Test Platform for Developing New Optical Position Tracking Technology towards Improved Head Motion Correction in Magnetic Resonance Imaging.

Optical tracking of head pose via fiducial markers has been proven to enable effective correction of motion artifacts in the brain during magnetic resonance imaging but remains difficult to implement in the clinic due to lengthy calibration and set up times. Advances in deep learning for markerless head pose estimation have yet to be applied to this problem because of the sub-millimetre spatial resolution required for motion correction. In the present work, two optical tracking systems are described for the development and training of a neural network: one marker-based system (a testing platform for measuring ground truth head pose) with high tracking fidelity to act as the training labels, and one markerless deep-learning-based system using images of the markerless head as input to the network. The markerless system has the potential to overcome issues of marker occlusion, insufficient rigid attachment of the marker, lengthy calibration times, and unequal performance across degrees of freedom (DOF), all of which hamper the adoption of marker-based solutions in the clinic. Detail is provided on the development of a custom moiré-enhanced fiducial marker for use as ground truth and on the calibration procedure for both optical tracking systems. Additionally, the development of a synthetic head pose dataset is described for the proof of concept and initial pre-training of a simple convolutional neural network. Results indicate that the ground truth system has been sufficiently calibrated and can track head pose with an error of <1 mm and <1°. Tracking data of a healthy, adult participant are shown. Pre-training results show that the average root-mean-squared error across the 6 DOF is 0.13 and 0.36 (mm or degrees) on a head model included and excluded from the training dataset, respectively. Overall, this work indicates excellent feasibility of the deep-learning-based approach and will enable future work in training and testing on a real dataset in the MRI environment.

Temporal and spatial progression of microstructural cerebral degeneration in ALS: A multicentre longitudinal diffusion tensor imaging study.

OBJECTIVE: The corticospinal tract (CST) reveals progressive microstructural alterations in ALS measurable by DTI. The aim of this study was to evaluate fractional anisotropy (FA) along the CST as a longitudinal marker of disease progression in ALS. METHODS: The study cohort consisted of 114 patients with ALS and 110 healthy controls from the second prospective, longitudinal, multicentre study of the Canadian ALS Neuroimaging Consortium (CALSNIC-2). DTI and clinical data from a harmonized protocol across 7 centres were collected. Thirty-nine ALS patients and 61 controls completed baseline and two follow-up visits and were included for longitudinal analyses. Whole brain-based spatial statistics and hypothesis-guided tract-of-interest analyses were performed for cross-sectional and longitudinal analyses. RESULTS: FA was reduced at baseline and longitudinally in the CST, mid-corpus callosum (CC), frontal lobe, and other ALS-related tracts, with alterations most evident in the CST and mid-CC. CST and pontine FA correlated with functional impairment (ALSFRS-R), upper motor neuron function, and clinical disease progression rate. Reduction in FA was largely located in the upper CST; however, the longitudinal decline was greatest in the lower CST. Effect sizes were dependent on region, resulting in study group sizes between 17 and 31 per group over a 9-month interval. Cross-sectional effect sizes were maximal in the upper CST; whereas, longitudinal effect sizes were maximal in mid-callosal tracts. CONCLUSIONS: Progressive microstructural alterations in ALS are most prominent in the CST and CC. DTI can provide a biomarker of cerebral degeneration in ALS, with longitudinal changes in white matter demonstrable over a reasonable observation period, with a feasible number of participants, and within a multicentre framework.

Intracapsular neck of femur fractures secondary to civilian gunshot injuries: an inter- and intra-observer agreement study on classification and treatment using the AO/OTA classification.

PURPOSE: Numerous classification systems have been developed for neck of femur fractures, but none have been tested for reliability in gunshot injuries. Our primary objective was to assess the inter-observer and intra-observer reliability of the AO/OTA classification system when applied to intracapsular neck of femur fractures secondary to low-velocity civilian gunshots wounds (GSWs). Our secondary objective was to test the reliability of the AO/OTA classification system in guiding surgeon treatment choices for these fractures. PATIENTS AND METHODS: Eighteen reviewers (six orthopaedic traumatologists, six general orthopaedic surgeons and six junior orthopaedic fellows) were given a set of 25 plain radiographs and CT scans of femur neck fractures secondary to GSW. For each clinical case, all reviewers selected a classification as well as treatment option from a list of given options. Inter-observer reliability was measured at the initial classification. The exercise was repeated 10-12 weeks later by the same 18 reviewers to test intra-observer reliability. RESULTS: The Fleiss kappa values indicate only slight agreement amongst raters, across all experience levels, for both injury classification and treatment. Intra-observer agreement was fair across all experience levels for both injury classification and treatment. CONCLUSION: The AO/OTA classification showed only slight reliability in classification of gunshot fractures of the femur neck. With only fair reliability, it also failed to guide surgical treatment thus rendering its routine use in daily clinical practice of questionable value.

