Clinical Imaging Modalities Research Articles

The use of smartphone-application based medical photography for open fractures: A national survey of orthoplastic affiliated Major Trauma Centres in England

IntroductionBAPRAS/BOAST 4 guidelines recommend the use of medical photography for peri-operative management of open fractures. Smartphones are a common commodity for the modern day plastic surgeon and there is evidence their utilization improves guideline compliance at Major Trauma Centres (MTCs). AimTo capture national data assessing the prevalence and intricacies of smartphone app-based photography systems used for open fractures in plastic surgery units at MTCs in England. MethodA structured questionnaire survey was used to collate and analyze the responses of plastic surgeons and trainees at all MTCs in England. The survey included participant demographics, type and use of medical photography systems, and opinions on the usefulness of integrating a dedicated app in practice. We later explore the background, costs, download process, functionality and NHS governance applicability of each application. ResultsThe most popular clinical imaging modalities included professional photographers (65%) and departmental cameras (60%). Only 6 (26%) of MTCs use the following four smartphone app-based photography systems: Oxford University Hospital FotoApp, Medical Data Solutions and Services, Haiku and Secure Clinical Image Transfer. All systems are GDPR compliant and three systems auto upload images onto hospital databases. Five units report using messaging apps (Forward, Siilo, Whatsapp) with photography functionality. All participants agreed that a dedicated imaging smartphone app would be useful in open fracture management. ConclusionPlastic surgery is a highly visual specialty and clinical photography complements patient care. In the era of COVID-19 where resources are finite and professional photography not always available, this national survey highlights a demand for integrating smartphone app-based photography to improve guideline compliance, inter- and intra-disciplinary team communication and patient care.

Congenital systemic arteriovenous fistulas: Interventional strategies and embryological perspectives.

Background:Data on congenital systemic arteriovenous fistulas are largely based on individual case reports. A true systemic arteriovenous fistula needs to be differentiated from other vascular malformations like capillary or venous hemangiomas, which are far more common.Objectives:We sought to identify the varied symptoms, diagnostic challenges, describe interventional treatment options, and postulate an embryological basis for this uncommonly described entity.Methods:This is a descriptive study of a cohort of systemic arteriovenous fistulas seen in the department of pediatric cardiology at a tertiary cardiac institute from 2010 to 2020, with prospective medium-term follow-up. A total of seven cases were identified. The diagnosis was confirmed by computed tomographic imaging, magnetic resonance angiography, or conventional angiography.Results:All were successfully closed using duct occluders or embolization coils with no recurrence in six cases over a median duration of follow-up of 48 months (interquartile range: 16; 36–52 months). Four of the seven cases underwent follow-up imaging using echocardiography or ultrasound.Conclusion:The incidence of congenital systemic arteriovenous fistulas is low and accounted for 0.009% of pediatric outpatients seen over 10 years at our institute. The spectrum of clinical presentation varies from an innocuous swelling or a pulsating mass to frank heart failure. Strong clinical suspicion and advanced imaging modalities have helped identify some hitherto undescribed connections. Large malformations with multiple communications may persist or recur despite transcatheter closure.

Reliability as a Precondition for Trust-Segmentation Reliability Analysis of Radiomic Features Improves Survival Prediction.

Machine learning results based on radiomic analysis are often not transferrable. A potential reason for this is the variability of radiomic features due to varying human made segmentations. Therefore, the aim of this study was to provide comprehensive inter-reader reliability analysis of radiomic features in five clinical image datasets and to assess the association of inter-reader reliability and survival prediction. In this study, we analyzed 4598 tumor segmentations in both computed tomography and magnetic resonance imaging data. We used a neural network to generate 100 additional segmentation outlines for each tumor and performed a reliability analysis of radiomic features. To prove clinical utility, we predicted patient survival based on all features and on the most reliable features. Survival prediction models for both computed tomography and magnetic resonance imaging datasets demonstrated less statistical spread and superior survival prediction when based on the most reliable features. Mean concordance indices were Cmean = 0.58 [most reliable] vs. Cmean = 0.56 [all] (p < 0.001, CT) and Cmean = 0.58 vs. Cmean = 0.57 (p = 0.23, MRI). Thus, preceding reliability analyses and selection of the most reliable radiomic features improves the underlying model’s ability to predict patient survival across clinical imaging modalities and tumor entities.

