̽��ֱ�� of Cambridge - Florian Markowetz

AI versus cancer - the Cambridge researchers using machine intelligence to beat disease

sb726 — Mon, 15 Jul 2024 07:00:31 +0000

‘Game changing’ technology which can predict how patients will respond to cancer treatment is part of a wave of Cambridge research harnessing AI to fight the disease.

Tumour ‘signatures’ could provide key to more accurate treatment for deadliest cancers

Anonymous — Wed, 15 Jun 2022 15:00:27 +0000

Currently, scientists use individual genetic changes to develop mutational signatures, which can be used to understand the origin of a cancer, and to predict how a cancer progresses. However, so far, there has not been a framework to interpret the larger, more complex patterns of genetic changes seen in chromosome instability in the same way.

Our genetic code is stored on 23 pairs of chromosomes, the ‘chapters’ that make up to the genome. But when our genome gets copied, these chromosomes can become unstable and segments of DNA can get duplicated, deleted or re-arranged.

Chromosomal instability is a common feature of cancer, occurring in around 80% of tumours, but this jumble of fragments can be difficult to read, making it hard to understand exactly what types or 'patterns' of instability are present in any given tumour. Instead, tumours are divided into broad categories of having either high or low amounts of chromosomal instability.

Cancers with high levels of chromosomal instability are extremely deadly, often having survival rates of less than 10%. As such, understanding and treating chromosomal instability is central to improving the outcomes for millions of cancer patients worldwide.

Now, for the first time, scientists at the ̽��ֱ�� of Cambridge and the National Cancer Research Center, Madrid, have published a robust framework to allow them to analyse chromosomal instability in human cancers.

Dr Florian Markowetz and colleagues investigated patterns of chromosomal instability across 7,880 tumours, representing 33 types of cancer, such as liver and lung cancer, from ̽��ֱ��Cancer Genome Atlas. By analysing the differences in the number of repetitions of sequences of DNA within the tumours, they were able to characterise 17 different types of chromosomal instability. These chromosomal instability signatures were able to predict how tumours might respond to drugs, as well as helping in the identification of future drug targets.

This research has led to the formation of Tailor Bio, a spin-out company from the Cancer Research UK Cambridge Institute, which aims to build a new pan-cancer precision medicine platform. This platform will allow the team to develop better drugs for a wide range of cancers and to group patients according to their cancer type more accurately, ensuring they get the best, most targeted treatment for their tumour.

Dr Markowetz, Senior Group Leader at the Cancer Research UK Cambridge Institute, said: “ ̽��ֱ��more complex the genetic changes that underlie a cancer, the more difficult they are to interpret and the more challenging it is to treat the tumour. This is tragically clear from the very low survival rates for cancers that arise as a result of chromosomal instability.

“Our discovery offers hope that we can turn things around, providing much more sophisticated and accurate treatments. With Tailor Bio, we are now working hard to bring our technology to patients and develop it to a level where it can transform patients’ lives.”

Reference

Drews, RM et al. A pan-cancer compendium of chromosomal instability. Nature; 15 Jun 2022; DOI: 10.1038/s41586-022-04789-9

Scientists have found a way to identify and interpret ‘signatures’ that reveal the complex genetic causes of some of the deadliest cancers – which often have a survival rate of less than 10%. ̽��ֱ��results, published today in Nature, could allow them to develop more accurate treatments and significantly improve survival rates.

̽��ֱ��more complex the genetic changes that underlie a cancer, the more difficult they are to interpret and the more challenging it is to treat the tumour

Florian Markowetz

PublicDomainPictures

DNA illustration

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Public Domain

Cambridge academics win European Research Council Advanced Grants

cg605 — Tue, 26 Apr 2022 11:14:19 +0000

Nine Cambridge academics have won Advanced Grants awarded by the European Research Council (ERC). This is the greatest number of grants won by a UK institution in the 2021 round of funding.

Artificial intelligence could be used to triage patients suspected at risk of early-stage oesophageal cancer

cjb250 — Thu, 15 Apr 2021 15:00:49 +0000

When researchers applied the technique to analysing samples obtained using the ‘pill on a string’ diagnostic tool Cytosponge, they found that it was capable of reducing by half pathologists’ workload while matching the accuracy of even experienced pathologists.

Early detection of cancer often leads to better survival because pre-malignant lesions and early stage tumours can be more effectively treated. This is particularly important for oesophageal cancer, the sixth most common cause for cancer-related deaths. Patients usually present at an advanced stage with swallowing difficulties and weight loss. ̽��ֱ��five-year overall survival can be as low as 13%.

