The CapsoCam® Plus video capsule system is intended for visualization of the small bowel mucosa in adults. It may be used as a tool in the detection of abnormalities of the small bowel.

Device Description

CapsoCam Plus (SV-3) Capsule Endoscope System is a single-use, ingestible video capsule that acquires and stores video images in on-board memory while moving through the gastrointestinal tract, propelled by natural peristalsis. The patient retrieves the capsule using the provided retrieval kit and returns it to the physician who downloads and reviews the images on a computer. The capsule is typically excreted within 3 to 30 hours after swallowing. The device is contraindicated in patients:

· Who have known or suspected gastrointestinal obstructions, strictures or fistula
· Who are pregnant
· Who have gastroparesis
· Who have a swallowing disorder

CapsoCam Plus (SV-3) capsule endoscope system is a single-use ingestible capsule system for diagnostic visualization of the adult small bowel. The overall system consists of an ingestible CapsoCam (SV-3), the CapsoRetrieve® (CVR1) Capsule Retrieval Kit, the CapsoAccess® Capsule Data Access System (CDAS) and the CapsoView® (CVV) software. The capsule contains a panoramic color digital video camera, two silver-oxide watch batteries, white-LED light sources, a laser diode for data download and system-control and nonvolatile flashmemory data-storage electronics.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the comparison to the predicate device (CapsoCam SV-1) and the studies conducted to demonstrate equivalence and improved performance. However, explicit numerical acceptance criteria are not presented in a formal table within this document. The studies' results are presented as evidence of meeting performance expectations relative to the predicate and overall diagnostic quality.

Acceptance Criterion	Reported Device Performance (CapsoCam Plus SV-3)	Reference
Diagnostic Quality	40 out of 42 subjects (95.2%) showed "Yes" for Image Diagnostic Quality.	Study 1, Demographics, Image Diagnostic Quality table
Small Bowel Completeness	41 out of 42 subjects (97.6%) showed "Yes" for "Small Bowel Complete".	Study 1, Demographics, Small Bowel Complete table
Pathology Identification	Various pathologies identified (Angiectasia: 2/40, Ulcer: 2/40, Other: 4/38). None considered clinically significant in Study 1. Consensus on vascular (5/42) and polyp/mass (1/42) in Study 2.	Study 1, Pathologies Identified table; Study 2, Consensus on pathologies
Landmark Identification	High identification rates for 1st Esophageal (40/43), 1st Gastric (42/42), 1st Duodenal (42/42), 1st Cecal (41/42), Papilla (35/42).	Study 1, Landmarks Identified table
Overall Image Quality (vs. Predicate)	28 out of 40 clips (70%) ranked SV-3 image as better than SV-1. 12 (30%) ranked as comparable. 0 (0%) ranked SV-1 better.	Study 3, Results for Video Image Quality
Clinical Assessment Quality (vs. Predicate)	1 out of 40 clips (2.5%) ranked SV-3 image as better than SV-1. 39 (97.5%) ranked as comparable. 0 (0%) ranked SV-1 better.	Study 3, Results for Clinical Assessment Quality
Software Ease of Use (vs. Predicate)	1 out of 40 clips (2.5%) ranked SV-3 software as easier. 39 (97.5%) ranked as equal. 0 (0%) ranked SV-1 software as easier.	Study 3, Ease of use
Reviewing Experience (vs. Predicate)	2 out of 40 (5%) ranked SV-1 software as worse. 38 (95%) ranked as the same. 0 (0%) ranked SV-1 software as better.	Study 3, Reviewing Experience
Consensus with Predicate Software (Study 3)	100% agreement between old and new versions of software when consensus was reached. 90.9% consensus for landmarks (10/11 clips). 86.2% consensus for significant clinical pathology (25/29 clips).	Study 3

2. Sample Size Used for the Test Set and Data Provenance

Study 1 (CVI-006 "Validation of CapsoCam® SV-3 Capsule Endoscopy System"):
- Sample Size: 42 "Per-Protocol" subjects (from 49 enrolled healthy volunteers).
- Data Provenance: Prospective, healthy volunteers, country not specified but implied to be in a clinical trial setting.
Study 2 (Comparisons of reads of select video clips from CVI-006 by Independent Blinded readers):
- Sample Size: Not explicitly stated as a number of subjects, but refers to "images of landmarks and pathologies" extracted from the 42 subjects of Study 1. The tables show N=42 for overall consensus.
- Data Provenance: Retrospective analysis of clips from the prospective Study 1.
Study 3 (Comparison of SV-1 and SV-3 software performance):
- Sample Size: 40 video clips (11 normal, 29 with pathology) from the original SV-1 study.
- Data Provenance: Retrospective analysis of clips from an earlier SV-1 study.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

