Incidental Pulmonary Nodules on CT

Purpose	Detection and characterization of incidental pulmonary nodules on computed tomography (CT)
Tag(s)
Panel	Thoracic
Define-AI ID	08190003
Originator	Carol C. Wu, STR Big Data Subcommittee
Panel Chair	Eric J. Stern
Panel Reviewers	Thoracic Panel
License	Creative Commons 4.0
Status	Published
RadElement Set	RDES99

Clinical Implementation

Value Proposition

Incidental pulmonary nodules are commonly seen on computed tomography (CT) studies that include the lungs. A recent study shows that incidental nodules are seen in 13.9% of CT coronary angiogram (Robertson J et al. Heart Lung Circ 2017). Even though the majority of these nodules eventually prove to be benign, a small percentage of them are malignant. Follow-up chest CTs are often required to evaluate for growth, which is an indicator of malignancy. Automated identification and characterization of these nodules can result in significant improvement in workflow efficiency for radiologists. Subsequent recommendations of appropriate follow-up of these incidental pulmonary nodules based on patients’ risk factors and comorbidities are key to patient care.

Narrative(s)

A 68 year old smoker presents after a motor vehicle accident and undergoes a CT of the chest, abdomen and pelvis in the emergency room. Algorithm evaluates images of the lungs, detects and characterizes any incidental pulmonary nodules to allow radiologists to quickly review and insert these descriptions into the imaging report. The algorithm might also suggest appropriate follow-up recommendation based on Fleischer Society Guidelines. If follow-up imaging is required, the algorithm can prompt the referring provider to order the study prior to patient discharge from the acute care setting. If the algorithm or radiologist is able to determine that the patient meets criteria for low-dose CT lung screening based on the electronic medical record, a recommendation can be made to enroll the patient in a screening program.

A 70 year old admitted to ICU with COPD exacerbation and chest CT was performed for evaluation of respiratory distress. Algorithm evaluates image and detects small solid incidental pulmonary nodules which are stable since the patient’s oldest available comparison CT from 4 years prior. The algorithm describes the nodules and notes that the nodules are stable and do not require further imaging follow-up. The radiologist can insert these findings into the imaging report and focus on other more relevant and urgent CT findings.
A 45 year old otherwise healthy man presents to the emergency center with right lower quadrant abdominal pain and fever. A CT abdomen and pelvis reveals findings consistent with appendicitis and three cavitary nodules in the lung bases measuring up to 8mm. Algorithm detects these concerning incidental pulmonary nodules and alerts the radiologist to evaluate the lung bases. The algorithm inserts these findings into the imaging report.

Workflow Description

CT images sent to PACS and the AI engine. Image analyzed by engine. System detects and characterizes the incidental pulmonary nodules. A message is sent to PACS from the engine with the information, highlighting each incidental pulmonary nodules with a list of nodule characteristics.

Considerations for Dataset Development

Procedure(s):	Chest CT w/ or w/o intravenous contrast*, including High-resolution chest CT and low dose chest CT, cardiac CT, abdominal CT, neck CT, cervical/thoracic/lumbar spine CT, serial CTs over time} Clinical Note: CTs that include any part of the lung
Slice:	Continuous thin sections preferred (≤ 1.5 mm)
Sex at Birth:	Male, Female
Nodule Attenuation:	solid*, part-solid*, groundglass*, internal fat density, calcification, cavitary
Nodule Size (mm):	[3,30]
Age:	[18, no limit]
Nodule Shape :	2D: round, oval, triangular, lobular, irregular; 3D: spherical, flat
Nodule Margin:	smooth, irregular, spiculated, ill-defined
Nodule Location:	subpleural, peri-fissural, parenchymal, intraluminal
Comorbidities:	Smokers, non-smokers, emphysema, bronchitis, bronchiolitis, focal inflammatory lesions, usual interstitial pneumonia and other diffuse lung diseases}, other primary malignancy or history of primary malignancy Clinical Note: Focal inflammatory lesions, particular with surrounding emphysema, can mimic lung cancers
Pathologic Diagnosis:	Fine needle aspiration, core needle biopsy, surgical specimen, if not available, obtain information regarding stability over time

Technical Specifications

Inputs

DICOM Study

Procedure	CT
Views	Axial, multiplanar reformats, MIPS
Data Type	DICOM
Modality	CT
Body Region	Chest
Anatomic Focus	Lung
Pharmaceutical	N/A
Scenario	N/A

 

 

Primary Outputs

Detection of Nodule

Nodule Attenuation

Nodule Diameter

Nodule Volume

Secondary Outputs

Nodule Shape 

Nodule Margin 

Nodule Location 

Nodule Growth

Probability of Malignancy

Future Development Ideas

Based on nodule attributes and probability of malignancy, Return follow-up recommendations according to Fleischer and/or LUNG-RADS guidelines.

Related Datasets

The Cancer Imaging Archive (TCIA)

• CPTAC-LUAD
• ACRIN-NSCLC-FDG-PET (ACRIN 6668)
• LCTSC
• Lung-PET-CT-Dx
• NSCLC-Radiomics

Know of more related datasets? Please let us know