Recommender-based bone tumour classification with radiographs-a link to the past

OBJECTIVES

To develop an algorithm to link undiagnosed patients to previous patient histories based on radiographs, and simultaneous classification of multiple bone tumours to enable early and specific diagnosis.

MATERIALS AND METHODS

For this retrospective study, data from 2000 to 2021 were curated from our database by two orthopaedic surgeons, a radiologist and a data scientist. Patients with complete clinical and pre-therapy radiographic data were eligible. To ensure feasibility, the ten most frequent primary tumour entities, confirmed histologically or by tumour board decision, were included. We implemented a ResNet and transformer model to establish baseline results. Our method extracts image features using deep learning and then clusters the k most similar images to the target image using a hash-based nearest-neighbour recommender approach that performs simultaneous classification by majority voting. The results were evaluated with precision-at-k, accuracy, precision and recall. Discrete parameters were described by incidence and percentage ratios. For continuous parameters, based on a normality test, respective statistical measures were calculated.

RESULTS

Included were data from 809 patients (1792 radiographs; mean age 33.73 ± 18.65, range 3-89 years; 443 men), with Osteochondroma (28.31%) and Ewing sarcoma (1.11%) as the most and least common entities, respectively. The dataset was split into training (80%) and test subsets (20%). For k = 3, our model achieved the highest mean accuracy, precision and recall (92.86%, 92.86% and 34.08%), significantly outperforming state-of-the-art models (54.10%, 55.57%, 19.85% and 62.80%, 61.33%, 23.05%).

CONCLUSION

Our novel approach surpasses current models in tumour classification and links to past patient data, leveraging expert insights.

CLINICAL RELEVANCE STATEMENT

The proposed algorithm could serve as a vital support tool for clinicians and general practitioners with limited experience in bone tumour classification by identifying similar cases and classifying bone tumour entities.

KEY POINTS

• Addressed accurate bone tumour classification using radiographic features. • Model achieved 92.86%, 92.86% and 34.08% mean accuracy, precision and recall, respectively, significantly surpassing state-of-the-art models. • Enhanced diagnosis by integrating prior expert patient assessments.

Deep Learning-Based Detection of Bone Tumors around the Knee in X-rays of Children

Even though tumors in children are rare, they cause the second most deaths under the age of 18 years. More often than in other age groups, underage patients suffer from malignancies of the bones, and these mostly occur in the area around the knee. One problem in the treatment is the early detection of bone tumors, especially on X-rays. The rarity and non-specific clinical symptoms further prolong the time to diagnosis. Nevertheless, an early diagnosis is crucial and can facilitate the treatment and therefore improve the prognosis of affected children. A new approach to evaluating X-ray images using artificial intelligence may facilitate the detection of suspicious lesions and, hence, accelerate the referral to a specialized center. We implemented a Vision Transformer model for image classification of healthy and pathological X-rays. To tackle the limited amount of data, we used a pretrained model and implemented extensive data augmentation. Discrete parameters were described by incidence and percentage ratio and continuous parameters by median, standard deviation and variance. For the evaluation of the model accuracy, sensitivity and specificity were computed. The two-entity classification of the healthy control group and the pathological group resulted in a cross-validated accuracy of 89.1%, a sensitivity of 82.2% and a specificity of 93.2% for test groups. Grad-CAMs were created to ensure the plausibility of the predictions. The proposed approach, using state-of-the-art deep learning methodology to detect bone tumors on knee X-rays of children has achieved very good results. With further improvement of the algorithm, enlargement of the dataset and removal of potential biases, this could become a useful additional tool, especially to support general practitioners for early, accurate and specific diagnosis of bone lesions in young patients.

Differentiating Enchondromas and Atypical Cartilaginous Tumors in Long Bones with Computed Tomography and Magnetic Resonance Imaging

