A case of scapular metastasis from hepatocellular carcinoma.

.

[Applications of artificial intelligence for imaging-driven diagnosis and treatment of bone and soft tissue tumors].

Bone and soft tissue tumors occur in the musculoskeletal system, and malignant bone tumors of bone and soft tissue account for 0.2% of all human malignant tumors, and if not diagnosed and treated in a timely manner, patients may be at risk of a poor prognosis. Image interpretation plays an increasingly important role in the diagnosis of bone and soft tissue tumors. Artificial intelligence (AI) can be applied in clinical treatment to integrate large amounts of multidimensional data, derive models, predict outcomes, and improve treatment decisions. Among these methods, deep learning is a widely employed technique in AI that predominantly utilizes convolutional neural networks (CNN). The network is implemented through repeated training of datasets and iterative parameter adjustments. Deep learning-based AI models have successfully been applied to various aspects of bone and soft tissue tumors, encompassing but not limiting in image segmentation, tumor detection, classification, grading and staging, chemotherapy effect evaluation, recurrence and prognosis prediction. This paper provides a comprehensive review of the principles and current state of AI in the medical image diagnosis and treatment of bone and soft tissue tumors. Additionally, it explores the present challenges and future prospects in this field.

Monostotic femoral Caffey disease masquerading as Ewing sarcoma.

We describe a rare case of monostotic infantile cortical hyperostosis (Caffey disease) involving the left femur of an infant, who presented with recent onset left thigh swelling, following vaccination. Radiological workup showed a lamellated periosteal reaction involving the left femoral diaphysis on radiographs masquerading as a bone tumour. The child underwent MRI of the left thigh, which showed extensive muscle oedema without any abnormal soft-tissue proliferation, marrow signal alteration, cortical breach or collection. The follow-up radiograph showed exuberant new bone formation in the second week. The patient was given symptomatic treatment and the parents were counselled. The child recovered well with gradual resolution of symptoms and bony remodelling on a 6-month follow-up radiograph. Here, we describe the serial changes on the radiographs in Caffey disease with monostotic involvement and the role of MRI in difficult cases to differentiate it from other common mimickers, such as infections and neoplasia.

MR-guided Focused Ultrasound for Musculoskeletal Applications.

MR-guided focused ultrasound (MRgFUS) has a wide range of musculoskeletal applications. Some indications are well validated, specifically the treatment of painful osseous metastases and osteoid osteoma. Others are only beginning to be studied, such as the treatment of painful facet, sacroiliac, and knee joints. MRgFUS of soft tissue lesions also shows promise, particularly in patients whom alternative modalities are not feasible or may result in significant morbidity. Ongoing and future research will illuminate the full potential for MRgFUS in the treatment of musculoskeletal conditions.

Effect of PSMA PET/CT on the Use of Bone Scintigraphy for Prostate Cancer at a University Hospital System.

We observed at our university-based imaging centers that when prostate-specific membrane antigen (PSMA) PET/CT became available for staging and restaging prostate cancer, the volume of bone scanning on patients with prostate cancer (BS-P) markedly decreased. We aimed to study use patterns of PSMA PET/CT and BS-P at our imaging centers during the 4-y period around U.S. Food and Drug Administration approval of PSMA PET/CT in December 2020. We tested the hypothesis that the rate of decline of BS-P accelerated after U.S. Food and Drug Administration approval, as physicians planned for use of PSMA PET/CT in their patients. Methods: Our clinical report system was searched for BS-P and PSMA PET/CT scans from January 2019 through June 2023. Numbers of scans were tabulated by quarter and year. Quantitative and statistical analyses were performed. Results: Annualized average monthly BS-P peaked at 53.7 scans/mo in 2021 and then decreased over time. There were 552 BS-Ps performed in 2019, 503 in 2020, 614 in 2021, 481 in 2022, and 152 in the first half of 2023. BS-P monthly averages declined by 22% from 2021 to 2022 and by 36% from 2022 to 2023, whereas monthly PSMA PET/CT scan averages increased by 1,416% from 2021 to 2022 and by 69% from 2022 to 2023. There was a significantly greater decline in BS-Ps from 2022 to 2023 than from 2021 to 2022 (36% vs. 22%, P < 0.0001). There were 30 PSMA PET/CT scans performed in 2021, 455 in 2022, and 384 in the first half of 2023. The greatest quarterly increase in these scans (400%) occurred at the outset of PSMA PET/CT implementation in quarter 4 of 2021. In quarter 2 of 2023, the percentage of total studies was higher for PSMA PET/CT than for BS-P (74% vs. 26%, P < 0.0001). Conclusion: At our university-based imaging centers, use of BS-P has declined in correlation with the timing of U.S. Food and Drug Administration approval and implementation of PSMA PET/CT. This study illustrates one instance of workflow changes that occur in the nuclear medicine clinic when new agents are introduced and affect clinical management options.

