Search

Objective: To evaluate the performance of a deep learning (DL) model in an external dataset to assess radiographic knee osteoarthritis using Kellgren-Lawrence (KL) grades against versatile human readers. Materials and methods: Two-hundred-eight knee anteroposterior conventional radiographs (CRs) were included in this retrospective study. Four readers (three radiologists, one orthopedic surgeon) assessed the KL grades and consensus grade was derived as the mean of these. The DL model was trained using all the CRs from Multicenter Osteoarthritis Study (MOST) and validated on Osteoarthritis Initiative (OAI) dataset and then tested on our external dataset. To assess the agreement between the graders, Cohen's quadratic kappa (k) with 95 ​% confidence intervals were used. Diagnostic performance was measured using confusion matrices and receiver operating characteristic (ROC) analyses. Results: The multiclass (KL grades from 0 to 4) diagnostic performance of the DL model was multifaceted: sensitivities were between 0.372 and 1.000, specificities 0.691–0.974, PPVs 0.227–0.879, NPVs 0.622–1.000, and AUCs 0.786–0.983. The overall balanced accuracy was 0.693, AUC 0.886, and kappa 0.820. If only dichotomous KL grading (i.e. KL0-1 vs. KL2-4) was utilized, superior metrics were seen with an overall balanced accuracy of 0.902 and AUC of 0.967. A substantial agreement between each reader and DL model was found: the inter-rater agreement was 0.737 [0.685–0.790] for the radiology resident, 0.761 [0.707–0.816] for the musculoskeletal radiology fellow, 0.802 [0.761–0.843] for the senior musculoskeletal radiologist, and 0.818 [0.775–0.860] for the orthopedic surgeon. Conclusion: In an external dataset, our DL model can grade knee osteoarthritis with diagnostic accuracy comparable to highly experienced human readers.

Abstract To evaluate the acoustic emissions (AE) and kinematic instability (KI) of the osteoarthritic (OA) knee joints, and to compare these signals to radiographic findings. Sixty-six female and 43 male participants aged 44–67 were recruited. On radiography, joint-space narrowing, osteophytes and Kellgren–Lawrence (KL) grade were evaluated. Based on radiography, 54 subjects (the study group) were diagnosed with radiographic OA (KL-grade ≥ 2) while the remaining 55 subjects (KL-grade

Abstract Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection—DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set—average precision of 0.99 (0.99–0.99) versus 0.64 (0.46–0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98–0.99) versus 0.84 (0.72–0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems.

Abstract The treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin–eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning–predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63–0.77) on 354 TMA samples and 0.67 (95% CI, 0.62–0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology–based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15–0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer.

Knee osteoarthritis (OA) is the most common musculoskeletal disease in the world. In primary healthcare, knee OA is diagnosed using clinical examination and radiographic assessment. Osteoarthritis Research Society International (OARSI) atlas of OA radiographic features allows performing independent assessment of knee osteophytes, joint space narrowing and other knee features. This provides a fine-grained OA severity assessment of the knee, compared to the gold standard and most commonly used Kellgren–Lawrence (KL) composite score. In this study, we developed an automatic method to predict KL and OARSI grades from knee radiographs. Our method is based on Deep Learning and leverages an ensemble of residual networks with 50 layers. We used transfer learning from ImageNet with a fine-tuning on the Osteoarthritis Initiative (OAI) dataset. An independent testing of our model was performed on the Multicenter Osteoarthritis Study (MOST) dataset. Our method yielded Cohen’s kappa coefficients of 0.82 for KL-grade and 0.79, 0.84, 0.94, 0.83, 0.84 and 0.90 for femoral osteophytes, tibial osteophytes and joint space narrowing for lateral and medial compartments, respectively. Furthermore, our method yielded area under the ROC curve of 0.98 and average precision of 0.98 for detecting the presence of radiographic OA, which is better than the current state-of-the-art.

