This article is more than 5 years old. Information may no longer be current.
Software identified pulmonary nodules from adenocarcinoma
Click Here to Manage Email Alerts
A computer-aided nodule assessment tool afforded noninvasive preoperative characterization and risk stratification of pulmonary nodules in the lung adenocarcinoma spectrum through automated volumetric quantitation of the lesions, according to study results.
Prior data from single-arm observational studies indicate that some high-resolution CT screen-detected lung cancers may be more indolent than their clinically detected counterparts. Most of these lesions are included in the lung adenocarcinoma spectrum and are characterized by distinctive morphological and radiologic features and varying prognoses.
Fabien Maldonado
“Because alternative therapeutic strategies to standard lobectomy (such as sublobar resections) are currently being investigated, the noninvasive risk stratification of these nodules will facilitate individualized patient management,” Fabien Maldonado, MD, of the division of pulmonary and critical care medicine at Mayo Clinic in Rochester, Minn., and colleagues wrote. “Currently, this assessment requires surgical resection of the lesion with histopathologic examination of the entire lesion, which cannot be reliably performed on nonsurgical tissue biopsies.”
To assess the accuracy of their newly developed computer-aided nodule assessment and risk yield (CANARY) software, Maldonado and colleagues performed a review of 86 pulmonary nodules of the adenocarcinoma spectrum consecutively resected from 80 patients from 2006 to 2007.
Researchers had previously developed radiologic measurements of histopathologic tissue invasion in a training set of 54 pulmonary nodules of the adenocarcinoma spectrum. The researchers isolated the nodules and characterized them by computer-aided analysis, and they analyzed data by Spearman rank correlation, sensitivity and specificity, and the positive and negative predictive values.
Results demonstrated that unsupervised CANARY-based analysis of high-resolution CT data identified nine patterns across the spectrum of pulmonary nodules of the lung adenocarcinoma spectrum.
After clustering these patterns in 3-D space corresponding to tissue invasion and lepidic growth, the CANARY decision algorithm successfully categorized these pulmonary nodules as invasive adenocarcinoma or adenocarcinoma in situ and minimally invasive adenocarcinoma.
The standard distribution within each nodule correlated significantly with the proportion of histologic tissue invasion (Spearman rank correlation=0.87, P<.0001 for the training set; and Spearman rank correlation=0.89, P<.0001 for the validation set).
“After further validation, the CANARY-based noninvasive risk stratification of pulmonary nodules of the adenocarcinoma spectrum using a preoperative [high-resolution CT] could be applied to guide the individualized management of these lesions and may offer valuable insight into the biology of this type of lung cancer,” Maldonado and colleagues wrote.
“Furthermore, future use of CANARY for the assessment of serial imaging studies to highlight both qualitative and quantitative longitudinal changes across serial imaging studies might improve its diagnostic yield beyond that of the current single time point evaluation.”
Disclosure: The researchers report no relevant financial disclosures.
Click Here to Manage Email Alerts