Hybrid Transcatheter Approach to an Iatrogenic Left Ventricle-Coronary Sinus Fistula

This clinical case describes a subacute presentation of decompensated heart failure secondary to an iatrogenic left ventricle-to-coronary sinus fistula after sequential mitral valve surgical procedures. Computed tomography was used to select an unconventional hybrid transapical access approach and facilitate successful closure using a vascular plug.

Using optical coherence tomography to assess luster of pearls: technique suitability and insights

Luster is one of the vital indexes in pearl grading. To find a fast, nondestructive, and low-cost grading method, optical coherence tomography (OCT) is introduced to predict the luster grade through the texture features. After background removal, flattening, and segmentation, the speckle pattern of the region of interest is described by seven kinds of feature textures, including center-symmetric auto-correlation (CSAC), fractal dimension (FD), Gabor, gray level co-occurrence matrix (GLCM), histogram of oriented gradients (HOG), laws texture energy (LAWS), and local binary patterns (LBP). To find the relations between speckle-derived texture features and luster grades, four Four groups of pearl samples were used in the experiment to detect texture differences based on support vector machines (SVMs) and random forest classifier (RFC)) for investigating the relations between speckle-derived texture features and luster grades. The precision, recall, F1-score, and accuracy are more significant than 0.9 in several simulations, even after dimension reduction. This demonstrates that the texture feature from OCT images can be applied to class the pearl luster based on speckle changes.

Applications of Tissue Clearing in Central and Peripheral Nerves

The techniques of tissue clearing have been proposed and applied in anatomical and biomedical research since the 19th century. As we all know, the original study of the nervous system relied on serial ultrathin sections and stereoscopic techniques. The 3D visualization of the nervous system was established by software splicing and reconstruction. With the development of science and technology, microscope equipment had constantly been upgraded. Despite the great progress that has been made in this field, the workload is too complex, and it needs high technical requirements. Abundant mistakes due to manual sections were inescapable and structural integrity remained questionable. According to the classification of tissue transparency methods, we introduced the latest application of transparency methods in central and peripheral nerve research from optical imaging, molecular markers and data analysis. This review summarizes the application of transparent technology in neural pathways. We hope to provide some inspiration for the continuous optimization of tissue clearing methods.

Corrigendum: Comparison of indocyanine green angiography and swept-source wide-field optical coherence tomography angiography in posterior uveitis

[This corrects the article DOI: 10.3389/fmed.2022.853315.].

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs-A Systematic Review

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

A Far-Red Fluorescent Probe to Visualize Gram-Positive Bacteria in Patient Samples

Gram-positive bacteria, in particular Staphylococcus aureus (S. aureus), are the leading bacterial cause of death in high-income countries and can cause invasive infections at various body sites. These infections are associated with prolonged hospital stays, a large economic burden, considerable treatment failure, and high mortality rates. So far, there is only limited knowledge about the specific locations where S. aureus resides in the human body during various infections. Hence, the visualization of S. aureus holds significant importance in microbiological research. Herein, we report the development and validation of a far-red fluorescent probe to detect Gram-positive bacteria, with a focus on staphylococci, in human biopsies from deep-seated infections. This probe displays strong fluorescence and low background in human tissues, outperforming current tools for S. aureus detection. Several applications are demonstrated, including fixed- and live-cell imaging, flow cytometry, and super-resolution bacterial imaging.

Hot Carrier Trapping and It's Influence to the Carrier Diffusion in CsPbBr3 Perovskite Film Revealed by Transient Absorption Microscopy

The defects in perovskite film can cause charge carrier trapping which shortens carrier lifetime and diffusion length. So defects passivation has become promising for the perovskite studies. However, how defects disturb the carrier transport and how the passivating affects the carrier transport in CsPbBr3 are still unclear. Here the carrier dynamics and diffusion processes of CsPbBr3 and LiBr passivated CsPbBr3 films are investigated by using transient absorption spectroscopy and transient absorption microscopy. It's found that there is a fast hot carrier trapping process with the above bandgap excitation, and the hot carrier trapping would decrease the population of cold carriers which are diffusible, then lower the carrier diffusion constant. It's proved that LiBr can passivate the defect and lower the trapping probability of hot carriers, thus improve the carrier diffusion rate. The finding demonstrates the influence of hot carrier trapping to the carrier diffusion in CsPbBr3 film.