History of traumatic brain injury is associated with increased grey-matter loss in patients with mild cognitive impairment.

OBJECTIVES: To investigate whether a history of traumatic brain injury (TBI) is associated with greater long-term grey-matter loss in patients with mild cognitive impairment (MCI). METHODS: 85 patients with MCI were identified, including 26 with a previous history of traumatic brain injury (MCI[TBI-]) and 59 without (MCI[TBI+]). Cortical thickness was evaluated by segmenting T1-weighted MRI scans acquired longitudinally over a 2-year period. Bayesian multilevel modelling was used to evaluate group differences in baseline cortical thickness and longitudinal change, as well as group differences in neuropsychological measures of executive function. RESULTS: At baseline, the MCI[TBI+] group had less grey matter within right entorhinal, left medial orbitofrontal and inferior temporal cortex areas bilaterally. Longitudinally, the MCI[TBI+] group also exhibited greater longitudinal declines in left rostral middle frontal, the left caudal middle frontal and left lateral orbitofrontal areas sover the span of 2 years (median = 1-2%, 90%HDI [-0.01%: -0.001%], probability of direction (PD) = 90-99%). The MCI[TBI+] group also displayed greater longitudinal declines in Trail-Making-Test (TMT)-derived ratio (median: 0.737%, 90%HDI: [0.229%: 1.31%], PD = 98.8%) and differences scores (median: 20.6%, 90%HDI: [-5.17%: 43.2%], PD = 91.7%). CONCLUSIONS: Our findings support the notion that patients with MCI and a history of TBI are at risk of accelerated neurodegeneration, displaying greatest evidence for cortical atrophy within the left middle frontal and lateral orbitofrontal frontal cortex. Importantly, these results suggest that long-term TBI-mediated atrophy is more pronounced in areas vulnerable to TBI-related mechanical injury, highlighting their potential relevance for diagnostic forms of intervention in TBI.

Persistent fatigue in post-acute COVID syndrome is associated with altered T1 MRI texture in subcortical structures: a preliminary investigation.

Post-acute COVID syndrome (PACS) is a global health concern and is often associated with debilitating symptoms. Post-COVID fatigue is a particularly frequent and troubling issue, and its underlying mechanisms remain incompletely understood. One potential contributor is micropathological injury of subcortical and brainstem structures, as has been identified in other patient populations. Texture-based analysis (TA) may be used to measure such changes in anatomical MRI data. The present study develops a methodology of voxel-wise TA mapping in subcortical and brainstem regions, which is then applied to T1-weighted MRI data from a cohort of 48 individuals who had PACS (32 with and 16 without ongoing fatigue symptoms) and 15 controls who had cold and flu-like symptoms but tested negative for COVID-19. Both groups were assessed an average of 4-5 months post-infection. There were no significant differences between PACS and control groups, but significant differences were observed within the PACS groups, between those with and without fatigue symptoms. This included reduced texture energy and increased entropy, along with reduced texture correlation, cluster shade and profile in the putamen, pallidum, thalamus and brainstem. These findings provide new insights into the neurophysiological mechanisms that underlie PACS, with altered tissue texture as a potential biomarker of this debilitating condition.

Identifying Research Priorities in Limb Reconstruction Surgery in the United Kingdom.