One main subtype of oesophageal cancer is preceded by a condition known as Barrett oesophagus, in which cells in the lining of the oesophagus change shape. Barrett oesophagus occurs in patients with Gastro-oesophageal Reflux Disease (GORD), a digestive disorder where acid and bile from the stomach return into the oesophagus leading to heartburn symptoms. In Western countries, 10-15% of the adult population are affected by GORD and are hence at an increased risk of having Barrett oesophagus.

At present Barrett oesophagus can only be detected by a gastroscopy and tissue biopsy. Researchers at the ̽��ֱ�� of Cambridge have developed a far-less invasive diagnostic tool called the Cystosponge – a ‘pill on a string’ that dissolves in the stomach and which, as it is withdrawn, picks up some cells from the lining of the oesophagus. These cells are then stained using a laboratory marker called TFF3 and can then by examined under a microscope.

Now, in a study published today in Nature Medicine, a team at Cambridge has applied deep learning techniques to the sample analysis, stratifying patients into eight triage classes that determine whether a patient sample requires manual review or if automated review would suffice. ̽��ֱ��algorithms were trained using 4,662 pathology slides from 2,331 patients.

Professor Rebecca Fitzgerald from the MRC Cancer Unit at the ̽��ֱ�� of Cambridge, who developed the Cytosponge and worked with the AI team, said: “Any system that supports clinical decisions needs to balance its performance against workload reduction and potential economic impact. Replacing pathologists entirely could lead to substantial workload reduction and speed up diagnoses, but such an approach would only be viable if the performance remains comparable to that of human experts and there are regulatory hurdles to overcome.”

For the analysis of Cytosponge-TFF3 samples, the triaging approach showed several benefits, substantially reducing workload and matching the sensitivity and specificity of experienced pathologists. Sensitivity is the ‘true positive’ rate – that is, how often a test correctly generates a positive result for people who have Barrett oesophagus. Specificity, on the other hand, measures a test’s ability to correctly generate a negative result for people who don’t have the disease.

̽��ֱ��researchers showed that a fully manual review by a pathologist achieves 82% sensitivity and 93% specificity. In a fully automated approach, they observed a sensitivity of 73% and a specificity of 93%. ̽��ֱ��team was able to demonstrate that using a triage-driven approach, up to two-thirds of cases can be reviewed automatically while achieving a sensitivity of 83% and specificity of 93%. ̽��ֱ��team estimates that this approach would reduce workload for the pathologists by 57%.

̽��ֱ��team were able to build into their algorithm problem-solving techniques applied by pathologists familiar with Cytosponge-TFF3 samples. This meant that the algorithms were interpretable – in other words, a clinician would be able to understand why they had reached a particular decision. This is important for accountability.

Dr Florian Markowetz from the CRUK Cambridge Institute, who led the work on the AI algorithm, said: “We’ve shown that it’s possible to use computer-aided tools to streamline identification of people at risk of Barrett oesophagus. By semi-automating the process, we can reduce the workload by more than half while retaining the accuracy of a skilled pathologist. This could potentially speed up the diagnosis of Barrett oesophagus and, potentially, the identification of those individuals at greatest risk of oesophageal cancer.”

̽��ֱ��team say that this triage-driven approach could be applied beyond the Cytosponge to a number of tests for other conditions such as pancreatic cancer, thyroid cancer or salivary gland malignancies.

̽��ֱ��research was supported by Cancer Research UK, the Medical Research Council and Cambridge ̽��ֱ�� Hospitals NHS Foundation Trust.

Reference
Gehrung, M et al. Triage-driven diagnosis of Barrett esophagus for early detection of esophageal adenocarcinoma using deep learning. Nat Med; 15 Apr 2021; DOI: 10.1038/s41591-021-01287-9

Artificial intelligence ‘deep learning’ techniques can be used to triage suspected cases of Barrett oesophagus, a precursor to oesophageal cancer, potentially leading to faster and earlier diagnoses, say researchers at the ̽��ֱ�� of Cambridge.

We’ve shown that it’s possible to use computer-aided tools to streamline identification of people at risk of Barrett oesophagus... This could potentially speed up the diagnosis of Barrett oesophagus and, potentially, the identification of those individuals at greatest risk of oesophageal cancer

Florian Markowetz

Cytosponge

Yes