AI powered robotics for a
safer procedure

Technology. Needleye Robotics is bringing to the market the results of many years of research on AI-powered robotic devices for the diagnosis of prostate cancer. Our product combines the power of AI, machine learning, and robotics to help radiologists and urologists minimizing the diagnostic error and achieve a speedy and effective therapy.

PROBLEM

According to the World Cancer Research Fund, with 1.3 million new cases worldwide, prostate cancer is the second most common cancer in men, causing more than 350,000 deaths each year.

Early diagnosis is crucial to improve the patients’ quality of life and reduce the mortality. When prostate cancer is suspected, diagnosis must be confirmed by a biopsy and subsequent histological analysis.

However, biopsy is far from being accurate, as its mostly manual nature causes a significant diagnostic error that may exceed 30%.

This is due to human cognitive (bad target identification) and manual (bad needle guidance) shortcomings and leads to late or, in the worst case, wrong diagnosis.

To perform a biopsy on suspect tissues, physicians mostly adopt the so-called Freehand Transrectal (TRUS) or, alternatively, Transperineal (TPUS) Ultrasound technique.

Basically, they manually identify the prostate capsule through real-time ultrasound (US) images and overlay MRI to US images to pinpoint the lesion location. Tissue samples are then collected by manually reaching the lesions with a biopsy needle.

Icon Counter
new cases
0 M
deaths
0 K
error excess
0 %

SOLUTION

Needleye platform brings a paradigm shift in biopsy procedures that can turn a subjective and operator-dependent procedure into a safer and more accurate diagnostic tool.

The technology should be able to prove that the biopsy procedure can be done in an ambulatory environment at a reasonable cost, with state-of-the- art accuracy levels.

It allows to treat patients earlier, and its “one–insertion to target” capability makes the procedure predictable and efficient.

It requires minimal learning curve, and it is a truly mobile system. The cognitive and manual functions carried out by the physician are replaced in the Needleye solution by AI algorithms and by robotic motions, but still all decisions are made by the physician.

AI Icon

AI algorithms provide guidance for

Tech Icon
Identification of the prostate boundaries and biopsy targets in the MRI images

Tech Icon
Fusion of MRI and US images

Tech Icon
Real-time processing of US images

Tech Icon
Computation of the optimal needle trajectories

Robot Icon

The robotic actions are

Bullet Point Icon
Computation of the robot positions

Bullet Point Icon
Tracking of the needle by the US probe

Bullet Point Icon
Robot motion to the entry point

Bullet Point Icon
Adjustment of the US probe

Bullet Point Icon
Needle positioning and insertion monitoring

This process is repeated until all biopsy targets have been reached.

TECHNICAL DETAILS

The Needleye robot continues the idea to use a SCARA robotic structure to guide a biopsy needle as demonstrated by the first prototype –PROST. The Needleye solution aims at transitioning to the much harder case of realistic anatomical signals, assessing robot’s performance with the complex and noisy signals generated by real-time imaging of human tissues in a realistic environment (TRL 6).

Since the very beginning of the development roadmap, the team has adopted a design thinking approach to the product development, involving physicians (e.g., Prof. Prokar Dasgupta, Prof. Alessandro Antonelli, etc) and value chain partners to collect information on the product features, both in terms of expected performance and for its integration with existing medical equipment.

TECHNICAL DETAILS

The Needleye robot continues the idea to use a SCARA robotic structure to guide a biopsy needle as demonstrated by the first prototype –PROST. The Needleye solution aims at transitioning to the much harder case of realistic anatomical signals, assessing robot’s performance with the complex and noisy signals generated by real-time imaging of human tissues in a realistic environment (TRL 6).

Since the very beginning of the development roadmap, the team has adopted a design thinking approach to the product development, involving physicians (e.g., Prof. Prokar Dasgupta, Prof. Alessandro Micali, etc) and value chain partners to collect information on the product features, both in terms of expected performance and for its integration with existing medical equipment.

SCIENTIFIC RESOURCES