Polymer-tethered quenched fluorescent probes for enhanced imaging of tumor associated proteases

Fluorescence-based contrast agents enable real-time detection of solid tumors and their neovasculature, making them ideal for use in image-guided surgery. Several agents have entered late-stage clinical trials or secured FDA approval, suggesting they are likely to become standard of care in cancer surgeries. One of the key parameters to optimize in contrast agent is molecular size, which dictates much of the pharmacokinetic and pharmacodynamic properties of the agent. Here, we describe the development of a class of protease-activated quenched fluorescent probes in which a N-(2-hydroxypropyl)methacrylamide copolymer is used as the primary scaffold. This copolymer core provides a high degree of probe modularity to generate structures that cannot be achieved with small molecules and peptide probes. We used a previously validated cathepsin substrate and evaluated the effects of length and type of linker as well as positioning of the fluorophore/quencher pair on the polymer core. We found that the polymeric probes could be optimized to achieve increased over-all signal and tumor-to-background ratios compared to the reference small molecule probe. Our results also revealed multiple structure-activity relationship trends that can be used to design and optimize future optical imaging probes. Furthermore, they confirm that a hydrophilic polymer is an ideal scaffold for use in optical imaging contrast probes, allowing a highly modular design that enables efficient optimization to maximize probe accumulation and overall biodistribution properties.

Malignant glomus tumor of the breast: a case report

Malignant glomus tumor (MGT) is a rare mesenchymal neoplasm. It is rarely located in the breast. We present a case of a 57-year-old female patient presenting with complaints of a progressively growing mass found in her left breast. Though multiple imaging examinations have been performed, especially multimodal ultrasound examinations, an accurate diagnosis still cannot be determined. Finally, the lesion was confirmed to be a MGT of the breast by postoperative pathological diagnosis. In conclusion, MGT originating from breast is extremely rare. No such case has ever been described before. This study demonstrates the imaging characteristics of a patient with MGT of the breast in order to provide more extensive insights to consider the differential diagnosis of breast lesions.

The Scope of Virtual Reality Simulators in Radiology Education: Systematic Literature Review

Background

In recent years, virtual reality (VR) has gained significant importance in medical education. Radiology education also has seen the induction of VR technology. However, there is no comprehensive review in this specific area. This review aims to fill this knowledge gap.

Objective

This systematic literature review aims to explore the scope of VR use in radiology education.

Methods

A literature search was carried out using PubMed, Scopus, ScienceDirect, and Google Scholar for articles relating to the use of VR in radiology education, published from database inception to September 1, 2023. The identified articles were then subjected to a PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses)-defined study selection process.

Results

The database search identified 2503 nonduplicate articles. After PRISMA screening, 17 were included in the review for analysis, of which 3 (18%) were randomized controlled trials, 7 (41%) were randomized experimental trials, and 7 (41%) were cross-sectional studies. Of the 10 randomized trials, 3 (30%) had a low risk of bias, 5 (50%) showed some concerns, and 2 (20%) had a high risk of bias. Among the 7 cross-sectional studies, 2 (29%) scored "good" in the overall quality and the remaining 5 (71%) scored "fair." VR was found to be significantly more effective than traditional methods of teaching in improving the radiographic and radiologic skills of students. The use of VR systems was found to improve the students' skills in overall proficiency, patient positioning, equipment knowledge, equipment handling, and radiographic techniques. Student feedback was also reported in the included studies. The students generally provided positive feedback about the utility, ease of use, and satisfaction of VR systems, as well as their perceived positive impact on skill and knowledge acquisition.