Study 1: The "principal investigator" assessed landmarks, completion of exam, pathologies, and image quality. The number of principal investigators is not specified (implied to be one for reporting purposes). Their qualifications are not explicitly detailed but should be a medical professional qualified to read capsule endoscopy studies.
Study 2: "Independent Blinded readers" assessed landmark video quality, pathologies, and subjective questions. The number of independent readers is not explicitly stated in detail for consensus; however, the "Consensus Amongst readers with video clips of Landmarks" table implies multiple readers reached consensus. An example note clarifies for "discordant finding was identical for all 3 readers" in Study 3, suggesting at least 3 readers were involved in such assessments. Their qualifications are not explicitly detailed again, but should be experts in capsule endoscopy interpretation.
Study 3: "Independent blinded readers" were used. As noted above, the text mentions "all 3 readers" for the discordant findings, suggesting 3 readers were involved in comparing the software versions. Their qualifications are not explicitly detailed.

4. Adjudication Method for the Test Set

Study 1: The Principal Investigator made the assessments. No explicit adjudication method among multiple initial readers is mentioned for this phase.
Study 2 & 3: "Consensus Amongst readers" and "Consensus agreement" are mentioned for various aspects. This implies an adjudication process where readers' opinions were reconciled into a single agreed-upon finding. While the specific mechanism (e.g., majority vote, discussion to consensus, expert adjudicator) is not detailed, it indicates a method was used to arrive at a single 'ground truth' for these multi-reader assessments. For Study 3, it notes that "The discordant finding was identical for all 3 readers," which means even where there wasn't full agreement with the original finding, the readers were consistent with each other.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

Yes, Study 3 involved multiple readers comparing the performance of the SV-3 software to the SV-1 software on the same set of video clips. This constitutes a form of MRMC study in terms of software comparison.
Effect Size of Human Readers Improve with AI vs. without AI Assistance:
- This document describes a comparison between two versions of a device/software (SV-1 vs SV-3 software), not AI assistance for human readers versus human readers alone. The SV-3 software is an improvement to the device's image processing and viewing capabilities.
- The results show improvement in image quality preference: "28 (70%) Ranked the SV-3 image as better than the SV-1 image; 12 (30%) Ranked both SV-3 image and SV-1 image as comparable; 0 (0%) Ranked the SV-1 image as better than the SV 3-image."
- For clinical assessment quality, "39 (97.5%) Ranked both SV-3 image and SV-1 image as comparable; 1 (2.5%) Ranked the SV-3 image as better than the SV-1 image."
- This indicates the newer device/software improved image quality, but there was largely comparable clinical assessment quality, and slight improvements in ease of use and reviewing experience for a small percentage of readers.

6. Standalone Performance Study

Yes, Study 1 appears to be a standalone performance study for the CapsoCam Plus (SV-3) capsule endoscope system. It assesses the device's diagnostic quality, small bowel completeness, and ability to identify pathologies and landmarks in healthy volunteers using the SV-3 device alone. The results in the tables for Study 1 directly reflect the performance of the SV-3 system.

7. Type of Ground Truth Used

Expert Consensus/Clinical Assessment:
- Study 1: The ground truth for pathologies, landmarks, diagnostic quality, and completeness was established by the "Principal Investigator's" clinical assessment during the study.
- Study 2 & 3: The ground truth for landmark and pathology identification in these studies appears to be based on "Consensus Amongst readers" or agreement with the "original pathologies identified" from the prior studies. This points to expert consensus as the primary ground truth.

8. Sample Size for the Training Set

The document does not provide information about a training set. This document describes clinical validation studies for the device itself and its software, not the development or training of an AI algorithm. If the device incorporates AI, the training data for that AI is not detailed here.

9. How the Ground Truth for the Training Set Was Established

As no training set is mentioned for an AI algorithm, this information is not available in the provided text.

Summary

{0}------------------------------------------------

Image /page/0/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo is a circular seal with the words "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" around the perimeter. Inside the circle is an image of three stylized human profiles facing to the right, with flowing lines beneath them.

Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002

October 21, 2016

CapsoVision, Inc Azimun Jamal Director of QA/RA 18805 Cox Avenue, Suite 250 Saratoga, California 95070

Re: K161773

Trade/Device Name: Capsocam Plus (SV-3) Capsule Endoscope System Regulation Number: 21 CFR 876.1300 Regulation Name: Ingestible Telemetric Gastrointestinal Capsule Imaging System Regulatory Class: Class II Product Code: NEZ Dated: September 20, 2016 Received: September 21, 2016

Dear Azimun Jamal:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food. Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set

{1}------------------------------------------------

forth in the quality systems (OS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/Resourcesfor You/Industry/default.htm. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.

Sincerely,

Joyce M. Whang -S

for

Benjamin R. Fisher, Ph.D. Director Division of Reproductive, Gastro-Renal, and Urological Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K161773

Device Name

CapsoCam Plus (SV-3) Capsule Endoscope System

Indications for Use (Describe)

The CapsoCam® Plus video capsule system is intended for visualization of the small bowel mucosa in adults. It may be used as a tool in the detection of abnormalities of the small bowel.

Type of Use (Select one or both, as applicable)
-------------------------------------------------

X Prescription Use (Part 21 CFR 801 Subpart D)

| Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

Image /page/3/Picture/0 description: The image shows the logo for CapsoVision. The logo consists of a blue and green circular design at the top, followed by the word "CapsoVision" in a bold, sans-serif font. Below the company name is the tagline "empowering through innovation" in a cursive font.

5.0 510(k) Summary

This traditional 510(k) summary for the CapsoCam Plus (SV-3) Capsule Endoscope System is submitted in accordance with the requirements of 21 C.F.R. § 807.92.

5.1 General Information:

Date:	October 21, 2016
Manufacturer:	CapsoVision, Inc.18805 Cox Ave, Suite 250Saratoga, CA 95070Phone: (408) 624-1488Fax: (408) 370-4795
Registration No.:	3008062894
Contact Person:	Azimun JamalDirector, Quality Assurance & Regulatory AffairCapsoVision, Inc.Phone: (408) 866-6358E-mail: azimun.jamal@capsovision.com

Device Information:

Classification:	Class II
Trade Name:	CapsoCam Plus (SV-3) Capsule Endoscope System
Common Name:	System Imaging, Gastrointestinal Wireless Capsule
Classification Name:	Ingestible telemetric gastrointestinal capsule imaging system(21 CFR § 876.1300)
Predicate Devices:	CapsoCam (SV-1) (K151635)

Intended Use:

The CapsoCam Plus video capsule system is intended for visualization of the small bowel mucosa in adults. It may be used as a tool in the detection of abnormalities of the small bowel.

Device Description:

· Who have known or suspected gastrointestinal obstructions, strictures or fistula

{4}------------------------------------------------

Image /page/4/Picture/0 description: The image shows the logo for CapsoVision. The logo consists of a blue and green circular design above the company name. Below the company name is the tagline "empowering through innovation" in a handwritten-style font.

· Who are pregnant
· Who have gastroparesis
· Who have a swallowing disorder

5.2 Comprehensive Description of the Product:

Optics: The capsule contains four wide-angle optical objectives oriented at 90° intervals around the circumference of the capsule. The four objectives are assembled in a monolithic lens mount with four bores. Each objective has a longitudinal field of view of 74°and a transverse field of view of 162°. Taken together, the four lenses image the 360° circumference of the capsule over a length of 5± 1 mm.

Imaging sensor: The four optical objectives produce images on a single custom CMOS image sensor that has four separate pixel arrays. A color filter mosaic produces pixels sensitive to red, green, or blue light respectively.

Multi-chip Package (MCP): molded package containing multiple silicon chips:

. ASIC: Includes voltage regulator. RAM, CPU, and dedicated circuitry for functions such as IPEG image compression and motion detection.
. Flash Memory: Two chips. The capacity of each chip is 4Gb.

Illumination: 16 independently controlled "white" LEDs. Each LED is an AIGaN blue LED packaged with a phosphor epoxy in a lead-frame package.

Battery/Switch Pack: Subassembly with two 1.55V SR927W silver-oxide watch batteries and a magnetically-actuated switch that activates the capsule when removed from the package. Printed circuit board (PCB): All electronic components are soldered onto a rigid-flex PCB that is folded inside the capsule.

