A Case Report of Osteopoikilosis in the ribs, pelvic region and spine

Osteopoikilosisis a rare inherited benign bone dysplasia incidentally found on radiological exams. It ischaracterized by a specific radiological pattern which consists in diffuse, round or oval, symmetrically shaped sclerotic bone areas distributed throughout the skeleton. It is important to do a correct diagnosis because these lesions could be easily confused with bone metastasis. We reported a case of an osteopoikilosis patient presenting to our clinic with transient loss of consciousness and without any numbness, tingling and weakness in the legs or other parts of the body. The CT scan showed multiple small sclerotic foci bone islands, scattered throughout the thoracic and lumbar spine, ribs, pelvic bone, sacrum and bilateral proximal femur. No significant increase in the activity was detected in Technetium-99m (Tc-99m) whole body bone scintigraphy. The patient was diagnosed with characteristic radiological findings of osteopoikilosis and was followed up.

Brown Tumor of Lower Right Limb in Patients With Primary Hyperparathyroidism: A Case Report

Background.Brown tumor of Hyperparathyroidism is a metabolic disorder that can affect the entire skeleton and reactive process due to bone resorption caused by primary or secondary hyperparathyroidism (HPT). Brown tumors can occur as solitary or multiple lesions in any bone, most often in the pelvis, ribs, clavicle, mandibula, and extremities. Here, we report the Brown tumor in the lower right limb in patients with primary HPT, and the literature is reviewed. Case presentation. Patients was women 30 years old had married and come with main complains of difficulty walking. This condition has been experienced by patients since diagnosis with lunb of tibia last 8 months and caused pain from hip to lower leg. On laboratory results, it showed elevated PTH 1.249 (normal 15-65) pg/dL, elevated phosphatase alkali 1156 (normal 40-150) u/dL, elevated Ca 10,8 (n:8,6 -10,3) mg/dL, phosphor 2,1 (3–4,5) mg/dL. Histology examination of tibia lump was a benign lesion of bone (Brown Tumor). Ultrasonography transabdominal result revealed kidney stones with bilateral renal pelvis dilation, nephrolithiasis non-obstructive was found with size 1 cm & left kidney cyst with size 0.6 cm. On Neck USG showed giant cyst lesion on parathyroid glands. Radiologist pelvic examination results showed bone metastasis disease. Head CT Scan examination concluded as suspect metastatic bone. Body bone scans examination showed pathological bone metastatic process. Conclusion. Brown tumor in right lower limb caused by primary HPT

Automatic identification of suspicious bone metastatic lesions in bone scintigraphy using convolutional neural network

Background We aimed to construct an artificial intelligence (AI) guided identification of suspicious bone metastatic lesions from the whole-body bone scintigraphy (WBS) images by convolutional neural networks (CNNs). Methods We retrospectively collected the 99mTc-MDP WBS images with confirmed bone lesions from 3352 patients with malignancy. 14,972 bone lesions were delineated manually by physicians and annotated as benign and malignant. The lesion-based differentiating performance of the proposed network was evaluated by fivefold cross validation, and compared with the other three popular CNN architectures for medical imaging. The average sensitivity, specificity, accuracy and the area under receiver operating characteristic curve (AUC) were calculated. To delve the outcomes of this study, we conducted subgroup analyses, including lesion burden number and tumor type for the classifying ability of the CNN. Results In the fivefold cross validation, our proposed network reached the best average accuracy (81.23%) in identifying suspicious bone lesions compared with InceptionV3 (80.61%), VGG16 (81.13%) and DenseNet169 (76.71%). Additionally, the CNN model's lesion-based average sensitivity and specificity were 81.30% and 81.14%, respectively. Based on the lesion burden numbers of each image, the area under the receiver operating characteristic curve (AUC) was 0.847 in the few group (lesion number n ≤ 3), 0.838 in the medium group (n = 4–6), and 0.862 in the extensive group (n > 6). For the three major primary tumor types, the CNN-based lesion identifying AUC value was 0.870 for lung cancer, 0.900 for prostate cancer, and 0.899 for breast cancer. Conclusion The CNN model suggests potential in identifying suspicious benign and malignant bone lesions from whole-body bone scintigraphic images.

Imaging of Fibrous Dysplasia Protuberans, an Extremely Rare Exophytic Variant of Fibrous Dysplasia

This paper details the case report of a 26-year-old man who presented with a growing right-sided skull mass evaluated with ultrasound, non-contrast CT, contrast-enhanced MRI and 99mTc-MDP whole body bone scan with SPECT/CT. These studies suggested a broad differential diagnosis favoring benign osseous lesions. Given a more recent increase in the rate of growth, headache and large size, the lesion was excised via craniotomy followed by cranioplasty. Pathology confirmed fibrous dysplasia (FD) as the diagnosis. Interestingly, this report is the imaging evaluation of the exophytic subtype of FD, the so-called FD protuberance, an extremely rare variant of FD, of which only two case reports are found in the literature.

Bone Metastasis Detection in the Chest and Pelvis from a Whole-Body Bone Scan Using Deep Learning and a Small Dataset

The aim of this study was to establish an early diagnostic system for the identification of the bone metastasis of prostate cancer in whole-body bone scan images by using a deep convolutional neural network (D-CNN). The developed system exhibited satisfactory performance for a small dataset containing 205 cases, 100 of which were of bone metastasis. The sensitivity and precision for bone metastasis detection and classification in the chest were 0.82 ± 0.08 and 0.70 ± 0.11, respectively. The sensitivity and specificity for bone metastasis classification in the pelvis were 0.87 ± 0.12 and 0.81 ± 0.11, respectively. We propose the use of hard example mining for increasing the sensitivity and precision of the chest D-CNN. The developed system has the potential to provide a prediagnostic report for physicians’ final decisions.