Schematic illustration of the researchers im4MEC deep learning pipeline: (A)...
Schematic illustration of the researchers' im4MEC deep learning pipeline: (A) Whole-slide images were segmented and cut into non-overlapping square tiles of 360 μm at 40× magnification and resized to 224 × 224 pixels. (B) The optimal number of tiles were sampled from each whole-slide image to build a training dataset for the MoCo-v2 self-supervised learning model. (C) Features were extracted from all tiles of the whole-slide image by use of the self-supervised learning encoder, ResNet-50, at the last layer resulting in features of size 2048. (D) The model was trained to molecularly classify the whole-slide image, assigning attention scores to each tile and molecular class. Attention heatmaps are displayed from low attention (blue) to high attention (red). (E) The top 20 attended tiles were extracted from the predicted attention branch only. The predictions of HoVer-Net, a nuclear segmentation and classification deep learning model trained on an endometrial cancer tile image dataset, were used to compute counts of the three cell types and size and shape of the tumour nuclei. Subsequent analyses described these morphological features in association with the molecular classes and measured their relative feature importance with a support vector machine. MMRd=mismatch repair protein deficient. NSMP=no specific molecular profile. p53abn=abnormal cellular tumour antigen p53 expression.

Image source: Fremond et al., Lancet Digital Health 2022 (CC BY 4.0)

News • Application in pathology

Endometrial cancer diagnostics: AI gives new insights

Research at the Leiden University Medical Center (LUMC) Department of Pathology shows the power of artificial intelligence (AI) applied to endometrial carcinoma microscopy images.

The group of Dr. Tjalling Bosse offers novel insights that could improve diagnosis and treatment of uterine cancer. Their findings have been published in The Lancet Digital Health

Endometrial carcinoma is the most common cancer of the gynecologic tract. At the LUMC both clinical trials and translational research is conducted to improve the care for these patients. In the past years, the LUMC has had a leading role in the development of a novel tumor classification system based on molecular alterations, resulting in four endometrial cancer subtypes. Would it be possible to predict these molecular classes, based on microscopy-images alone?

Photo
Sarah Fremond

Image source: LUMC

Bosse and colleagues applied artificial intelligence on microscopy images of thousands of endometrial carcinoma images from patients that participated in the PORTEC-1 trials. His team developed a model that robustly predicts the four molecular classes of endometrial carcinomas based on one (hematoxylin and eosin)-stained microscopy slide image, which is the standard histological stain used in diagnostics for assessment of tumour grading and histological subtyping. This model was not “a black-box”, but through reverse-engineering the researchers were able to show which image-features were relevant for its predictions. The model provided the team with important novel insights that can be utilized in future studies to further improve diagnostics, prognostication, and management of endometrial cancer patients. “The application of AI in pathology is emerging. In this project we studied the morphology of tumors that shared the same molecular alteration to better understand the effect these changes have on the appearance of the tumor. With this work, the computer model has directed us to areas in- and outside the tumor that are important,” Bosse notes. 

“In cancer diagnostics, the number of variables (molecular, tumour morphology, patient data) has increased exponentially and has complexified patient prognosis prediction. Through training unbiased AI models, AI predictions can also teach pathologists in return by, for instance, identifying novel morphological details on microscopy slide images with prognostic value,” says Sarah Fremond, first author of the new publication. 


Source: Leiden University Medical Center

20.12.2022

Read all latest stories

Related articles

Photo

News • Women's health

Breast and ovarian cancer risk assessment from cervical samples

Scientists have discovered a means of identifying the risk of breast and ovarian cancer by measuring epigenetic changes in cervical samples from over a thousand women.

Photo

Video • Digital patient support tool

Ovarian cancer: "Olivia" to provide information and support

Patients affected by ovarian cancer can turn to "Olivia": The interactive digital resource provides information about diagnostics, treatment and life with ovarian cancer.

Photo

News • CSCC study finds distinct subgroups

Cervical cancer: major new clue to understanding aggressiveness

Scientists have discovered that cervical cancer can be divided into 2 distinct molecular subgroups – one far more aggressive than the other – as part of the largest ‘omics’ study of its kind.

Related products

Fujifilm · Dynamyx

Pathology

Fujifilm · Dynamyx

FUJIFILM Europe GmbH
Hologic · 3DQuorum SmartSlices

Artificial Intelligence

Hologic · 3DQuorum SmartSlices

Hologic, Inc.
Hologic · Genius AI Detection*

Artificial Intelligence

Hologic · Genius AI Detection*

Hologic, Inc.
ScreenPoint Medical · Transpara

Artificial Intelligence

ScreenPoint Medical · Transpara

ScreenPoint Medical
ScreenPoint Medical · Transpara

Artificial Intelligence

ScreenPoint Medical · Transpara

ScreenPoint Medical
Subscribe to Newsletter