Month: July 2021

Deep Bio renews Research Collaboration Agreement with Dana-Farber Cancer Institute

SEOUL, South Korea, July 22, 2021 – Deep Bio, a leading company in digital pathology and cancer diagnostics, today announced a renewal of their Research Collaboration Agreement with Dana-Farber Cancer Institute aimed at evaluating prostate cancer tumors. This collaboration with Dana-Farber is a part of the Men of African Descent and Carcinoma of the Prostate (MADCaP) Consortium, a global collaboration formed to evaluate the high burden of prostate cancer in the Sub-Saharan African (SSA) population. Dana-Farber is a principal teaching affiliate of Harvard Medical School and the founding member of Dana–Farber/Harvard Cancer Center, the largest National Cancer Institute (NCI) designated Comprehensive Cancer Center in the nation.

This research project will investigate if Deep Bio’s deep learning algorithm, DeepDx® Prostate, can serve as an adjunct to pathologist diagnosis of pathology specimens. Tumor tissue images collected from eight separate centers in Sub-Saharan Africa will be processed and analyzed by DeepDx® Prostate. These AI-based pathology reads will be compared with human pathologist evaluations. This study is led by Dr. Timothy Rebbeck, the Vincent L. Gregory, Jr. Professor of Cancer Prevention at the Harvard TH Chan School of Public Health and Professor of Medical Oncology at the Dana-Farber Cancer Institute.

“We are honored to contribute to the meaningful research at Dana-Farber Cancer Institute, a leading cancer treatment and research center,” said Sun Woo Kim, the CEO and founder of Deep Bio. “This research has clinically significant implications if DeepDx® Prostate shows comparable output to human pathologists. If AI can serve as adjunct to human pathologists, the capacity for cancer diagnosis can improve significantly, particularly in regions such as Sub-Saharan Africa that are facing an extreme shortage of pathologists,” he added.

MADCaP involves 28 centers and over 15,000 men of African descent in North America, the Caribbean, Europe, and Africa to address the global epidemic of prostate cancer in the African diaspora. Prostate cancer has the highest heritability of the common cancers, and men of African descent have a disproportionately high incidence and mortality due to prostate cancer compared to men of other races.

About Deep Bio

Deep Bio Inc. is an AI biotech company with in-house expertise in deep learning, pathology, life sciences, and pharmacotherapeutics. As the country’s first to obtain MFDS approval of an AI-based cancer pathology solution, Deep Bio envisions a suite of AI-based IVD SaMDs (In Vitro Diagnostics Software as a Medical Device) for diagnosis and prognosis of multiple cancers. Deep Bio is actively engaged in the research space and participating in ongoing collaborations with top US medical centers.

DeepDx® Prostate is a clinically-validated AI for prostate core needle biopsy tissue image analysis. Whole-slide images (WSIs) of H&E-stained biopsy tissue specimens are analyzed for prostate cancer, Gleason scores and grade group. Extensively tested at a US CLIA lab (>540k cores as of June 2021), DeepDx® Prostate can alleviate the shortage of pathologists and the resultant increase in workload, while reducing diagnostic subjectivity and variability. To learn more, visit www.deepbio.co.kr.

2021.07.22
DeepBio

ARUP applies Deep Bio’s deep learning-based prostate cancer detection and classification solution for research

SEOUL, SOUTH KOREA (PRWEB) JULY 16, 2021– Deep Bio, a leading company in AI cancer diagnostics, announced a Research Collaboration Agreement with ARUP Laboratories, a top U.S. reference laboratory and worldwide leader in innovative laboratory research and development. DeepDx® Prostate, Deep Bio’s AI-based prostate cancer diagnosis software, will be used for the joint research.

This is the first of multiple research projects that ARUP and Deep Bio will collaborate on, under the multi-year Research Program. The first project aims to evaluate the impact of DeepDx® Prostate by evaluating whether applying the software in ARUP’s pathology workflow can lead to higher diagnostic performance compared to the current microscope-based diagnosis. For the next project, cancer prognosis-related research is being considered.