Study Design.: This is a retrospective observational study to externally validate a deep learning image classification model. Objective.: Deep learning models such as SpineNet offer the possibility of automating the process of disk degeneration (DD) classification from magnetic resonance imaging (MRI). External validation is an essential step to their development. The aim of this study was to externally validate SpineNet predictions for DD using Pfirrmann classification and Modic changes (MCs) on data from the Northern Finland Birth Cohort 1966 (NFBC1966). Summary of Data.: We validated SpineNet using data from 1331 NFBC1966 participants for whom both lumbar spine MRI data and consensus DD gradings were available. Materials and Methods.: SpineNet returned Pfirrmann grade and MC presence from T2-weighted sagittal lumbar MRI sequences from NFBC1966, a data set geographically and temporally separated from its training data set. A range of agreement and reliability metrics were used to compare predictions with expert radiologists. Subsets of data that match SpineNet training data more closely were also tested. Results.: Balanced accuracy for DD was 78% (77%–79%) and for MC 86% (85%–86%). Interrater reliability for Pfirrmann grading was Lin concordance correlation coefficient=0.86 (0.85–0.87) and Cohen κ=0.68 (0.67–0.69). In a low back pain subset, these reliability metrics remained largely unchanged. In total, 20.83% of disks were rated differently by SpineNet compared with the human raters, but only 0.85% of disks had a grade difference >1. Interrater reliability for MC detection was κ=0.74 (0.72–0.75). In the low back pain subset, this metric was almost unchanged at κ=0.76 (0.73–0.79). Conclusions.: In this study, SpineNet has been benchmarked against expert human raters in the research setting. It has matched human reliability and demonstrates robust performance despite the multiple challenges facing model generalizability. [ABSTRACT FROM AUTHOR]

Morphological changes in knee cartilage subregions are valuable imaging‐based biomarkers for understanding progression of osteoarthritis, and they are typically detected from magnetic resonance imaging (MRI). So far, accurate segmentation of cartilage has been done manually. Deep learning approaches show high promise in automating the task; however, they lack clinically relevant evaluation. We introduce a fully automatic method for segmentation and subregional assessment of articular cartilage, and evaluate its predictive power in context of radiographic osteoarthritis progression. Two data sets of 3D double‐echo steady‐state (DESS) MRI derived from the Osteoarthritis Initiative were used: first, n = 88; second, n = 600, 0‐/12‐/24‐month visits. Our method performed deep learning‐based segmentation of knee cartilage tissues, their subregional division via multi‐atlas registration, and extraction of subregional volume and thickness. The segmentation model was developed and assessed on the first data set. Subsequently, on the second data set, the morphological measurements from our and the prior methods were analyzed in correlation and agreement, and, eventually, by their discriminative power of radiographic osteoarthritis progression over 12 and 24 months, retrospectively. The segmentation model showed very high correlation (r > 0.934) and agreement (mean difference < 116 mm3) in volumetric measurements with the reference segmentations. Comparison of our and manual segmentation methods yielded r = 0.845–0.973 and mean differences = 262–501 mm3 for weight‐bearing cartilage volume, and r = 0.770–0.962 and mean differences = 0.513–1.138 mm for subregional cartilage thickness. With regard to osteoarthritis progression, our method found most of the significant associations identified using the manual segmentation method, for both 12‐ and 24‐month subregional cartilage changes. The method may be effectively applied in osteoarthritis progression studies to extract cartilage‐related imaging biomarkers. [ABSTRACT FROM AUTHOR]

To evaluate the acoustic emissions (AE) and kinematic instability (KI) of the osteoarthritic (OA) knee joints, and to compare these signals to radiographic findings. Sixty-six female and 43 male participants aged 44–67 were recruited. On radiography, joint-space narrowing, osteophytes and Kellgren–Lawrence (KL) grade were evaluated. Based on radiography, 54 subjects (the study group) were diagnosed with radiographic OA (KL-grade ≥ 2) while the remaining 55 subjects (KL-grade < 2) formed the control group. AE and KI were recorded with a custom-made prototype and compared with radiographic findings using area-under-curve (AUC) and independent T-test. Predictive logistic regression models were constructed using leave-one-out cross validation. In females, the parameters reflecting consistency of the AE patterns during specific tasks, KI, BMI and age had a significant statistical difference between the OA and control groups (p = 0.001–0.036). The selected AE signals, KI, age and BMI were used to construct a predictive model for radiographic OA with AUC of 90.3% (95% CI 83.5–97.2%) which showed a statistical improvement of the reference model based on age and BMI, with AUC of 84.2% (95% CI 74.8–93.6%). In males, the predictive model failed to improve the reference model. AE and KI provide complementary information to detect radiographic knee OA in females. [ABSTRACT FROM AUTHOR]