Capsule housing: The capsule is cylindrical with hemispheric domes at each end. The capsule is 30.5 mm long and 11.3mm in diameter. The capsule housing comprises two thermoplastic parts joined and sealed with an adhesive.

Capsule Physical:
Length:	30.5mm
Diameter:	11.3mm
Weight	3.74g
Optical:
Field of View:	74° x 360°

CapsoCam System Technical Specifications:

{5}------------------------------------------------

Image /page/5/Picture/0 description: The image shows the logo for CapsoVision. The logo consists of a blue and green swirl above the company name, which is written in a simple, sans-serif font. Below the company name is the tagline "empowering through innovation" in a cursive font.

Depth of field:	0 – 18mm.
Object resolution:	0.1 mm
Illumination:	16 independently controlled white light-emitting diodes (LEDs).
Capsule image storage format:	JPEG color images
Video format:	4 x 288 x 206 pixels
Operational:
Frame rate:	3-5 fps
Operating time:	15 hours

Upon excretion, the capsule is retrieved by the patient using Capsole retrieval system. The system includes a strainer, which is placed in the patient's toilet to retrieve the capsule while passing fecal matter, a cup for rinsing, a magnetic rod for grasping the capsule and a vial for storing and transporting the excreted capsule. The patient then returns the capsule to the clinic. where a technician disinfects the capsule and retrieves the data using the CapsoAccess, Capsule Data Access System (CDAS). The data is transferred to the workstation over the link, shown schematically in Figure 4 under the executive summary, from the capsule to the docking system by a serial interface and to the workstation by a Universal Serial Bus (USB).

The reviewing workstation is a computer with the CapsoView image review software installed. The CapsoView (CVV) software displays the video and employs a variety of image enhancement, video navigation, and image analysis features to facilitate the physician's diagnosis. The software allows the physician to efficiently annotate individual frames from the video and compile a procedure report.

The battery life for the CapsoCam is approximately 15 hours in order to allow complete imaging of the small bowel. Battery-life data collected during the clinical trial was provided with the predicate device (SV-1-K151635). Software Description:

CapsoView is CapsoVision's proprietary software program used to download and view CapsoCam images and to generate capsule endoscopy reports.

5.2.1 Software Level of Concern:

The software is determined to be "MODERATE" level of concern. This is unchanged from the cleared device SV-1 K161535. The software does not directly cause, control and/or mitigate hazards that could result in injury to the patient or the operator. The risk of malfunctions of the software that leads to an erroneous diagnosis or a delay in delivery of appropriate medical care is minimal.

5.2.2Image Review Software

5.2.2.1 System requirements

CapsoView can be installed on a computer that meets the following requirements:

CPU	Minimum Required	Recommended
	Intel Core i3 (for image reviewand reporting only)	Intel Core i7 Quad-Core (for optimaldownloading performance)

{6}------------------------------------------------

Image /page/6/Picture/0 description: The image shows the logo for CapsoVision. The logo consists of a blue and green swirl above the company name. Below the company name is the tagline "empowering through innovation" in a cursive font.

	Intel® Core™ i5 (fordownloading, review andreporting)

Memory	For 32-bit Operating System	For 64-bit Operating System
	Minimum 2GB	Minimum 4GB
Operating System	For PC	For Mac
	Windows 7 (Service Pack 1)	OS X Yosemite
	Windows 8.1	OS X El Capitan
	Windows 10 (Recommended for
	optimal downloading
	performance)
Display	Minimum Required	Recommended
	Display Resolution of:1366x768 for Windows	Display Resolution: 1920x1080
	1280x800 for Mac	Panel Type: IPS (In-Plane Switching)
		Color Gamut: 100% sRGB with Delta-E
		<2 (For maximum color accuracy)
Additional Software	Adobe Reader XI

5.2.2.2 Report Output Format:

Portable Document Format (PDF) and DICOM compatible PDF

5.2.2.3 Features:

CapsoView Software possesses the following features, which are described in detail in the noted sections of CapsoView (CVV) IFU-2757.

• Downloading data and Opening Video File	IFU-2757, Section 6
• Adding and Editing Procedure Information	IFU-2757, Section 7
• Accessing Full-Screen and Standard-View Modes	IFU-2757, Section 7
• Playback Toolbar	IFU-2757, Section 7
• Playback Status Bar	IFU-2757, Section 7
• Annotation User Interfaces	IFU-2757, Section 7
• Generating Capsule Endoscopy Reports	IFU-2757, Section 8
• Exporting Images and Videos	IFU-2757, Section 9
• Adjusting System Settings	IFU-2757, Section 10

5.3 Performance Data

The CapsoCam Plus (SV-3) Capsule Endoscope System performance testing was conducted per the appropriate FDA Recognized Consensus Standards and required bench testing. A detailed test list is provided on page 10 of this summary.