Treatment of left tenth rib haemangioma vascularised by a costal artery giving the artery of Adamkiewicz.

Haemangioma of the ribs is considered an extremely rare benign tumour. Here, we present a case of a young male with left tenth rib haemangioma vascularised by a costal artery giving the artery of Adamkiewicz presented as chronic cough. This was successfully treated through preoperative embolisation and surgical resection. A preoperative angiogram was performed to identify the origin of the artery of Adamkiewicz. The final diagnosis was confirmed histopathologically. There were no complications in the postoperative course and no recurrence during 12 months of follow-up.

Clinical performance of deep learning-enhanced ultrafast whole-body scintigraphy in patients with suspected malignancy.

BACKGROUND: To evaluate the clinical performance of two deep learning methods, one utilizing real clinical pairs and the other utilizing simulated datasets, in enhancing image quality for two-dimensional (2D) fast whole-body scintigraphy (WBS). METHODS: A total of 83 patients with suspected bone metastasis were retrospectively enrolled. All patients underwent single-photon emission computed tomography (SPECT) WBS at speeds of 20 cm/min (1x), 40 cm/min (2x), and 60 cm/min (3x). Two deep learning models were developed to generate high-quality images from real and simulated fast scans, designated 2x-real and 3x-real (images from real fast data) and 2x-simu and 3x-simu (images from simulated fast data), respectively. A 5-point Likert scale was used to evaluate the image quality of each acquisition. Accuracy, sensitivity, specificity, and the area under the curve (AUC) were used to evaluate diagnostic efficacy. Learned perceptual image patch similarity (LPIPS) and the Fréchet inception distance (FID) were used to assess image quality. Additionally, the count-level consistency of WBS was compared between the two models. RESULTS: Subjective assessments revealed that the 1x images had the highest general image quality (Likert score: 4.40 ± 0.45). The 2x-real, 2x-simu and 3x-real, 3x-simu images demonstrated significantly better quality than the 2x and 3x images (Likert scores: 3.46 ± 0.47, 3.79 ± 0.55 vs. 2.92 ± 0.41, P < 0.0001; 2.69 ± 0.40, 2.61 ± 0.41 vs. 1.36 ± 0.51, P < 0.0001), respectively. Notably, the quality of the 2x-real images was inferior to that of the 2x-simu images (Likert scores: 3.46 ± 0.47 vs. 3.79 ± 0.55, P = 0.001). The diagnostic efficacy for the 2x-real and 2x-simu images was indistinguishable from that of the 1x images (accuracy: 81.2%, 80.7% vs. 84.3%; sensitivity: 77.27%, 77.27% vs. 87.18%; specificity: 87.18%, 84.63% vs. 87.18%. All P > 0.05), whereas the diagnostic efficacy for the 3x-real and 3x-simu was better than that for the 3x images (accuracy: 65.1%, 66.35% vs. 59.0%; sensitivity: 63.64%, 63.64% vs. 64.71%; specificity: 66.67%, 69.23% vs. 55.1%. All P < 0.05). Objectively, both the real and simulated models achieved significantly enhanced image quality from the accelerated scans in the 2x and 3x groups (FID: 0.15 ± 0.18, 0.18 ± 0.18 vs. 0.47 ± 0.34; 0.19 ± 0.23, 0.20 ± 0.22 vs. 0.98 ± 0.59. LPIPS: 0.17 ± 0.05, 0.16 ± 0.04 vs. 0.19 ± 0.05; 0.18 ± 0.05, 0.19 ± 0.05 vs. 0.23 ± 0.04. All P < 0.05). The count-level consistency with the 1x images was excellent for all four sets of model-generated images (P < 0.0001). CONCLUSIONS: Ultrafast 2x speed (real and simulated) images achieved comparable diagnostic value to that of standardly acquired images, but the simulation algorithm does not necessarily reflect real data.

