A deep learning approach for virtual contrast enhancement in Contrast Enhanced Spectral Mammography.

Contrast Enhanced Spectral Mammography (CESM) is a dual-energy mammographic imaging technique that first requires intravenously administering an iodinated contrast medium. Then, it collects both a low-energy image, comparable to standard mammography, and a high-energy image. The two scans are combined to get a recombined image showing contrast enhancement. Despite CESM diagnostic advantages for breast cancer diagnosis, the use of contrast medium can cause side effects, and CESM also beams patients with a higher radiation dose compared to standard mammography. To address these limitations, this work proposes using deep generative models for virtual contrast enhancement on CESM, aiming to make CESM contrast-free and reduce the radiation dose. Our deep networks, consisting of an autoencoder and two Generative Adversarial Networks, the Pix2Pix, and the CycleGAN, generate synthetic recombined images solely from low-energy images. We perform an extensive quantitative and qualitative analysis of the model's performance, also exploiting radiologists' assessments, on a novel CESM dataset that includes 1138 images. As a further contribution to this work, we make the dataset publicly available. The results show that CycleGAN is the most promising deep network to generate synthetic recombined images, highlighting the potential of artificial intelligence techniques for virtual contrast enhancement in this field.

A Review of the Paradigmatic Role of Adipose Tissue in Renal Cancer: Fat Measurement and Tumor Behavior Features.

(1) Background: Renal-cell carcinoma (RCC) incidence has been steadily rising, with obesity identified as a potential risk factor. However, the relationship between obesity and RCC prognosis remains unclear. This systematic review aims to investigate the impact of different adipose tissue measurements on RCC behavior and prognosis. (2) Methods: A search of MEDLINE databases identified 20 eligible studies focusing on various fat measurements, including visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), perirenal adipose tissue (PRAT), and the Mayo adhesive probability (MAP) score. (3) Results: The review revealed conflicting findings regarding the association between adipose tissue measurements and RCC outcomes. While some studies suggested a protective role of certain fat deposits, particularly VAT, against disease progression and mortality, others reported contradictory results across different adipose metrics and RCC subtypes. (4) Conclusions: Methodological variations and limitations, such as retrospective designs and sample size constraints, pose challenges to standardization and generalizability. Further research is needed to understand these associations better and establish standardized approaches for adiposity assessment in RCC patients, which could inform clinical practice and therapeutic decision-making.

Temporal Bone High Resolution Computed Tomography Findings in a Case of Postpartum Otosclerosis.

We describe temporal bone high resolution computed tomography (HRCT) findings in a case of bilateral mixed fenestral and retrofenestral otosclerosis with onset in the postpartum period. This condition should be considered in women complaining of postpartum hearing loss and temporal bone HRCT is a fundamental tool leading to the diagnosis.

Sarcopenia does not impact the outcome of patients with Multiple Mieloma consolidated with autologous Hematopoietic Stem Cell Transplantation.

Sarcopenia has been associated with chronic diseases and cancer. Aim of this study was to evaluate sarcopenia in Multiple Myeloma patients undergoing autologous stem cell trans-plantation. In 68 eligible patients' measurement of skeletal muscle area (cm2) on computed tomography scans at the level of the L3 vertebra (L3-SMI) was performed. 37(54%) patients were categorized as sarcopenic: 26 males with L3-SMI values < 52.4 cm2/m2, and 11 women with L3-SMI values < 38.9 cm2/m2. The majority of sarcopenic patients included were older than 60 years (69%, p=0.0005), and with BMI <25 (75%; p=0.0000). A significant association was found between sarcopenia and Sorror score value > 1 (p=0.02). The Kaplan Meyer curve showed a median OS of 73.5 months for non-sarcopenic patients vs. 86.5 months for sarcopenic patients, suggesting that sarcopenia is not an independent prognostic factor in this cohort of patients.

