SIS Software version 3.3.0

K183019

Surgical Information Sciences, Inc. · cleared 2019-03-19 · product code LLZ · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.3)

“SIS Software is an application intended for use in the viewing, presentation and documentation of medical imaging, including different modules for image processing, image fusion, and intraoperative functional planning where the 3D output can be used with stereotactic image guided surgery or other devices for further processing and visualization.”

AlgorithmThe SIS Software uses machine learning and image processing to enhance standard clinical images for the visualization of the subthalamic nucleus (“STN”). The methodology relies on a reference database of high-resolution brain images (7T MRI) and standard clinical brain images (1.5T or 3T MRI). The algorithm uses the 7T images from a database to find regions of interest within the brain (e.g., the STN) on a patient's clinical (1.5 or 3T MRI) image. Two separate commonly used outlier detection machine learning models were trained: an elliptic envelope and an isolation forest.

source quote (p.4)

“SIS Software uses machine learning and image processing to enhance standard clinical images for the visualization of the subthalamic nucleus (“STN”). The software makes use of the fact that some structures in the brain are better visualized using high-resolution and high-contrast 7T MRI than via 1.5T or 3T clinical MRI. The methodology relies on a reference database of high-resolution brain images (7T MRI) and standard clinical brain images (1.5T or 3T MRI). The algorithm uses the 7T images from a database to find regions of interest within the brain (e.g., the STN) on a patient's clinical (1.5 or 3T MRI) image. Briefly, two separate commonly used outlier detection machine learning models were trained using the brains from the training set, from which the same brain geometry characteristics were extracted as described below: One of these models is an elliptic envelope, which defines a volume in feature space based on the distributions of feature values from the training set; visualizations with characteristics (features) that fall outside the envelope will be considered anomalies. The second model is an isolation forest, which contains a population of decision trees based on random partitioning of the training set.”

Adaptive (vs locked)No

source quote (p.5)

“None of the 68 STNs were part of the company's database for algorithm development and none were used to optimize or design the company's software. Thus, this validation data set was completely separate from the data set that was used for development. The software development was frozen and labeled before tested on this validation set.”

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (3)

Retrospective clinical

n=68 cases

endpoints: Center of mass distance; Surface distance; Dice coefficient values

Bench

n=5 scans

endpoints: distance between the fiducial points

Retrospective clinical

n=45 other

endpoints: Distance between center of mass (COM) of the electrode tip and contacts; Angle between the orientation of contacts

Reported performance (3 observations)

sensitivity0.5

source quote (p.8)

“50.00%”

specificity0.8939

source quote (p.8)

“89.39%”

diceas written: “Dice coefficient”0.69

source quote (p.6)

“In addition, the Dice coefficient in this dataset was 0.69, which was expected given the small size of the STN and substantially similar to the predicate device.”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

recalls in product code, 24mo

295

MAUDE reports in code, 12mo

+683%

vs code's own 3-yr baseline

drift signals on this device

re_clearance
The FDA AI/ML device list shows a newer 510(k) K241083 (decision 2024-06-14) from Surgical Information Sciences, Inc. for a matching device line ("SIS System") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K241083
re_clearance
The FDA AI/ML device list shows a newer 510(k) K230977 (decision 2023-05-02) from Surgical Information Sciences, Inc. for a matching device line ("SIS System") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K230977
re_clearance
The FDA AI/ML device list shows a newer 510(k) K223032 (decision 2022-11-21) from Surgical Information Sciences, Inc. for a matching device line ("SIS System (Version 5.6.0)") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K223032
re_clearance
The FDA AI/ML device list shows a newer 510(k) K210071 (decision 2021-03-31) from Surgical Information Sciences, Inc. for a matching device line ("SIS System (Version 5.1.0)") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K210071
re_clearance
The FDA AI/ML device list shows a newer 510(k) K192304 (decision 2019-09-13) from Surgical Information Sciences, Inc. for a matching device line ("SIS Software Version 3.6.0") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K192304
adverse_event_inflection
MAUDE adverse-event reports for product code LLZ: 295 in the 12 months ending 2026-06, vs a 37.7/12mo average over the prior 3 windows (+683%). Code-level count — reports are not attributed to this specific device.
first seen 2026-07-08 · openFDA /device/event.json count=date_received product_code=LLZ
…and 25 more.

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).