Indications for nuclear medicine imaging in prostate cancer.

Nuclear medicine imaging for prostate cancer has advanced significantly over the past decade. A survey is presented in this review. PSMA-PET/CT is a new highly accurate method that has been introduced, but bone scans and bone-PET continue to be widely applied. PSMA-PET/CT still lacks sufficient patient outcome data to be recommended for treatment allocation when used for primary staging. However, the literature and clinical guidelines support its use at the stage of biochemical recurrence. In Denmark, the use of nuclear medicine examinations for prostate cancer aligns with clinical guideline recommendations.

When advanced MRI is not about naming musculoskeletal lesions.

Nowadays, the use of advanced MRI sequences such as diffusion-weighted imaging or perfusion-weighted imaging in the field of musculoskeletal radiology remains limited compared to other anatomical regions and subspecialties. Several reasons underpin this, primarily technical challenges, and a longstanding reliance on conventional and morphological evaluations of soft tissue and bone lesions. Experienced radiologists often assert that these advanced sequences do not offer added diagnostic value, claiming that a morphological approach suffices. However, in our opinion, the role of these advanced MRI sequences extends beyond merely naming an MSK lesion. In this commentary, we elucidate how these sequences can aid radiologists in various scenarios, from determining patient prognosis and tracking treatment progress to enhancing clinical-radiological correlations or guiding less experienced radiologists in evaluating soft tissues or bone tumours.

En bloc resection and reconstruction using a talar prosthesis for malignant talar bone tumor: a surgical technique.

En bloc resection is required for treatment of intermediate-grade talar tumors with extraosseous extension (Enneking stage 3) and malignant talar tumors without intra-articular invasion (Enneking stages IA and IIA). After resection, reconstruction options include tibiocalcaneal fusion, frozen autograft, and talar prosthesis; however, a talar prosthesis is preferable because it preserves ankle range of motion, does not cause leg length discrepancy, and is associated with good long-term outcomes. To the best of our knowledge, en bloc resection and reconstruction of a malignant talar tumor has not been previously reported in detail. We report a detailed surgical technique for en bloc resection of a malignant talar bone tumor using combined anterior and lateral approaches followed by reconstruction using a talar prosthesis.

Intra-abdominal telangiectatic osteosarcoma: a case report.

BACKGROUND: Telangiectatic osteosarcoma is rare and it rarely affects flat bones, especially the bones of the pelvis. It is uncommon for telangiectatic osteosarcoma to be considered as a differential diagnosis when assessing a large intrabdominal mass. CASE REPORT: We present our case of a 33-year-old African female who presented with a sizeable telangiectatic osteosarcoma of the left iliac bone. She reported a 3-year duration of a painless, slow-growing mass arising from the left flank. At examination, a large bony hard mass extending from the left ilium to the umbilicus was noted, almost mimicking an intra-abdominal pregnancy. All laboratory tests were within normal limits and an unconventional surgical approach was used for a one-stage excision of the tumor without complications. The definitive histopathological diagnosis postexcision was that of a telangiectatic osteosarcoma only on the second review of the histological specimen. CONCLUSIONS: Pelvic telangiectatic osteosarcoma is rare, and the ilium is the commonly affected pelvic bone. These tumors can be sizeable at presentation with intra-abdominal or pelvic extension with a high chance of misdiagnosis. Fortunately surrounding soft tissue involvement seems to be a rare and late finding when present.

Undifferentiated sarcoma arising from fibrous dysplasia in a young adult.

Fibrous dysplasia (FD) is a skeletal disorder characterized by the replacement of normal bone by fibrous tissue. Malignant transformation of FD is extremely rare and has been reported in both monostotic and polyostotic forms of FD. The most frequently reported malignant transformation is osteosarcoma. Among malignant bone tumors, spindle cell sarcomas are uncommon and difficult to diagnose. This report presents the case of a 30-year-old woman with an unusual presentation of a malignant undifferentiated spindle cell neoplasm secondary to fibrous dysplasia. The clinical features, radiological findings and management are discussed.