Transoral percutaneous radiofrequency ablation with a steerable needle and cementoplasty under CBCT and infrared augmented reality navigation system guidance for the treatment of a C1 solitary plasmacytoma: A case report.

We report a case of a 40-year-old female with a solitary plasmacytoma of the right transverse apophysis of C1 who underwent combined transoral ablation using a curved steerable needle and cementoplasty under CBCT and infra-red augmented reality navigation system. An imaging work-up revealed an osteolytic lesion determining partial collapse of the right lateral mass of C1 and involving the vertebral foramen. After a biopsy, that revealed a solid tissue consistent with plasmacytoma, it was decided to proceed with radiation therapy. Subsequent PET-CT restaging scans showed residual tumors treated with a transoral percutaneous approach, combining ablation and cementoplasty. This report evaluates the benefits of this combined procedure and the transoral approach, focusing on the advantages of steerable devices and navigation systems.

CT-Based Radiogenomics of P4HA3 Expression in Clear Cell Renal Cell Carcinoma.

RATIONALE AND OBJECTIVES: The sequencing of the renal cell carcinoma (RCC) genome identified several mutations with prognostic significance. Genomic analysis, collected in The Cancer Genome Atlas Research Network, revealed several clear cell renal cell carcinoma (ccRCC) gene mutations and gene expressions. Radiogenomics is a new branch of diagnostic imaging based on the association between imaging phenotypes and genomics of diseases. P4HA3 expression has recently been shown to correlate with increased aggressiveness of ccRCC, with poor prognosis, proliferation, migration, invasion, and metastases, suggesting P4HA3 as a prognostic marker and therapeutic target in ccRCC. The aim of this study is to investigate the computed tomography (CT) imaging phenotype of P4HA3 expression in ccRCC patients. MATERIALS AND METHODS: In this retrospective study we enrolled 196 ccRCC patients divided into two groups: ccRCC patients with P4HA3 expression (n = 13) and ccRCC patients without P4HA3 expression (n = 183). Several imaging features were evaluated on preoperative CT scan. The statistical significance threshold was set at P < .05. RESULTS: A statistically significant association was found with larger primary tumor size (P = .033), tumor infiltration (P = .023), ill-defined tumor margins (P = .025), and advanced tumor stage American Joint Committee of Cancer (P = .014). CONCLUSION: This study demonstrates CT imaging features associated with P4HA3 expression in ccRCC. These results could contribute to better understand P4HA3 expression with a noninvasive approach and could be applied to the development of targeted therapies.

Percutaneous Cryoablation of Recurrent or Oligometastatic Tumors in Thoracoabdominal Soft Tissues: Safety, Effectiveness, and Technical Aspects.

PURPOSE: To assess the effectiveness and safety of cryoablation (CRA) for the treatment of recurrent or oligometastatic solid tumors located in the thoracoabdominal soft tissues. MATERIALS AND METHODS: Twenty-two percutaneous CRA procedures performed in 19 patients to treat recurrent or oligometastatic tumors in thoracoabdominal soft tissue were retrospectively examined. All procedures were performed between January 2015 and June 2021 under ultrasound and computed tomography (CT) guidance, and the most complex procedures were performed with CT-based navigation systems. The histology of the primary tumors included colorectal adenocarcinoma, squamous cell lung carcinoma, pancreatic adenocarcinoma, renal cell carcinoma, and hepatocellular carcinoma. Adverse events, technical success, and local tumor control were analyzed. RESULTS: The mean age of the patients was 66.5 years, with a mean tumor size of 24.8 mm. The mean time of the procedures was 68 minutes, with a mean number of 2.5 cryoprobes used. Hydrodissection was performed in 63% of the procedures to protect the surrounding anatomical structures. The mean size of the ice ball, measured on axial CT scans at the end of the procedures, was 43.5 mm. No severe adverse events were observed. Technical success was achieved in all cases. Three patients experienced local tumor progression (2 residual disease and 1 recurrence), which were successfully treated with a second CRA procedure. CONCLUSIONS: Percutaneous CRA is a safe and effective therapy in selected cases of recurrent or oligometastatic tumors in the thoracoabdominal soft tissues.