Delayed diagnosis and subsequently increased severity of acute appendicitis (compatible with clinical-pathologic grounds) during the COVID-19 pandemic: an observational case-control study

BackgroundDuring a global crisis like the current COVID-19 pandemic, delayed admission to hospital in cases of emergent medical illness may lead to serious adverse consequences. We aimed to determine whether such delayed admission affected the severity of an inflammatory process regarding acute appendicitis, and its convalescence.MethodsIn a retrospective observational cohort case-control study, we analyzed the medical data of 60 patients who were emergently and consecutively admitted to our hospital due to acute appendicitis as established by clinical presentation and imaging modalities, during the period of the COVID-19 pandemic (our study group). We matched a statistically control group consisting of 97 patients who were admitted during a previous 12-month period for the same etiology. All underwent laparoscopic appendectomy. The main study parameters included intraoperative findings (validated by histopathology), duration of abdominal pain prior to admission, hospital stay and postoperative convalescence (reflecting the consequences of delay in diagnosis and surgery).ResultsThe mean duration of abdominal pain until surgery was significantly longer in the study group. The rate of advanced appendicitis (suppurative and gangrenous appendicitis as well as peri-appendicular abscess) was greater in the study than in the control group (38.3 vs. 21.6%, 23.3 vs. 16.5%, and 5 vs. 1% respectively), as well as mean hospital stay.ConclusionsA global crisis like the current viral pandemic may significantly affect emergent admissions to hospital (as in case of acute appendicitis), leading to delayed surgical interventions and its consequences.

Caroli’s Disease: A Mini-Review

Caroli’s disease is a rare congenital condition that is characterised by intrahepatic biliary duct dilatation without fibrosis. It is associated with an increased risk of cholelithiasis, cholangitis and cholangiocarcinoma. As such, it is an important clinical entity to be aware of. Most of the literature surrounding Caroli’s disease is limited to case reports and case series. This review will explore the clinical characteristics, imaging modalities and management of Caroli’s disease

Anti-KIT DNA aptamer-conjugated porous silicon nanoparticles for the targeted detection of gastrointestinal stromal tumors.

Evaluation of Gastrointestinal Stromal Tumors (GIST) during initial clinical staging, surgical intervention, and postoperative management can be challenging. Current imaging modalities (e.g., PET and CT scans) lack sensitivity and specificity. Therefore, advanced clinical imaging modalities that can provide clinically relevant images with high resolution would improve diagnosis. KIT is a tyrosine kinase receptor overexpressed on GIST. Here, the application of a specific DNA aptamer targeting KIT, decorated onto a fluorescently labeled porous silicon nanoparticle (pSiNP), is used for the in vitro & in vivo imaging of GIST. This nanoparticle platform provides high-fidelity GIST imaging with minimal cellular toxicity. An in vitro analysis shows greater than 15-fold specific KIT protein targeting compared to the free KIT aptamer, while in vivo analyses of GIST-burdened mice that had been injected intravenously (IV) with aptamer-conjugated pSiNPs show extensive nanoparticle-to-tumor signal co-localization (>90% co-localization) compared to control particles. This provides an effective platform for which aptamer-conjugated pSiNP constructs can be used for the imaging of KIT-expressing cancers or for the targeted delivery of therapeutics.