Structural dynamics of calcified cartilage (CC) are poorly understood. Conventionally, CC structure is analyzed using histological sections. Micro‐computed tomography (µCT) allows for three‐dimensional (3D) imaging of mineralized tissues; however, the segmentation between bone and mineralized cartilage is challenging. Here, we present state‐of‐the‐art deep learning segmentation for µCT images to assess 3D CC morphology. The sample includes 16 knees from 12 New Zealand White rabbits dissected into osteochondral samples from six anatomical regions: lateral and medial femoral condyles, lateral and medial tibial plateaus, femoral groove, and patella (n = 96). The samples were imaged with µCT and processed for conventional histology. Manually segmented CC from the images was used to train segmentation models with different encoder–decoder architectures. The models with the greatest out‐of‐fold evaluation Dice score were selected. CC thickness was compared across 24 regions, co‐registered between the imaging modalities using Pearson correlation and Bland–Altman analyses. Finally, the anatomical CC thickness variation was assessed via a Linear Mixed Model analysis. The best segmentation models yielded average Dice of 0.891 and 0.807 for histology and µCT segmentation, respectively. The correlation between the co‐registered regions was strong (r = 0.897, bias = 21.9 µm, standard deviation = 21.5 µm). Finally, both methods could separate the CC thickness between the patella, femoral, and tibial regions (p < 0.001). As a conclusion, the proposed µCT analysis allows for ex vivo 3D assessment of CC morphology. We demonstrated the biomedical relevance of the method by quantifying CC thickness in different anatomical regions with a varying mean thickness. CC was thickest in the patella and thinnest in the tibial plateau. Our method is relatively straightforward to implement into standard µCT analysis pipelines, allowing the analysis of CC morphology. In future research, µCT imaging might be preferable to histology, especially when analyzing dynamic changes in cartilage mineralization. It could also provide further understanding of 3D morphological changes that may occur in mineralized cartilage, such as thickening of the subchondral plate in osteoarthritis and other joint diseases. [ABSTRACT FROM AUTHOR]

Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection—DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set—average precision of 0.99 (0.99–0.99) versus 0.64 (0.46–0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98–0.99) versus 0.84 (0.72–0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems. [ABSTRACT FROM AUTHOR]

The treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin–eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning–predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63–0.77) on 354 TMA samples and 0.67 (95% CI, 0.62–0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology–based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15–0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer. [ABSTRACT FROM AUTHOR]

Knee osteoarthritis (OA) is one of the highest disability factors in the world. This musculoskeletal disorder is assessed from clinical symptoms, and typically confirmed via radiographic assessment. This visual assessment done by a radiologist requires experience, and suffers from moderate to high inter-observer variability. The recent literature has shown that deep learning methods can reliably perform the OA severity assessment according to the gold standard Kellgren-Lawrence (KL) grading system. However, these methods require large amounts of labeled data, which are costly to obtain. In this study, we propose the Semixup algorithm, a semi-supervised learning (SSL) approach to leverage unlabeled data. Semixup relies on consistency regularization using in- and out-of-manifold samples, together with interpolated consistency. On an independent test set, our method significantly outperformed other state-of-the-art SSL methods in most cases. Finally, when compared to a well-tuned fully supervised baseline that yielded a balanced accuracy (BA) of 70.9 ± 0.8% on the test set, Semixup had comparable performance - BA of 71 ± 0.8% (${p}=0.368$) while requiring 6 times less labeled data. These results show that our proposed SSL method allows building fully automatic OA severity assessment tools with datasets that are available outside research settings. [ABSTRACT FROM AUTHOR]

Summary: Background: In horses, osteoarthritis (OA) mostly affects metacarpophalangeal and metatarsophalangeal (fetlock) joints. The current modalities used for diagnosis of equine limb disorders lack ability to detect early OA. Here, we propose a new alternative approach to assess experimental cartilage damage in fetlock joint using Acoustic Emissions (AE). Objectives: To evaluate the potential of AE technique in diagnosing OA and see how AE signals changes with increasing severity of OA. Study design: An in vitro experimental study. Methods: A total of 16 distal limbs (8 forelimbs and 8 hindlimbs) from six Finn horses were collected from an abattoir and fitted in a custom‐made frame allowing fetlock joint bending. Eight fetlock joints were opened, and cartilage surface was progressively damaged mechanically three times using sandpaper to mimic mild, moderate and severe OA. The remaining eight fetlock joints were opened and closed without any mechanical procedure, serving as controls. Before cartilage alteration, synovial fluid was aspirated, mixed with phosphate‐buffered saline solution, and then reinjected before suturing for constant joint lubrication. For each simulated condition of OA severity, a force was applied to the frame and then released to mimic joint flexion and extension. AE signals were acquired using air microphones. Results: A strong association was found between the joint condition and the power of AE signals analysed in 1.5–6 kHz range. The signal from both forelimb and hindlimb joints followed a similar pattern for increased cartilage damage. There were statistically significant differences between each joint condition progressively (generalised linear mixed model, P<0.001) in limbs with in vitro cartilage damage of varying severity while the control limbs did not show any changes. Main limitations: Small sample size using in vitro, mechanically induced cartilage damage. Conclusion: The AE technique presented here could differentiate the severity of fetlock joint cartilage damage. The consistent results for each simulated condition suggest there is potential for this method in the diagnosis of OA. [ABSTRACT FROM AUTHOR]