Conclusions

The evidence from this review shows that the use of VR had significant benefit for students in various aspects of radiology education. However, the variable nature of the studies included in the review reduces the scope for a comprehensive recommendation of VR use in radiology education.

Molecular histopathology of matrix proteins through autofluorescence super-resolution microscopy

Extracellular matrix diseases like fibrosis are elusive to diagnose early on, to avoid complete loss of organ function or even cancer progression, making early diagnosis crucial. Imaging the matrix densities of proteins like collagen in fixed tissue sections with suitable stains and labels is a standard for diagnosis and staging. However, fine changes in matrix density are difficult to realize by conventional histological staining and microscopy as the matrix fibrils are finer than the resolving capacity of these microscopes. The dyes further blur the outline of the matrix and add a background that bottlenecks high-precision early diagnosis of matrix diseases. Here we demonstrate the multiple signal classification method-MUSICAL-otherwise a computational super-resolution microscopy technique to precisely estimate matrix density in fixed tissue sections using fibril autofluorescence with image stacks acquired on a conventional epifluorescence microscope. We validated the diagnostic and staging performance of the method in extracted collagen fibrils, mouse skin during repair, and pre-cancers in human oral mucosa. The method enables early high-precision label-free diagnosis of matrix-associated fibrotic diseases without needing additional infrastructure or rigorous clinical training.

Naphtho[1,8-ef]isoindole-7,8,10(9H)-trione as novel theranostic agents for photodynamic therapy and multi-subcellular organelles localization

A series of naphtho[1,8-ef]isoindole-7,8,10(9H)-trione as novel theranostic agents for photodynamic therapy and multi-subcellular organelles localization were designed and synthesized. Most of them possess moderate fluorescence quantum yield and long wavelength absorption simultaneously, these made them possible for dual effects of imaging and therapy. Especially, 7b and 7d exhibited significant light-toxicity but slight dark-toxicity. Confocal fluorescence microscopy experiments demonstrated that 7b can locate and image in special multi-subcellular organelles. All the research results implied that carbonyl-phenalene-2,3-dicarboximides derivatives can be applied as a new series of theranostic agents with the characteristics of photodynamic therapy and multi-subcellular organelles imaging.

Intra- and interobserver agreement in computed tomography localization of primary nonhematopoietic hepatic masses and comparison with surgical and histopathological outcomes in 21 cats

Computed tomography (CT) is commonly used in the staging of hepatic masses and for liver lobectomy planning. Mass location is an important factor in determining the feasibility of resection, including surgical technique and the likelihood of surgical complications. The objectives of this retrospective descriptive cross-sectional, observer agreement, method comparison study were to assess the reliability of CT in correctly determining the hepatic division and lobar site of origin of feline primary nonhematopoietic hepatic masses, compared with surgically confirmed locations. Furthermore, it provides an overview of the types and locations of liver masses found in a cohort of cats. Pre- and postcontrast CT images of 21 cats were independently and simultaneously reviewed by two observers. Intra- and interobserver agreements and descriptive statistics on demographic and histological diagnoses were calculated. Based on surgical assessment, it was found that masses most frequently originated from the left hepatic division (13/24, 54%). The most frequent lobar origins were the left lateral (8/24, 33%), left medial (5/24, 21%), and right medial lobes (5/24, 21%). No masses were found originating from the right lateral lobe. CT correctly determined hepatic division and lobar origin in 76% of cases, with good-to-excellent intra- and interobserver agreement. The hepatic division had higher agreements overall for both observers. Most of the masses were benign (17/21, 81%), and the most prevalent histological diagnoses were biliary cystadenoma (11/21, 52%) and hepatocellular adenoma (6/21, 29%). Findings suggest that postcontrast CT is a reliable method for correctly determining hepatic mass division and lobar origin in cats.

