Automated pathological imaging and detection of cancer

This technology is an imaging platform for the automated analysis of abnormalities in large tissue specimens that can be used to detect breast cancer and related diseases.

Unmet Need: Efficient anatomic analysis of large tissue specimens for detecting disease

Treatment for breast cancer often requires a lumpectomy or mastectomy, after which the excised tissue must undergo histopathological analysis to determine the cancer’s invasiveness, disease stage, and whether it was fully removed during surgery. However, because these specimens are large, pathologists currently rely on visual methods of gross analysis to determine which blocks of the specimen should be submitted for further pathological assessment. These current methods are inefficient, work intensive, and lack sensitivity for detecting the microscopic features that indicate which tissue blocks contain malignancies.

The Technology: High-resolution imaging and analysis platform for automated diagnostic pathology

The technology uses optical coherence tomography (OCT) and artificial intelligence to image tissue blocks and automatically detect abnormalities indicative of breast cancer. The OCT used in this technology is high-speed and offers microscopic resolution with a large field of view to produce high-quality images. These images are evaluated using deep-learning algorithms that can discriminate between areas of normal or potentially cancerous tissue. The automated analysis features of this technology significantly improve the efficiency and speed of the pathology workflow while maintaining the ability to accurately detect anomalies related to breast cancer.

This technology has been validated using human tissue samples and was shown to outperform human experts in classifying cancerous versus non-cancerous samples.

Applications:

• Diagnostic imaging for breast cancer
• Diagnostic imaging for cancer in other organs (e.g. prostate)
• Research tool for studying tissue anatomy

Advantages:

• High-throughput
• High-resolution
• Automated and unbiased analysis algorithms
• Cost-effective
• High-sensitivity and specificity
• Time-efficient

Lead Inventor:

Christine P. Hendon, Ph.D.

Patent Information:

Patent Pending

Related Publications:

• Mojahed D, Ha RS, Chang P, Gan Y, Yao X, Angelini B, Hibshoosh H, Taback B, Hendon CP. “Fully automated post-lumpectomy breast margin assessment utilizing convolutional neural network based optical coherence tomography image classification method” Acad Radiol. 2020 May; 27(5): e81-e86.

• Ha R, Friedlander LC, Hibshoosh H, Hendon C, Feldman S, Ahn S, Schmidt H, Akens MK, Fitzmaurice M, Wilson BC, Mango VL. “Optical coherence tomography: A novel imaging method for post-lumpectomy breast margin assessment- A multi-reader study” Acad Radiol. 2018 Mar; 25(3): 279-287.

• Yao X, Gan Y, Chang E, Hibshoosh H, Feldman S, Hendon C. “Visualization and tissue classification of human breast cancer images using ultrahigh-resolution OCT” Lasers Surg Med. 2017 Mar; 49(3): 258-269.

Tech Ventures Reference:

• IR CU20175

• Licensing Contact: Dovina Qu