How multiple -omics merge to predict Gleason grading

Liz Carey
Nov 8, 2023

Sunday, November 26 | 9:50 a.m.-10:00 a.m. | S1-SSNMMI01-6 | Room E350

A new multiomics machine learning model may perform better for the prediction of Gleason grading than current methods used to determine the prognosis and management of prostate cancer, according to this scientific paper.

Attendees of this session will learn how radiomics data, genomics data, and pathomics data combined into a machine learning-based approach in a study that included a two-year follow-up of 146 patients. These were patients who underwent gallium-68 (Ga-68) prostate-specific membrane antigen (PSMA)-11 PET/MRI before radical prostatectomy between May 2014 and April 2020.

The research team led by Prof. Lukas Kenner and Alexander Haug, that included Jing Ning, who is affiliated to Christian Doppler Lab for Applied Metabolomics at the Medical University of Vienna, sought to improve the predictive performance of whole-mount Gleason grading in prostate cancer for a “smart and better stratification for radical prostatectomy” by deploying a high-throughput, machine-learning model to merge multiple “omics,” according to the RSNA abstract. For the machine-learning model, the team gathered this data using three strategies:

  1. Radiomics data acquisition involved delineated Ga-68 PSMA-11 PET/MR images from Hermes software with features computed using PyRadiomics.
  2. Genomics data acquisition involved isolating DNA from formalin-fixed paraffin-embedded (FFPE) samples from the radical prostatectomy. Ning and colleagues noted that whole-exome sequencing analysis was conducted, and functional pathway states were quantified using established in-silico tools. Clinical endpoints were also defined.
  3. Pathomics data acquisition involved constructing tissue microarrays from RP specimens, and immunohistochemical analysis was performed on 2-5-µm-thick sections from FFPE samples.

From these efforts, five machine learning-based models were established. The classification results were validated using 100-fold Monte Carlo cross-validation.

How well did the algorithm perform? You'll need to watch the presentation on Sunday to find out.

Latest in 2023 AI Preview
AI software flags missed intracranial aneurysms on CTA
November 8, 2023
Algorithm hunts for unreported osteoporosis markers on chest x-rays
November 8, 2023
Deep-learning model can spot patients at high risk of COPD
November 8, 2023
Opportunity for osteoporosis check on lumbar spine plain radiographs
November 8, 2023
More in 2023 AI Preview
AI software flags missed intracranial aneurysms on CTA
By Erik L. Ridley
In this talk, researchers from Tel Aviv University in Israel will describe how an AI algorithm can retrospectively detect intracranial aneurysms that had been missed on CT angiography (CTA) exams.
November 8, 2023
Algorithm hunts for unreported osteoporosis markers on chest x-rays
By Liz Carey
An AI algorithm can find radiographic markers for osteoporosis that are common but often not reported on radiology reports, according to this scientific paper.
November 8, 2023
Deep-learning model can spot patients at high risk of COPD
By Liz Carey
This scientific presentation will present external validation results for a deep-learning model in identifying individuals at high risk of incident chronic obstructive pulmonary disease (COPD) on routine outpatient chest x-rays.
November 8, 2023
Opportunity for osteoporosis check on lumbar spine plain radiographs
By Liz Carey
A deep learning-based framework for automated screening of osteoporosis on lumbar spine plain radiographs shows potential as another way to opportunistically make use of imaging studies performed for other indications, according to this presentation.
November 8, 2023
AI analysis of chest CT exams predicts cardiovascular disease
By Erik L. Ridley
A deep-learning algorithm can predict a patient’s risk of atherosclerotic cardiovascular disease from analysis of a single chest CT image, according to a group of researchers from Harvard Medical School.
November 8, 2023
Can CAD software reduce missed fractures in the ED?
By Liz Carey
Deep learning-based computer-aided detection (CAD) software shows potential for helping to avoid missed fractures on radiographs in the emergency department (ED), according to this talk.
November 8, 2023
CT radiomics can help classify indeterminate solitary pulmonary nodules
By Liz Carey
CT radiomics analysis can be a viable noninvasive option for aiding management decisions of indeterminate solitary lung nodules detected on noncontrast chest CT scans in colorectal cancer patients, this study has found.
November 8, 2023
AI algorithm predicts morbidity, mortality on spine DEXA exams
By Erik L. Ridley
In this Tuesday morning talk, researchers will describe how a deep-learning algorithm’s assessment of biological age on dual-energy x-ray absorptiometry (DEXA) exams can facilitate morbidity and mortality predictions.
November 8, 2023
CT body composition metrics portend post-TIPS mortality
By Erik L. Ridley
CT body composition metrics calculated by an AI model can improve mortality predictions in patients receiving a transjugular intrahepatic portosystemic shunt (TIPS), according to this presentation.
November 8, 2023
Machine-learning model detects, characterizes rib fractures on CT
By Erik L. Ridley
A machine-learning model can detect traumatic rib fractures on CT scans and automatically provide a fracture severity score, according to this scientific presentation.
November 8, 2023
Team studies CT image features for lung adenocarcinoma prognostication
By Liz Carey
Deep learning-based analysis of morphological and histopathological features on CT can successfully predict survival in lung adenocarcinomas, according to this retrospective dual-institution study.
November 8, 2023
AI algorithm helps to spot overlooked fractures
By Erik L. Ridley
In this talk, researchers will highlight the potential for AI software in detecting fractures that are often missed on radiographs.
November 8, 2023
Page 1 of 2
Next Page