Background: This study aimed to compare deep learning with radiologists’ assessments for diagnosing ovarian carcinoma using MRI. Methods: This retrospective study included 194 patients with pathologically confirmed ovarian carcinomas or borderline tumors and 271 patients with non-malignant lesions who underwent MRI between January 2015 and December 2020. T2WI, DWI, ADC map, and fat-saturated contrast-enhanced T1WI were used for the analysis. A deep learning model based on a convolutional neural network (CNN) was trained using 1798 images from 146 patients with malignant tumors and 1865 images from 219 patients with non-malignant lesions for each sequence, and we tested with 48 and 52 images of patients with malignant and non-malignant lesions, respectively. The sensitivity, specificity, accuracy, and AUC were compared between the CNN and interpretations of three experienced radiologists. Results: The CNN of each sequence had a sensitivity of 0.77–0.85, specificity of 0.77–0.92, accuracy of 0.81–0.87, and an AUC of 0.83–0.89, and it achieved a diagnostic performance equivalent to the radiologists. The CNN showed the highest diagnostic performance on the ADC map among all sequences (specificity = 0.85; sensitivity = 0.77; accuracy = 0.81; AUC = 0.89). Conclusion: The CNNs provided a diagnostic performance that was non-inferior to the radiologists for diagnosing ovarian carcinomas on MRI.

Purpose: To compare the diagnostic performance of deep learning models using convolutional neural networks (CNN) with that of radiologists in diagnosing endometrial cancer and to verify suitable imaging conditions. Methods: This retrospective study included patients with endometrial cancer or non-cancerous lesions who underwent MRI between 2015 and 2020. In Experiment 1, single and combined image sets of several sequences from 204 patients with cancer and 184 patients with non-cancerous lesions were used to train CNNs. Subsequently, testing was performed using 97 images from 51 patients with cancer and 46 patients with non-cancerous lesions. The test image sets were independently interpreted by three blinded radiologists. Experiment 2 investigated whether the addition of different types of images for training using the single image sets improved the diagnostic performance of CNNs. Results: The AUC of the CNNs pertaining to the single and combined image sets were 0.88–0.95 and 0.87–0.93, respectively, indicating non-inferior diagnostic performance than the radiologists. The AUC of the CNNs trained with the addition of other types of single images to the single image sets was 0.88–0.95. Conclusion: CNNs demonstrated high diagnostic performance for the diagnosis of endometrial cancer using MRI. Although there were no significant differences, adding other types of images improved the diagnostic performance for some single image sets.

Photoimmunotherapy (PIT) is a highly cell-selective cancer therapy, which employs monoclonal antibodies conjugated to a potent photosensitizer (mAb-IR700). Once the conjugate has bound to the target cell, exposure to near infrared (NIR) light induces necrosis only in targeted cells with minimal damage to adjacent normal cells in vivo. Herein, we report on the effect of altering mAb-IR700 and light power and dose on effectiveness of PIT. For evaluating cytotoxicity, we employed ATP-dependent bioluminescence imaging using a luciferase-transfected MDA-MB-468luc cell line, which expresses EGFR and luciferase. In in vitro experiments, panitumumab-IR700 (Pan-IR700) concentration was varied in combination with varying NIR light doses administered by an LED at one of three power settings, 100 mA and 400 mA continuous wave and 1733 mA intermittent wave. For in vivo experiments, the MDA-MB-468luc orthotopic breast cancer was treated with varying doses of Pan-IR700 and light. The in vitro cell study demonstrated that PIT induced cytotoxicity depended on light dose, when the conjugate concentration was kept constant. Increasing the dose of Pan-IR700 allowed lowering of the light dose to achieve equal effects thus indicating that for a given level of efficacy, the conjugate concentration multiplied by the light dose was a constant. A similar relationship between conjugate and light dose was observed in vivo. The efficacy of PIT is defined by the product of the number of bound antibody conjugates and the dose of NIR light and can be achieve equally with continuous and pulse wave LED light using different power densities.

