Search Results (8)

Objectives: Spinal diseases are commonly encountered health problems with a wide spectrum. In addition to degenerative changes, other common spinal pathologies include metastases and compression fractures. Benign tumors like hemangiomas and infections such as spondylodiscitis are also frequently observed. Although magnetic resonance imaging (MRI) is considered the gold standard in diagnostic imaging, the morphological similarities of lesions can pose significant challenges in differential diagnoses. In recent years, the use of artificial intelligence applications in medical imaging has become increasingly widespread. In this study, we aim to detect and classify vertebral body lesions using the YOLO-v8 (You Only Look Once, version 8) deep learning architecture. Materials and Methods: This study included MRI data from 235 patients with vertebral body lesions. The dataset comprised sagittal T1- and T2-weighted sequences. The diagnostic categories consisted of acute compression fractures, metastases, hemangiomas, atypical hemangiomas, and spondylodiscitis. For automated detection and classification of vertebral lesions, the YOLOv8 deep learning model was employed. Following image standardization and data augmentation, a total of 4179 images were generated. The dataset was randomly split into training (80%) and validation (20%) subsets. Additionally, an independent test set was constructed using MRI images from 54 patients who were not included in the training or validation phases to evaluate the model’s performance. Results: In the test, the YOLOv8 model achieved classification accuracies of 0.84 and 0.85 for T1- and T2-weighted MRI sequences, respectively. Among the diagnostic categories, spondylodiscitis had the highest accuracy in the T1 dataset (0.94), while acute compression fractures were most accurately detected in the T2 dataset (0.93). Hemangiomas exhibited the lowest classification accuracy in both modalities (0.73). The F1 scores were calculated as 0.83 for T1-weighted and 0.82 for T2-weighted sequences at optimal confidence thresholds. The model’s mean average precision (mAP) 0.5 values were 0.82 for T1 and 0.86 for T2 datasets, indicating high precision in lesion detection. Conclusions: The YOLO-v8 deep learning model we used demonstrates effective performance in distinguishing vertebral body metastases from different groups of benign pathologies. Full article

The most common peripheral nerve tumors are of a benign nature and include schwannoma or neurofibroma. In rare cases, other tumors or non-tumorous lesions can mimic peripheral nerve tumors clinically or radiologically. Based on data from the multicentric German Peripheral Nerve Tumor Registry (PNTR), which encompasses current information on 315 surgically treated patients from three high-volume centers, we present 61 cases of rare tumors and lesions that mimic tumors associated with peripheral nerves. This cohort displays considerable heterogeneity, featuring a broad spectrum of morphological features and biological potentials. Histopathological diagnoses include various intrinsic peripheral nerve tumors such as malignant peripheral nerve tumors (MPNSTs) (n = 13), perineurioma (n = 17), and hybrid nerve sheath tumors (HPNSTs, comprising schwannoma/perineurioma and schwannoma/neurofibroma) (n = 14), as well as atypical neurofibromatous neoplasm with unknown biological potential (ANNUBP) (n = 1). Additionally, the cohort encompasses extrinsic tumorous lesions like lymphoma (n = 3), lymphangioma (n = 2), hemangioma (n = 2), solitary fibrous tumor (n = 2), metastatic disease (n = 1), and single cases of other rare tumor entities (n = 6). An overview of the underlying pathology, imaging features, and clinical presentation is provided, with a brief description of each entity. A definitive preoperative differentiation between benign peripheral nerve tumors and rare intrinsic and extrinsic tumors is often not possible. Clinical examination and subtle imaging clues can at least indicate the possibility of a rare entity. The basic requirement is close cooperation between radiologists, neurologists, neuropathologists, and neurosurgeons at a specialized center to develop a multidisciplinary concept and offer the patient the best therapeutic approaches. Full article

Hepatic hemangiomas are the most common benign liver tumors. Typically, small- to medium-sized hemangiomas are asymptomatic and discovered incidentally through the widespread use of imaging techniques. Giant hemangiomas (>5 cm) have a higher risk of complications. A variety of imaging methods are used for diagnosis. Cavernous hemangioma is the most frequent type, but radiologists must be aware of other varieties. Conservative management is often adequate, but some cases necessitate targeted interventions. Although surgery was traditionally the main treatment, the evolution of minimally invasive procedures now often recommends transarterial chemoembolization as the treatment of choice. Full article

Fabry disease (FD) is a multisystemic X-linked lysosomal storage disease that presents with angiokeratomas (AKs). Our objective was to investigate the clinical and morphologic features of AKs and to present two experimental techniques, multispectral imaging (MSI) and non-linear microscopy (NLM). A thorough dermatological examination was carried out in our 26 FD patients and dermoscopic images (n = 136) were evaluated for specific structures. MSI was used for the evaluation of AKs in seven patients. NLM was carried out to obtain histology samples of two AKs and two hemangiomas. Although AKs were the most common manifestation, the majority of patients presented an atypical distribution and appearance, which could cause a diagnostic challenge. Dermoscopy revealed lacunae (65%) and dotted vessels (56%) as the most common structures, with a whitish veil present in only 25%. Autofluorescence (405 nm) and diffuse reflectance (526 nm) images showed the underlying vasculature more prominently compared to dermoscopy. Using NLM, AKs and hemangiomas could be distinguished based on morphologic features. The clinical heterogeneity of FD can result in a diagnostic delay. Although AKs are often the first sign of FD, their presentation is diverse. A thorough dermatological examination and the evaluation of other cutaneous signs are essential for the early diagnosis of FD. Full article

