Not without Context-A Multiple Methods Study on Evaluation and Correction of Automated Brain Tumor Segmentations by Experts.

RATIONALE AND OBJECTIVES: Brain tumor segmentations are integral to the clinical management of patients with glioblastoma, the deadliest primary brain tumor in adults. The manual delineation of tumors is time-consuming and highly provider-dependent. These two problems must be addressed by introducing automated, deep-learning-based segmentation tools. This study aimed to identify criteria experts use to evaluate the quality of automatically generated segmentations and their thought processes as they correct them. MATERIALS AND METHODS: Multiple methods were used to develop a detailed understanding of the complex factors that shape experts' perception of segmentation quality and their thought processes in correcting proposed segmentations. Data from a questionnaire and semistructured interview with neuro-oncologists and neuroradiologists were collected between August and December 2021 and analyzed using a combined deductive and inductive approach. RESULTS: Brain tumors are highly complex and ambiguous segmentation targets. Therefore, physicians rely heavily on the given context related to the patient and clinical context in evaluating the quality and need to correct brain tumor segmentation. Most importantly, the intended clinical application determines the segmentation quality criteria and editing decisions. Physicians' personal beliefs and preferences about the capabilities of AI algorithms and whether questionable areas should not be included are additional criteria influencing the perception of segmentation quality and appearance of an edited segmentation. CONCLUSION: Our findings on experts' perceptions of segmentation quality will allow the design of improved frameworks for expert-centered evaluation of brain tumor segmentation models. In particular, the knowledge presented here can inspire the development of brain tumor-specific metrics for segmentation model training and evaluation.

Imaging diagnosis and treatment selection for brain tumors in the era of molecular therapeutics.

Currently, most CNS tumors require tissue sampling to discern their molecular/genomic landscape. However, growing research has shown the powerful role imaging can play in non-invasively and accurately detecting the molecular signature of these tumors. The overarching theme of this review article is to provide neuroradiologists and neurooncologists with a framework of several important molecular markers, their associated imaging features and the accuracy of those features. A particular emphasis is placed on those tumors and mutations that have specific or promising imaging correlates as well as their respective therapeutic potentials.

Enhancing foci on breast MRI: Identifying criteria that increase levels of suspicion.

OBJECTIVE: Prior studies evaluating features of foci associated with malignancy have not been conclusive. This study evaluates foci that were deemed suspicious and assesses multiple imaging and clinical findings with the goal of identifying criteria that can increase diagnostic confidence when evaluating foci on breast MRI. METHODS: After Institutional Review Board approval, a retrospective chart review was performed to identify patients who underwent an image-guided biopsy of an enhancing focus. To be included in the study, a breast MRI performed between 2012 and 2019 must have been classified as suspicious for an enhancing focus or foci, and a biopsy using imaging guidance must have been subsequently performed. Patient and imaging characteristics as well as the corresponding biopsy results were recorded and statistically analyzed. RESULTS: There were 74 patients with 85 foci of enhancement who underwent biopsy within the study period. Thirteen of the 85 foci yielded malignant results for an overall positive predictive value of 15.3% (95% confidence interval: 7.7-22.9%). Additionally, twenty-six of the 85 cases (30.6%) yielded high risk lesions. There was a statistically significant negative correlation between screening breast MRIs and biopsies that yielded cancer or atypia (p = 0.04). There was also a significant association between foci and malignant results if the focus was in the same quadrant of a known malignancy (p = 0.001). CONCLUSION: Clinical information, such as the indication for a breast MRI or the location of a focus relative to a known cancer, can play an important role in evaluating foci of enhancement. Diagnostic confidence in identifying suspicious foci can be aided by incorporating clinical context with imaging findings deemed suspicious by prior research studies.

Epstein-Barr virus LMP2A utilizes Syk and PI3K to activate NF-κB in B-cell lymphomas to increase MIP-1α production.

The incidence of Hodgkin's lymphoma (HL) is growing due to an increase in Epstein-Barr virus (EBV)-associated HL in AIDS patients. The HL tumor microenvironment is vital for the survival of the malignant Hodgkin-Reed Sternberg (HRS) cells of HL, which express the EBV protein latent membrane protein 2A (LMP2A). While previous work shows that LMP2A mimics B-cell receptor (BCR) signaling to promote the survival of HRS cells, the ability of LMP2A to establish and maintain the tumor microenvironment through the production of chemokines remains unknown. Since BCR signaling induces the production of the chemokine macrophage inflammatory protein-1α (MIP-1α), and since LMP2A is a BCR mimic, we hypothesized that LMP2A increases MIP-1α levels. A comparison of multiple LMP2A-negative and -positive cell lines demonstrates that LMP2A increases MIP-1α. Additionally, LMP2A-mutant cell lines and pharmacologic inhibitors indicate that LMP2A activates a Syk/PI3K/NF-κB pathway to enhance MIP-1α. Finally, based on the finding that an NF-κB inhibitor decreased MIP-1α RNA/protein in LMP2A-positive cells, we are the first to demonstrate that LMP2A increases the nuclear localization of the NF-κB p65 subunit using DNA-binding assays and confocal microscopy in human B cells. These findings not only have implications for the treatment of HL, but also other LMP2A-expressing B-cell tumors that overexpress NF-κB.