Speckle Reduction in Medical Ultrasound Imaging based on Visual Perception Model

Ultrasound imaging technology is one of the most important clinical imaging modalities due to its safety, low cost, in addition to its versatile applications. The main technical problem in this technology is its noisy appearance due to the presence of speckle, which makes reading imaging more difficult. In this study, a new method of speckle reduction in medical ultrasound images is proposed based on adaptive shifting of the contrast sensitivity function of human vision using a bias field map estimated from the original image. The aim of this work is to have an effective image enhancement strategy that reduces speckle while preserving diagnostically useful image features and allowing practical implementation in real-time for medical ultrasound imaging applications. The new method is used to improve the visual perception of image quality of ultrasound images by adding a local brightness bias to the areas with speckle noise. This allows the variations in image pixels due to speckle noise to be better perceived by the human observer because of the visual perception model. The performance of the proposed method is objectively assessed using quantitative image quality metrics and compared to previous methods. Furthermore, given that image quality perception is subjective, the level of added bias is controlled by a single parameter that accommodates the different needs for different users and applications. This method has potential to offer better viewing conditions of ultrasound images, which translates to higher diagnostic accuracy.

Light on osteoarthritic joint: from bench to bed.

Osteoarthritis (OA) is one of the rapidly growing disability-associated conditions with population aging worldwide. There is a pressing need for precise diagnosis and timely intervention for OA in the early stage. Current clinical imaging modalities, including pain radiography, magnetic resonance imaging, ultrasound, and optical coherent tomography, are limited to provide structural changes when the damage has been established or advanced. It prompts further endeavors in search of novel functional and molecular imaging, which potentially enables early diagnosis and intervention of OA. A hybrid imaging modality based on photothermal effects, photoacoustic imaging, has drawn wide attention in recent years and has seen a variety of biomedical applications, due to its great performance in yielding high-contrast and high-resolution images from structure to function, from tissue down to molecular levels, from animals to human subjects. Photoacoustic imaging has witnessed gratifying potentials and preliminary effects in OA diagnosis. Regarding the treatment of OA, photothermal-triggered therapy has exhibited its attractions for enhanced therapeutic outcomes. In this narrative review, we will discuss photoacoustic imaging for the diagnosis and monitoring of OA at different stages. Structural, functional, and molecular parameter changes associated with OA joints captured by photoacoustics will be summarized, forming the diagnosis perspective of the review. Photothermal therapy applications related to OA will also be discussed herein. Lastly, relevant clinical applications and its potential solutions to extend photoacoustic imaging to deeper OA situations have been proposed. Although some aspects may not be covered, this mini review provides a better understanding of the diagnosis and treatment of OA with exciting innovations based on tissue photothermal effects. It may also inspire more explorations in the field towards earlier and better theranostics of OA.

NEGATIVE APPENDECTOMIES ARE MORE COMMON IN FEMALES OF REPRODUCTIVE AGE GROUP

Objective: To compare the negative appendectomy in the females of reproductive and non-reproductive age groups.&#x0D; Study Design: Cross-sectional study.&#x0D; Place and Duration of Study: Department of Pathology, Diagnostic and Research Laboratory, Liaquat University of Medical and Health Sciences, Hyderabad, Pakistan, from January 2018 to December 2019.&#x0D; Methodology: A total of 1126 appendectomy specimens were enrolled irrespective of age and gender. The biodata of patients was retrieved from the database. Statistical analysis was done using SPSS version 22.&#x0D; Results: Out of total 1126 reported cases, 787 (69.9%) were males and 339 (30.1%) were females. The mean age was calculated to be 24.43 ± 12.42 years ranging from 2-94 years. Histopathological examination revealed cases of acute appendicitis 374 (33.2%), acute appendicitis with peri-appendicitis 478 (42.5%), fibrous obliteration 28 (2.5%) and parasitic infestation 7 (0.6%). Overall negative appendectomies were 219 (19.4%) and were prominent in females 100 (29.5%) than males 119 (15.1%). Also it was higher in females of reproductive age group 77 (30.4%) than in non-reproductive age group 23 (27.9%).&#x0D; Conclusion: In our study negative appendectomy in females of reproductive age groups was found to be higher than expected. Clinical scoring systems, biochemical markers, imaging modalities, and second opinion from other specialties like internal medicine, gynae and obstetric have been introduced to substantiate the diagnosis of acute appendicitis and thereby decreases the negative appendectomy.

