We presented a session titled "Imaging-based risk stratification solutions for prostate cancer care"

We presented a talk on imaging-based Artificial Intelligence applications for prostate cancer care.

Our collaborator Dr. Tamara L. Lotan, Johns Hopkins Medical presented some of the solutions we have been working on together: AI-based prediction of prostate cancer molecular subtype and metastasis using multi-modality data.

We conducted a workshop at the 19th European Congress of Toxicologic Pathology by Erio Barale-Thomas (Janssen R&D), Sabina Soldati (Pathology Experts GmBH) & Tijo Thomas (AIRA Matrix).

We discussed solutions for the automated stage-aware assessment of spermatogenesis in rodent testis, quantification of relevant toxicity endpoints in testis, as well as elucidate approaches for automated estrus staging and ovarian follicle counting in rodents.

We presented a session titled "Application of Artificial Intelligence in Enhanced histopathology of Spleen" with Debra Tokarz, EPL.

We also presented four different applications of Deep Learning in Preclinical Toxicology around Rodent Liver, Kidney, Testes and Pancreas.

We presented an oral presentation titled "Tumour region identification & TPS estimation of PDL-1 expression in NSCLC using deep learning" in the Machine Learning and AI-Clinical Application session.

We presented a poster titled "Deep learning-based application for sub-classification of Gleason pattern 4 in prostate carcinoma".

We presented our Prostate Cancer Decision Support Suite, designed to provide diagnostic, prognostic, and predictive assistance to Oncology teams.

We presented our prostate cancer decision support suite for the Prostate Cancer Care pathway.

We talked about how Deep Learning networks trained on histopathological ground truth can increase the accuracy of non-invasive diagnostic technologies like mpMRI and provide a potential translational approach to better staging and therapeutic planning.

Talk

Abstract title: A Deep Learning method for Tumour Region Identification and Tumour Proportion Score Estimation for PD L1 Expression in Non Small Cell Lung Carcinoma

We propose a computational technique using Deep Learning for detecting the cancer regions and calculating the Tumor Proportion Score (TPS) for PD L1 expression, in immunohistochemically stained sections from Non Small Cell Lung Carcinoma (NSCLC).

We demonstrated AIRADHI, an Image Management System for Preclinical Digital Pathology Workflows and Peer Reviews, at STP-I 2021.

Chaith Kondragunta, CEO of AIRA MATRIX, spoke at IHAI 2021 about the usage of deep learning applications in pathology.

Tech Talk

AIRA MATRIX presented two papers at the ARVO: IMAGING IN THE EYE CONFERENCE on May 13,2021.

The first presentation discussed a deep learning-based automated screening system capable of detecting and diagnosing diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), and few other pathologies in retinal images.

The second presentation introduced a deep learning tool for the early detection and grading of Diabetic Macular Edema (DME) using color fundus images, achieved by performing a LEsion Aware Prediction (LEAP) by segmenting hard exudates (HE).

Event Website

AIRA MATRIX hosted a session titled, “Demystifying Deep Learning for Pathologists” on June 25th, 2019 at the Society of Toxicologic Pathology (STP) 38th Annual Symposium.

AIRA MATRIX presented an informative session on optimizing preclinical pathology reporting using AI techniques. The session familiarized participants with deep learning (DL) modules that help speed up complex workflow processes in toxicologic pathology.

AIRA MATRIX announced the development of an Artificial Intelligence based image analysis solution for Rapid On Site Evaluation (“ROSE”) of EBUS-TBNA samples in collaboration with Dr. Suman Paul, Specialist Registrar in Respiratory Medicine, Warrington and Halton Hospitals NHS Foundation Trust.