Introduction: Limb reconstruction surgery (LRS) has a wide range of clinical applications within orthopaedic and trauma surgery. We sought a consensus view from limb reconstruction healthcare practitioners across the United Kingdom to help guide research priorities within LRS. Our aim is to guide future clinical research in LRS, and assist healthcare practitioners, clinical academics, and funding bodies in identifying key research priorities to improve patient care. Materials and methods: A modified Delphi approach was used; it involved an initial scoping survey and a 2-round Delphi process to identify the consensus research priorities in both adult and paediatric LRS. Participants were asked to rank approved submitted questions according to perceived importance on a 5-point Likert scale, where 1 represented lowest importance and 5 indicated highest importance. Mean scores were calculated to identify a consensus of the top ten research priorities for adult and paediatric LRS. Results: One hundred and fifteen participants primarily from across the United Kingdom working in LRS contributed to the modified Delphi process. Participants ranked and then re-ranked the presented research topics in terms of perceived importance. This led to the identification of a top ten research priorities in both adult and paediatric LRS, respectively, based on the collective responses of LRS practitioners. The highest-ranked questions in both adult and paediatric practice related to how to best assess and record patient-reported outcome measures (PROMs) in LRS patients. Other priorities included the effectiveness of specialist physiotherapy, the use of patient-focused psychological support, and the use of various operative management strategies for infection and limb length discrepancies. Conclusion: We present a consensus-driven research priority study that outlines the key research topics and themes determined by healthcare professionals within LRS in the United Kingdom. Clinical significance: These questions will assist funding bodies in prioritising where research funding may be best utilised and help drive future improvement in patient care. How to cite this article: British Limb Reconstruction Society Research Collaborative. Identifying Research Priorities in Limb Reconstruction Surgery in the United Kingdom. Strategies Trauma Limb Reconstr 2024;19(1):1-8.

Evaluation of the immunogenicity of an mRNA vectored Nipah virus vaccine candidate in pigs.

Nipah virus (NiV) poses a significant threat to human and livestock populations across South and Southeast Asia. Vaccines are required to reduce the risk and impact of spillover infection events. Pigs can act as an intermediate amplifying host for NiV and, separately, provide a preclinical model for evaluating human vaccine candidate immunogenicity. The aim of this study was therefore to evaluate the immunogenicity of an mRNA vectored NiV vaccine candidate in pigs. Pigs were immunized twice with 100 µg nucleoside-modified mRNA vaccine encoding soluble G glycoprotein from the Malaysia strain of NiV, formulated in lipid nanoparticles. Potent antigen-binding and virus neutralizing antibodies were detected in serum following the booster immunization. Antibody responses effectively neutralized both the Malaysia and Bangladesh strains of NiV but showed limited neutralization of the related (about 80% amino acid sequence identity for G) Hendra virus. Antibodies were also capable of neutralizing NiV glycoprotein mediated cell-cell fusion. NiV G-specific T cell cytokine responses were also measurable following the booster immunization with evidence for induction of both CD4 and CD8 T cell responses. These data support the further evaluation of mRNA vectored NiV G as a vaccine for both pigs and humans.

Neuroanatomical correlates of distracted straight driving performance: a driving simulator MRI study across the lifespan.

Background: Driving is the preferred mode of transportation for adults across the healthy age span. However, motor vehicle crashes are among the leading causes of injury and death, especially for older adults, and under distracted driving conditions. Understanding the neuroanatomical basis of driving may inform interventions that minimize crashes. This exploratory study examined the neuroanatomical correlates of undistracted and distracted simulated straight driving. Methods: One-hundred-and-thirty-eight participants (40.6% female) aged 17-85 years old (mean and SD = 58.1 ± 19.9 years) performed a simulated driving task involving straight driving and turns at intersections in a city environment using a steering wheel and foot pedals. During some straight driving segments, participants responded to auditory questions to simulate distracted driving. Anatomical T1-weighted MRI was used to quantify grey matter volume and cortical thickness for five brain regions: the middle frontal gyrus (MFG), precentral gyrus (PG), superior temporal cortex (STC), posterior parietal cortex (PPC), and cerebellum. Partial correlations controlling for age and sex were used to explore relationships between neuroanatomical measures and straight driving behavior, including speed, acceleration, lane position, heading angle, and time speeding or off-center. Effects of interest were noted at an unadjusted p-value threshold of 0.05. Results: Distracted driving was associated with changes in most measures of straight driving performance. Greater volume and cortical thickness in the PPC and cerebellum were associated with reduced variability in lane position and heading angle during distracted straight driving. Cortical thickness of the MFG, PG, PPC, and STC were associated with speed and acceleration, often in an age-dependent manner. Conclusion: Posterior regions were correlated with lane maintenance whereas anterior and posterior regions were correlated with speed and acceleration, especially during distracted driving. The regions involved and their role in straight driving may change with age, particularly during distracted driving as observed in older adults. Further studies should investigate the relationship between distracted driving and the aging brain to inform driving interventions.

Mitosis detection, fast and slow: Robust and efficient detection of mitotic figures.