“DeepDx® Prostate has been recognized for its exceptional performance and innovative technology both at home and abroad. I am confident that this partnership with the prestigious ARUP Laboratories will bring us closer to the end users as our brand awareness will increase overseas” said Sun Woo Kim, the CEO and founder of Deep Bio. “We will actively endeavor to expand collaborations with top domestic and foreign laboratories to strengthen our position in the global market as well as demonstrate our leadership in AI-based cancer diagnostics,” he added.

“Computer-assisted diagnostic software tools bear enormous promise; however, little is known about their adoption by pathologists,” said Beatrice Knudsen, MD, PhD, ARUP medical director of Digital and Computational Pathology. “The collaboration with Deep Bio will provide important insights into pathologists’ preferences for how to use AI-based software solutions, as well as real life clinical implementation data.”

About Deep Bio

Deep Bio Inc. is an AI biotech company with in-house expertise in deep learning, pathology, life sciences, and pharmacotherapeutics. As the country’s first to obtain Korea’s MFDS approval of an AI-based cancer pathology solution, Deep Bio envisions a suite of AI-based IVD SaMDs (In Vitro Diagnostics Software as a Medical Device) for diagnosis and prognosis of multiple cancers. Deep Bio is actively engaged in the research space and participating in ongoing collaborations with top US medical centers. To learn more, visit www.deepbio.co.kr.

DeepDx® Prostate is a clinically-validated AI for prostate core needle biopsy tissue image analysis. Whole-slide images (WSIs) of H&E-stained biopsy tissue specimens are analyzed for prostate cancer, Gleason scores and grade group. Extensively tested at a US CLIA lab (>500k cores as of June 2021), DeepDx® Prostate can alleviate the shortage of pathologists and the resultant increase in workload, while reducing diagnostic subjectivity and variability. To learn more, visit www.deepbio.co.kr.

About ARUP Laboratories

Founded in 1984, ARUP Laboratories is a leading national reference laboratory and a nonprofit enterprise of the University of Utah and its Department of Pathology. ARUP offers more than 3,000 tests and test combinations, ranging from routine screening tests to esoteric molecular and genetic assays. ARUP serves clients across the United States, including many of the nation’s top university teaching hospitals and children’s hospitals, as well as multihospital groups, major commercial laboratories, group purchasing organizations, military and other government facilities, and major clinics. In addition, ARUP is a worldwide lead in innovative laboratory research and development, led by the efforts of the ARUP Institute for Clinical and Experimental Pathology®. ARUP is ISO 15189 CAP accredited.

ARUP Media Contact

Lisa Carricaburu, 801-541-5041, lisa.carricaburu@aruplab.com

2021.07.16
DeepBio

Deep Bio provides its AI-based prostate cancer detection software for research

SEOUL, SOUTH KOREA (PRWEB) JULY 16, 2021 – Deep Bio, a leading company in digital pathology and cancer diagnostics, announced an extension of Software License Agreement with Stanford University School of Medicine. DeepDx® Prostate, Deep Bio’s deep learning-based prostate cancer diagnosis software, is being used in a study conducted by Stanford Medicine researchers on radical prostatectomy specimens.

In the study, the researchers aim to evaluate the diagnostic performance of DeepDx® Prostate by comparing its results with the diagnosis data provided by the researchers. The study also explores the performance of DeepDx® Prostate in patient stratification by clinical use cases to guide therapy. The study results will be published in a peer-reviewed, scientific journal after the research is completed.

“We are proud to collaborate with Stanford Medicine and provide our AI diagnostic software to the research. We are excited that an algorithm such as DeepDx® Prostate which was trained on prostate core needle biopsy samples is being utilized in clinical research on radical prostatectomies,” said Sun Woo Kim, the CEO of Deep Bio. “Through this continued research collaboration, we strive to improve our technology and optimize digital pathology workflows for streamlined cancer diagnosis,” he added.