{7}------------------------------------------------

Image /page/7/Picture/0 description: The image shows the logo for CapsoVision. The logo features a blue and green swirl above the company name, which is written in a modern, sans-serif font. Below the company name is the tagline "empowering through innovation" in a cursive font.

5.4 Accuracy of the Device

Relevance of SV-1 to SV-3 Clinical performance

Capso Vision conducted three (3) studies to demonstrate the equivalence of the images obtained by the SV-3 to the predicate device (CapsoVision SV-1).

Study 1:

Protocol CVI-006 "Validation of CapsoCam® SV-3 Capsule Endoscopy System"; 49 healthy volunteers were enrolled. All subjects were assessed to the inclusion/exclusion criteria and signed the IRB approved Informed Consent prior to participation. Subjects who ingested the SV-3 CE, were assessed for adverse read by the Principal Investigator. The investigator noted on the CRF any landmarks visualized and if any, pathology found (the pathology may or may not be clinically significant). Of the 49 Intent to Treat Study Subjects, 7 dropped out, yielding a total of 42 Per-Protocol subjects for evaluation. In this protocol, the principal investigator was asked to identify key landmarks, completion of exam, identify any pathologies (whether clinically relevant or not), assess image quality. The results are displayed in the tables below:

Demographics

Confidence Level

(95.0%)

Age:	Gender:
Male 25 (53.52%)			Diagnostic Quality
Female 17 (40.48%)		Image DiagnosticQuality	Yes	No
			40	2
Mean	36.85714	Small Bowel Complete
Standard Error	1.678093		Yes	No
Median	37.5		41	1
Mode	30
Standard Deviation	10.87528	Pathologies Identified (grouped by type)
Sample Variance	118.2718	Pathology	Yes	No
Range	42	Blood	0	42
Minimum	19	Angiectasia	2	40
		Ulcer	2	40
Maximum	61	Polyp/Mass	0	42
Sum	1548	Other	4	38
Count	42	Of the list above, none of the pathological

3.388977

Of the list above, none of the pathological findings were considered clinically significant.

{8}------------------------------------------------

Image /page/8/Picture/0 description: The image shows the logo for CapsoVision. The logo features a blue and green circular design above the company name. Below the company name is the tagline "empowering through innovation" in a cursive font.

Landmarks Identified
	Identified	Not identified
1st Esophageal	40	3
1st Gastric	42	0
1st Duodenal	42	0
1st Cecal	41	1
Papilla	35	7

Overall Image Quality

Images better than	Yes	No
previous generation	4	38

Study 2: Comparisons of reads of select video clips from the study CVI-006 by Independent Blinded readers.

In this study, the images of landmarks and pathologies were extracted from the complete video clips. These video clips were randomized and sent to independent readers who were blind to the nature of the CVI-006 study. Readers were asked to assess landmark video quality, pathologies identified and subjective questions on video/diagnostic quality. The results are provided in the tables, below:

Consensus Amongst readers with video clips of Landmarks

Landmarks	Consensus
1st Duodenal	15
1st Cecal/IC Valve	12
None	15

In summary all blinded readers were in consensus with one another regarding the landmark video clips from the original CVI-006 Study.

Overall Consensus for Readers	N=42
Excellent	26
Good	0
Poor	0
N/A	15
Discordant amongst Readers	1

Consensus agreement on landmark video Ouality

Consensus agreement on pathologies found in CVI-006

Consensus amongst the independent readers

Pathology	Overall readerConsensus (N=42)
Blood	0
Ulcer	0
Vascular	5
Polyp/Mass	1
Other	2
None	34

Consensus when comparing to the original pathologies identified in CVI-006:

Pathology	Original versus Over-read
Blood	0/0
Ulcer	2/0
Vascular	2/5
Other	4/2
None	34/34

{9}------------------------------------------------

Image /page/9/Picture/0 description: The image shows the logo for CapsoVision. The logo features a blue and green circular design above the company name, which is written in a simple, sans-serif font. Below the company name is the tagline "empowering through innovation" in a cursive font. The logo is clean and modern, with a focus on the company's name and tagline.

