leukaemia

Leukaemia: AI provides support in diagnostics

Posted by

0


AI-based processing of bone-marrow smears to support leukaemia diagnosis. Using...

AI-based processing of bone-marrow smears to support leukaemia diagnosis. Using so-called unsupervised learning methods, single-cell images are extracted from extremely high-resolution image data. Then, using neural networks, these cell images are examined to check for any visual anomalies which might have a genetic origin. Areas which are important for the decision of the neural network are highlighted in colour by using so-called “explainable AI” strategies.

IT specialists and physicians develop new method for recognising genetic aberrations

Decisions on treatment for patients with acute myeloid leukemia (AML) – a highly aggressive form of leukemia – are based, among other things, on a series of certain genetic features of the disease; but at the time when a diagnosis is made, this information is not available. However, evidence of these genetic anomalies is crucial in providing targeted treatment for patients at an early stage. As genetic testing is expensive and time-consuming, there is a great need for inexpensive, fast and broadly accessible tests to predict such anomalies. A team of IT specialists and physicians at the University of Münster and the University Hospital Münster has now published a study showing how a method based on artificial intelligence (AI) can be used to predict various genetic features on the basis of high-resolution microscopic images of bone marrow smears. As a result, decisions on a more precise treatment can be made in future directly on the day of the diagnosis, without the need to wait for genetic analyses. The results have been published in the journal “Blood Advances”.

Interestingly, several patterns recognized by the algorithm can not be identified by human observers. This is for example because the patterns may be too faint or because extremely fine textures are involved which remain hidden to the human eyeBenjamin Risse

In this new method, the genetic aberrations were extracted directly from extremely high-resolution multi-gigabyte scans from whole bone marrow smears taken from more than 400 AML patients. The scans had a resolution of 270,000 times 135,000 pixels on average, with one image being several gigabytes in size. Proceeding from this enormous dataset, it was possible to extract more than two million single-cell images. “We developed a new type of Deep Learning method, fully automatic, which was trained for a complex task by means of machine learning technology,” explains Prof. Benjamin Risse, who headed the work on algorithmic developments on the IT side. “In our case, the basic algorithm can automatically recognise the genetic features and the very fine patterns in big cytological images. The method then filtered the single-cell images into categories of different cell types, and it also showed any genetic aberrations. Interestingly, several patterns recognized by the algorithm can not be identified by human observers. This is for example because the patterns may be too faint or because extremely fine textures are involved which remain hidden to the human eye, despite excellent imaging,” says Risse. 

One key advantage of the method presented is in the end-to-end AI pipeline which enables monitoring of the (interim) results and reduces to a minimum the manual preliminary work often necessary for machine learning. This is made possible by a combination of so-called unsupervised, self-supervised and supervised learning processes. The first two processes require no manual data selection at all but try to extract relevant content automatically from the image data instead. “Using a so-called incremental approach, we carried out intermediary steps with a human expert to examine the images. This is necessary for example in cell images categorised as problematic,” says Dr. Linus Angenendt, who heads the Personalised Cancer Therapy and Digital Medicine working group at Münster University Hospital. Problematic cell images can occur as a result of incorrect staining, for example. The model trained was subsequently evaluated on an independent dataset relating to a further 70 patients with over 440,000 single-cell images – as a test cohort. 

Although the new method cannot replace genetic analyses, it nevertheless helps at a very early stage in the diagnostic clarification process for a leukaemia patient, by providing an idea of which genetic aberrations might underlie the disease. This would be especially helpful in the case of aggressive diseases when there is no time to wait for the complete genetic analyses. 

The researchers are confident that in future digital methods and artificial intelligence will become increasingly important for large medical datasets when it is a question of making personalised recommendations for treatment for patients with malignant diseases. This study contributes an important basis for this, for example in the development of similar approaches for other bone marrow diseases.

Mixed-race US woman becomes first to be cured of HIV using new cord blood treatment

Posted by

0


a coral in the dark

 A leukaemia patient in the US has become the first woman and the third person ever to be cured of HIV, after receiving a transplant of umbilical cord blood in a novel treatment technique, a New York Times report said Tuesday.

The previous two male patients who had been cured received expensive bone marrow transplants. Both kinds of transplants have stem cells with a mutation that blocks HIV.

The latest case was presented this week at the Conference on Retroviruses and Opportunistic Infections in Denver, Colorado.

The results show great promise in facilitating more accessible HIV treatments, especially for those who are already suffering from cancer. Cord blood is much more widely available than adult stem cells that are used in bone marrow transplants.

The middle-age woman is of mixed race and received a partial match, unlike the previous bone marrow transplants where a closer racial match is required and donors are primarily Caucasian.

Earlier, two other women had naturally cured themselves of HIV by locking away the virus in their genome in what is a ‘sterilising cure’, where the body eliminates the virus completely.