Inter-laboratory reproduction and sensitivity study of a finite element model to quantify human femur failure load: Case of metastases.

INTRODUCTION: Metastases increase the risk of fracture when affecting the femur. Consequently, clinicians need to know if the patient's femur can withstand the stress of daily activities. The current tools used in clinics are not sufficiently precise. A new method, the CT-scan-based finite element analysis, gives good predictive results. However, none of the existing models were tested for reproducibility. This is a critical issue to address in order to apply the technique on a large cohort around the world to help evaluate bone metastatic fracture risk in patients. The aim of this study is then to evaluate 1) the reproducibility 2) the transposition of the reproduced model to another dataset and 3) the global sensitivity of one of the most promising models of the literature (original model). METHODS: The model was reproduced based on the paper describing it and discussion with authors to avoid reproduction errors. The reproducibility was evaluated by comparing the results given in the original model by the original first team (Leuven, Belgium) and the reproduced model made by another team (Lyon, France) on the same dataset of CT-scans of ex vivo femurs. The transposition of the model was evaluated by comparing the results of the reproduced model on two different datasets. The global sensitivity analysis was done by using the Morris method and evaluates the influence of the density calibration coefficient, the segmentation, the orientations and the length of the femur. RESULTS: The original and reproduced models are highly correlated (r2 = 0.95), even though the reproduced model gives systematically higher failure loads. When using the reproduced model on another dataset, predictions are less accurate (r2 with the experimental failure load decreases, errors increase). The global sensitivity analysis showed high influence of the density calibration coefficient (mean variation of failure load of 84 %) and non-negligible influence of the segmentation, orientation and length of the femur (mean variation of failure load between 7 and 10 %). CONCLUSION: This study showed that, although being validated, the reproduced model underperformed when using another dataset. The difference in performance depending on the dataset is commonly the cause of overfitting when creating the model. However, the dataset used in the original paper (Sas et al., 2020a) and the Leuven's dataset gave similar performance, which indicates a lesser probability for the overfitting cause. Also, the model is highly sensitive to density parameters and automation of measurement may minimize the uncertainty on failure load. An uncertainty propagation analysis would give the actual precision of such model and improve our understanding of its behavior and is part of future work.

Rib myelolipoma: a case report.

BACKGROUND: Myelolipoma is an uncommon benign tumor composed of mature adipose tissue and hematopoietic elements. These tumors generally affect the adrenal glands, with anomalous presentations being rare and with few cases described in the literature. Most myelolipomas are asymptomatic and discovered incidentally, either through imaging tests or at autopsies. However, depending on the location and size of the lesion, myelolipomas can cause symptoms of mass effect. This article aims to report a very rare presentation of a symptomatic primary myelolipoma affecting the ribs. CASE PRESENTATION: A 21-year-old white female patient presented with a complaint of burning chest pain over 3 months, with gradual worsening in intensity, accompanied by a progressively growing bulge in the right thoracic wall. The patient underwent thoracotomy of the fifth and sixth ribs with complete excision of the lesion with a safety margin. Thoracic wall reconstruction was performed using a polypropylene mesh. The patient had a good postoperative course and was discharged on postoperative day 3. Histopathological examination revealed a histological image consistent with myelolipoma. CONCLUSIONS: This report underscores the importance of considering a myelolipoma diagnosis for tumor masses in the ribs.

CT radiomics-based machine learning model for differentiating between enchondroma and low-grade chondrosarcoma.

It may be difficult to distinguish between enchondroma and low-grade malignant cartilage tumors (grade 1) radiologically. This study aimed to construct machine learning models using 3D computed tomography (CT)-based radiomics analysis to differentiate low-grade chondrosarcoma from enchondroma. A total of 30 patients with enchondroma and 26 with chondrosarcoma were included in this retrospective study. Tumor volume segmentation was manually performed by 2 musculoskeletal radiologists. In total, 107 radiomic features were obtained for each patient. The intraclass correlation coefficient was used to assess interobserver reliability and estimate the absolute agreement between the 2 radiologists. Algorithm-based information gain was used as a feature reduction method, and the 5 most important features were detected. For classification, 7 machine learning models were utilized. Classification was carried out using either all features or 5 features. There was good to excellent agreement between the 2 radiologists for the 107 features of each patient. Therefore, a dataset containing 107 features was used for machine learning classification. When assessed based on area under curve (AUC) values, classification using all features revealed that naive Bayes was the best model (AUC = 0.950), while classification using 5 features revealed that random forest was the best model for differentiating chondrosarcoma from enchondroma (AUC = 0.967). In conclusion, machine learning models using CT-based radiomics analysis can be used to differentiate between low-grade chondrosarcoma and enchondroma.