Relationship between chronic kidney disease and cerebral white matter hyperintensities: a systematic review.

Background: This systematic review summarizes available evidence on the relationship between white matter hyperintensities (WMH) volumetric quantification on brain MRI scans and chronic kidney disease (CKD). Methods: The literature search was performed in March 2022 using MEDLINE PubMed Central, Scopus and Web of Science - Publons as search engines. Relevant articles investigating, with a quantitative volumetric approach, the link between WMH and CKD patients were selected. Results: The database search strategy found 987 articles, after excluding duplicates, the titles and abstracts of the remaining 320 articles were examined. Subsequently 276 articles were excluded as they were not relevant to the topic. Of the 44 articles evaluated for eligibility, 36 were excluded because the quantitative analysis of WMH was not volumetric. Finally, 8 articles were included in this systematic review. Conclusions: Literature on this topic is extremely heterogeneous in terms of methodology and samples. However, evidence shows that there is a relationship between CKD and WMH volume of the brain. We recommend that quantifiable biomarkers such as estimated glomerular filtration rate (eGFR) and urine albumin to creatinine ratio (UACR) should be included in studies dealing with cerebrovascular disease. The biological and molecular mechanisms underlying cerebrovascular damage in patients with chronic renal failure deserve to be further explored.

Imaging of knee osteoarthritis: a review of multimodal diagnostic approach.

Knee osteoarthritis (KOA) is a common chronic condition among the elderly population that significantly affects the quality of life. Imaging is crucial in the diagnosis, evaluation, and management of KOA. This manuscript reviews the various imaging modalities available until now, with a little focus on the recent developments with Artificial Intelligence. Currently, radiography is the first-line imaging modality recommended for the diagnosis of KOA, owing to its wide availability, affordability, and ability to provide a clear view of bony components of the knee. Although radiography is useful in assessing joint space narrowing (JSN), osteophytes and subchondral sclerosis, it has limited effectiveness in detecting early cartilage damage, soft tissue abnormalities and synovial inflammation. Ultrasound is a safe and affordable imaging technique that can provide information on cartilage thickness, synovial fluid, JSN and osteophytes, though its ability to evaluate deep structures such as subchondral bone is limited. Magnetic resonance imaging (MRI) represents the optimal imaging modality to assess soft tissue structures. New MRI techniques are able to detect early cartilage damage measuring the T1ρ and T2 relaxation time of knee cartilage. Delayed gadolinium-enhanced MRI of cartilage, by injecting a contrast agent to enhance the visibility of the cartilage on MRI scans, can provide information about its integrity. Despite these techniques can provide valuable information about the biochemical composition of knee cartilage and can help detect early signs of osteoarthritis (OA), they may not be widely available. Computed tomography (CT) has restricted utility in evaluating OA; nonetheless, weight-bearing CT imaging, using the joint space mapping technique, exhibits potential in quantifying knee joint space width and detecting structural joint ailments. PET-MRI is a hybrid imaging technique able to combine morphological information on bone and soft tissue alterations with the biochemical changes, but more research is needed to justify its high cost and time involved. The new tools of artificial intelligence, including machine learning models, can assist in detecting patterns and correlations in KOA that may be useful in the diagnosis, grading, predicting the need for arthroplasty, and improving surgical accuracy.

Can Machine Learning Models Detect and Predict Lymph Node Involvement in Prostate Cancer? A Comprehensive Systematic Review.