Cord blood treatment

The US mixed-race patient had been diagnosed with HIV in 2013 and had been on antiretroviral drugs. In March 2017, she was diagnosed with acute myelogenous leukaemia, and in August the same year, received the mutation-containing cord blood transplant.

She has not shown any signs of relapse since October 2020, when she received the transplant.

During and after the transplant, she also received blood for a close relative for temporary immunity, as cord blood cells can take up to six weeks to engraft. She was discharged 17 days after her transplant, and didn’t develop graft vs host disease, which was previously thought to be a step that contributed to the cure of HIV after bone marrow transplants.

Antiretroviral therapy, which typically is a drug cocktail that prevents replication and keeps viral levels low, was discontinued 37 months after the transplant, and 14 months since then, she continues to be in remission. Blood tests show no signs of both HIV and antibodies to HIV.

While the blood from her relative formed a crucial aid in keeping the immune system running until the cord blood cells took over, it is still unclear why cord cells were so effective.

However, the therapy itself is highly risky and only suitable for patients with cancer, as it destroys a large portion of the immune system using chemotherapy or radiation. 

Previous cures

In 2008, Timothy Ray Brown from California, who came to be known as the ‘Berlin Patient’, was the first to be cured of AIDS. His identity was revealed in 2010, and he died in 2020 from leukaemia.

Adam Castillejo, who was known as the ‘London Patient’, was the second to be cured, in 2019. 

Both men had painful and expensive bone marrow transplants from donors with a rare genetic mutation that is resistant to HIV. They were also on antiretroviral therapy.

Another patient, a 36-year-old man in Brazil, dubbed the Sao Paulo Patient, was temporarily able to remove the virus from his body using a drug cocktail and without surgery two years ago, but the virus rebounded with a detectable viral load 72 weeks or 15 months after he went off antiretroviral therapy.

Two women have been shown to be able to remove the disease naturally from their bodies. 

In 2020, scientists announced that 66-year old Loreen Willenberg from California was able to get rid of the disease by locking the virus away inside her genome, where it would typically replicate. Her body’s defensive action was described by researchers as a “functional cure”. She had been diagnosed with HIV in 1992.

Last year, a woman from Argentina, called the Esperanza patient, was also able to naturally remove the virus from her body completely in a “sterilising cure”. She had been diagnosed in 2013 and is now disease free. 

Such individuals whose bodies are able to suppress and lock away the virus, or eliminate it, are called elite controllers. It is thought that about 0.5 per cent of the 38 million HIV patients around the world make up elite controllers.

Young children have also been known to stay in remission when antiretroviral therapy is started at a very early age after birth.

New treatment uses altered blood cells to attack leukaemia

Posted by

0


Scientists have figured out how to reprogram the blood of cancer patients to attack their leukaemia, and 19 of the 30 patients who received the treatment remain in complete remission.

blood-transfusion

A team of researchers led by immunotherapist Carl June from the University of Pennsylvania in the US has announced the results of a new treatment for leukaemia patients that turns their own blood cells against their disease.

The researchers chose to work with patients who were dealing with particularly aggressive cases of leukaemia. All of the participants in the study had cancers that had returned at least four times before.

According to Elizabeth Lopatto at the Verge, the treatment works by first having a patient’s T cells – a type of white blood cell that plays a crucial role in the body’s immune response – harvested through a blood transfusion process. These T cells are then engineered to seek out a particular protein called a B cell receptor, found on the surface of the patient’s B cells. B cells are another type of white blood cell that’s specifically targeted by leukaemia.

The patient’s altered T cells will then be transplanted back into their blood stream so they can start hunting B cell receptor proteins, and kill the leukaemia and the B cells they’re attached to.

Of course, this means that the patient’s entire supply of B cells will be wiped out by this treatment. Because the main role of B cells is to produce antibodies to fight anything that might threaten our bodies, including viruses and bacteria, the patients will be left extremely vulnerable until they can generate more. This is something that hospitals will need to be aware of if the treatment ends up being used more widely, but the benefit of this treatment is that it only has to be administered once for it to work.

According to the study, which was published in the New England Journal of Medicine, of the 30 children and adults that received the treatment, complete remission was achieved in 27 patients (90 percent). Remission was sustained past the six-month point in 19 of the 30 patients. One of the early success stories is a nine-year-old girl called Emily Whitehead, who started the treatment when she was six. She’s been cancer-free now for two years.

“This is unlike almost all cell and gene therapies in that it’s actually ahead of the schedule we set for ourselves when we first started treating patients,” June told Lopatto at the Verge. “We pinch ourselves because, you know, until recently we didn’t know if we got lucky or if it would last. Our initial patients are still in remission, so we know it’s durable and reproducible. That’s something that makes us excited every day.”

The team is now working on easing the side effects of the treatment, which include fever, nausea, muscle pain and difficulty breathing.