Subjective questions on video Quality

Were Images of Diagnostic Quality	Yes	No
	42	0
Better Diagnostic Quality from EarlierGeneration	Yes	No
	25	17

Study 3: From the original SV-1 Study, a total of 40 video clips (both normal (11) and with pathology (29) Consensus agreement was reached in 35 of the clips or 87.5% were in agreement with the landmark or clinical pathology findings. There was 100% agreement between the old and new versions of the software. This comparison agreement was manifested even when there was a lack of consensus manifested in the original SV-1 study results.

Of those video clips with landmarks identified in the original SV-1 study, there was consensus in 10 of 11 clips (90.9%). The discordant finding was identical for all 3 readers when using either the original SV-1 software or the new SV-3 software.

Of those video clips with significant clinical pathology identified in the original SV-1 study, there was consensus in 25 of 29 clips (86.2%). The discordant findings were identical for all 3 readers when using either the original SV-1 software or the new SV-3 software.

Subjective Evaluation Questions

For each video clip presented to the independent blinded readers, each were asked to answer the following questions: In general, the newer SV-3 software (CVV 3.3 US) had a more favorable assessment than the SV-1 software (CVV 2.2) for Image quality

a. Video Image Quality Readers were asked when comparing the clips side if the quality was better than. equal to, or worse than another.
ﻒ Clinical Assessment Quality – Readers were asked; when image quality side by side, to determine a clinical assessment, were they equal or was the quality of one better than the other.
C. Ease of Use – Readers were asked, when comparing the two software versions used for each clip (viewing them side by side) was one version easier than, equal to or more difficult than the other.
Reviewing Experience-readers were asked to compare their reviewing experience (viewing them side by side) d. with each clip (and software version used for each), was their experience better than, equal to, or worse than the other.

Results for Video Image Quality

Of all 40 clips reviewed, using the original SV-1 Software (CVV 2.2) for one image and the newer, SV-3 software (CVV 3.2 US) for the other, reviewers responded as follows for Image Quality:

28 (70%) Ranked the SV-3 image as better than the SV-1 image;
12 (30%) Ranked both SV-3 image and SV-1 image as comparable;
0 (0%) Ranked the SV-1 image as better than the SV 3-image

Results for Clinical Assessment Quality

Of all 40 clips reviewed, using the original SV-1 Software (CVV 2.2) for one image and the newer, SV-3 software (CVV 3.2 US) for the other, reviewers responded as follows for Clinical Assessment Quality:

1 (2.5%) Ranked the SV-3 image as better than the SV-1 image;
39 (97.5%) Ranked both SV-3 image and SV-1 image as comparable; ●

{10}------------------------------------------------

Image /page/10/Picture/0 description: The image shows the logo for CapsoVision. The logo features a blue and green circular design above the company name, which is written in a simple, sans-serif font. Below the company name is the tagline "empowering through innovation" in a cursive font. The overall design is clean and professional.

0 (0%) Ranked the SV-1 image as better than the SV-3 image ●

Ease of use

Of all 40 clips reviewed, using the original SV-1 Software (CVV-2.2) for one image and the newer, SV-3 software (CCV 3.2 US) for the other, reviewers responded as follows for Software Ease of Use:

0 (0%) Ranked the SV-1 software as easier than the SV-3 software;
39 (97.5%) Ranked both SV-3 software and SV-1 software as equal;
. 1 (2.5%) Ranked the SV-3 software as easier to use than the SV-1 Software

Reviewing Experience

Of all 40 clips reviewed, using the original SV-1 software (CVV-2.2) for one image and the newer, SV-3 software (CVV 3.2 US) for the other, reviewers responded as follows regarding their reviewing experience:

0 (0%) Ranked the SV-1 software as a better reviewing experience; ●
38 (95.0%) Ranked both software versions as the same;
2 (5.0%) Ranked the SV-1 software as a worse reviewing experience

5.4 Substantial Equivalence:

The characteristics of the CapsoVision, Inc., CapsoCam Plus (SV-3) Capsule Endoscope System is substantially equivalent to the following currently approved predicate device based on the indications for use, typical clinical use, and operational and fundamental technological characteristics.