Intrarenal pH-Responsive Self-Assembly of Luminescent Gold Nanoparticles for Diagnosis of Early Kidney Injury

Metabolic acidosis-induced kidney injury (MAKI) is asymptomatic and lack of clinical biomarkers in early stage, but rapidly progresses to severe renal fibrosis and ultimately results in end-stage kidney failure. Therefore, developing rapid and noninvasive strategies direct responsive to renal tubular acidic microenvironment rather than delayed biomarkers are essential for timely renoprotective interventions. Herein, we develop pH-responsive luminescent gold nanoparticles (p-AuNPs) in the second near-infrared emission co-coated with 2,3-dimethylaleic anhydride conjugated β-mercaptoethylamine and cationic 2-diethylaminoethanethiol hydrochloride, which showed sensitive pH-induced charge reversal and intrarenal self-assembly for highly sensitive and long-time (~24 h) imaging of different stages of MAKI. By integrating advantages of pH-induced intrarenal self-assembly and enhanced interactions between pH-triggered positively charged p-AuNPs and renal tubular cells, the early- and late-stage MAKI could be differentiated rapidly within 10 min post-injection (p.i.) with contrast index (CI) of 3.5 and 4.3, respectively. The corresponding maximum CI could reach 5.1 and 9.2 at 12 h p.i., respectively. Furthermore, p-AuNPs were demonstrated to effectively real-time monitor progressive recovery of kidney injury in MAKI mice after therapy, and also exhibit outstanding capabilities for drug screening. This pH-responsive strategy showed great promise for feedback on kidney dysfunction progression, opening new possibilities for early-stage diagnosis of pH-related diseases.

Diffusion-weighted magnetic resonance imaging for the diagnosis of giant cell arteritis: a comparison with T1-weighted black-blood imaging

OBJECTIVES

To investigate the diagnostic performance of diffusion-weighted imaging (DWI) of the superficial cranial arteries in the diagnosis of GCA.

METHODS

Retrospectively, 156 patients with clinically suspected GCA were included. A new 4-point ordinal DWI rating scale was developed. A post-contrast, fat-suppressed, T1-weighted 'black-blood' sequence (T1-BB) was rated for comparison. Ten arterial segments were assessed: common superficial temporal arteries, temporal and parietal branches, occipital and posterior auricular arteries bilaterally. The expert clinical diagnosis after ≥6 months of follow-up was the diagnostic reference standard. Diagnostic accuracy was evaluated for different rating methods.

RESULTS

The study cohort consisted of 87 patients with and 69 without GCA. For DWI, the area under the curve was 0.90. For a cut-off of ≥2 consecutive pathological slices, DWI showed a sensitivity of 75.9%, a specificity of 94.2% and a positive likelihood ratio of 13.09. With a cut-off of ≥3 consecutive pathological slices, sensitivity was 70.1%, specificity was 98.6% and the positive likelihood ratio was 48.38. For the T1-BB, values were 88.5%, 88.4% and 7.63, respectively. The inter-rater analysis for DWI with a cut-off of ≥2 pathological slices showed a kappa of 1.00 on the patient level and 0.85 on the arterial segment level. For the T1-BB the kappa was 0.78 and 0.79, respectively.

CONCLUSION

DWI of the superficial cranial arteries demonstrates a good diagnostic accuracy and reliability for the diagnosis of GCA. DWI is widely available and can be used immediately in clinical practice for patients with suspected GCA.

Diagnostic yield of dental radiography and digital tomosynthesis for the identification of anatomic structures in cats

Introduction

Digital tomosynthesis (DT) has emerged as a potential imaging modality for evaluating anatomic structures in veterinary medicine. This study aims to validate the diagnostic yield of DT in identifying predefined anatomic structures in feline cadaver heads, comparing it with conventional intraoral dental radiography (DR).

Methods

A total of 16 feline cadaver heads were utilized to evaluate 19 predefined clinically relevant anatomic structures using both DR and DT. A semi-quantitative scoring system was employed to characterize the ability of each imaging method to identify these structures.

