VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images.

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.

Different administration routes of recombinant human endostatin combined with concurrent chemoradiotherapy might lead to different efficacy and safety profile in unresectable stage III non-small cell lung cancer: Updated follow-up results from two phase II trials.

BACKGROUND: There are two main choices of administration route of recombinant human endostatin (Endostar) available and the treatment options of concurrent chemoradiotherapy (CCRT) have changed over time. The aim of this study was to observe the long-term efficacy and safety of different administration routes of Endostar combined with CCRT. METHODS: Patients with unresectable stage III non-small cell lung cancer (NSCLC) from two phase II trials were included as two cohorts. Both were treated with Endostar combined with CCRT. Endostar was administrated by intravenous injection (7.5 mg/m2 /day, seven days) in the IV arm and by continuous intravenous pumping (7.5 mg/m2 /24 hours, 120 hours) in the CIV arm. RESULTS: A total of 48 patients were included in the IV arm and 67 patients in the CIV arm. The median progression-free survival (PFS), overall survival (OS), local recurrence-free survival (LRFS) and distant metastasis-free survival (DMFS) in the IV arm and CIV arm were 9.9 months versus 15.4 months (HR = 0.751, 95% CI 0.487-1.160, P = 0.200), 24.0 months versus 38.5 months (HR = 0.746, 95% CI 0.473-1.178, P = 0.209), 32.3 months versus 27.1 months (HR = 1.193, 95% CI 0.673-2.115, P = 0.546), 20.1 months versus 49.7 months (HR = 0.603, 95% CI 0.351-1.036, P = 0.067). The one, three, five-year PFS in the IV arm and CIV arm was 45.8% versus 52.9%, 18.3% versus 31.4%, and 18.3% versus 27.7% and the one, three, five-year OS was 81.2% versus 82.1%, 31.1% versus 50.3%, and 31.1% versus 41%, respectively. Incidence of hematological adverse reactions were numerically lower in the CIV arm than the IV arm. CONCLUSIONS: Endostar delivered by CIV with CCRT may be a better option than IV in terms of potential survival and safety for unresectable stage III NSCLC. KEY POINTS: Significant findings of the study Endostar delivered by continuous intravenous pumping might achieve more favorable survival over intravenous injection and reduce adverse hematological reactions in patients with unresectable stage III NSCLC treated with Endostar combined with CCRT.What this study adds The administration route of recombinant human endostatin is also one key factor for survival and safety to consider when treating patients with unresectable stage III NSCLC.