CapsoCam Imaging Systems with the following product information:
- 510(k) #: K151635. O
  - Product name: CapsoCam (SV-1) O
  - Classification: Class II O
  - Classification Regulation:21 CFR § 876.1300 O
  - Panel: Gastroenterology: Urology o
  - O Product Code:78 NEZ
  - Common Name: Capsule Imaging System O
  - Classification Name: Ingestible Telemetric Gastrointestinal Capsule Imaging System. o

ર્સ્ડ Predicate Device Description: (K151635)

CapsoCam (SV-1) is a single-use, ingestible video capsule that acquires and stores video images in on-board memory while moving through the gastrointestinal tract, propelled by natural peristalsis. The patient retrieves the capsule using the provided retrieval kit and returns it to the physician who downloads and reviews the images on a computer. The capsule is typically excreted within 3 to 30 hours after swallowing.

The CapsoCam (SV-1) capsule endoscopy system components that support the CapsoCam (SV-1) Capsule endoscopy procedure consists of the following:

CapsoCam (SV-1) capsules, which is intended for visualization of the small bowel mucosa in adults and used as a tool in the detection of abnormalities of the small bowel.
CapsoView (CVV) software program which is used to download and view CapsoCam images and to generate capsule endoscopy reports.
CapsoAccess (CDAS) Capsule Data Access System which accesses data from the CapsoCam capsule ● endoscopes.

{11}------------------------------------------------

Image /page/11/Picture/0 description: The image shows the logo for CapsoVision. The logo consists of a blue and green circular graphic above the company name, which is written in a stylized font. Below the company name is the tagline "empowering through innovation" in a smaller, handwritten-style font.

CapsoRetrieve (CVR1) Capsule Retrieval Kit which is used for the collection, storage, and transportation of the excreted CapsoCam capsule.
The CapsoCam SV-1 and the CapsoCam Plus (SV-3) capsule endoscope system have identical indications for use and very similar operating principles.

The substantial equivalence between the CapsoCam Plus (SV-3) Capsule Endoscope System and the predicate device CapsoCam (SV-1) Endoscope System Capsule is provided in a detailed discussion and side-by-side comparison in the substantial equivalence discussion.

5.6 Summary of Technical Differences Between CapsoCam Plus (SV-3) capsule endoscope system and Predicate Device

The differences in technical characteristics between the CapsoCam Plus (SV-3) capsule endoscope system and the CapsoCam® SV-1 are minimal and bear no significance on safety or effectiveness. The hardware changes to the modified device is shown in the table below:

	CapsoCam Plus (SV-3) capsule endoscope system
*Hardware	CMOS Image Sensor
	ASIC with larger frame buffer
	Flash Memory
	Camera field-of-view increased
	LED dies
	Capsule Data Access System (CDAS)
	Capsule startup routine
	Mechanical Design-added internal light pipe and reduced dimple on capsule tip
	PCB and PCBA components
	Magnetically Actuated Switch

The CapsoCam Plus (SV-3) capsule endoscope system is an updated version of the CapsoCam (SV-1) (K151635). Unchanged characteristics include: the intended use; the housing materials and sealing process; the form, fit and function while in contact with the patient; the system architecture; the package; the lens; and the illumination system. The implemented design changes are intended to maintain the same clinical function while improving the performance, particularly image quality, and to change the method of data download in the clinic after the capsule is excreted.

To improve image quality, the SV-3 includes a new CMOS image sensor with smaller pixels and more numerous pixels than the sensor in SV-1. In order to compress and save images with more pixels, and to be compatible with the new image sensor, SV-3 includes a new ASIC.

In order to provide a simpler process to clinical users, the way that data is downloaded from the CapsoCam capsule at the clinic after excretion and retrieval has been changed. For SV-1, the capsule's plastic cap is cut open, revealing contact pads that electrically connect to the CDAS1 (CapsoVision Data Access System), allowing the CDAS1 to power the SV-1 and to download the data over an SPI (Serial Peripheral Interface) bus. For SV-3, the capsule does not need to be cut open. The CDAS3 communicates with the capsule optically through the plastic cap and inductively powers the capsule during the data download.

The SV-3 is very similar to the SV-1, with the same basic mechanical design, system architecture, and functionality. Most of the components are identical. The camera and illumination system are essentially the same, but with

{12}------------------------------------------------

Image /page/12/Picture/0 description: The image shows the logo for CapsoVision. The logo features a blue and green swirl above the company name. Below the company name is the tagline "empowering through innovation" in a cursive font.

improved resolution and efficiency. All the changes are designed to change the method of download or to incrementally improve performance without changing the method of image capture, storage, and presentation. In addition to capsule hardware commonalities, the capsules' indications-for-use, contraindications, specified patient condition and recommended clinical protocol (including bowel prep) are unchanged.