Results

DT demonstrated a significantly higher diagnostic yield compared to DR for all evaluated anatomic structures. Orthogonal DT imaging identified 13 additional anatomic landmarks compared to a standard 10-view feline set obtained via DR. Moreover, DT achieved statistically significant higher scores for each of these landmarks, indicating improved visualization over DR.

Discussion

These findings validate the utility of DT technology in reliably identifying clinically relevant anatomic structures in the cat skull. This validation serves as a foundation for further exploration of DT imaging in detecting dentoalveolar and other maxillofacial bony lesions and pathologies in cats.

Urothelial Carcinoma: Epidemiology and Imaging-Based Review

Bladder cancer is the 6th most common malignancy in the United States, with urothelial carcinomas comprising over 95% of cases of bladder cancer, and commands a significant disease burden in Rhode Island. Imaging studies can provide valuable diagnostic information for urothelial carcinomas at initial presentation and are routinely used for noninvasive staging, treatment response monitoring, and post-treatment surveillance. This review aims to discuss and highlight three imaging modalities: ultrasonography, computed tomography, and magnetic resonance imaging, with particular focus on the notable features and appearance of urothelial carcinoma on each modality and their relative utility throughout the disease course. A general overview of disease epidemiology and treatment practices is also provided.

An actively stabilized, miniaturized epi-fluorescence widefield microscope for real-time observation in vivo

Recent developments in real-time, in vivo micro-imaging have allowed for the visualization of tissue pathological changes, facilitating rapid diagnosis. However, miniaturization, magnification, the field of view, and in vivo image stabilization remain challenging factors to reconcile. A key issue for this technology is ensuring it is user friendly for surgeons, enabling them to use the device manually and obtain instantaneous information necessary for surgical decision-making. This descriptive study introduces a handheld, actively stabilized, miniaturized epi-fluorescence widefield microscope (MEW-M) for real-time observation in vivo with high resolution. The methodology of MEW-M system includes high resolution microscopy miniaturization technology, thousandfold shaking suppression (actively stabilized), ultra-photosensitivity, and tailored image signal processing cell image capture and processing technology, which support for the excellent real-time imaging performance of MEW-M system in brain, mammary, liver, lung, and kidney tissue imaging of rats in vivo. With a single-objective and high-frame-rate imaging, the MEW-M system facilitates roving image acquisition, enabling contiguous analysis of large tissue areas. RESEARCH HIGHLIGHTS: A handheld, actively stabilized MEW-M system was introduced. Excellent real-time, in vivo imaging with high resolution and active stabilization in brain, mammary, liver, lung, and kidney tissue of rats.

Gait pattern in patients treated with a total hip arthroplasty due to an acute displaced cervical neck fracture: a randomised comparison between 29 cases with a cemented femoral stem and 16 cases with an uncemented femoral stem

BACKGROUND

The choice between cemented or uncemented stem fixation in the treatment of a femoral neck fracture may influence patient rehabilitation and the resulting gait pattern, due to potential differences in implant positioning and fixation. We used gait analysis to study temporal gait parameters, hip kinematics and kinetics in patients who, 2 years previously, had been randomised to treatment with a cemented or uncemented stem and due to an acute femoral neck fracture.

METHODS

45 Patients implanted with a cemented Lubinus SP II (n = 29) and an uncemented (n = 16) Corail stem were studied. Gait analysis was performed using a 16-camera motion capture system and force plates. 28 subjects served as controls. Temporal gait parameters, hip kinematics and kinetics were analysed. The patients had no or minimum pain (median Harris pain score 44, range 40-44) and the majority had no limp (median Harris limp score 11, range 5-11).

RESULTS

Temporospatial gait parameters and abduction-adduction motions and moments did not differ between patients with cemented or uncemented stems (p > 0.05). Patients with cemented stems did, however, show more hip flexion and less extension during walking than those with an uncemented stem (p < 0.05). Moreover, the flexion-extension range was less in the cemented group (p < 0.04). Compared with controls, the hip fracture patients walked more slowly, with a shorter stride length and a longer stance phase.

