Machine learning in whole-body MRI: experiences and challenges from an applied study using multicentre data.

Machine learning is now being increasingly employed in radiology to assist with tasks such as automatic lesion detection, segmentation, and characterisation. We are currently involved in an National Institute of Health Research (NIHR)-funded project, which aims to develop machine learning methods to improve the diagnostic performance and reduce the radiology reading time of whole-body magnetic resonance imaging (MRI) scans, in patients being staged for cancer (MALIBO study). We describe here the main challenges we have encountered during the course of this project. Data quality and uniformity are the two most important data traits to be considered in clinical trials incorporating machine learning. Robust data pre-processing and machine learning pipelines have been employed in MALIBO, a task facilitated by the now freely available machine learning libraries and toolboxes. Another important consideration for achieving the desired clinical outcome in MALIBO, was to effectively host the resulting machine learning output, along with the clinical images, for reading in a clinical environment. Finally, a range of legal, ethical, and clinical acceptance issues should be considered when attempting to incorporate computer-assisting tools into clinical practice. The road from translating computational methods into potentially useful clinical tools involves an analytical, stepwise adaptation approach, as well as engagement of a multidisciplinary team.

Clinical translation of [18F]ICMT-11 for measuring chemotherapy-induced caspase 3/7 activation in breast and lung cancer.

BACKGROUND: Effective anticancer therapy is thought to involve induction of tumour cell death through apoptosis and/or necrosis. [18F]ICMT-11, an isatin sulfonamide caspase-3/7-specific radiotracer, has been developed for PET imaging and shown to have favourable dosimetry, safety, and biodistribution. We report the translation of [18F]ICMT-11 PET to measure chemotherapy-induced caspase-3/7 activation in breast and lung cancer patients receiving first-line therapy. RESULTS: Breast tumour SUVmax of [18F]ICMT-11 was low at baseline and unchanged following therapy. Measurement of M30/M60 cytokeratin-18 cleavage products showed that therapy was predominantly not apoptosis in nature. While increases in caspase-3 staining on breast histology were seen, post-treatment caspase-3 positivity values were only approximately 1%; this low level of caspase-3 could have limited sensitive detection by [18F]ICMT-11-PET. Fourteen out of 15 breast cancer patients responded to first-line chemotherapy (complete or partial response); one patient had stable disease. Four patients showed increases in regions of high tumour [18F]ICMT-11 intensity on voxel-wise analysis of tumour data (classed as PADS); response was not exclusive to patients with this phenotype. In patients with lung cancer, multi-parametric [18F]ICMT-11 PET and MRI (diffusion-weighted- and dynamic contrast enhanced-MRI) showed that PET changes were concordant with cell death in the absence of significant perfusion changes. CONCLUSION: This study highlights the potential use of [18F]ICMT-11 PET as a promising candidate for non-invasive imaging of caspase3/7 activation, and the difficulties encountered in assessing early-treatment responses. We summarize that tumour response could occur in the absence of predominant chemotherapy-induced caspase-3/7 activation measured non-invasively across entire tumour lesions in patients with breast and lung cancer.

Histogram analysis of apparent diffusion coefficient from whole-body diffusion-weighted MRI to predict early response to chemotherapy in patients with metastatic colorectal cancer: preliminary results.

AIM: To evaluate apparent diffusion coefficient (ADC) histogram analysis parameters, acquired from whole-body diffusion-weighted magnetic resonance imaging (DW-MRI), as very early predictors of response to chemotherapy in patients with metastatic colorectal cancer (mCRC). MATERIALS AND METHODS: This was a single-institution prospective study, approved by the West Midlands-South Birmingham research ethics committee. All patients gave fully informed consent prior to imaging. Sixteen patients with histologically confirmed mCRC were enrolled to the study and 11 were successfully scanned with whole-body DW-MRI before (baseline) and 10.8±2.7 days after commencing chemotherapy (follow-up). Therapy response was assessed by RECIST 1.1. Mean ADC and histogram parameters (skewness, kurtosis, 25th, 50th, and 75th percentiles) were compared between progressors and non-progressors at baseline and follow-up. Receiver operating characteristics (ROC) analysis was performed for the statistically significant parameters. Data from metastases were also compared to normative tissue data acquired from healthy volunteers. RESULTS: Three patients had progressive disease (progressors) and eight had partial response/stable disease (non-progressors). Mean, 25th, 50th, and 75th percentiles were significantly lower for progressors at baseline (p=0.012, 0.012, 0.012 and 0.025 respectively) with areas under the ROC curves (AUC)=0.58, 0.50, 0.58 and 0.63, respectively. Skewness and kurtosis were significantly lower for non-progressors at follow-up (p=0.001 and 0.003 respectively) with AUC=0.67 and 0.79 respectively. CONCLUSION: ADC histogram analysis shows potential in discriminating progressive from non-progressive disease in patients with mCRC, who underwent whole-body DW-MRI. The technique can potentially be tested as a response assessment methodology in larger trials.

Towards an MMP-2-activated molecular agent for cancer imaging.

Matrix metalloproteinases (MMPs) have been identified as biomarkers for cancer, offering prognostic potential; however, non-invasive detection protocols are currently lacking. Herein, we describe the synthesis of a DOTA-containing peptide sequence that can be radiolabelled easily with 68Gallium or can be incorporated with gadolinium for possible MRI applications with clear selectivity for MMP-2 over other members of the MMP family, giving MMP-2 selective cleavage of the labelled peptides.