A 78-year-old man with newly diagnosed high-risk prostate cancer underwent ⁶⁸Ga-PSMA PET/CT for primary staging. This showed a single, very intense PSMA uptake in the vertebral body of Th2, without discrete morphological changes on low-dose CT. Thus, the patient was considered oligometastatic and underwent MRI of the spine for stereotactic radiotherapy planning. MRI demonstrated an atypical hemangioma in Th2. A bone algorithm CT scan confirmed the MRI findings. The treatment was changed, and the patient underwent a prostatectomy with no concomitant therapy. At three and six months after the prostatectomy, the patient had an unmeasurable PSA level, confirming the benign etiology of the lesion. Full article

Intrahepatic cholangiocarcinoma (ICC) is the second most common primary hepatic malignancy, with mass-forming growth pattern being the most common. The typical imaging appearance of mass-forming ICC (mICC) consists of irregular ring enhancement in the arterial phase followed by the progressive central enhancement on portal venous and delayed phases. However, atypical imaging presentation in the form of hypervascular mICC might also be seen, which can be attributed to distinct pathological characteristics. Ancillary imaging features such as lobular shape, capsular retraction, segmental biliary dilatation, and vascular encasement favor the diagnosis of mICC. Nevertheless, these radiological findings may also be present in certain benign conditions such as focal confluent fibrosis, sclerosing hemangioma, organizing hepatic abscess, or the pseudosolid form of hydatid disease. In addition, a few malignant lesions including primary liver lymphoma, hemangioendothelioma, solitary hypovascular liver metastases, and atypical forms of hepatocellular carcinoma (HCC), such as scirrhous HCC, infiltrative HCC, and poorly differentiated HCC, may also pose a diagnostic dilemma by simulating mICC in imaging studies. Diffusion-weighted imaging and the use of hepatobiliary contrast agents might be helpful for differential diagnosis in certain cases. The aim of this manuscript is to provide a comprehensive overview of mICC imaging features and to describe useful tips for differential diagnosis with its potential mimickers. Full article

Background: To evaluate the diagnostic accuracy of quantitative perfusion parameters in contrast-enhanced ultrasound to differentiate malignant from benign liver lesions. Methods: In this retrospective study 134 patients with a total of 139 focal liver lesions were included who underwent contrast enhanced ultrasound (CEUS) between 2008 and 2018. All examinations were performed by a single radiologist with more than 15 years of experience using a second-generation blood pool contrast agent. The standard of reference was histopathology (n = 60), MRI or CT (n = 75) or long-term CEUS follow up (n = 4). For post processing regions of interests were drawn both inside of target lesions and the liver background. Time–intensity curves were fitted to the CEUS DICOM dataset and the rise time (RT) of contrast enhancement until peak enhancement, and a late-phase ratio (LPR) of signal intensities within the lesion and the background tissue, were calculated and compared between malignant and benign liver lesion using Student’s t-test. Quantitative parameters were evaluated with respect to their diagnostic accuracy using receiver operator characteristic curves. Both features were then combined in a logistic regression model and the cumulated accuracy was assessed. Results: RT of benign lesions (14.8 ± 13.8 s, p = 0.005), and in a subgroup analysis, particular hemangiomas (23.4 ± 16.2 s, p < 0.001) differed significantly to malignant lesions (9.3 ± 3.8 s). The LPR was significantly different between benign (1.59 ± 1.59, p < 0.001) and malignant lesions (0.38 ± 0.23). Logistic regression analysis with RT and LPR combined showed a high diagnostic accuracy of quantitative CEUS parameters with areas under the curve of 0.923 (benign vs. malignant) and 0.929 (hemangioma vs. malignant. Conclusions: Quantified CEUS parameters are helpful to differentiate malignant from benign liver lesions, in particular in case of atypical hemangiomas. Full article

Spindle cell hemangioma is a benign vascular tumor typically occurring in the dermis or subcutis of distal extremities as red–brown lesions that can grow in both size and number over time. They can be very painful and potentially disabling. A family history of cancer or previous history may be relevant and must be taken into consideration. Juxtaglomerular cell tumor (reninoma) is an extremely rare cause of secondary hypertension diagnosed mostly among adolescents and young adults. Excessive renin secretion results in secondary hyperaldosteronism. Subsequent hypokalemia and metabolic alkalosis, together with high blood pressure, are clues for clinical diagnosis. Histological examination of the excised tumor leads to a definitive diagnosis. Reninoma is found in subcapsular localization, in most cases as a solitary mass, in imaging studies of kidneys. Exceptionally, it can be located in another part of a kidney. Both spindle cell hemangioma and reninoma are extremely rare tumors in children and adolescents. Herein, the authors present a case report of a patient with hereditary BRCA1 interacting protein C-terminal helicase 1 (BRIP1) mutation, spindle cell hemangioma, and secondary hypertension caused by atypically localized reninoma. Full article