Trial Outcomes & Findings for Evaluation of Computer-Aided Lung Nodule Detection Software in Thoracic CT for Riverain Technologies LLC (NCT NCT02440139)

Results Overview

The detection rates in accuracy, sensitivity, and specificity on clinically actionable lung nodules were computed and compared for Aim 1 (baseline) and Arm 2 (study participants were aided with ClearRead CT software) studies.

Recruitment status

COMPLETED

Study phase

NA

Target enrollment

12 participants

Primary outcome timeframe

4 months

Results posted on

2021-11-04

Participant Flow

12 radiologists were invited to participate in a two-arms reader study.

Unit of analysis: CT cases

Participant milestones

Participant milestones
Measure	Arm 1 Participating radiologists performed clinical reading on 328 cases. They marked all locations of concern (clinically actionable nodules) on conventional thoracic CT images. Computer measured time, readers score regions according to action and suspiciousness.
Overall Study STARTED	12 324
Overall Study COMPLETED	12 324
Overall Study NOT COMPLETED	0 0

Reasons for withdrawal

Withdrawal data not reported

Baseline Characteristics

Race and Ethnicity were not collected from any participant.

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure	Arm 1: Baseline Study n=12 Participants 12 participating radiologists performed clinical reading on 324 cases. They marked all locations of concern (clinically actionable nodules) on conventional thoracic CT images. Computer measured time, readers score regions according to action and suspiciousness.
Age, Categorical <=18 years	0 Participants n=12 Participants
Age, Categorical Between 18 and 65 years	12 Participants n=12 Participants
Age, Categorical >=65 years	0 Participants n=12 Participants
Sex: Female, Male Female	4 Participants n=12 Participants
Sex: Female, Male Male	8 Participants n=12 Participants
Region of Enrollment United States	12 participants n=12 Participants

PRIMARY outcome

Timeframe: 4 months

Population: Of the study chest CT cases, some contained cancers and/or clinically actionable benign nodules. They were considered targets in the study. The remaining study cases had no cancer nor clinically actionable nodules which served as true-negative for the study.

The detection rates in accuracy, sensitivity, and specificity on clinically actionable lung nodules were computed and compared for Aim 1 (baseline) and Arm 2 (study participants were aided with ClearRead CT software) studies.

Outcome measures

Outcome measures
Measure	Arm 1 n=4728 CT-case \| nodule Participating radiologists performed a clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on conventional thoracic CT images. Computer measured time, readers score regions according to action and suspiciousness.	Arm 2 n=4728 CT-case \| nodule Participating radiologists performed clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on thoracic CT images aided by ClearRead CT Insight software as the intervention. Computer measured time, readers score regions according to action and suspiciousness. ClearRead CT Insight: During the second reading session (concurrent read), the radiologist was presented with a standard appearing CT with CADe marks placed and the vessel suppressed images with the vessel suppressed view as the intervention. The second image, vessel suppressed, was not shown until the radiologist move the mouse to the second panel. The radiologist will mark locations. These may or may not correspond to the locations of the CAD markers. As before, the radiologist then assigned a level of suspicious to each mark and indicate the need, if any, of an additional diagnostic action (CT Follow-up, Contrast CT, PET-CT, or Biopsy).
Comparing the Detection Accuracy, Sensitivity, and Specificity of Clinically Actionable Lung Nodules Detection Sensitivity	1283 CT-case \| nodule	1548 CT-case \| nodule
Comparing the Detection Accuracy, Sensitivity, and Specificity of Clinically Actionable Lung Nodules Detection Accuracy	3612 CT-case \| nodule	3735 CT-case \| nodule
Comparing the Detection Accuracy, Sensitivity, and Specificity of Clinically Actionable Lung Nodules Detection Specificity	2329 CT-case \| nodule	2187 CT-case \| nodule

PRIMARY outcome

Timeframe: 4 months

The areas under location-specific Receiver Operating Characteristic (LROC) curves were computed and compared for Aim 1 (baseline) and Aim 2 (study participants were aided with ClearRead CT software).