Counting of mitotic figures is a fundamental step in grading and prognostication of several cancers. However, manual mitosis counting is tedious and time-consuming. In addition, variation in the appearance of mitotic figures causes a high degree of discordance among pathologists. With advances in deep learning models, several automatic mitosis detection algorithms have been proposed but they are sensitive to domain shift often seen in histology images. We propose a robust and efficient two-stage mitosis detection framework, which comprises mitosis candidate segmentation (Detecting Fast) and candidate refinement (Detecting Slow) stages. The proposed candidate segmentation model, termed EUNet, is fast and accurate due to its architectural design. EUNet can precisely segment candidates at a lower resolution to considerably speed up candidate detection. Candidates are then refined using a deeper classifier network, EfficientNet-B7, in the second stage. We make sure both stages are robust against domain shift by incorporating domain generalization methods. We demonstrate state-of-the-art performance and generalizability of the proposed model on the three largest publicly available mitosis datasets, winning the two mitosis domain generalization challenge contests (MIDOG21 and MIDOG22). Finally, we showcase the utility of the proposed algorithm by processing the TCGA breast cancer cohort (1,124 whole-slide images) to generate and release a repository of more than 620K potential mitotic figures (not exhaustively validated).

Task Activation Results in Regional 13 C-Lactate Signal Increase in the Human Brain.

Hyperpolarized- 13 C magnetic resonance imaging (HP- 13 C MRI) was used to image changes in 13 C-lactate signal during a visual stimulus condition in comparison to an eyes-closed control condition. Whole-brain 13 C-pyruvate, 13 C-lactate and 13 C-bicarbonate production was imaged in healthy volunteers (N=6, ages 24-33) for the two conditions using two separate hyperpolarized 13 C-pyruvate injections. BOLD-fMRI scans were used to delineate regions of functional activation. 13 C-metabolite signal was normalized by 13 C-metabolite signal from the brainstem and the percentage change in 13 C-metabolite signal conditions was calculated. A one-way Wilcoxon signed-rank test showed a significant increase in 13 C-lactate in regions of activation when compared to the remainder of the brain ( p = 0.02, V = 21). No significant increase was observed in 13 C-pyruvate ( p = 0.11, V = 17) or 13 C-bicarbonate ( p = 0.95, V = 3) signal. The results show an increase in 13 C-lactate production in the activated region that is measurable with HP- 13 C MRI.

Fracture related infection in open tibial fractures.

Open tibia fractures frequently occur following high-energy trauma. Contamination of the fracture site combined with limited soft tissue coverage and blood supply means that these open fractures are associated with a high rate of complications, including fracture related infection (FRI). FRI is associated with lowered patient outcomes and requires early recognition and appropriate surgical and medical management. The current evidence on FRI after open tibial fractures largely is limited to case series, small retrospective cohort studies and expert opinion. Recent expert consensus has produced guidelines with the aim of standardising care for these patients. This review summarises the current management strategies employed in treating FRI following open tibial fractures and where possible the evidence behind them.

Designing Community Services for People With Borderline Personality Disorder to Reduce Hospitalizations.

Previous evaluations of interventions for borderline personality disorder have focused on psychotherapies. This study (N=42 patients), conducted in Liverpool, United Kingdom, reviewed the effect on out-of-area treatments (OATs) and hospital admissions of establishing a local case management team and a combined day treatment and crisis service for patients who are too dysregulated to access typical office-based psychotherapy. Data from 12, 24, and 36 months postintervention were compared with baseline data. All patients in OATs were repatriated to the local community. No new patients were sent to OATs. Admissions decreased (at 12 months, 49%; 24 months, 64%; 36 months, 74%), achieving savings in hospitalization costs. Moderate increases in the use and costs of some other services were observed.

Optimising the Orthopaedic Trauma Society Open Fracture Classification system: a proposal for modification in the context of high civilian gunshot fractures.

OBJECTIVES: Uniformly classifying long bone open fractures is challenging. The purpose of this study was to propose a modified Orthopaedic Trauma Society (OTS) Open Fracture Classification System, developed in a setting with a high incidence of civilian gunshot fractures. METHODS: From our prospectively collected database, we identified all patients with open tibia and femur fractures treated with intramedullary nailing over a 4 year period. All open fractures were retrospectively reclassified from the Gustilo-Anderson Classification system to the OTS Open Fracture Classification System. RESULTS: One hundred and thirty-seven cases were identified. Ninety per cent of subjects were males. Their mean age was 34 years. The most common mechanism of injury was low-velocity civilian gunshot wounds (GSW) in 54.7% of cases. Soft tissue management was primary closure in 23.4% and soft tissue reconstruction in 24.1%. In 52.6% of cases (these all being secondary to civilian GSW), soft tissue management was healing via secondary intention. This is not included as a soft tissue management option in the OTS classification system. Fracture reclassification using the OTS Open Fracture Classification System was only possible in 47.5% of cases (Simple in 23.4%, Complex B in 24.1%). CONCLUSION: We conclude that the OTS Open Fracture Classification System is not inclusive of all open tibia and femur fractures as it does not cater for gunshot fractures. We propose a modification as follows: alter 'wound debridement' to 'appropriate wound care' and to subcategorise 'Simple' into type A and B: healing via secondary intention and primary closure, respectively.