Limitations of Muscle Ultrasound Shear Wave Elastography for Clinical Routine-Positioning and Muscle Selection.

Shear wave elastography (SWE) is a clinical ultrasound imaging modality that enables non-invasive estimation of tissue elasticity. However, various methodological factors—such as vendor-specific implementations of SWE, mechanical anisotropy of tissue, varying anatomical position of muscle and changes in elasticity due to passive muscle stretch—can confound muscle SWE measurements and increase their variability. A measurement protocol with a low variability of reference measurements in healthy subjects is desirable to facilitate diagnostic conclusions on an individual-patient level. Here, we present data from 52 healthy volunteers in the areas of: (1) Characterizing different limb and truncal muscles in terms of inter-subject variability of SWE measurements. Superficial muscles with little pennation, such as biceps brachii, exhibit the lowest variability whereas paravertebral muscles show the highest. (2) Comparing two protocols with different limb positioning in a trade-off between examination convenience and SWE measurement variability. Repositioning to achieve low passive extension of each muscle results in the lowest SWE variability. (3) Providing SWE shear wave velocity (SWV) reference values for a specific ultrasound machine/transducer setup (Canon Aplio i800, 18 MHz probe) for a number of muscles and two positioning protocols. We argue that methodological issues limit the current clinical applicability of muscle SWE.

Abdominal computed tomography localizer image generation: A deep learning approach

Background and ObjectiveComputed Tomography (CT) has become an important clinical imaging modality, as well as the leading source of radiation dose from medical imaging procedures. Modern CT exams are usually led by two quick orthogonal localization scans, which are used for patient positioning and diagnostic scan parameter definition. These two localization scans contribute to the patient dose but are not used for diagnosis purposes. In this study, we investigate the possibility of using deep learning models to reconstruct one localization scan image from the other, thus reducing the patient dose and simplifying the clinical workflow. MethodsWe propose a modified encoder-decoder network and a scaled mixture loss function specifically for the focal task. In this study, 12,487 clinical abdominal exams were retrieved from a clinical medical imaging storage system and randomly split for training, validation, and test in the ratio of 7:1:2. Reconstructed images were compared with the ground truth in terms of location prediction error, profile prediction error, and attenuation prediction error. ResultsThe average location error, profile error, and attenuation error were 1.02±3.37 mm, 4.43±2.02%, and 6.2 ± 2.94% for lateral prediction, and 6.46±6.43 mm, 3.9 ± 2.32%, and 7.12±3.54% for AP prediction, respectively. ConclusionsWe conclude that although the reconstructed abdominal CT localization images may lack some details on the internal organ structures, they could be used effectively for tube current modulation calculation and patient positioning purposes, leading to a reduction of radiation dose and scan time in clinical CT exams.

Microscopic multifrequency magnetic resonance elastography of ex vivo abdominal aortic aneurysms for extracellular matrix imaging in a mouse model

An abdominal aortic aneurysm (AAA) is a permanent dilatation of the abdominal aorta, usually accompanied by thrombus formation. The current clinical imaging modalities cannot reliably visualize the thrombus composition. Remodeling of the extracellular matrix (ECM) during AAA development leads to stiffness changes, providing a potential imaging marker. 14 apolipoprotein E-deficient mice underwent surgery for angiotensin II-loaded osmotic minipump implantation. 4 weeks post-op, 5 animals developed an AAA. The aneurysm was imaged ex vivo by microscopic multifrequency magnetic resonance elastography (µMMRE) with an in-plane resolution of 40 microns. Experiments were performed on a 7-Tesla preclinical magnetic resonance imaging scanner with drive frequencies between 1000 Hz and 1400 Hz. Shear wave speed (SWS) maps indicating stiffness were computed based on tomoelastography multifrequency inversion. As control, the aortas of 5 C57BL/6J mice were examined with the same imaging protocol. The regional variation of SWS in the thrombus ranging from 0.44 ± 0.07 to 1.20 ± 0.31 m/s was correlated fairly strong with regional histology-quantified ECM accumulation (R2 = 0.79). Our results suggest that stiffness changes in aneurysmal thrombus reflect ECM remodeling, which is critical for AAA risk assessment. In the future, µMMRE could be used for a mechanics-based clinical characterization of AAAs in patients. Statement of significanceTo our knowledge, this is the first study mapping the stiffness of abdominal aortic aneurysms with microscopic resolution of 40 µm. Our work revealed that stiffness critically changes due to extracellular matrix (ECM) remodeling in the aneurysmal thrombus. We were able to image various levels of ECM remodeling in the aneurysm reflected in distinct shear wave speed patterns with a strong correlation to regional histology-quantified ECM accumulation. The generated results are significant for the application of microscopic multifrequency magnetic resonance elastography for quantification of pathological remodeling of the ECM and may be of great interest for detailed characterization of AAAs in patients.

