Search

Deep learning models are used to minimize the number of polyps that goes unnoticed by the experts and to accurately segment the detected polyps during interventions. Although state-of-the-art models are proposed, it remains a challenge to define representations that are able to generalize well and that mediate between capturing low-level features and higher-level semantic details without being redundant. Another challenge with these models is that they are computation and memory intensive, which can pose a problem with real-time applications. To address these problems, PlutoNet is proposed for polyp segmentation which requires only 9 FLOPs and 2,626,537 parameters, less than 10% of the parameters required by its counterparts. With PlutoNet, a novel decoder consistency training approach is proposed that consists of a shared encoder, the modified partial decoder , which is a combination of the partial decoder and full-scale connections that capture salient features at different scales without redundancy, and the auxiliary decoder which focuses on higher-level semantic features. The modified partial decoder and the auxiliary decoder are trained with a combined loss to enforce consistency, which helps strengthen learned representations. Ablation studies and experiments are performed which show that PlutoNet performs significantly better than the state-of-the-art models, particularly on unseen datasets., Competing Interests: The authors declare no conflicts of interest., (© 2024 The Author(s). Healthcare Technology Letters published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.)

Objective: Greater trochanteric pain syndrome (GTPS) is a prevalent condition that can significantly affect patient comfort and function. This study aims to compare the effectiveness of ultrasound (USG)-guided and anatomic landmark-guided corticosteroid injections in managing GTPS., Methods: Patients diagnosed with GTPS received either USG or anatomic landmark-guided corticosteroid injections. Pain scores (Visual Analog Scale, VAS) and functional outcomes (modified Harris Hip Score, HHS) were assessed at baseline, 1 month, and 1 year postinjection. Cost-effectiveness was calculated using public and private payor pricing from June 2024., Results: Both treatment groups exhibited significant improvements in pain and function. The USG group demonstrated greater initial improvements at the 1-month mark, particularly in VAS activity and HHS. However, these differences between the groups converged over time, with similar long-term outcomes observed in these parameters. The USG-guided injections showed more pronounced initial benefits, especially for patients with higher initial pain levels and lower functional scores. USG was found to be more cost-effective in terms of HHS, but not VAS measures., Conclusion: While both USG and anatomic landmark-guided injections are effective for managing GTPS, USG-guided injections may provide greater initial relief in pain and function, particularly for patients with higher initial pain levels. USG does not demonstrate longterm superiority over anatomic injections. The study underscores the importance of evaluating long-term outcomes to comprehensively assess the sustained effectiveness of different treatment strategies for GTPS., Level of Evidence: Level III, Therapeutic study.

Background/Objectives: Post-polio syndrome (PPS) affects former polio patients, manifesting decades after initial infection with progressive symptoms like pain, fatigue, and muscle weakness. Diagnosis relies on the clinical criteria and exclusion of other probable causes. The purpose of this study is to determine the scope and new diagnostic value of magnetic resonance imaging (MRI) in identifying muscle involvement in PPS and distinguishing it from prior poliomyelitis (PPM). Methods: This study was approved by the Koç University Ethics Committee with Approval No. 2023.409.IRB2.090. Electronic medical archives from two academic institutions were searched for records tagged with ICD code B-91 for poliomyelitis sequalae. The resulting search query of 291 records was manually sorted for PPS and PPM, medical history, clinical examination findings, and lumbar MR images down to 32 patients. Two independent radiologists evaluated the paraspinal musculature in the MRIs using the Mercuri scale. Inter-rater agreement, comparison of the paraspinal musculatures between groups, and their relationship to leg involvement were assessed with the resulting data. Results: Inter-rater agreement was found to be almost perfect across all muscles, except for the multifidus muscle. When clinical examination findings were included for these muscles, quadratus lumborum (QL) degradation was found in both right-side ( p = 0.017) and left-side ( p = 0.002) leg involvement. Conclusions: QL muscle deterioration may serve as a diagnostic marker for PPS, potentially guiding lumbar pain treatment through rehabilitation.