Mismatch between clinically defined classification of ALS stage and the burden of cerebral pathology.

This study aimed to investigate the clinical stratification of amyotrophic lateral sclerosis (ALS) patients in relation to in vivo cerebral degeneration. One hundred forty-nine ALS patients and one hundred forty-four healthy controls (HCs) were recruited from the Canadian ALS Neuroimaging Consortium (CALSNIC). Texture analysis was performed on T1-weighted scans to extract the texture feature "autocorrelation" (autoc), an imaging biomarker of cerebral degeneration. Patients were stratified at baseline into early and advanced disease stages based on criteria adapted from ALS clinical trials and the King's College staging system, as well as into slow and fast progressors (disease progression rates, DPR). Patients had increased autoc in the internal capsule. These changes extended beyond the internal capsule in early-stage patients (clinical trial-based criteria), fast progressors, and in advanced-stage patients (King's staging criteria). Longitudinal increases in autoc were observed in the postcentral gyrus, corticospinal tract, posterior cingulate cortex, and putamen; whereas decreases were observed in corpus callosum, caudate, central opercular cortex, and frontotemporal areas. Both longitudinal increases and decreases of autoc were observed in non-overlapping regions within insula and precentral gyrus. Within-criteria comparisons of autoc revealed more pronounced changes at baseline and longitudinally in early- (clinical trial-based criteria) and advanced-stage (King's staging criteria) patients and fast progressors. In summary, comparative patterns of baseline and longitudinal progression in cerebral degeneration are dependent on sub-group selection criteria, with clinical trial-based stratification insufficiently characterizing disease stage based on pathological cerebral burden.

Interaction of Alzheimer Disease and Traumatic Brain Injury on Cortical Thickness.

INTRODUCTION: Traumatic brain injury (TBI) is associated with an accelerated course of dementia, although biological relationships are incompletely understood. METHODS: The study examined 1124 participants, including 343 with Alzheimer disease (AD), 127 with AD with TBI, 266 cognitively normal adults with TBI, and 388 cognitively normal adults without TBI. Cortical thickness was quantified from T1-weighted magnetic resonance imaging data. Multiple linear regression was used to determine the interaction between AD and TBI on cortical thickness. RESULTS: Among those with AD, TBI was associated with an earlier age of AD onset but, counterintuitively, less cortical thinning in frontotemporal regions relative to non-AD controls. DISCUSSION: AD with TBI represents a distinct group from AD, likely with distinct pathologic contributions beyond gray matter loss. This finding has important implications for the diagnosis and treatment of AD in the presence of TBI and indicates that models of AD, aging, and neural loss should account for TBI history.

Establishing Consensus on Essential Resources for Musculoskeletal Trauma Care Worldwide: A Modified Delphi Study.

BACKGROUND: Despite evidence that formalized trauma systems enhance patient functional outcomes and decrease mortality rates, there remains a lack of such systems globally. Critical to trauma systems are the equipment, materials, and supplies needed to support care, which vary in availability regionally. The purpose of the present study was to identify essential resources for musculoskeletal trauma care across diverse resource settings worldwide. METHODS: The modified Delphi method was utilized, with 3 rounds of electronic surveys. Respondents consisted of 1 surgeon with expertise in musculoskeletal trauma per country. Participants were identified with use of the AO Trauma, AO Alliance, Orthopaedic Trauma Association, and European Society for Trauma and Emergency Surgery networks. Respondents rated resources on a Likert scale from 1 (most important) to 9 (least important). The "most essential" resources were classified as those rated ≤2 by ≥75% of the sampled group. RESULTS: One hundred and three of 111 invited surgeons completed the first survey and were included throughout the subsequent rounds (representing a 93% response rate). Most participants were fellowship-trained (78%) trauma and orthopaedic surgeons (90%) practicing in an academic setting (62%), and 46% had >20 years of experience. Respondents represented low-income and lower-middle-income countries (LMICs; 35%), upper-middle income countries (UMICs; 30%), and high-income countries (HICs; 35%). The initial survey identified 308 unique resources for pre-hospital, in-hospital, and post-hospital phases of care, of which 71 resources achieved consensus as the most essential. There was a significant difference (p < 0.0167) in ratings between income groups for 16 resources, all of which were related to general trauma care rather than musculoskeletal injury management. CONCLUSIONS: There was agreement on a core list of essential musculoskeletal trauma care resources by respondents from LMICs, UMICs, and HICs. All significant differences in resource ratings were related to general trauma management. This study represents a first step toward establishing international consensus and underscores the need to prioritize resources that are locally available. The information can be used to develop effective guidelines and policies, create best-practice treatment standards, and advocate for necessary resources worldwide. CLINICAL RELEVANCE: This study utilized the Delphi method representing expert opinion; however, this work did not examine patient management and therefore does not have a clinical Level of Evidence.