Knee osteoarthritis (OA) is the most common musculoskeletal disease without a cure, and current treatment options are limited to symptomatic relief. Prediction of OA progression is a very challenging and timely issue, and it could, if resolved, accelerate the disease modifying drug development and ultimately help to prevent millions of total joint replacement surgeries performed annually. Here, we present a multi-modal machine learning-based OA progression prediction model that utilises raw radiographic data, clinical examination results and previous medical history of the patient. We validated this approach on an independent test set of 3,918 knee images from 2,129 subjects. Our method yielded area under the ROC curve (AUC) of 0.79 (0.78–0.81) and Average Precision (AP) of 0.68 (0.66–0.70). In contrast, a reference approach, based on logistic regression, yielded AUC of 0.75 (0.74–0.77) and AP of 0.62 (0.60–0.64). The proposed method could significantly improve the subject selection process for OA drug-development trials and help the development of personalised therapeutic plans. [ABSTRACT FROM AUTHOR]

Introduction: The relevance of spine MRI data to understanding low back pain (LBP) is questioned but it remains one of the few ways to assess pathoanatomical features of the condition. A need for more reliable quantitative interpretation of clinical MRI data has arisen in step with growing interest in the genetic architecture of LBP and associated systemic and immunometablolic factors. Methods: We aim to quantitatively classify disc degeneration (DD) imaging phenotypes using deep learning (DL). We have identified from the Northern Finland Birth Cohort target phenotypes derived from qualitative DD schemas and Modic change size. We will use DL and radiomic analysis to train models classifying these target phenotypes, externally validated on TwinsUK. We will then use the results to refine phenotype definitions. These data-driven phenotypes will be investigated in genome wide association studies (GWAS) to locate associated single nucleotide polymorphisms and immunometabolic pathways. Results: We expect the resultant model to accurately classify DD phenotypes, allowing coding of large cohorts for GWAS and other data-driven approaches identifying biological aspects of LBP. Discussion: For MRI to benefit LBP sufferers, quantitative approaches to interpretation are needed. DL can contribute to effective sub-grouping based on MRI that can impact both research and clinical management. Process evaluation: This study is limited by analysing MRI data independent of psychosocial and systemic variables. Future DL studies should tackle this with multimodal solutions. [ABSTRACT FROM AUTHOR]

Knee osteoarthritis (OA) is the most common musculoskeletal disease in the world. In primary healthcare, knee OA is diagnosed using clinical examination and radiographic assessment. Osteoarthritis Research Society International (OARSI) atlas of OA radiographic features allows performing independent assessment of knee osteophytes, joint space narrowing and other knee features. This provides a fine-grained OA severity assessment of the knee, compared to the gold standard and most commonly used Kellgren–Lawrence (KL) composite score. In this study, we developed an automatic method to predict KL and OARSI grades from knee radiographs. Our method is based on Deep Learning and leverages an ensemble of residual networks with 50 layers. We used transfer learning from ImageNet with a fine-tuning on the Osteoarthritis Initiative (OAI) dataset. An independent testing of our model was performed on the Multicenter Osteoarthritis Study (MOST) dataset. Our method yielded Cohen's kappa coefficients of 0.82 for KL-grade and 0.79, 0.84, 0.94, 0.83, 0.84 and 0.90 for femoral osteophytes, tibial osteophytes and joint space narrowing for lateral and medial compartments, respectively. Furthermore, our method yielded area under the ROC curve of 0.98 and average precision of 0.98 for detecting the presence of radiographic OA, which is better than the current state-of-the-art. [ABSTRACT FROM AUTHOR]