A Generalized Deep Learning-Based Diagnostic System for Early Diagnosis of Various Types of Pulmonary Nodules

Abstract

A novel framework for the classification of lung nodules using computed tomography scans is proposed in this article. To get an accurate diagnosis of the detected lung nodules, the proposed framework integrates the following 2 groups of features: (1) appearance features modeled using the higher order Markov Gibbs random field model that has the ability to describe the spatial inhomogeneities inside the lung nodule and (2) geometric features that describe the shape geometry of the lung nodules. The novelty of this article is to accurately model the appearance of the detected lung nodules using a new developed seventh-order Markov Gibbs random field model that has the ability to model the existing spatial inhomogeneities for both small and large detected lung nodules, in addition to the integration with the extracted geometric features. Finally, a deep autoencoder classifier is fed by the above 2 feature groups to distinguish between the malignant and benign nodules. To evaluate the proposed framework, we used the publicly available data from the Lung Image Database Consortium. We used a total of 727 nodules that were collected from 467 patients. The proposed system demonstrates the promise to be a valuable tool for the detection of lung cancer evidenced by achieving a nodule classification accuracy of 91.20%.

Automatic Pulmonary Nodule Detection Applying Deep Learning or Machine Learning Algorithms to the LIDC-IDRI Database: A Systematic Review

“…Data presented in Table 2 showcase the 22 studies that applied DL algorithms [6,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47]. Some of the authors tested different types of algorithms; the results shown in Table 2 are the best performing algorithms presented in the literature.…”

“…The study by Nibali et al [46] is the only study that applied a deep residual neural network and achieved accuracy, sensitivity, and specificity above 88% [46]. Shaffie et al [42] and Naqi et al [47] both presented an architecture utilizing autoencoders. Naqi et al [47] presented results above 95% in accuracy, sensitivity, and specificity.…”

Artificial intelligence in dermatology

“…The beginning of dermatological AI lags far behind the radiological AI. Radiological AI is leading in small pulmonary nodules [2] and lung cancer. [10] From the very beginning, the location of suspected nodules, including the description of its shape and the nodules detection, benign and malignant judgments, AI can now follow up and judge nodule changes at different times.…”

“…In the early 1970s, medical researchers discovered the applicability of AI in life sciences. [1] AI can play a role in many aspects, such as medical image recognition and auxiliary diagnosis, [2] biotechnology, [3] drug research and development, [4] etc. Currently, medical image recognition is the most widely used.…”

Pilot study: Application of artificial intelligence for detecting left atrial enlargement on canine thoracic radiographs

“…tion, detection of left atrial enlargement was used as a simple clinically relevant exemplar to illustrate the efficacy of deep learning to address common clinical imaging questions using a large archive of diagnostic images with known left atrial enlargement status based on echocardiographic results. As the database of canine thoracic radiographs and the deep learning-based software platform are expanded and refined, the technique could also be applied to detection/diagnosis of pulmonary nodules, pneumonia, left ventricular failure, developmental cardiac anomalies, and other thoracic pathologic conditions in future investigations 26,[33][34][35][36]. By extension, creation of other databases using images from other imaging modalities and other anatomic regions could be used to address an endless number of clinical diagnostic questions.The algorithm used for this study provides a percent likelihood of a positive result (presence of left atrial enlargement) for a given image.…”