Mesoporous Silica Nanoparticle-Based Imaging Agents for Hepatocellular Carcinoma Detection.

Hepatocellular carcinoma (HCC) is characterized by poor prognosis and high mortality. The treatment of HCC is closely related to the stage, and the early-stage of HCC patients usually accompanies a more long-term survival rate after clinical treatment. Hence, there are critical needs to develop effective imaging agents with superior diagnostic precision for HCC detection at an early stage. Recently, mesoporous silica nanoparticles (MSNs) based imaging agents have gained extensive attentions in HCC detection, which can serve as a multifunctional nanoplatform with controllable size and facile surface functionalization. This perspective summarizes recent advances in MSNs based imaging agents for HCC detection by the incorporation of several clinical imaging modalities. Multi-modal imaging system has been developed for higher spatial resolution and sensitivity. Even though some limitations and challenges need to be overcome, we envision the development of novel MSNs based imaging agents will offer great potential applications in clinical HCC detection.

Abstract 10644: Impact of Cardiopulmonary Bypass Surgery on Myocardial Perfusion Assessed by Ultrafast Power Doppler: A Human Proof-of-Concept Study

Introduction: Inadequate myocardial coronary perfusion is a major cause of cardiac dysfunction in several clinical settings including congenital heart disease and cardiopulmonary bypass surgery (CPB). Blood flow to the myocardium (i.e. coronary perfusion) is primarily controlled by the coronary microvasculature (vessels &lt; 500 μm) which plays a key part in coronary perfusion autoregulation. Until recently, direct quantitative coronary perfusion assessment had been infeasible due to limitations in spatial and/or temporal resolution of clinical imaging modalities. The study objective is to assess if ultrafast ultrasound-mediated power Doppler (PD) can approximate changes in myocardial perfusion in humans. Methods: We used a 6.9 MHz linear array probe connected to a programmable ultrafast ultrasound scanner (Verasonics Vantage®). We included 7 neonates with transposition of the great arteries (TGA) and acquired epicardial ultrafast acquisitions immediately before and after CPB (arterial switch operation) via open chest. The acquisitions were acquired at 2000 fps (PRF=10000Hz, 5 sources). Tissue clutter was separated from coronary signals with a sliding spatiotemporal filter. PD was measured as a representative of blood volume that scales with hematocrit. Fractional moving blood volume (FMBV) was calculated to normalize the PD signal: mean PD divided by the PD of the ventricular blood pool, a region with 100% vascular amplitude. Results and Conclusions: The FMBV post-operatively increased by a factor of two compared to pre-operative assessment, a reflection of hyperemia. These values returned to baseline on repeat assessment prior to discharge. Our findings suggest that ultrafast PD is a reliable tool in approximating changes in myocardial perfusion in the operating room and beyond. Thus, ultrafast power Doppler can be utilized to quantitatively assess the impact of CPB on coronary perfusion in humans.

Anti-BCMA Immuno-NanoPET Radiotracers for Improved Detection of Multiple Myeloma.