(1) Background: Recently, Artificial Intelligence (AI)-based models have been investigated for lymph node involvement (LNI) detection and prediction in Prostate cancer (PCa) patients, in order to reduce surgical risks and improve patient outcomes. This review aims to gather and analyze the few studies available in the literature to examine their initial findings. (2) Methods: Two reviewers conducted independently a search of MEDLINE databases, identifying articles exploring AI's role in PCa LNI. Sixteen studies were selected, and their methodological quality was appraised using the Radiomics Quality Score. (3) Results: AI models in Magnetic Resonance Imaging (MRI)-based studies exhibited comparable LNI prediction accuracy to standard nomograms. Computed Tomography (CT)-based and Positron Emission Tomography (PET)-CT models demonstrated high diagnostic and prognostic results. (4) Conclusions: AI models showed promising results in LN metastasis prediction and detection in PCa patients. Limitations of the reviewed studies encompass retrospective design, non-standardization, manual segmentation, and limited studies and participants. Further research is crucial to enhance AI tools' effectiveness in this area.

Liver abscess after endoscopic sleeve gastroplasty: A case report.

Endoscopic sleeve gastroplasty is a minimally invasive procedure for the treatment of obesity. The procedure is generally safe and well-tolerated, but major adverse events occur in up to 3% of patients. Perigastric abscess is a potential complication caused by postprocedural gastric leak. To the best of our knowledge, no cases of hepatic abscess (HA) following endoscopic sleeve gastroplasty have been reported, while HA is a well-known complication of laparoscopic sleeve gastrectomy. We report the case of a patient who developed a liver abscess 2 weeks after endoscopic sleeve gastroplasty. The patient improved with administration of intravenous antibiotics and endoscopic drainage.

Adverse Effects of Immune-Checkpoint Inhibitors: A Comprehensive Imaging-Oriented Review.

Immune-checkpoint inhibitors (ICIs) are immunomodulatory monoclonal antibodies, which increase antitumor immunity of the host and facilitate T-cell-mediated actions against tumors. These medications have been used in recent years as a weapon against advanced stage malignancies, such as melanoma, renal cell carcinoma, lymphoma, small or non-small cell lung cancer, and colorectal cancer. Unfortunately, they are not free from possible adverse effects (immune-related adverse events-irAEs) that mainly affect skin, gastrointestinal, hepatic, and endocrine systems. Early diagnosis of irAEs is essential to correctly and rapidly manage patients, with ICIs suspension and therapies administration. Deep knowledge of the imaging and clinical patterns of irAEs is the key to promptly rule out other diagnoses. Here, we performed a review of the radiological signs and differential diagnosis, based on the organ involved. The aim of this review is to provide guidance to recognize the most significant radiological findings of the main irAEs, based on incidence, severity, and the role of imaging.

CT, MR, and CEUS imaging features of recurrent GIST of the pre-sacral space: A case report.

We present the case of a 50-year-old woman affected by a rectal gastrointestinal stromal tumor (GIST), with a recurrence in pre-sacral and pre-coccygeal space after surgery and Imatinib therapy. GISTs are the most common mesenchymal tumors of the gastrointestinal tract and rectal GISTs are rare (only 2% of cases); magnetic resonance and computed tomography are the main imaging techniques for diagnosis and follow-up, while ultrasound and contrast-enhanced ultrasound may be useful to perform a percutaneous biopsy, as in the case presented: the imaging features of the lesion in all these imaging methods are displayed.

COVID-19 vaccination simulating lymph node progression in a patient with prostate cancer.

Several cases of cancer patients with 18-fluorodeoxyglucose (18FDG) Positron Emission Tomography/Computed Tomography (PET/CT) evidence of metabolically active axillary lymph nodes after COVID-19 vaccination have been described, creating a diagnostic dilemma and sometimes leading to further unnecessary examinations. A 62-year-old male, diagnosed with prostate cancer, treated with hormone-therapy and radiotherapy of the prostate 2 years before, underwent fluorine-18 choline (F-FCH) PET/CT for restaging purpose, less than 3 weeks after he had received the second dose of the Pfizer BioNTech-BNT162b2 mRNA COVID-19 vaccine. This exam showed an increased F-FCH uptake and an enlargement of the left axillary, paratracheal, para-aortic, subcarinal, and hilar bilateral lymph nodes. Fourteen weeks later, the patient underwent a new F-FCH PET-CT scan, displaying an almost complete regularization of the FCH uptake in all the previously involved regions. The patient was not treated after the first PET-CT scan, thus, the aforementioned PET/CT findings represented inflammatory vaccine-related lymph nodes. This case highlights the significance of knowing vaccination history to correctly interpret imaging findings and to avoid false-positive reports.