[68Ga]Ga-PSMA-11 PET and Prostate Cancer Bone Metastases: Diagnostic Performance of Available Standardized Criteria.

In up to two thirds of prostate-specific membrane antigen (PSMA) PET scans, unspecific bone uptake has been described. The aim of this study was to estimate the diagnostic accuracy of [68Ga]Ga-PSMA-11 PET/CT for bone metastases and the occurrence of equivocal lesions. Methods: We analyzed retrospectively 118 patients who underwent a [68Ga]Ga-PSMA-11 PET/CT for initial staging or recurrence evaluation. Lesions were interpreted according to the PSMA reporting and data system (PSMA-RADS) and the prostate cancer molecular imaging standardized evaluation (PROMISE) criteria. The SUVmax and the localization of each lesion were recorded. A combination of prior or follow-up examinations was used as a reference standard to categorize benign and malignant lesions. Correlation between the final diagnosis and imaging or clinicobiochemical parameters was tested. The diagnostic accuracy was calculated for different cutoffs of PSMA-RADS criteria, for PROMISE criteria, and the sequential combination of both. Results: In total, 265 bone abnormalities were identified in 70 of 118 patients. Among these, 148 (55.8%) lesions in 50 (42.4%) patients were classified as PSMA-RADS-3B. There were no PSMA-RADS-3D lesions in our cohort. Equivocal lesions were more frequent on the ribs (30.6%) followed by the pelvis (26.5%), but in the ribs, such an uptake was malignant in 33.3% of cases versus 66.7% in the pelvis. A significant association was found between the final diagnosis and the SUVmax, prostate-specific antigen (PSA), PSA doubling time, International Society of Urological Pathology score, and the number of foci. The sensitivity and specificity were 100% and 63.6% for the PSMA-RADS-3B cutoff, respectively; 40.5% and 100% for the PSMA-RADS-4 cutoff, respectively; and 89.3% and 96.6% for both the PROMISE criteria and the sequential PSMA-RADS/PROMISE strategy, respectively. In the sequential method, the number of equivocal lesions was reduced from 147 to 2. We found that 53% of PSMA-RADS-3B lesions were malignant; 95.5% of lesions classified positive by the sequential method were true positives, whereas 32.6% were false negatives. Conclusion: [68Ga]Ga-PSMA-11 PET/CT has high accuracy for the diagnosis of bone metastases. Equivocal lesions constitute nearly half of the lesions seen on PSMA PET. The sequential combination of PSMA-RADS and PROMISE criteria reduces the number of lesions classified as equivocal. PSMA-RADS-3B lesions which are positive according to the PROMISE criteria should be considered highly suggestive of malignancy.

Solitary Osseous Metastasis of Hepatocellular Carcinoma on SPECT/CT.

Hepatocellular carcinoma (HCC), sixth most common cancer world-over, commonly metastasizes to lung, lymph nodes and adrenal glands. Incidence of osseous metastases in HCC has been reported to be 3-20 % which occurs predominantly in the axial skeleton. It only rarely occurs in the appendicular skeleton and that too as the solitary focus of metastatic deposit.3,4 We present a case of HCC with solitary osseous metastases to the proximal tibia.

Bone metastasis prediction in non-small-cell lung cancer: primary CT-based radiomics signature and clinical feature.

