Empirical Driven Automatic Detection of Lobulation Imaging Signs in Lung CT

Abstract

Computer-aided detection (CAD) of lobulation can help radiologists to diagnose/detect lung diseases easily and accurately. Compared to CAD of nodule and other lung lesions, CAD of lobulation remained an unexplored problem due to very complex and varying nature of lobulation. Thus, many state-of-the-art methods could not detect successfully. Hence, we revisited classical methods with the capability of extracting undulated characteristics and designed a sliding window based framework for lobulation detection in this paper. Under the designed framework, we investigated three categories of lobulation classification algorithms: template matching, feature based classifier, and bending energy. The resultant detection algorithms were evaluated through experiments on LISS database. The experimental results show that the algorithm based on combination of global context feature and BOF encoding has best overall performance, resulting in F1 score of 0.1009. Furthermore, bending energy method is shown to be appropriate for reducing false positives. We performed bending energy method following the LIOP-LBP mixture feature, the average positive detection per image was reduced from 30 to 22, and F1 score increased to 0.0643 from 0.0599. To the best of our knowledge this is the first kind of work for direct lobulation detection and first application of bending energy to any kind of lobulation work.

Malignancy risk stratification for solitary pulmonary nodule: A clinical practice guideline

“…Traditionally, the evaluation of lobulation signs was made on subjective judgment. But given its important role in identifying the nature of SPNs, quantitative evaluation of lobulations, bending energy, and bigger rectangles overlapping, have been developed in recent years 26 . In this recommendation, the border of nodules was considered for SPN evaluation and we defined a positive border as either a spiculation or a lobulation.…”

Nomogram model to predict pneumothorax after computed tomography-guided coaxial core needle lung biopsy

“…The mechanism of lobulation sign might be as follows: First, the differentiation degree and growth rate of each part of the tumour are not same. Secondly, the connective tissue, blood vessels and bronchi in the lungs impede tumour growth [37,38]. We consider that the pull of the surrounding lung tissue on the lobulated lesions and the inflammation caused by the lesion led to the formation of some small air spaces in the surrounding lung tissue.…”

A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD

“…Signs are also called “CT features,” “CT manifestation,” “CT patterns,” or sometimes “CT findings” [21]. Lobulation signs [22, 23], spiculation signs [15, 24–28], and some texture signs [29, 30] play crucial roles in radiologists' ability to differentiate benign from malignant nodules [31, 32]. Noncentral calcification, such as punctate sign or eccentric sign calcification, usually indicates that a nodule is malignant [33–35].…”

“…Various works on the CAD based on CT signs have been published. Han G et al [22] designed a sliding-window-based framework to detect lobulation sign. Suzuki K et al [39] developed a computer-aided diagnostic (CAD) scheme to distinguish benign from malignant nodules in LDCT scans using a massive training artificial neural network (MTANN) and concluded that spiculation sign is a highly differentiated feature for distinguishing benign from malignant nodules.…”