In this paper we show how simple text-driven variations of given statements in mathematics can lead to interesting new problems and push forward a whole theory around simple initial questions. We exemplify this in two cases. Case 1 deals with problem-posing activities suitable for pupils and case 2 is a rational reconstruction of the organisation of mathematical knowledge within problems of graph colorings. Mathematicians learn to systematically look for subsequent problems around a given problem. We argue that this toy-model captures a nontrivial part of professional mathematical research within the pure fields and conjecture that it even grasps high level developments in mathematics. By doing this, we implicitly encourage a very simplistic view on criteria, so to speak a "cowpath" approach to progress in mathematics. The term "cowpath" is borrowed from architecture and software design, where it is commonly used. While we can contemplate which pathways are ideal, we may also just plant grass and see where people choose to walk. Those pathways are also self-enforcing, since we are less hesitant to walk on those rather than criss-cross the landscape., (Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Background: We aimed to find out whether the Mini Nutritional Assessment-Short Form (MNA-SF) can predict mortality up to 7 years when compared with the Mini Nutritional Assessment-Long Form (MNA-LF) in geriatric outpatients., Methods: This retrospective study was conducted in patients (≥65 years) who were admitted to the geriatric outpatient clinic of a university hospital. MNA-SF and MNA-LF results were available for all patients. Patients were grouped as normal nutrition status (score 12-14), at risk of malnutrition (score between 8 and 11), or malnourished (score ≤7) according to MNA-SF. Based on MNA-LF, patients had normal nutrition status (score ≥24), were at risk of malnutrition (score 17-23.5), or were malnourished (score <17). Survival of the patients was assessed retrospectively., Results: The study included 209 patients (62.2% female). During the 7-year follow-up, 77 (36.8%) patients died. After adjusting for age, sex, and Charlson comorbidity index, MNA-SF was significantly associated with all-cause mortality during 6-month, 1-year, 3-year, 5-year, and 7-year follow-up time. MNA-LF was superior to MNA-SF to estimate 6-month (P = 0.004) and 1-year mortality (P = 0.031). There was no difference between MNA-SF and MNA-LF regarding 3-year, 5-year, and 7-year mortality., Conclusion: MNA-SF can predict short-term and long-term mortality in geriatric outpatients as well as MNA-LF. A cut-off value of 11, indicating risk of malnutrition according to MNA-SF, may be used for the risk estimation of 1-year, 3-year, and 5-year mortality. Therefore, this study highlights the importance of screening all geriatric outpatients for malnutrition and especially the risk of malnutrition for early intervention and treatment., (© 2022 American Society for Parenteral and Enteral Nutrition.)

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process., Competing Interests: Declaration of Competing Interest Anand Malpani is a future employee at Mimic Technologies Inc. (Seattle, WA, US). Johannes Fallert and Lars Mündermann are employed at KARL STORZ SE & Co. KG (Tuttlingen, Germany). Hirenkumar Nakawala is employed at CMR Surgical Ltd (Cambridge, UK). Nicolas Padoy is a scientific advisor of Caresyntax (Berlin, Germany). Daniel A. Hashimoto is a consultant for Johnson & Johnson (New Brunswick, NJ, USA), Verily Life Sciences (San Francisco, CA, USA), and Activ Surgical (Boston, MA, USA). He has received research support from Olympus Corporation and the Intuitive Foundation. Carla Pugh is the founder of 10 Newtons Inc. (Madison, WI, US). Danail Stoyanov is employed at Digital Surgery Ltd (London, UK) and Odin Vision Ltd (London, UK). Teodor Grantcharov is the founder of Surgical Safety Technologies Inc. (Toronto, Ontario, Canada). Tobias Roß is employed at Quality Match GmbH (Heidelberg, Germany). All other authors do not declare any conflicts of interest., (Copyright © 2021. Published by Elsevier B.V.)