DeepDx® Prostate analyzes whole slide images (WSIs) of prostate core needle biopsy samples to detect cancer and grade cancer severity based on the Gleason scoring system. DeepDx® Prostate automatically analyzes other critical values such as the area of each Gleason pattern and the total tumor area. Deep Bio plans to expand their suite of AI algorithms to breast cancer, lymph nodes metastasis of breast cancer, and bladder cancer.

Deep Bio has participated in research collaborations with multiple reputable universities and published clinical validation studies in prominent peer-reviewed journals including Cancers, a respected oncology journal.

About Deep Bio

Deep Bio Inc. is an AI biotech company with in-house expertise in deep learning, pathology, life sciences, and pharmacotherapeutics. As the country’s first to obtain Korea’s MFDS approval of an AI-based cancer pathology solution, Deep Bio envisions a suite of AI-based IVD SaMDs (In Vitro Diagnostics Software as a Medical Device) for diagnosis and prognosis of multiple cancers. Deep Bio is actively engaged in the research space and participating in ongoing collaborations with top US medical centers. To learn more, visit www.deepbio.co.kr.

2021.07.16
DeepBio

Spokane, WA, and Seoul, Korea (July 14, 2021) – Gestalt Diagnostics and Deep Bio today announced their strategic relationship on the development of an integrated workflow for pathologists to use Artificial Intelligence algorithms directly within Gestalt’s PathFlow® platform. Deep Bio’s algorithm analyzes whole slide images (WSIs) of H&E-stained prostate core needle biopsy tissue specimens to detect and classify prostate cancer. Using the PathFlow® platform, pathologists now have a superior support tool in diagnosing prostate cancer.

“Optimizing the pathology workflow with an interoperable solution that combines the value of Gestalt’s full digital pathology platform and Deep Bio’s DeepDx® AI algorithms enables a high throughput diagnostic process,” says Gestalt COO & Chief Strategy Officer, Lisa-Jean Clifford. “Providing pathologists with instant access to AI algorithms directly within their workflow presents them with key data in real-time, shortening the time to diagnosis for cancer patients. We are excited to be collaborating with Deep Bio to provide pathology labs, and pathologists, with this superior solution.”

“Deep Bio’s relationship with Gestalt Diagnostics brings us one step closer to our vision of supporting pathologists and oncologists with timely and accurate diagnosis and prognosis, for better treatment decision-making. We believe our AI-powered DeepDx® is a powerful addition to the seamless and integrated clinical workflow afforded by PathFlow®”, said Deep Bio’s founder and CEO Sun Woo Kim

Visit Gestalt at www.gestaltdiagnostics.com and Deep Bio at www.deepbio.co.kr to learn more.

About Gestalt Diagnostics

Gestalt Diagnostics is a private, profit-driven software company who provides technology solutions, technical and integration services and support to pathology laboratories. Gestalt has developed PathFlow, an enterprise software platform specifically designed to bring the benefits of digital workflow to pathologists and pathology laboratories. This product was originally developed, by what is now Gestalt’s team, to support a fully digital reading platform for radiology. The radiology platform is used in leading hospitals across the United States and supports more than 15 million studies annually. Gestalt has expanded and redesigned this proven, robust solution to work in the laboratory space – engineered for the unique needs and workflow of pathologists. To learn more, visit www.gestaltdiagnostics.com.

About Deep Bio

Deep Bio Inc. is an AI biotech company with in-house expertise in deep learning, pathology, life sciences, and pharmacotherapeutics. As the country’s first to obtain KFDA approval of an AI-based cancer pathology solution, Deep Bio envisions a suite of AI-based IVD SaMDs (In Vitro Diagnostics Software as a Medical Device) for diagnosis and prognosis prediction of multiple cancers. Deep Bio is actively engaged in the research space and participating in ongoing collaborations with top US medical centers.