Current clinical imaging modalities for the sensitive and specific detection of multiple myeloma (MM) rely on nonspecific imaging contrast agents based on gadolinium chelates for magnetic resonance imaging (MRI) or for 18 F-FDG-directed and combined positron emission tomography (PET) and computed tomography (CT) scans. These tracers are not, however, able to detect minute plasma cell populations in the tumor niche, leading to false negative results. Here, a novel PET-based anti-BCMA nanoplatform labeled with 64 Cu is developed to improve the monitoring of these cells in both the spine and femur and to compare its sensitivity and specificity to more conventional immunoPET (64 Cu labeled anti-BCMA antibody) and passively targeted PET radiotracers (64 CuCl2 and 18 F-FDG). This proof-of-concept preclinical study confirmed that by conjugating up to four times more radioisotopes per antibody with the immuno-nanoPET platform, an improvement in the sensitivity and in the specificity of PET to detect tumor cells in an orthotopic model of MM is observed when compared to the traditional immunoPET approach. It is anticipated that when combined with tumor biopsy, this immuno-nanoPET platform may improve the management of patients with MM.

OxyChip embedded with radio-opaque gold nanoparticles for anatomic registration and oximetry in tissues.

Electron paramagnetic resonance oximetry using the OxyChip as an implantable oxygen sensor can directly and repeatedly measure tissue oxygen levels. A phase I, first-in-human clinical study has established the safety and feasibility of using OxyChip for reliable and repeated measurements of oxygen levels in a variety of tumors and treatment regimens. A limitation in these studies is the inability to easily locate and identify the implanted probes in the tissue, particularly in the long term, thus limiting spatial/anatomical registration of the implant for proper interpretation of the oxygen data. In this study, we have developed and evaluated an enhanced oxygen-sensing probe embedded with gold nanoparticles (GNP), called the OxyChip-GNP, to enable visualization of the sensor using routine clinical imaging modalities. In vitro characterization, imaging, and histopathology studies were carried out using tissue phantoms, excised tissues, and in vivo animal models (mice and rats). The results demonstrated a substantial enhancement of ultrasound and CT contrast using the OxyChip-GNP without compromising its electron paramagnetic resonance and oxygen-sensing properties or biocompatibility. The OxyChips embedded with gold nanoparticles (OxyChip-GNP) can be readily identified in soft tissues using standard clinical imaging modalities such as CT, cone beam-CT, or ultrasound imaging while maintaining its capability to make repeated in vivo measurements of tissue oxygen levels over the long term. This unique capability of the OxyChip-GNP facilitates precisely localized in vivo oxygen measurements in the clinical setting.

Simulation and Mitigation of the Wrap-Around Artifact in the MRI Image.

Magnetic resonance imaging (MRI) is an essential clinical imaging modality for diagnosis and medical research, while various artifacts occur during the acquisition of MRI image, resulting in severe degradation of the perceptual quality and diagnostic efficacy. To tackle such challenges, this study deals with one of the most frequent artifact sources, namely the wrap-around artifact. In particular, given that the MRI data are limited and difficult to access, we first propose a method to simulate the wrap-around artifact on the artifact-free MRI image to increase the quantity of MRI data. Then, an image restoration technique, based on the deep neural networks, is proposed for wrap-around artifact reduction and overall perceptual quality improvement. This study presents a comprehensive analysis regarding both the occurrence of and reduction in the wrap-around artifact, with the aim of facilitating the detection and mitigation of MRI artifacts in clinical situations.