Background and Objective: Automatic surgical workflow recognition is an essential step in developing context-aware computer-assisted surgical systems. Video recordings of surgeries are becoming widely accessible, as the operational field view is captured during laparoscopic surgeries. Head and ceiling mounted cameras are also increasingly being used to record videos in open surgeries. This makes videos a common choice in surgical workflow recognition. Additional modalities, such as kinematic data captured during robot-assisted surgeries, could also improve workflow recognition. This paper presents the design and results of the MIcro-Surgical Anastomose Workflow recognition on training sessions (MISAW) challenge whose objective was to develop workflow recognition models based on kinematic data and/or videos., Methods: The MISAW challenge provided a data set of 27 sequences of micro-surgical anastomosis on artificial blood vessels. This data set was composed of videos, kinematics, and workflow annotations. The latter described the sequences at three different granularity levels: phase, step, and activity. Four tasks were proposed to the participants: three of them were related to the recognition of surgical workflow at three different granularity levels, while the last one addressed the recognition of all granularity levels in the same model. We used the average application-dependent balanced accuracy (AD-Accuracy) as the evaluation metric. This takes unbalanced classes into account and it is more clinically relevant than a frame-by-frame score., Results: Six teams participated in at least one task. All models employed deep learning models, such as convolutional neural networks (CNN), recurrent neural networks (RNN), or a combination of both. The best models achieved accuracy above 95%, 80%, 60%, and 75% respectively for recognition of phases, steps, activities, and multi-granularity. The RNN-based models outperformed the CNN-based ones as well as the dedicated modality models compared to the multi-granularity except for activity recognition., Conclusion: For high levels of granularity, the best models had a recognition rate that may be sufficient for applications such as prediction of remaining surgical time. However, for activities, the recognition rate was still low for applications that can be employed clinically. The MISAW data set is publicly available at http://www.synapse.org/MISAW to encourage further research in surgical workflow recognition., Competing Interests: Declaration of Competing Interest The authors declare that they have no conflict of interest., (Copyright © 2021 Elsevier B.V. All rights reserved.)

Cortical injury, such as stroke, causes neurotoxic cascades that lead to rapid death and/or damage to neurons and glia. Axonal and myelin damage in particular, are critical factors that lead to neuronal dysfunction and impair recovery of function after injury. These factors can be exacerbated in the aged brain where white matter damage is prevalent. Therapies that can ameliorate myelin damage and promote repair by targeting oligodendroglia, the cells that produce and maintain myelin, may facilitate recovery after injury, especially in the aged brain where these processes are already compromised. We previously reported that a novel therapeutic, Mesenchymal Stem Cell derived extracellular vesicles (MSC-EVs), administered intravenously at both 24 h and 14 days after cortical injury, reduced microgliosis (Go et al. 2019), reduced neuronal pathology (Medalla et al. 2020), and improved motor recovery (Moore et al. 2019) in aged female rhesus monkeys. Here, we evaluated the effect of MSC-EV treatment on changes in oligodendrocyte maturation and associated myelin markers in the sublesional white matter using immunohistochemistry, confocal microscopy, stereology, qRT-PCR, and ELISA. Compared to vehicle control monkeys, EV-treated monkeys showed a reduction in the density of damaged oligodendrocytes. Further, EV-treatment was associated with enhanced myelin maintenance, evidenced by upregulation of myelin-related genes and increases in actively myelinating oligodendrocytes in sublesional white matter. These changes in myelination correlate with the rate of motor recovery, suggesting that improved myelin maintenance facilitates this recovery. Overall, our results suggest that EVs act on oligodendrocytes to support myelination and improves functional recovery after injury in the aged brain. SIGNIFICANCE: We previously reported that EVs facilitate recovery of function after cortical injury in the aged monkey brain, while also reducing neuronal pathology (Medalla et al. 2020) and microgliosis (Go et al. 2019). However, the effect of injury and EVs on oligodendrocytes and myelination has not been characterized in the primate brain (Dewar et al. 1999; Sozmen et al. 2012; Zhang et al. 2013). In the present study, we assessed changes in myelination after cortical injury in aged monkeys. Our results show, for the first time, that MSC-EVs support recovery of function after cortical injury by enhancing myelin maintenance in the aged primate brain., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Video understanding of robot-assisted surgery (RAS) videos is an active research area. Modeling the gestures and skill level of surgeons presents an interesting problem. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. We propose a solution to the tool detection and localization open problem in RAS video understanding, using a strictly computer vision approach and the recent advances of deep learning. We propose an architecture using multimodal convolutional neural networks for fast detection and localization of tools in RAS videos. To the best of our knowledge, this approach will be the first to incorporate deep neural networks for tool detection and localization in RAS videos. Our architecture applies a region proposal network (RPN) and a multimodal two stream convolutional network for object detection to jointly predict objectness and localization on a fusion of image and temporal motion cues. Our results with an average precision of 91% and a mean computation time of 0.1 s per test frame detection indicate that our study is superior to conventionally used methods for medical imaging while also emphasizing the benefits of using RPN for precision and efficiency. We also introduce a new data set, ATLAS Dione, for RAS video understanding. Our data set provides video data of ten surgeons from Roswell Park Cancer Institute, Buffalo, NY, USA, performing six different surgical tasks on the daVinci Surgical System (dVSS) with annotations of robotic tools per frame.