Ferroptosis is a newly recognized mechanism of regulated cell death. It was reported to be highly associated with immune therapy and chemotherapy. However, its mechanism of regulation in the tumor microenvironment (TME) and influence on oral squamous cell carcinoma (OSCC) therapy are unknown. We identified a ferroptosis-specific gene-expression signature, an FPscore, developed by a principal component analysis (PCA) algorithm to evaluate the ferroptosis regulation patterns of individual tumor. Multi-omics analysis of ferroptosis regulation patterns was conducted. Three distinct ferroptosis regulation subtypes, which linked to outcomes and the clinical relevance of each patient, were established. A high FPscore of patients with OSCC was associated with a favorable prognosis, a ferroptosis-related immune-activation phenotype, potential sensitivities to the chemotherapy and immunotherapy. Importantly, a high FPscore correlated with a low gene copy number burden and high immune checkpoint expressions. We validated the prognostic value of the FPscore using independent immunotherapy and pan-cancer cohorts. Comprehensive evaluation of individual tumors with distinct ferroptosis regulation patterns provides new mechanistic insights, which may be clinically relevant for the application of combination therapies in OSCC.

Objectives:To investigate the distribution and clearance of retained gadolinium (Gd) in various parts of the brain after intravenously administering a Gd-based contrast agent (GBCA) in normal and renal failure mouse models.Materials and Methods:Two different mouse models: normal (n = 12) and renal failure (n = 12) were used. Clinical GBCAs (Gd-DTPA-BMA, 5 mmol/kg or Gd-DOTA, 5 mmol/kg) were intravenously administered five times per week for 4 weeks. Both groups were divided into two subgroups based on the time-point for sample collection: 3 days (3d) and 45 days (45d) after the last injection. Normal saline (5 mL/kg) was intravenously administered to mice of the control groups in the same manner. Samples of the following parts of the mouse brain were obtained on dissection: olfactory bulb, cerebral cortex, hippocampus, thalamus, midbrain, cerebellum, pons and medulla. 158Gd concentrations in each sample were quantified using inductively coupled plasma mass spectrometry.Results:The olfactory bulb had the h...

Sarcoidosis–lymphoma syndrome (SLS) is a rare disease in which both entities coexist. We aimed to study the role of 18F-fluorodeoxyglucose (FDG) and L–[3-18F] α-methyltyrosine (FAMT) positron emission tomography (PET)/computed tomography (CT) in differentiating between these two lesions. A 54-year-old female with large liver tumors was referred to our Nuclear Medicine Department for staging using FDG PET/CT. She had a history of primary biliary cirrhosis (PBC) for 15 years and developed lung and mediastinal sarcoidosis 1 year before the liver tumors were noted. Abdominal dynamic CT revealed two well-circumscribed, peripherally-enhancing, low-density masses in the right lobe of the liver with intensive ring-form FDG uptakes at maximum standard uptake values (SUVmax) of 18.3 and 19.5, respectively. In the arterial phase, a hepatic artery was seen penetrating the tumor, a phenomenon known as “angiogram sign”. Chest PET/CT findings showed irregular thickening of the bronchovascular bundles, central peribronchial shaggy consolidations in the right middle and lower lobes (SUVmax, 4.6), and mediastinal and hilar lymphadenopathies (SUVmax, 2.7). After assessment, chemotherapy with rituximab, cyclophosphamide, doxorubicin hydrochloride, vincristine sulfate, and prednisone (R–CHOP) was administered for eight cycles. Follow-up imaging studies using FDG and FAMT PET/CT were performed 3 months after the last cycle of chemotherapy, which showed that the two highly FDG-avid tumors in the liver had disappeared. However, faint FDG uptake persisted in the lung consolidations (SUVmax, 6.3), and FDG uptake for the mediastinal lymphadenopathies increased (SUVmax of 5.8). In contrast, there was no significant uptake of FAMT in the liver, as well as in the lungs and the bilateral mediastinal lymphadenopathies. These discrepant uptakes between FDG and FAMT were compatible with sarcoidosis. Combination of FDG and FAMT in PET/CT studies may play an important role in the management of SLS patients, especially in differentiating between sarcoidosis and lymphoma lesions.