5.7 Summary of Technical Differences Between CapsoView CVV 3.2 and CapsoView 2.2 (K151635) cleared version

Capso View 3.2 uses an innovative, streamlined user interface to make the image review process simpler and more efficient. Users can choose different viewing modes, adjust playback speed, and generate a capsule endoscopy report from a single screen. The software changes to the modified version is shown in the table below:

	CapsoView CVV-3.2
*Software	GUI design
	New GUI features
	Image processing improvements
	Data-download system
	System architecture: support download-only module, batch transcode and
	saving DICOM videos from AVI files
	OS: Windows and Mac OS X
	Resolution increase

CapsoRetrieve Capsule Retrieval Kit: 5.8

The addition of the Conformity Assessment Body street address was the only change to the Retrieval Kit Instruction for Use (IFU)

Summary of Bench Testing and In-Vivo Testing

Bench testing
Electrical Safety
IEC 60601-1	Medical electrical equipment - Part 1: General requirements for basic safety andessential performance.
IEC 60601-1-2	60601-1-2 4th Ed.: 2010/AC:2014, -Medical electrical equipment, Part 1: Generalrequirements for safety. 2. Collateral standard: Electromagnetic compatibility -Requirements and tests.
IEC 60601-1-6	Medical electrical Equipment-Part 1-6 General requirements for basic safety andessential Performance-Collateral Standard: Usability.
Biocompatibility
ISO 10993-1	Biological Evaluation of Medical Devices, Part 1: Evaluation and Testing.
ISO 10993-3	Biological Evaluation of Medical Devices, Part 3: Test for Genetoxicity,Carcinogenicity and Reproductive Toxicity.
ISO 10993-5	Biological Evaluation of Medical Devices, Part 5: Tests for cytotoxicity: in vitromethods.
ISO 10993-10	Biological evaluation of medical devices -- Part 10: Tests for irritation and delayed-type hypersensitivity.
ISO 10993-11	Biological Evaluation of Medical Devices, Part 11: Tests for systemic toxicity.
Other
Bite Test	Verification Test Protocol, CapsoCam® Bite Test # PRO-1401and PRO-2513

{13}------------------------------------------------

Image /page/13/Picture/0 description: The image shows the logo for CapsoVision. The logo features a blue and green swirl design above the company name. Below the company name is the tagline "empowering through innovation" in a cursive font.

Shelf life Test	Shelf-life Test Protocol, SV-3 # PRO-2513
Image Verification	Camera Image Verification Test Protocol # PRO-2504
LED	CapsoCam LED Verification Test Protocol # PRO-2350
Color Correction	Software color correction test per protocol # PRO-1910.
Clinical Validation	Validate the performance of the SV-3 capsule in clinical use # PRO-2497
Battery Life test	Battery Life Test Protocol # PRO-0529

In-Vivo testing

Study
Clinical Study	Validation of CapsoCam-SV-3 Capsule Endoscopy SystemProtocol Number: CVI-006

5.9 Conclusion:

Based on the similarities in indications for use, and in functional features as evaluated in both clinical and non-clinical performance testing. The CapsoCam Plus (SV-3) Capsule Endoscope System has demonstrated substantial equivalence to the listed predicate device (CapsoCam-SV-1-K151635). Any differences do not affect the product's safety or effectiveness.

All required testing and analyses were completed on the CapsoCam Plus (SV-3) Capsule Endoscope System to ensure that the device is safe and effective for its intended use.

Regulation Number and Section

§ 876.1300 Ingestible telemetric gastrointestinal capsule imaging system.

(a)
Identification. An ingestible telemetric gastrointestinal capsule imaging system is used for visualization of the small bowel mucosa as an adjunctive tool in the detection of abnormalities of the small bowel. The device captures images of the small bowel with a wireless camera contained in a capsule. This device includes an ingestible capsule (containing a light source, camera, transmitter, and battery), an antenna array, a receiving/recording unit, a data storage device, computer software to process the images, and accessories.(b)
Classification. Class II (special controls). The special control is FDA's guidance, “Class II Special Controls Guidance Document: Ingestible Telemetric Gastrointestinal Capsule Imaging Systems; Final Guidance for Industry and FDA.”