DeepDx® Prostate is a clinically-validated AI for prostate core needle biopsy tissue image analysis. Whole-slide images (WSIs) of H&E-stained biopsy tissue specimens are analyzed for prostate cancer, Gleason scores and grade group. Extensively tested at a US CLIA lab (>240k cores in 2020), DeepDx® Prostate can alleviate the shortage of pathologists and the resultant increase in workload, while reducing diagnostic subjectivity and variability. To learn more, visit www.deepbio.co.kr.

Gestalt Diagnostics Contact

Lisa-Jean Clifford, ljclifford@gestaltdiagnostics.com

Deep Bio Contact

YoonMin Lee, ymlee@deepbio.co.kr

2021.07.14
DeepBio

Deep Bio developed a novel deep learning-based prostate cancer detection model that demonstrates superb performance trained by a weakly supervised learning method 

Seoul, South Korea, July 1, 2021 – Deep Bio today announced that it published research results on a study, ‘Yet Another Automated Gleason Grading System (YAAGGS),’ in npj Digital Medicine which is a part of the prestigious international science and technology journals series, Nature Partner Journals. YAAGGS is Deep Bio’s original deep learning-based Gleason grading system that detects prostate cancer and classifies cancer severity.

The study presents a new weakly-supervised deep learning-based prostate cancer detection model. The study outlines training and validation of the model using whole slide images (WSIs) and their corresponding hospital diagnoses. To demonstrate the performance of YAAGS, a total of 7,600 H&E (Hematoxylin and Eosin)-stained prostate core needle biopsy samples images were used. The specimens were provided by Hanyang University Medical Center and Korea University Guro Hospital in South Korea.

In regard to cancer detection performance, the YAAGGS model exhibited a ROC AUC value of 0.983. Its sensitivity and specificity were 93.6%, and 96.0%, respectively. For the grade group prediction, analysis showed a Cohen’s kappa score of 0.650 and a quadratic-weighted kappa score of 0.897. The study demonstrated that the model can detect and grade the severity of prostate cancer just as well as a board-certified pathologist.

Detailed annotations on regions of interest specifying the severity of cancer are known to be essential for the development of deep learning-based cancer diagnostic algorithms. However, the manual annotation process is highly inefficient in terms of development time and cost. The novel approach to deep learning showcased in this paper can be used to expedite the development of additional diagnostic models.

Sun Woo Kim, the CEO of Deep Bio, said, “The YAAGGS study suggests a new method of deep learning that can significantly reduce the time and cost required to develop a cancer diagnostic solution. At the same time, YAAGGS also demonstrated superb performance, solidifying Deep Bio’s position as a leader in AI cancer diagnostics.” He also added, “Deep Bio will continue to innovate and work to optimize the digital pathology workflow to improve patient care.”

About Deep Bio

Deep Bio Inc. is an AI biotech company with in-house expertise in deep learning, pathology, life sciences, and pharmacotherapeutics. As the country’s first to obtain KFDA approval of an AI-based cancer pathology solution, Deep Bio envisions a suite of AI-based IVD SaMDs (In Vitro Diagnostics Software as a Medical Device) for diagnosis and prognosis prediction of multiple cancers. Deep Bio is actively engaged in the research space and participating in ongoing collaborations with top US medical centers.

DeepDx® Prostate is a clinically-validated AI for prostate core needle biopsy tissue image analysis. Whole-slide images (WSIs) of H&E-stained biopsy tissue specimens are analyzed for prostate cancer, Gleason scores and grade group. Extensively tested at a US CLIA lab (>240k cores in 2020), DeepDx® Prostate can alleviate the shortage of pathologists and the resultant increase in workload, while reducing diagnostic subjectivity and variability. To learn more, visit www.deepbio.co.kr.

2021.07.01
DeepBio