[Innovative Startups] Deep Bio will revolutionize prostate cancer diagnosis with an AI platform

Korean manufacturers of artificial intelligence-based medical equipment have increased their global presence through superior technologies.

Many companies use AI platforms to diagnose cancer. However, Deep Bio wants to make a difference by diagnosing prostate cancer using AI for the first time in Korea.

In April of last year, Deep Bio became the first company to receive approval from the Department of Food and Pharmaceutical Safety for an AI-based medical device that diagnoses prostate cancer – DeepDx-Prostate. This in vitro diagnostic software helps doctors diagnose prostate cancer.

Deep Bio was the first AI medical device manufacturer to diagnose cancer with biopsy images in the pathology department. There is no AI medical device that can diagnose prostate cancer that has received FDA approval. However, with a high unmet need in the field, Deep Bio’s technology has already gained worldwide recognition, according to the company.

The company has participated annually in the United States and the Canadian Academy of Pathology (USCAP) since 2018 and publishes papers annually. This year, the company published four articles.

Korea Biomedical Review sat down with Deep Bio CEO Kim Sun-woo to learn more about DeepDx-Prostate and its plans.

Deep Bio CEO Kim Sun-woo explains how his company’s devices are helping doctors make faster and more accurate diagnoses in a recent interview with Korea Biomedical Review at the company’s headquarters in Guro-gu, in southwest of Seoul.

Question: A solution for diagnosing prostate cancer with digital images seems unusual. Please explain how DeepDx Prostate works.

Reply: To diagnose prostate cancer, hospitals perform prostate specific antigen (PSA) tests.

Suppose the patient has a high PSA level and the doctor gives an opinion about prostate cancer. In this case, the hospital removes the tissue with a needle biopsy. The pathologist observes the cells to confirm whether it is cancer or not. If it is cancer, they indicate the severity according to the Gleason score.

However, there is a limit to what pathologists can do due to the size of the data.

DeepDx Prostate, developed by learning images diagnosed by a pathologist, is software to aid in the diagnosis of prostate cancer.

He analyzes all imaging slides of scanned prostate needle biopsy samples stained by H&E to determine the presence of cancer and cancer severity with Gleason scores 3-5.

The company has verified the performance of DeepDx Prostate from different angles, and our product has performed well against benchmarks set by pathologists at several hospitals, including Seoul National University Hospital.

Last year, DeepDx Prostate became the first AI medical device in Korea to obtain grade 3 in vitro diagnostic medical device approval from the Ministry of Food and Pharmaceutical Safety as auxiliary software for cancer diagnosis. by artificial diagnosis.

While developing the software, the company used thousands of sheets at the time of approval, and we are always adding more data.

In June of this year, the company also added more than 500,000 base images of the United States as a quality check.

Q: What are the advantages of DeepDx Prostate over conventional prostate cancer screening? Are treatment methods and options also provided?

A: Currently, pathologists diagnose prostate cancer by examining tissue under a microscope to determine the amount of cancer in the whole tissue.

When they find cancer, they divide it into a score of 1 to 5 depending on the type of cancer and calculate the Gleason score.

The Gleason score is the sum of the two patterns occupying the most and the next largest part of the cancerous tissue. Because patterns one and two are similar to normal cells, hospitals generally consider patterns greater than three to be significant.

However, the processing method is still different for models 3-5.

Therefore, it is important to accurately measure the Gleason score. However, unlike X-rays, which have a size of 1000×1000, the pathological image is very large, with an area of ​​150,000×100,000.

Viewing this image with the naked eye under a microscope is time consuming and difficult to clearly distinguish, so different pathologists sometimes diagnose the same cancerous tissue differently.

Since the method of treatment may be different in each case, there was a great unmet need for an additional diagnostic tool to increase agreement among pathologists.

The company believes that artificial intelligence can be the solution to these problems.

We are currently conducting a related study with a medical school in the United States, and the results show that our AI measures more accurately than the naked eye.

In terms of treatment, the company plans to conduct global clinical trials in the future.

Q: Is DeepDx Prostate used in the United States? What is the FDA approval timeframe?

R: CCurrently, several Clinical Laboratory Improvement Amendments (CLIA) laboratories in the United States have been using DeepDx Prostate d for quality control since last year.

Notably, the company signed a business partnership with Lumea, a digital pathology solutions company in the United States, and has been supplying products since March of this year.

We have also been granted commercial rights for the use of images and use them for product development.

The analysis of pathological images using AI is a new field and no company has yet received FDA approval.

Therefore, we are preparing the process by carefully organizing the data, and we plan to submit the licensing data to the FDA during this year. If that happens, I think the licensing schedule will become visible next year.

Q: Have you received feedback from pathologists who have used DeepDx Prostate?

A: In the United States, DeepDx Prostate provides measurements such as presence or absence of cancer, Gleason grade, percentage of cancer, and size of cancerous tissue and tumor.

Many researchers have rated this as very helpful and reducing the burden of diagnosis. For example, it can show cancer that occupies a small large area of ​​the whole pathology image with just one click, thus reducing the errors that individuals miss when observing with the naked eye. .

Q: Are there additional products in development after DeepDx Prostate?

A: We are developing AI software for the diagnosis of breast and bladder cancer.

In particular, for breast cancer, we are developing a product that detects lymph node metastases. During breast cancer surgery, hospitals look for metastases in the nearby sentinel lymph node, and if there are metastases, they remove them completely.

We are also expanding our product portfolio for prostate cancer.

The company has developed software that detects cancer by analyzing samples taken by transurethral resection of the prostate, performed on patients with benign prostatic hyperplasia at a commercial level, and is preparing for authorization procedures.

In addition, the software related to the analysis of samples on whole frames shows good performance, so it is in the process of being marketed.

Q: What are Deep Bio’s short and long term goals?

A: The short term goal is to generate significant revenue by successfully marketing DeepDx Prostate in the US market.

The long-term goal is to provide a companion diagnostic tool for the prognosis and treatment of disease through analysis of pathological images.

We will provide opportunities for high-risk patients through active treatment while helping to improve patient quality of life by avoiding overtreatment and reducing side effects for low-risk patients.

About Hector Hedgepeth

Check Also

New study challenges widely held beliefs about Alzheimer’s disease

A new study challenges the dogma behind drug trials for Alzheimer’s disease. The study found …

Leave a Reply

Your email address will not be published.