Month: April 2022

Five abstracts in prostate and breast cancers, Deep Bio’s main research areas, are presented during the online sessions.

SEOUL, SOUTH KOREA (PRWEB) APRIL 11, 2022 – Deep Bio, a pioneer in medical AI for pathologic cancer diagnostics, presented five abstracts in regards to cancer diagnosis and prognosis of multiple cancer types using deep learning-based algorithms at the American Association for Cancer Research (AACR) 2022 which took place both in-person and virtually in New Orleans.

These studies showed notable findings when the algorithms were used for prognosis, including recurrence risk prediction and survival analysis. Particularly, a study that aimed to find out the relationship between histomorphological features of adenocarcinoma lesions and patients’ survival using a deep learning model was highlighted, drawing attendees’ attention. In the study, the deep learning-based pancreatic adenocarcinoma survival model discovered that histomorphological features show correlations with patient survival. Also, the study brought into light the possibility of applying the survival analysis to other diseases such as rectum adenocarcinoma and breast adenocarcinoma. In another study, Deep Bio’s breast cancer survival analysis model was able to distinguish between the low-risk group and the high-risk group to some extent, suggesting it can be used as a screening tool prior to the 21-gene test which classifies patients in early-stage breast cancer for whom chemotherapy can be effective.

Deep Bio also shared meaningful study results in prostate cancer, its core research area. In the study, researchers sought to detect cancerous regions and grade their severity on a whole slide image (WSI) of prostate frozen sections with deep learning-based cancer diagnosis support software. The model demonstrated high performance, achieving 98%in sensitivity for detecting malignant cases and 99% sensitivity for detecting clinically significant risk cases*.

Tae-Yeong Kwak, the CTO of Deep Bio, said, “Prognosis analysis of cancer is crucial in that it directly affects patients’ treatment and care plans. The studies presented imply that deep learning algorithms can be a great help to predict the prognosis of cancer more precisely. Deep bio will continue its efforts to make these technologies for real clinical settings.”

“By presenting significant research results at this year’s AACR, Deep Bio not only showcased its commitment to AI-based cancer diagnosis and digital pathology but also expanded its presence globally. With the proven and tested technologies, we will lead digital pathology and AI through close partnerships with clinics, research institutes, and digital pathology platform providers,” said Sun Woo Kim, the CEO of Deep Bio.

Deep Bio continues to focus on not only AI diagnostics but also R&D and presenting the results at various international conferences and events. The company also continues to build its presence in the global market through overseas digital pathology solution providers in the US, Europe, and India, as well as conducting research cooperation with Stanford Medical School, Harvard Dana-Farber Cancer Center, and other top research institutions in the US.
Abstracts Presented Included (E-Posters):

• Breast cancer survival analysis with the size of the infiltrative cancer area
• Automated Gleason grading of digitized frozen section prostate tissue slide images
• Recurrence risk prediction based on automatic histopathologic analysis of breast cancer using whole slide images
• A deep learning based pancreatic adenocarcinoma survival prediction model applicable to adenocarcinoma of other organs
• Molecular mapping of prostate cancer on whole mount prostatectomy specimens using deep neural networks to quantify genotypic heterogeneity

(* clinically significant risk cases: Grade group 2 or over)
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 (Ministry of Food and Drug Safety) approval of an AI-based cancer diagnostic support 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 http://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 groups. Extensively tested at US CLIA labs (> 500k cores in 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 http://www.deepbio.co.kr.

Join Deep Bio at AACR 2022! At this year’s AACR, Deep Bio will present both on-site and virtually!

Visit us at booth #1461 to share your thoughts on the role of digital pathology and AI in cancer research. Also, don’t forget to see the latest version of DeepDx® Prostate, our innovation in cancer diagnostics.

For a meeting and a live demo, please send an email to  sales@deepbio.co.kr or visit www.deepbio.co.kr.

While we have a booth exhibition in person, there will be 5 abstracts from our latest research, which will be presented during the online sessions.

▶ E-Poster Presentation schedule: Apr 8 2022 12:00PM – 1:00 PM

#5054 Breast cancer survival analysis with the size of the infiltrative cancer area / Presenter: JunYoung Choi

#5056 Automated Gleason grading of digitized frozen section prostate tissue slide images / Presenter: Joonyoung Cho

#5058 Recurrence risk prediction based on automatic histopathologic analysis of breast cancer using whole slide images / Presenter: Geongyu Lee

#5060 A deep learning based pancreatic adenocarcinoma survival prediction model applicable to adenocarcinoma of other organs / Presenter: Joonho Lee

#5061 Molecular mapping of prostate cancer on whole mount prostatectomy specimens using deep neural networks to quantify genotypic heterogeneity / Presenter: Joonyoung Cho