Outcome measures

Outcome measures
Measure	Arm 1 n=3888 CT case Participating radiologists performed a clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on conventional thoracic CT images. Computer measured time, readers score regions according to action and suspiciousness.	Arm 2 n=3888 CT case Participating radiologists performed clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on thoracic CT images aided by ClearRead CT Insight software as the intervention. Computer measured time, readers score regions according to action and suspiciousness. ClearRead CT Insight: During the second reading session (concurrent read), the radiologist was presented with a standard appearing CT with CADe marks placed and the vessel suppressed images with the vessel suppressed view as the intervention. The second image, vessel suppressed, was not shown until the radiologist move the mouse to the second panel. The radiologist will mark locations. These may or may not correspond to the locations of the CAD markers. As before, the radiologist then assigned a level of suspicious to each mark and indicate the need, if any, of an additional diagnostic action (CT Follow-up, Contrast CT, PET-CT, or Biopsy).
Comparing LROC Curve in the Detection of Clinically Actionable Lung Nodules Among Normal	0.633 Probability Interval 0.594 to 0.672	0.773 Probability Interval 0.734 to 0.812

SECONDARY outcome

Timeframe: 4 months

The average reading times per reader per case were computed and comapred in both Aim 1 and Arm 2 (study participants were aided with ClearRead CT software) studies.

Outcome measures

Outcome measures
Measure	Arm 1 n=3888 CT case Participating radiologists performed a clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on conventional thoracic CT images. Computer measured time, readers score regions according to action and suspiciousness.	Arm 2 n=3888 CT case Participating radiologists performed clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on thoracic CT images aided by ClearRead CT Insight software as the intervention. Computer measured time, readers score regions according to action and suspiciousness. ClearRead CT Insight: During the second reading session (concurrent read), the radiologist was presented with a standard appearing CT with CADe marks placed and the vessel suppressed images with the vessel suppressed view as the intervention. The second image, vessel suppressed, was not shown until the radiologist move the mouse to the second panel. The radiologist will mark locations. These may or may not correspond to the locations of the CAD markers. As before, the radiologist then assigned a level of suspicious to each mark and indicate the need, if any, of an additional diagnostic action (CT Follow-up, Contrast CT, PET-CT, or Biopsy).
Average Reading Time Per Case	98.0 Second Interval 88.0 to 108.0	132.3 Second Interval 122.3 to 142.3

Adverse Events

Arm 1

Serious events: 0 serious events

Other events: 0 other events

Deaths: 0 deaths

Arm 2

Serious events: 0 serious events

Other events: 0 other events

Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Adverse event data not reported

Additional Information

Dr. ShihChung Benedict Lo

Virginia Tech

Phone: 301-9215754

Email: [email protected]

Results disclosure agreements

Principal investigator is a sponsor employee
Publication restrictions are in place

Measure	Arm 1 n=4728 CT-case \| nodule Participating radiologists performed a clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on conventional thoracic CT images. Computer measured time, readers score regions according to action and suspiciousness.	Arm 2 n=4728 CT-case \| nodule Participating radiologists performed clinical reading on the study cases. They marked all locations of concern (clinically actionable nodules) on thoracic CT images aided by ClearRead CT Insight software as the intervention. Computer measured time, readers score regions according to action and suspiciousness. ClearRead CT Insight: During the second reading session (concurrent read), the radiologist was presented with a standard appearing CT with CADe marks placed and the vessel suppressed images with the vessel suppressed view as the intervention. The second image, vessel suppressed, was not shown until the radiologist move the mouse to the second panel. The radiologist will mark locations. These may or may not correspond to the locations of the CAD markers. As before, the radiologist then assigned a level of suspicious to each mark and indicate the need, if any, of an additional diagnostic action (CT Follow-up, Contrast CT, PET-CT, or Biopsy).
Comparing the Detection Accuracy, Sensitivity, and Specificity of Clinically Actionable Lung Nodules Detection Sensitivity	1283 CT-case \| nodule	1548 CT-case \| nodule
Comparing the Detection Accuracy, Sensitivity, and Specificity of Clinically Actionable Lung Nodules Detection Accuracy	3612 CT-case \| nodule	3735 CT-case \| nodule
Comparing the Detection Accuracy, Sensitivity, and Specificity of Clinically Actionable Lung Nodules Detection Specificity	2329 CT-case \| nodule	2187 CT-case \| nodule