CONCLUSIONS

Increased hip flexion and reduced extension in patients using the Lubinus SP II cemented stem could be an effect of its anteverted neck, but this question requires further study. Despite acute treatment with THA, hip fracture patients demonstrated a change in gait pattern compared with controls 2 years after the operation. This suggests that these changes are caused by the presence of an implant, or the soft-tissue trauma partly caused by the surgery than by any degenerative disease present in patients undergoing elective surgery.ClinicalTrials.gov Identifier: NCT04791605.

Single Stance Radiography of the Knee Joint - A Novel Approach to Assess the Degree of Knee Osteoarthritis

Introduction

Conventional radiography has always been cited as the gold standard for assessing the structural changes associated with osteoarthritis (OA) of the knee. The purpose of the study was to compare the joint space width between both leg-standing and one-leg-standing radiographs in an assessment of the severity of OA of the knee.

Materials and Methods

Fifty patients with medial compartment OA were deployed for the study. Patients underwent both leg standing radiographs and one-leg standing radiograph on the affected leg. Kellgren-Lawrence (KL) radiographic classification was used to assess the severity of OA using joint space width.

Conclusion

The mean medial joint space width decreased from 3.26 mm in both legs of the standing radiograph to 1.98 mm in the one-leg standing radiograph. Patients on both leg standing radiographs appreciated an increase in grade during the single leg radiograph. Nearly 52% of patients with both leg standing radiographs have changed the KL grading to a more severe grade when undergone a single leg standing radiograph. One-leg standing radiograph was found to be a better representation of joint space width than both-leg standing radiographs.

Association Between Weightbearing CT and MRI Findings in Progressive Collapsing Foot Deformity

BACKGROUND

Weightbearing computed tomography (WBCT) scans allow for a better understanding of foot alignment in patients suffering from progressive collapsing foot deformity (PCFD). However, soft tissue integrity (eg, spring ligament complex or tibialis posterior tendon) cannot be easily assessed via WBCT. As performing both WBCT and magnetic resonance imaging (MRI) might not be cost effective, we aimed to assess whether there is an association between osseous and soft tissue findings in WBCT and MRI.

METHODS

In this observational study, a consecutive cohort of 24 patients of various stages of PCFD (mean age 51 ± 18 years) underwent WBCT scans and MRI. Twenty-four healthy individuals of similar age, body mass index (BMI), and sex with WBCT scans were used as a control group. In addition to of osseous sinus tarsi impingement, 4 commonly used 3-dimensional (3D) measurements (talocalcaneal overlap [TCO], talonavicular coverage [TNC], Meary angle [MA], axial/lateral) were obtained using a dedicated postprocessing software (DISIOR 2.1, Finland) on the WBCT data sets. Sinus tarsi obliteration, spring ligament complex, tibiospring ligament integrity, as well as tibialis posterior tendon degeneration were evaluated with MRI. Statistical analysis was performed for significant (P < .05) correlation between findings.

RESULTS

None of the assessed 3D measurements correlated with either spring ligament complex or tibiospring ligament tears. BMI and TCO were found to be associated with tibialis posterior tendon tears. Seventy-five percent of patients with osseous sinus tarsi impingement on WBCT also showed signs of sinus tarsi obliteration on MRI.

CONCLUSION

Although WBCT reflects foot alignment and can reveal osseous sinus tarsi impingement in PCFD patients, the association between WBCT-based 3D measurements and ligament or tendon tears assessed via MRI is limited. WBCT appears complimentary to MRI regarding its diagnostic value. Both imaging options add important information and may impact decision making in the treatment of PCFD patients.

LEVEL OF EVIDENCE

Level IV, observational study.

