significantly. The present scheme eliminates the requirement of separate feature extraction and classification algorithms for the detection of OSA. The proposed network performs both feature learning and classifies the features in a supervised manner. The scheme is computation-intensive, but can achieve very high degree of accuracy-on an average a margin of more than 9% compared to other published literature till date. The method also has a good immunity to the contamination of the signals by noise. Even with pessimistic signal to noise ratio values considered here, the methods already reported are not able to outshine the present method. The software for the algorithm reported here can be a good contender to constitute a module that can be integrated with a portable medical diagnostic system.

On-line detection of apnea/hypopnea events using SpO2 signal: a rule-based approach employing binary classifier models.

This paper presents an online method for automatic detection of apnea/hypopnea events, with the help of oxygen saturation (SpO2) signal, measured at fingertip by Bluetooth nocturnal pulse oximeter. Event detection is performed by identifying abnormal data segments from the recorded SpO2 signal, employing a binary classifier model based on a support vector machine (SVM). Thereafter the abnormal segment is further analyzed to detect different states within the segment, i.e., steady, desaturation, and resaturation, with the help of another SVM-based binary ensemble classifier model. Finally, a heuristically obtained rule-based system is used to identify the apnea/hypopnea events from the time-sequenced decisions of these classifier models. In the developmental phase, a set of 34 time domain-based features was extracted from the segmented SpO2 signal using an overlapped windowing technique. Later, an optimal set of features was selected on the basis of recursive feature elimination technique. A total of 34 subjects were included in the study. The results show average event detection accuracies of 96.7% and 93.8% for the offline and the online tests, respectively. The proposed system provides direct estimation of the apnea/hypopnea index with the help of a relatively inexpensive and widely available pulse oximeter. Moreover, the system can be monitored and accessed by physicians through LAN/WAN/Internet and can be extended to deploy in Bluetooth-enabled mobile phones.

Real-Time Adaptive Apnea and Hypopnea Event Detection Methodology for Portable Sleep Apnea Monitoring Devices.

This paper presents a novel real-time adaptive sleep apnea monitoring methodology, suitable for portable devices used in home care applications. The proposed method identifies apnea/hypopnea events with the help of oronasal airflow signal and aimed to meet clinical standards in the assessment mechanism of apnea severity. It uses a strategically combined adaptive two stage classifier model to detect apnea or hypopnea events on the basis of personalized breathing patterns. For the detection of events, optimum set of time, frequency, and nonlinear measures, extracted from overlapping segments of typical 8 s were fed to support vector machine-based classifiers model to identify the possible origin of the segments, i.e., whether from normal or abnormal (apnea/hypopnea) episodes, and then the decision of the classifier model on the time sequenced successive segments have been used to detect an event. The performance of the proposed real-time algorithm is validated on clinical tests online. Average accuracies of hypopnea, apnea, and combined event detection when compared with polysomnography-based respective indices on unseen subjects during online tests were found to be 91.8%, 94.9%, and 96.5%, respectively, which are quite acceptable.