Cardiac sphericity a possible early marker for cardiomyopathy and related adverse outcomes

6th April 2023

The presence of cardiac sphericity in normal hearts serves as a marker for predicting the risk of cardiomyopathy and related adverse outcomes

In a study using deep learning-enabled image segmentation of cardiac magnetic resonance imaging data, US researchers identified how variation in the left ventricle (LV) sphericity index in otherwise normal hearts, predicts the risk for cardiomyopathy and related outcomes such as atrial fibrillation.

Dilation of cardiac chambers and or a decline in systolic function are key indicators of disease and which can be assessed using conventional imaging modalities to quantify such changes. Moreover, deep neural networks have shown a great potential in image pattern recognition and automated methods achieve a performance on par with human experts in analysing cardiovascular magnetic resonance images and deriving clinically relevant measures. Cardiomyopathies of different aetiologies can often result in a similar end-stage phenotype of a more round, spherical ventricle. In fact, in patients with cardiac diseases, a greater sphericity of the left ventricle, has, for example, been shown to be an independent predictor of 10-year survival following an acute myocardial infarction. In the current study, researchers thought that even among those with normal heart function, there was likely to be variation in cardiac sphericity, in particular, sphericity of the left ventricle and that this may serve as marker of cardiac risk, especially among those with an underlying genetic risk.

Using automated deep-learning segmentation of cardiac magnetic resonance imaging (MRI) data, the researchers estimated and analysed the sphericity index in patients who were part of the UK Biobank database but excluded those with either abnormal left ventricular size or systolic function.

Cardiac sphericity and risk of cardiomyopathy

In a total of 38,897 participants, the researchers calculated that for one standard deviation increase in the sphericity index, or roundness of the heart, there was an associated 47% increased incidence of cardiomyopathy (hazard ratio, HR = 1.47, 95% CI 1.10 – 1.98, p = 0.01). In addition, the same increase in the sphericity index, was associated with a 20% increased incidence of atrial fibrillation (HR = 1.20, 95% CI 1.11 – 1.28, p < 0.001) and which was independent of clinical factors and traditional magnetic resonance imaging (MRI) measurements. In contrast, similar increases in the sphericity index were non-significantly associated with the risk of both heart failure (p = 0.3) and cardiac arrest (p = 0.70).

The team also identified four loci associated with sphericity at genome-wide significance and concluded that the variation in left ventricular sphericity in otherwise normal hearts, predicts the risk for cardiomyopathy and related outcomes and is caused by non-ischaemic cardiomyopathy.

Citation
Vukadinovic M et al. Deep learning-enabled analysis of medical images identifies cardiac sphericity as an early marker of cardiomyopathy and related outcomes. Med 2023

Deep learning algorithm outperforms radiologists in detecting head and neck cancer spread

31st October 2022

A deep learning algorithm predicted pathologic extranodal extension in patients with head and neck cancer more successfully than radiologists

A deep learning algorithm (DLA) has been found able to better predict pathologic microscopic and macroscopic extranodal extension (ENE), indicative of cancer spread, than radiologists according to the findings of a study presented at the World Cancer Congress, 2022.

Worldwide, head and neck cancers account for approximately 900,000 cases and over 400,000 deaths annually. Typically, treatment strategies consist of radiation with or without chemotherapy or upfront surgery followed by adjuvant radiation with chemotherapy. ENE, and which is also referred to extracapsular extension or extracapsular spread, occurs when metastatic tumour cells within the lymph node break through the nodal capsule into surrounding tissues. Moreover, in locally advanced head and neck cancer, extracapsular spread of the tumour from neck nodes is a significant prognostic factor associated with a poor outcome. A further problem is that ENE can only be reliably diagnosed from postoperative pathology and if present, warrants adjuvant treatment intensification with the addition of chemotherapy to radiation therapy. The presence of ENE can be determined from CT scans although the method is not very accurate. Nevertheless, in a previous study, the same researchers developed a deep learning algorithm that enabled the prediction of ENE with an area under the receiver operating characteristic curve (AUC) of 0.91, prompting the authors to conclude that such a model has the potential for use as a clinical decision-making tool to help guide head and neck cancer patient management.

But could this same deep learning-based model be generalisable to more high-risk patients, was the question addressed in the present study. The team turned to data collected as part of the E3311 trial, which was a phase II randomised trial of reduced- or standard-dose postoperative radiotherapy for high-risk patients with resected stage III-IVa, human papillomavirus associated (HPV+), oropharynx cancer (OPC). Using pre-treatment CT scan information and corresponding surgical pathology reports from E3311 patients, researchers designated patients as being at high-risk if there was ≥1 mm ENE and such individuals were assigned to chemotherapy and high-dose radiation following transoral surgery. The predictive ability of the model was assessed using the area under the curve (AUC) and four head and neck radiologists were used for comparative purposes.

Deep learning algorithm and prediction of ENE

From a total of 177 scans, 311 lymph nodes were annotated and of which, 23% had ENE and 13% had ENE >1 mm.

The deep learning algorithm accurately classified 85% (95% CI 80 – 89%) of the nodes as having ENE whereas the highest AUC for a radiologist was 70% (64 – 76%). The model was also better than all four radiologists for the detection of ENE >1 mm (model AUC = 85% vs a mean of 68% for the radiologists, p < 0.001).

The authors concluded that their model showed a high performance for predicting pathologic microscopic and macroscopic ENE in a cohort of patients with HPV-OPC from a prospective clinical trial, substantially outperforming expert head and neck radiologists. They added that the model should be evaluated in a clinical trial with the goal of reducing tri-modality (i.e., surgery, radiation, or chemotherapy) therapy.

Citation
Kann BH et al. Screening for Extranodal Extension with Deep Learning: Evaluation in ECOG-ACRIN E3311, a Randomized De-Escalation Trial for HPV-Associated Oropharyngeal Carcinoma. No 141. World Cancer Congress, 2022