Improving the spatial resolution and signal-to-noise ratio of ultrasound switchable fluorescence imaging

Ultrasound switchable fluorescence (USF) imaging, a hybrid imaging technology that combines the advantages of both fluorescence sensitivity and acoustic resolution in centimeter-deep tissue, has great potential for biomedical different applications. A camera-based USF imaging system reveals its capability of capturing both spatial and temporal dynamics of the USF signal in tissue. In this study, various algorithms were explored to enhance the spatial resolution and signal-to-noise ratio (SNR) of USF images, utilizing temporal and spatial information from a camera-based time-domain USF imaging system. The correlation method proved effective in boosting SNR, while the ascending-slope-weighted method enhanced spatial resolution. Additionally, the spatially back-projection method significantly improved spatial resolution in silicone phantoms. The results underscore the advantages of incorporating temporal and spatial information from USF signals.

Facts and Hopes in Using Omics to Advance Combined Immunotherapy Strategies

The field of oncology has been transformed by immune checkpoint inhibitors (ICI) and other immune-based agents; however, many patients do not receive a durable benefit. While biomarker assessments from pivotal ICI trials have uncovered certain mechanisms of resistance, results thus far have only scraped the surface. Mechanisms of resistance are as complex as the tumor microenvironment (TME) itself, and the development of effective therapeutic strategies will only be possible by building accurate models of the tumor-immune interface. With advancement of multi-omic technologies, high-resolution characterization of the TME is now possible. In addition to sequencing of bulk tumor, single-cell transcriptomic, proteomic, and epigenomic data as well as T-cell receptor profiling can now be simultaneously measured and compared between responders and nonresponders to ICI. Spatial sequencing and imaging platforms have further expanded the dimensionality of existing technologies. Rapid advancements in computation and data sharing strategies enable development of biologically interpretable machine learning models to integrate data from high-resolution, multi-omic platforms. These models catalyze the identification of resistance mechanisms and predictors of benefit in ICI-treated patients, providing scientific foundation for novel clinical trials. Moving forward, we propose a framework by which in silico screening, functional validation, and clinical trial biomarker assessment can be used for the advancement of combined immunotherapy strategies.

Diagnostic Performance of Artificial Intelligence for Detection of Scaphoid and Distal Radius Fractures: A Systematic Review

PURPOSE

To review the existing literature to (1) determine the diagnostic efficacy of artificial intelligence (AI) models for detecting scaphoid and distal radius fractures and (2) compare the efficacy to human clinical experts.

METHODS

PubMed, OVID/Medline, and Cochrane libraries were queried for studies investigating the development, validation, and analysis of AI for the detection of scaphoid or distal radius fractures. Data regarding study design, AI model development and architecture, prediction accuracy/area under the receiver operator characteristic curve (AUROC), and imaging modalities were recorded.

RESULTS

A total of 21 studies were identified, of which 12 (57.1%) used AI to detect fractures of the distal radius, and nine (42.9%) used AI to detect fractures of the scaphoid. AI models demonstrated good diagnostic performance on average, with AUROC values ranging from 0.77 to 0.96 for scaphoid fractures and from 0.90 to 0.99 for distal radius fractures. Accuracy of AI models ranged between 72.0% to 90.3% and 89.0% to 98.0% for scaphoid and distal radius fractures, respectively. When compared to clinical experts, 13 of 14 (92.9%) studies reported that AI models demonstrated comparable or better performance. The type of fracture influenced model performance, with worse overall performance on occult scaphoid fractures; however, models trained specifically on occult fractures demonstrated substantially improved performance when compared to humans.

CONCLUSIONS

AI models demonstrated excellent performance for detecting scaphoid and distal radius fractures, with the majority demonstrating comparable or better performance compared with human experts. Worse performance was demonstrated on occult fractures. However, when trained specifically on difficult fracture patterns, AI models demonstrated improved performance.

CLINICAL RELEVANCE

AI models can help detect commonly missed occult fractures while enhancing workflow efficiency for distal radius and scaphoid fracture diagnoses. As performance varies based on fracture type, future studies focused on wrist fracture detection should clearly define whether the goal is to (1) identify difficult-to-detect fractures or (2) improve workflow efficiency by assisting in routine tasks.