The differentiation between the atypical cartilaginous tumor (ACT) and the enchondromas is crucial as ACTs require a curettage and clinical as well as imaging follow-ups, whereas in the majority of cases enchondromas require neither a treatment nor follow-ups. Differentiating enchondromas from ACTs radiologically remains challenging. Therefore, this study evaluated imaging criteria in a combination of computed tomography (CT) and magnetic resonance (MR) imaging for the differentiation between enchondromas and ACTs in long bones. A total of 82 patients who presented consecutively at our institution with either an ACT (23, age 52.7 ±18.8 years; 14 women) or an enchondroma (59, age 46.0 ± 11.1 years; 37 women) over a period of 10 years, who had undergone preoperative MR and CT imaging and subsequent biopsy or/and surgical removal, were included in this study. A histopathological diagnosis was available in all cases. Two experienced radiologists evaluated several imaging criteria on CT and MR images. Likelihood of an ACT was significantly increased if either edema within the bone (p = 0.049), within the adjacent soft tissue (p = 0.006) or continuous growth pattern (p = 0.077) were present or if the fat entrapment (p = 0.027) was absent on MR images. Analyzing imaging features on CT, the likelihood of the diagnosis of an ACT was significantly increased if endosteal scalloping >2/3 (p < 0.001), cortical penetration (p < 0.001) and expansion of bone (p = 0.002) were present and if matrix calcifications were observed in less than 1/3 of the tumor (p = 0.013). All other imaging criteria evaluated showed no significant influence on likelihood of ACT or enchondroma (p > 0.05). In conclusion, both CT and MR imaging show suggestive signs which can help to adequately differentiate enchondromas from ACTs in long bones and therefore can improve diagnostics and consequently patient management. Nevertheless, these features are rare and a combination of CT and MR imaging features did not improve the diagnostic performance substantially.

Detection and Segmentation of Heterogeneous Bone Tumours in Limited Radiographs

Bone tumours are a rare and often highly malignant entity. Early clinical diagnosis is the most important step, but the difficulty of detecting and assessing bone malignancies is in its radiological peculiarity and limited experience of non-experts. Since X-ray imaging is the first imaging method of bone tumour diagnostics, the purpose of this study is to develop an artificial intelligence (AI) model to detect and segment the tumorous tissue in a radiograph. We investigated which methods are necessary to cope with limited and heterogeneous data. We collected 531 anonymised radiographs from our musculoskeletal tumour centre. In order to adapt to the complexity of recognizing the malignant tissue and cope with limited data, transfer learning, data augmentation as well as several architectures, some of which were initially designed for medical images, were implemented. Furthermore, dataset size was varied by adding another bone tumour entity. We applied a data split of 72%, 18%, 10% for training, validation and testing, respectively. To provide statistical significance and robustness, we applied a cross-validation and image stratification with respect to tumour pixels present. We achieved an accuracy of 99.72% and an intersection over union of 87.43% for hold-out test data by applying several methods to tackle limited data. Transfer learning and additional data brought the greatest performance increase. In conclusion, our model was able to detect and segment tumorous tissue in radiographs with good performance, although it was trained on a very limited amount of data. Transfer Learning and data augmentation proved to significantly mitigate the issue of limited data samples. However, to accomplish clinical significance, more data has to be acquired in the future. Through minor adjustments, the model could be adapted to other musculoskeletal tumour entities and become a general support tool for orthopaedic surgeons and radiologists.

[Total endoprosthetic replacement of femur, humerus and tibia]

Improvements in diagnostics and effectiveness of chemotherapy have resulted in most patients with primary malignant bone tumours being candidates for limb salvage surgery. Herewith, the use of modern modular tumour endoprostheses allows for the replacement of all big joints and even entire long bones such as the femur, humerus and tibia. In this article, we focus on individual prerequisites for and challenges with performing a total endoprosthetic reconstruction of the above-mentioned anatomic structures. Additionally, data from the literature with regards to functional outcome, problems and complications are presented.

Periprosthetic bone quality affects the fixation of anatomic glenoids in total shoulder arthroplasty: in vitro study

BACKGROUND

Glenoid loosening, a common complication of shoulder arthroplasty, could relate to implant design and bone quality. However, the role of bone density has not been tested experimentally yet. In this study, tests on cadaveric specimens of varying bone density were performed to evaluate the effects of bone quality on loosening of typical anatomic glenoid implants.

METHODS

Cadaveric scapulae scanned with a quantitative computed tomography scanner to determine bone mineral density (BMD) were implanted with either pegged or keeled cemented glenoid components and tested under constant glenohumeral load while a humeral head component was moved cyclically in the inferior and superior directions. Implant superior and inferior edge lifting, defined as displacement from the underlying bone, was measured with linear variable differential transducers until we reached 23,000 test cycles, and statistical testing was performed for differences in edge lifting due to implant design and related to periprosthetic BMD.

RESULTS

Edge lifting was statistically significant at all time points, but on average, implant design had no effect. Lifting was highest in specimens in which BMD below the lifting edge was lower, with trends of increased displacement with decreased BMD.

CONCLUSIONS

Implant lifting was greater in glenoids of lower bone density for both implant designs. This finding suggests that fixation failure will most likely occur in bone of lower density and that the fixation design itself may play a secondary role.