Role of MRI Diffusion Weighted Imaging in Evaluation of Gynecological Pelvic Masses

Background: Gynecological Pelvic masses are common problem that are commonly discovered during routine gynecologic or physical examinations. Radiologists routinely evaluate a wide range of pelvic masses during daily practice. Proper management depends on proper preoperative assessment with the help of clinical examination, laboratory tests and different imaging modalities. Radiological evaluation includes ultrasonography (US), computed tomography (CT) and recently magnetic resonance imaging (MRI). Diffusion weighted imaging (DWI) is widely used in protocols for magnetic resonance imaging (MRI) of the female pelvis. It provides functional and structural information about biological tissues, without the use of ionizing radiation or intravenous administration of contrast medium. Objective: This study aimed to evaluate the role of diffusion weighted imaging in the characterization of gynecological pelvic masses and differentiation between benign and malignant tumors. Patients and Methods: This study was performed on 63 patients. All patients had US findings of uterine and adnexal lesions then they underwent conventional MRI with contrast & DWI. Results: DWI is significant promising tool factors for characterization of gynecological tumors and differentiation between benign & malignant lesions with high sensitivity 95% (81%:99% with 95% CI). The sensitivity, specificity and accuracy of detection of the nature of the lesions have been increased after adding of DWI to the conventional imaging. Conclusions: Adding of DWI to the conventional MRI improves the sensitivity and specificity of diagnosis and allows confident diagnosis and differentiation between benign and malignant lesions.

Clinical and Radiological Outcomes After Isolated Anterior Horn Repair of Medial and Lateral Meniscus at 24 Months' Follow-up, With the Outside-In Technique.

BackgroundThe effects of repair of isolated anterior horn meniscus lesions have not been thoroughly described in the literature. We aimed to evaluate outcomes with subjective clinical scores and imaging modalities after repair of isolated anterior horn tears, at 24 months’ follow-up.MethodsRecords of all patients that opted for surgical repair of isolated, anterior horn tears of the medial and lateral meniscus were retrospectively reviewed, between 2016 and 2018. All patients were treated with arthroscopic outside-in technique by the same surgeon. Preoperative and postoperative clinical files were accessed to recover records of preoperative symptomatology, patient-reported scores [International Knee Documentation Committee (IKDC) rating, Lysholm score and Tegner activity level], preoperative and postoperative MRI data and time from injury to surgery.ResultsMean age of eight patients was 25.25 years (range 18-37 years). Diagnostic preoperative MRI revealed isolated anterior horn tear of the lateral meniscus and medial meniscus in five patients and an isolated anterior horn tear of the medial meniscus in three patients. Mean time from injury to surgical repair was 23.75 days (range 7-43). We considered seven out of eight repairs to be successfully healed. At 24 months’ follow-up: Mean Lysholm score was 92.25 (range 89-95), Tegner activity scale score was 6.5 (range 5-8) and IKDC score was 91.78 (range 87.8-94.4). All scores significantly improved compared to preoperative values (p<0.001).ConclusionsOutside-in is a reliable technique to repair meniscal anterior horn tears, both medially and laterally, with high healing rates and patient satisfaction in young, active patients.

Deep learning for distinguishing normal versus abnormal chest radiographs and generalization to two unseen diseases tuberculosis and COVID-19

Chest radiography (CXR) is the most widely-used thoracic clinical imaging modality and is crucial for guiding the management of cardiothoracic conditions. The detection of specific CXR findings has been the main focus of several artificial intelligence (AI) systems. However, the wide range of possible CXR abnormalities makes it impractical to detect every possible condition by building multiple separate systems, each of which detects one or more pre-specified conditions. In this work, we developed and evaluated an AI system to classify CXRs as normal or abnormal. For training and tuning the system, we used a de-identified dataset of 248,445 patients from a multi-city hospital network in India. To assess generalizability, we evaluated our system using 6 international datasets from India, China, and the United States. Of these datasets, 4 focused on diseases that the AI was not trained to detect: 2 datasets with tuberculosis and 2 datasets with coronavirus disease 2019. Our results suggest that the AI system trained using a large dataset containing a diverse array of CXR abnormalities generalizes to new patient populations and unseen diseases. In a simulated workflow where the AI system prioritized abnormal cases, the turnaround time for abnormal cases reduced by 7–28%. These results represent an important step towards evaluating whether AI can be safely used to flag cases in a general setting where previously unseen abnormalities exist. Lastly, to facilitate the continued development of AI models for CXR, we release our collected labels for the publicly available dataset.