Deep learning tool outperforms current brain tumour diagnosis and classification methods

25th March 2024

A deep learning-based diagnostic tool can accurately distinguish between three of the most common brain tumours, outperforming conventional techniques, Spanish researchers report.

Glioblastoma multiforme, brain metastasis from solid tumours and primary central nervous system lymphoma accounted for up to 70% of all brain malignancies, the researchers wrote in the journal Cell Reports Medicine.

Each type of tumour required a distinct therapeutic approach, but on imaging they appeared similar, making it difficult to distinguish each type.

Corresponding study author Dr Raquel Perez-Lopez, head of Vall d’Hebron Insitute of Oncology’s (VHIO) Radiomics Group, said magnetic resonance imaging (MRI) was currently used for non-invasive differential diagnosis.

‘However, a definitive diagnosis often requires neurosurgical interventions that compromise the quality of life of patients,’ she said.

To overcome these challenges, researchers from VHIO Radiomics Group and the Neuro-Radiology Unit at Bellvitge University Hospital, developed a deep learning-based tool, leveraging spatial and temporal information from dynamic susceptibility contrast (DSC) perfusion MRI to assist in classifying brain tumours.

‘In DSC, every voxel in the image yields a unique dynamic curve that describes the temporal evolution of the T2^∗-weighted signal intensity and reflects local tissue vascular properties,’ the researchers wrote.

‘The standard approach to analyse DSC is to derive metrics such as the relative cerebral blood volume (rCBV) and the percentage of signal recovery (PSR) which both simplify the dynamic signal.’

The tool, known as Diagnosis in Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), was trained to recognise characteristics of these common brain tumours using approximately 50,000 voxels from the DSC perfusion MRI images of 40 histology-confirmed patients.

It was then tested on 400 additional cases, plus an external validation cohort of 128 patients, with the researchers reporting it reached a three-way accuracy of 0.78, superior to the conventional MRI metrics of rCBV and PSR.

The tool required approximately two minutes to process a new case, the researchers said, and achieved optimal performance through training with a limited number of scans from somewhere in the order of 30 to 40 cases.

‘These data underscore the potential of DISCERN for differentiating among the three most common clinical diagnostic challenges in patients with enhancing brain lesions,’ they concluded.

Study co-author Dr Albert Pons-Escoda, a clinical neuroradiologist at Bellvitge University Hospital in Barcelona, said the work was the result of more than five years of research focused on identifying innovative magnetic resonance perfusion imaging biomarkers for differential diagnosis of brain tumors.

‘This present study integrates insights generated by other previous research projects on artificial intelligence, resulting in the development of software that automates presurgical diagnostic classification with very good precision, while facilitating its clinical applicability with a user-friendly interface for clinicians,’ he said.

AI models are increasingly being used for a range of healthcare applications. Deep learning has recently enabled scientists to accurately predict four subtypes of Parkinson’s disease based on images of patient-derived stem cells.

In a systemic review and meta-analysis published last year, Canadian researchers found that the performance of an AI model for the diagnosis of hip fractures was comparable with that of expert radiologists and surgeons.

And in research presented at the European Academy of Dermatology and Venereology Congress 2023, showed that the use of artificial intelligence software had a 100% detection rate for melanoma and saved over 1,000 face-to-face secondary care consultations during a 10-month period.

Apremilast benefits in psoriatic arthritis revealed by magnetic resonance imaging

15th June 2023

The impact of apremilast on inflammatory and structural changes in psoriatic arthritis (PsA) can be better understood through magnetic resonance imaging (MRI), according to a recent study presented at the European Congress of Rheumatology (EULAR) 2023.

The data came from the MOSAIC phase 4, multicentre, single-arm, open-label study, in which the researchers used MRI to examine the effect of the oral immunomodulating phosphodiesterase-4 inhibitor apremilast on inflammation in patients with active PsA.

MOSAIC was the first trial to use MRI to assess inflammation in peripheral joints and entheses instead of traditional X-ray methods. Participants received oral apremilast 30 mg daily, either as monotherapy or in combination with stable methotrexate. Treatment continued for 48 weeks and individuals had an MRI scan of the hand performed at baseline and at Weeks 24 and 48.

Researchers set the primary endpoint as the change from baseline in the composite score of hand bone marrow oedema, synovitis and tenosynovitis in fingers two to five, assessed by the PsA MRI Score (PsAMRIS) at Week 24, and for which a negative change reflects disease improvements.

In addition, a total inflammation score, which comprised of bone marrow oedema, synovitis, tenosynovitis and periarticular inflammation in fingers, was also assessed. The team also considered disease activity with the clinical disease activity index for psoriatic arthritis (cDAPSA), which is lowered as disease activity reduces.

Apremilast and inflammatory changes

MOSAIC enrolled 122 patients who received apremilast. The mean age was 47 years (55% women) and the mean duration of PsA was 1.9 years. Some 98 patients provided evaluable data for the primary endpoint.

The least-squares mean change from baseline in the composite inflammation score of bone marrow oedema, synovitis, and tenosynovitis assessed by PsAMRIS was -2.32 at Week 24 and -2.91 at Week 48.

Significant improvements from baseline were also seen in total inflammation scores for those taking apremilast, together with a reduction in cDAPSA score. In addition, no significant structural progression was observed.

The researchers suggested their findings highlighted the value of using MRI and PsAMRIS as measures of disease activity change following PsA treatments.