Dataset Information

Use of fractals in determining the malignancy degree of lung nodules.

ABSTRACT:

Introduction

A Computer-Assisted Detection (CAD) System for classification into malignant-benign classes using CT images is proposed.

Methods

Two methods that use the fractal dimension (FD) as a measure of the lung nodule contour irregularities (Box counting and Power spectrum) were implemented. The LIDC-IDRI database was used for this study. Of these, 100 slices belonging to 100 patients were analyzed with both methods.

Results

The performance between both methods was similar with an accuracy higher than 90%. Little overlap was obtained between FD ranges for the different malignancy grades with both methods, being slightly better in Power spectrum. Box counting had one more false positive than Power spectrum.

Discussion

Both methods are able to establish a boundary between the high and low malignancy degree. To further validate these results and enhance the performance of the CAD system, additional studies will be necessary.

SUBMITTER: Amador-Legon NV

PROVIDER: S-EPMC11002126 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Use of fractals in determining the malignancy degree of lung nodules.

Amador-Legon Noel Victor NV Perez-Diaz Marlen M

Frontiers in medical technology 20240326

<h4>Introduction</h4>A Computer-Assisted Detection (CAD) System for classification into malignant-benign classes using CT images is proposed.<h4>Methods</h4>Two methods that use the fractal dimension (FD) as a measure of the lung nodule contour irregularities (Box counting and Power spectrum) were implemented. The LIDC-IDRI database was used for this study. Of these, 100 slices belonging to 100 patients were analyzed with both methods.<h4>Results</h4>The performance between both methods was simi ...[more]

PMID: 38595696

Similar Datasets

Project description:RationaleLung computed tomography (CT) Screening Reporting and Data System (lung-RADS) has standardized follow-up and management decisions in lung cancer screening. To date, little is known how lung-RADS classification compares with radiological semantic features in risk prediction and diagnostic discrimination.ObjectivesTo compare the performance of radiological semantic features and lung-RADS in predicting nodule malignancy in lung cancer screening.MethodsWe used data and low-dose CT (LDCT) images from the National Lung Screening Trial (NLST). The training cohort contained 60 patients with screen-detected incident lung cancers who had a positive baseline screen (T0) that was not diagnosed and then was diagnosed at second follow-up (T2), and 139 nodule-positive controls who had 3 consecutive positive screens (T0 to T2) that were not diagnosed as lung cancer. The testing cohort included 40 patients with incident lung cancers that were diagnosed at first follow-up (T1) and 40 nodule-positive controls. Twenty-four semantic features were scored on a point scale from the LDCT images. Multivariable linear predictor model was built on the semantic features and the performances were compared with lung-RADS in 3 screening rounds. We also combined non-size-based semantic features with lung-RADS to improve malignancy detection.ResultsAt T0, the average area under the receiver operating characteristic curve (AUROC) for border definition in risk prediction was 0.72. The average AUROC for contour at T1 in risk prediction and T2 in diagnostic discrimination was 0.82 and 0.88, respectively. By comparison, the average AUROC of lung-RADS at T0, T1 and T2 were 0.60, 0.76 and 0.87, respectively. The combined model of the semantic features and lung-RADS shows improvement with AUROCs of 0.74, 0.88 and 0.96 at T0, T1, and T2, respectively, achieved by adding border definition (at T0) or contour (at T1 and T2).ConclusionWe find semantic features defined by border definition and contour performed similar to lung-RADS at follow-up time point and outperformed lung-RADS at baseline. These semantics alongside of lung-RADS shows improved performance to detect malignancy.

Project description:Background: Gene panels are routinely used to assess predisposition to hereditary cancers by simultaneously testing multiple susceptibility genes and/or variants. More recently, genetic panels have been implemented as part of solid tumor malignancy testing assessing somatic alterations. One example is targeted variant panels for thyroid nodules that are not conclusively malignant or benign upon fine-needle aspiration (FNA). We systematically reviewed published studies from 2009 to 2018 that contained genetic data from preoperative FNA specimens on cytologically indeterminate thyroid nodules (ITNs) that subsequently underwent surgical resection. Pooled prevalence estimates per gene and variant, along with their respective positive predictive values (PPVs) for malignancy, were calculated. Summary: Our systematic search identified 540 studies that were supplemented by 18 studies from bibliographies or personal files. Sixty-one studies met all inclusion criteria and included >4600 ITNs. Overall, 26% of nodules contained at least 1 variant or fusion. However, half of them did not include details on the specific gene, variant, and/or complete fusion pair reported for inclusion toward PPV calculations. The PPVs of genomic alterations reported at least 10 times were limited to BRAFV600E (98%, 95% confidence interval [CI 96-99%]), PAX8/PPARG (55% [CI 34-78%]), HRASQ61R (45% [CI 22-72%]), BRAFK601E (42% [CI 19-68%]), and NRASQ61R (38% [CI 23-55%]). Excluding BRAFV600E, the pooled PPV for all other specified variants and fusions was 47%. Multiple variants within the same nodule were identified in ∼1% of ITN and carried a cumulative PPV of 77%. Conclusions: The chance that a genomic alteration predicts malignancy depends on the individual variant or fusion detected. Only five alterations were reported at least 10 times; BRAFV600E had a PPV of 98%, while the remaining four had individual PPVs ranging from 38% to 55%. The small sample size of most variants and fusion pairs found among ITNs, however, limits confidence in their individual PPV point estimates. Better specific reporting of genomic alterations with cytological category, histological subtype, and cancer staging would facilitate better understanding of cancer prediction, and the independent contribution of the genomic profile to prognosis.

Dataset Information

Use of fractals in determining the malignancy degree of lung nodules.

Introduction

Methods

Results

Discussion

Publications

Use of fractals in determining the malignancy degree of lung nodules.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets