Imaging evaluation of a proposed 3D generative model for MRI to CT translation in the lumbar spine.

BACKGROUND CONTEXT: A computed tomography (CT) and magnetic resonance imaging (MRI) are used routinely in the radiologic evaluation and surgical planning of patients with lumbar spine pathology, with the modalities being complimentary. We have developed a deep learning algorithm which can produce 3D lumbar spine CT images from MRI data alone. This has the potential to reduce radiation to the patient as well as burden on the health care system. PURPOSE: The purpose of this study is to evaluate the accuracy of the synthetic lumbar spine CT images produced using our deep learning model. STUDY DESIGN: A training set of 400 unpaired CTs and 400 unpaired MRI scans of the lumbar spine was used to train a supervised 3D cycle-Gan model. Evaluators performed a set of clinically relevant measurements on 20 matched synthetic CTs and true CTs. These measurements were then compared to assess the accuracy of the synthetic CTs. PATIENT SAMPLE: The evaluation data set consisted of 20 patients who had CT and MRI scans performed within a 30-day period of each other. All patient data was deidentified. Notable exclusions included artefact from patient motion, metallic implants or any intervention performed in the 30 day intervening period. OUTCOME MEASURES: The outcome measured was the mean difference in measurements performed by the group of evaluators between real CT and synthetic CTs in terms of absolute and relative error. METHODS: Data from the 20 MRI scans was supplied to our deep learning model which produced 20 "synthetic CT" scans. This formed the evaluation data set. Four clinical evaluators consisting of neurosurgeons and radiologists performed a set of 24 clinically relevant measurements on matched synthetic CT and true CTs in 20 patients. A test set of measurements were performed prior to commencing data collection to identify any significant interobserver variation in measurement technique. RESULTS: The measurements performed in the sagittal plane were all within 10% relative error with the majority within 5% relative error. The pedicle measurements performed in the axial plane were considerably less accurate with a relative error of up to 34%. CONCLUSIONS: The computer generated synthetic CTs demonstrated a high level of accuracy for the measurements performed in-plane to the original MRIs used for synthesis. The measurements performed on the axial reconstructed images were less accurate, attributable to the images being synthesized from nonvolumetric routine sagittal T1-weighted MRI sequences. It is hypothesized that if axial sequences or volumetric data were input into the algorithm these measurements would have improved accuracy.

Modular structures and the delivery of inpatient care in hospitals: a Network Science perspective on healthcare function and dysfunction.

BACKGROUND: Reinforced by the COVID-19 pandemic, the capacity of health systems to cope with increasing healthcare demands has been an abiding concern of both governments and the public. Health systems are made up from non-identical human and physical components interacting in diverse ways in varying locations. It is challenging to represent the function and dysfunction of such systems in a scientific manner. We describe a Network Science approach to that dilemma. General hospitals with large emergency caseloads are the resource intensive components of health systems. We propose that the care-delivery services in such entities are modular, and that their structure and function can be usefully analysed by contemporary Network Science. We explore that possibility in a study of Australian hospitals during 2019 and 2020. METHODS: We accessed monthly snapshots of whole of hospital administrative patient level data in two general hospitals during 2019 and 2020. We represented the organisations inpatient services as network graphs and explored their graph structural characteristics using the Louvain algorithm and other methods. We related graph topological features to aspects of observable function and dysfunction in the delivery of care. RESULTS: We constructed a series of whole of institution bipartite hospital graphs with clinical unit and labelled wards as nodes, and patients treated by units in particular wards as edges. Examples of the graphs are provided. Algorithmic identification of community structures confirmed the modular structure of the graphs. Their functional implications were readily identified by domain experts. Topological graph features could be related to functional and dysfunctional issues such as COVID-19 related service changes and levels of hospital congestion. DISCUSSION AND CONCLUSIONS: Contemporary Network Science is one of the fastest growing areas of current scientific and technical advance. Network Science confirms the modular nature of healthcare service structures. It holds considerable promise for understanding function and dysfunction in healthcare systems, and for reconceptualising issues such as hospital capacity in new and interesting ways.

Segmentation of cervical nuclei using SLIC and pairwise regional contrast.

A framework to detect and segment nuclei from cervical cytology images is proposed in this study. Poor contrast, spurious edges, degree of overlap, and intensity inhomogeneity make the nuclei segmentation task more complex in overlapping cell images. The proposed technique segments cervical nuclei by merging over-segmented SLIC superpixel regions using a novel region merging criteria based on pairwise regional contrast and image gradient contour evaluations. The framework was evaluated using the first overlapping cervical cytology image segmentation challenge - ISBI 2014 dataset. The result shows that the proposed framework outperforms the state-of-the-art algorithms in nucleus detection and segmentation accuracies.

Circular shape constrained fuzzy clustering (CiscFC) for nucleus segmentation in Pap smear images.

Accurate detection and segmentation of cell nucleus is the precursor step towards computer aided analysis of Pap smear images. This is a challenging and complex task due to degree of overlap, inconsistent staining and poor contrast. In this paper, a novel nucleus segmentation method is proposed by incorporating a circular shape function in fuzzy clustering. The proposed method was evaluated quantitatively and qualitatively using the Overlapping Cervical Cytology Image Segmentation Challenge - ISBI 2014 challenge dataset comprised of 945 overlapping Pap smear images. It achieved superior performance in terms of Dice similarity coefficient of 0.938, pixel-based recall 0.939 and object based precision 0.968. The results were compared with the standard fuzzy c-means (FCM) clustering, ISBI 2014 challenge submissions and recent state-of-the-art methods. The outcome shows that the new approach can produce more accurate nucleus boundaries while keeping high level of precision and recall.