Objective: To investigate the effect of immunosuppressive anticancer therapy on titre levels of anti-hepatitis B surface antibodies (anti-HBs) in hepatitis B surface antigen (HBsAg) negative and anti-HBs positive patients with haematological malignancies or solid tumours., Methods: This retrospective study reviewed the medical records of patients with haematological malignancies or solid tumours. Pretreatment HBsAg negative and anti-HBs positive patients were included in the analysis. Anti-hepatitis B core antibody status was used to evaluate vaccinated patients and those with resolved HBV infections., Results: The medical records of 237 patients were reviewed retrospectively. The median anti-HBs titre decreased significantly after anticancer therapy compared with the pretreatment median anti-HBs titre in all patients (71 mIU/ml versus 57 mIU/ml). Anti-HBs titre decreased significantly in patients with haematological malignancies (70 mIU/m versus 37 mIU/ml) and in patients administered rituximab-based chemotherapy (67 mIU/ml versus 33 mIU/ml) following chemotherapy, whereas there was no significant change in patients with solid tumours. After chemotherapy, patients with low pretreatment anti-HBs titres (<100 mIU/ml) were more likely to become seronegative (<10 mIU/ml)., Conclusion: High levels of anti-HBs may have a protective effect against the reactivation of HBV especially in patients with haematological malignancies who received immunosuppressive anticancer therapy., (© The Author(s) 2016.)

In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients-manually annotated by up to four raters-and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%-85%), illustrating the difficulty of this task. We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously. Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource.

Background: Malnutrition is a pitfall in older adults despite its high prevalence and serious consequences. There are various screening tests however, none of them have been validated for our country. In this study, we aimed to test the hypothesis that MNA (long form of MNA) and MNA-SF (short form of MNA) are applicable to screen malnutrition in Turkish geriatric patients., Materials and Methods: Two hundred and thirty-six patients aged 65 years and over who were admitted to our geriatric medicine outpatient clinic were enrolled in the study. Four groups of data (anthropometric measurements, biochemical markers, three-day diet record and geriatric assessment scales) were recorded. Long and short forms of MNA test were performed. Two different geriatricians interpreted the patients' nutritional status with the aid of aforementioned data. Patients were divided into three groups which were patients with malnutrition, with malnutrition risk and well-nourished. Concordance between the two geriatricians' clinical assessment was analyzed by kappa statistics. Excellent concordance was found, therefore the first specialist's decisions were accepted as gold-standard. A third physician performed the long and short forms of MNA test. The concordance between the first clinician's assessment and MNA test results were compared subsequently., Results: MNA and MNA-SF results were compared with first clinician's decision of malnutrition and kappa coefficients were 0.68 and 0.66, respectively. Sensitivity analysis indicated that MNA was 92% sensitive and 86% specific, whereas MNA-SF was 94% sensitive and 81% specific., Conclusion: MNA and MNA-SF are suitable for malnutrition screening in Turkish older adults., (Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.)