Lateralized Functional Connectivity of the Sensorimotor Cortex and its Variations During Complex Visuomotor Tasks.

Previous studies have shown that the left hemisphere dominates motor function, often observed through homotopic activation measurements. Using a functional connectivity approach, this study investigated the lateralization of the sensorimotor cortex during handwriting and drawing, two complex visuomotor tasks with varying contextual demands. We found that both left- and right-lateralized connectivity in the primary motor cortex (M1), dorsal premotor cortex (PMd), somatosensory cortex, and visual regions were evident in adults (males and females), primarily in an interhemispheric integrative fashion. Critically, these lateralization tendencies remained highly invariant across task contexts, representing a task-invariant neural architecture for encoding fundamental motor programs consistently implemented in different task contexts. Additionally, the PMd exhibited a slight variation in lateralization degree between task contexts, reflecting the ability of the high-order motor system to adapt to varying task demands. However, connectivity-based lateralization of the sensorimotor cortex was not detected in 10-year-old children (males and females), suggesting that the maturation of connectivity-based lateralization requires prolonged development. In summary, this study demonstrates both task-invariant and task-sensitive connectivity lateralization in sensorimotor cortices that support the resilience and adaptability of skilled visuomotor performance. These findings align with the hierarchical organization of the motor system and underscore the significance of the functional connectivity-based approach in studying functional lateralization.

AI-based intra-tumor heterogeneity score of Ki67 expression as a prognostic marker for early-stage ER+/HER2- breast cancer.

Early-stage estrogen receptor positive and human epidermal growth factor receptor negative (ER+/HER2-) luminal breast cancer (BC) is quite heterogeneous and accounts for about 70% of all BCs. Ki67 is a proliferation marker that has a significant prognostic value in luminal BC despite the challenges in its assessment. There is increasing evidence that spatial colocalization, which measures the evenness of different types of cells, is clinically important in several types of cancer. However, reproducible quantification of intra-tumor spatial heterogeneity remains largely unexplored. We propose an automated pipeline for prognostication of luminal BC based on the analysis of spatial distribution of Ki67 expression in tumor cells using a large well-characterized cohort (n = 2,081). The proposed Ki67 colocalization (Ki67CL) score can stratify ER+/HER2- BC patients with high significance in terms of BC-specific survival (p < 0.00001) and distant metastasis-free survival (p = 0.0048). Ki67CL score is shown to be highly significant compared with the standard Ki67 index. In addition, we show that the proposed Ki67CL score can help identify luminal BC patients who can potentially benefit from adjuvant chemotherapy.

LYSTO: The Lymphocyte Assessment Hackathon and Benchmark Dataset.

We introduce LYSTO, the Lymphocyte Assessment Hackathon, which was held in conjunction with the MICCAI 2019 Conference in Shenzhen (China). The competition required participants to automatically assess the number of lymphocytes, in particular T-cells, in images of colon, breast, and prostate cancer stained with CD3 and CD8 immunohistochemistry. Differently from other challenges setup in medical image analysis, LYSTO participants were solely given a few hours to address this problem. In this paper, we describe the goal and the multi-phase organization of the hackathon; we describe the proposed methods and the on-site results. Additionally, we present post-competition results where we show how the presented methods perform on an independent set of lung cancer slides, which was not part of the initial competition, as well as a comparison on lymphocyte assessment between presented methods and a panel of pathologists. We show that some of the participants were capable to achieve pathologist-level performance at lymphocyte assessment. After the hackathon, LYSTO was left as a lightweight plug-and-play benchmark dataset on grand-challenge website, together with an automatic evaluation platform.

CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting.

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.