BACKGROUND: Radiomics provided opportunities to quantify the tumor phenotype non-invasively. This study extracted contrast-enhanced computed tomography (CECT) radiomic signatures and evaluated clinical features of bone metastasis in non-small-cell lung cancer (NSCLC). With the combination of the revealed radiomics and clinical features, the predictive modeling on bone metastasis in NSCLC was established. METHODS: A total of 318 patients with NSCLC at the Tianjin Medical University Cancer Institute & Hospital was enrolled between January 2009 and December 2019, which included a feature-learning cohort (n = 223) and a validation cohort (n = 95). We trained a radiomics model in 318 CECT images from feature-learning cohort to extract the radiomics features of bone metastasis in NSCLC. The Kruskal-Wallis and the least absolute shrinkage and selection operator regression (LASSO) were used to select bone metastasis-related features and construct the CT radiomics score (Rad-score). Multivariate logistic regression was performed with the combination of the Rad-score and clinical data. A predictive nomogram was subsequently developed. RESULTS: Radiomics models using CECT scans were significant on bone metastasis prediction in NSCLC. Model performance was enhanced with each information into the model. The radiomics nomogram achieved an AUC of 0.745 (95% confidence interval [CI]: 0.68,0.80) on predicting bone metastasis in the training set and an AUC of 0.808(95% confidence interval [CI]: 0.71,0.88) in the validation set. CONCLUSION: The revealed invisible image features were of significance on guiding bone metastasis prediction in NSCLC. Based on the combination of the image features and clinical characteristics, the predictive nomogram was established. Such nomogram can be used for the auxiliary screening of bone metastasis in NSCLC.

Quantitative analysis of standardized uptake values (SUV) of metastatic bone lesions in scintigraphy with [99mTc]Tc-EDDA/HYNIC-Tyr3-octreotide in patients with neuroendocrine tumours.

BACKGROUND: Neuroendocrine tumours (NETs) are a group of cancers that can produce hormones and other metabolically active compounds. The majority of NETs have specific tissue characteristics, such as the expression of somatostatin receptors (SSTR). Metabolic testing with [99mTc]Tc-EDDA/HYNIC-Tyr3-octreotide ([99mTc]Tc-EDDA/HYNIC-TOC) can be used in patients with NETs to visualize the presence of receptors in different locations of pathological lesions, including the skeletal system. The study aimed to calculate the body weight maximum standardized uptake value (SUVbwmax) of pathological bone lesions and healthy bone tissues, estimate the size of lesions, and identify a relationship between the SUVbwmax of the bone tissues, age and body mass of the study participants. MATERIAL AND METHODS: The somatostatin receptor scintigraphies (SRS) with [99mTc]Tc-EDDA/HYNIC-TOC were carried out at the Department of Nuclear Medicine, University Clinical Hospital No. 1, Pomeranian Medical University (PMU) in Szczecin from 2019 to 2022. Whole body and single photon emission computed tomography/computed tomography (SPECT/CT) scans were performed four hours after the injection of 700-800 MBq of [99mTc]Tc-EDDA/HYNIC-TOC in 344 patients with neuroendocrine tumours of various primary lesion locations. In 19 patients, who showed foci of increased radiopharmaceutical accumulation in bone location, the SUVbwmax was measured. The SUVbwmax of pathological bone lesions and healthy tissues were determined on SPECT/CT cross-sectional images using Xeleris 4 software. RESULTS: The total number of foci with increased SSTR expression in bone regions seen on scintigraphic images was 89. Among them, 32 bone lesions were visible on the corresponding CT scans. The mean SUVbwmax of these lesions was 31.39 [standard deviation (SD) 34.31]. For the other 57 lesions that were not visible on corresponding CT scans, the mean SUVbwmax was 19.12 (SD 24.24). The smallest bone lesion detected on the scintigram and visible on the corresponding CT location was 5 mm × 5 mm, measured in cross-section, and was located in the Th8 vertebral body; the largest, measuring 20 mm × 22 mm, was detected in the L3 vertebral body. The SUVbwmax of these lesions was 24.70 and 142.40, respectively. CONCLUSIONS: Bone lesions seen on SPECT/CT in [99mTc]Tc-EDDA/HYNIC-TOC scintigraphy can be quantitatively analysed using the SUV index. Even a very small pathological bone lesion can be detected on [99mTc]Tc-EDDA/HYNIC-TOC scintigraphy. It was shown that in cases where bone lesions were visible on CT scans, the SUVbwmax of bone tumour lesions was higher than when lesions were not visible on CT. Body mass does not affect the SUVbwmax of bone lesions. SUVbwmax of healthy bone tissue decreased with age.