A comparative analysis of thermal ablation techniques in the treatment of primary and secondary lung tumors: a single-center experience.

PURPOSE: To evaluate efficacy and safety of radiofrequency ablation (RFA) and microwave ablation (MWA) in unresectable lung malignancies. METHODS: Data regarding patients with primary and secondary lung tumors treated with RFA or MWA from 2008 to 2020 were reviewed retrospectively. Primary study objectives such as technical success, primary and secondary technique efficacy rates, local tumor progression (LTP) rate, LPT-free survival (LPTFS) and overall survival (OS) were assessed. Secondary study objectives were side effects and complications. RFA and MWA were compared using the Chi-square test for continuous variables. Kaplan-Meier curves were calculated for survival statistical analysis. RESULTS: A total of 113 patients with primary or secondary lung tumor underwent 74 RFA (48%) and 81 MWA (52%). Technical success rate was 151/155 (97%); primary and secondary technique efficacy rates were 123/155 (79%) and 129/155 (83%), respectively. During the entire study follow-up, 32 cases experienced disease progression (20%), of which 18 underwent repeat ablation (12%), in 6 cases with success (4%). Residual unablated tumor happened in 4/155 cases (3%). LTP occurred in 28/155 cases (17%). The only factor associated with poorer LTP-FS was lesion diameter ≥ 30 mm (P < 0.05). One-, 3- and 5-years LTP-FS was 83%, 82%, 82%, respectively. One-, 3- and 5-years OS of the entire population was 87%, 74%, 73%, respectively. Minor and major complication rates were 53/155 (34%) and 29/155 (19%), respectively. CONCLUSIONS: In conclusion, this study confirms the appropriateness of RFA and MWA for lung tumors treatment, in terms of safety and efficacy.

A Case of Secretory Carcinoma in a Patient With a History of Contralateral Medullary Carcinoma.

Background: Secretory and medullary carcinomas of the breast are rare subtypes of infiltrating ductal carcinoma. The different histological behavior of medullary and secretory carcinomas is correlated with different imaging features on mammography, ultrasound, and magnetic resonance imaging. Case Report: We report the case of a Caucasian woman in which both subtypes of tumors were diagnosed in an 8-year time interval and evaluate, in antithesis, histopathological and imaging aspects of medullary and secretory carcinoma. Conclusion: To our knowledge, this is the first case reported in literature of secretory carcinoma with a complete imaging tumor evaluation in a patient with a previous contralateral medullary cancer.

Novel Magnetic Resonance Imaging Tools for the Diagnosis of Degenerative Disc Disease: A Narrative Review.

Low back pain (LBP) is one of the leading causes of disability worldwide, with a significant socioeconomic burden on healthcare systems. It is mainly caused by degenerative disc disease (DDD), a progressive, chronic, and age-related process. With its capacity to accurately characterize intervertebral disc (IVD) and spinal morphology, magnetic resonance imaging (MRI) has been established as one of the most valuable tools in diagnosing DDD. However, existing technology cannot detect subtle changes in IVD tissue composition and cell metabolism. In this review, we summarized the state of the art regarding innovative quantitative MRI modalities that have shown the capacity to discriminate and quantify changes in matrix composition and integrity, as well as biomechanical changes in the early stages of DDD. Validation and implementation of this new technology in the clinical setting will allow for an early diagnosis of DDD and ideally guide conservative and regenerative treatments that may prevent the progression of the degenerative process rather than intervene at the latest stages of the disease.