It is important to recognize osteonecrosis of the jaws in patients treated with bisphosphonates because an early diagnosis can make a significant difference to the outcome of the disease. The aim of this study is to describe the radiological features of bisphosphonate osteonecrosis (BON) in order to aid its prompt recognition. A conventional radiograph, a computed tomograph (CT), a magnetic resonance image (MRI) and a 99Tc(m)-MDP 3-phase bone scan were carried out for 11 patients with BON. The main imaging findings of osteonecrosis are described. Conventional radiography and CT displayed osteolytic lesions with the involvement of cortical bone. MRI demonstrated the characteristic features of osteonecrosis and the oedema of soft tissues. Both CT and MRI were very useful in defining the extent of the lesions. 99Tc(m)-MDP three-phase bone scan was the most sensitive tool to detect the osteonecrosis at an early stage. 99Tc(m)-MDP three-phase bone scans who could be used as a screening test to detect subclinical osteonecrosis in patients who have received bisphosphonates. CT scans and MRI are useful in defining the features and extent of osteolytic lesions.

Endovenous bisphosphonate therapy seems associated with osteonecrosis of the jaw. The aim of this study was to evaluate the additional diagnostic value of hybrid SPECT/CT in ^99mTc-methylene diphosphonate 3-phase bone scintigraphy of osteonecrosis of the jaw in bisphosphonate-treated patients. Methods: We studied 15 patients (12 women and 3 men) with extraoral tumors affected by lytic bone metastases and multiple myeloma. All patients were previously treated with intravenous bisphosphonates (zoledronic acid) for 1–3 y, were negative for dental disease at clinical examination, and had suspected osteonecrosis of the jaw. All 15 patients underwent panoramic x-ray orthopantomography, CT or MRI (or both), microbiologic examination, 3-phase bone scintigraphy, and SPECT/CT of the maxillary region. Results: Three-phase bone-scintigraphy showed increased perfusion and an increased blood pool in 9 of 12 and 10 of 12 patients, respectively; at the metabolic phase, SPECT was positive in all patients and showed abnormal hyperactivity in the maxilla of 2 patients, in the mandible of 9 patients, and in both the mandible and the maxilla of 4 patients. Hybrid SPECT/CT was of particular value in 8 of 15 patients, allowing discrimination of the osteonecrotic core from nearby hyperactivity due to viable bone. Whole-body scintigraphy showed remote and multiple metastases in all patients. Orthopantomography showed nonspecific bone rarefaction in all patients but was not able to aid diagnosis of osteonecrosis of the jaw. CT and MRI showed anomalies in all symptomatic patients: CT was helpful in evaluating both cortical and trabecular bone aspects, and MRI was able to detect soft-tissue involvement but not cortical bone destruction. Conclusion: In appropriately selected oncology patients treated with bisphosphonates, an increased uptake of ^99mTc-methylene diphosphonate in maxillary bones may suggest probable osteonecrosis of the jaw. In such cases, SPECT/CT may be of value in increasing the diagnostic accuracy of bone scanning, providing a precise functional anatomic correlation for the definition of the extent of disease.

In the realm of liver transplantation, accurately determining hepatic steatosis levels is crucial. Recognizing the essential need for improved diagnostic precision, particularly for optimizing diagnosis time by swiftly handling easy-to-solve cases and allowing the expert time to focus on more complex cases, this study aims to develop cutting-edge algorithms that enhance the classification of liver biopsy images. Additionally, the challenge of maintaining data privacy arises when creating automated algorithmic solutions, as sharing patient data between hospitals is restricted, further complicating the development and validation process. This research tackles diagnostic accuracy by leveraging novel techniques from the rapidly evolving field of quantum machine learning, known for their superior generalization abilities. Concurrently, it addresses privacy concerns through the implementation of privacy-conscious collaborative machine learning with federated learning. We introduce a hybrid quantum neural network model that leverages real-world clinical data to assess non-alcoholic liver steatosis accurately. This model achieves an image classification accuracy of $97\%$, surpassing traditional methods by $1.8\%$. Moreover, by employing a federated learning approach that allows data from different clients to be shared while ensuring privacy, we maintain an accuracy rate exceeding $90\%$. This initiative marks a significant step towards a scalable, collaborative, efficient, and dependable computational framework that aids clinical pathologists in their daily diagnostic tasks.