Simulation training in mammography with AI-generated images: a multireader study.

OBJECTIVES: The interpretation of mammograms requires many years of training and experience. Currently, training in mammography, like the rest of diagnostic radiology, is through institutional libraries, books, and experience accumulated over time. We explore whether artificial Intelligence (AI)-generated images can help in simulation education and result in measurable improvement in performance of residents in training. METHODS: We developed a generative adversarial network (GAN) that was capable of generating mammography images with varying characteristics, such as size and density, and created a tool with which a user could control these characteristics. The tool allowed the user (a radiology resident) to realistically insert cancers within different regions of the mammogram. We then provided this tool to residents in training. Residents were randomized into a practice group and a non-practice group, and the difference in performance before and after practice with such a tool (in comparison to no intervention in the non-practice group) was assessed. RESULTS: Fifty residents participated in the study, 27 underwent simulation training, and 23 did not. There was a significant improvement in the sensitivity (7.43 percent, significant at p-value = 0.03), negative predictive value (5.05 percent, significant at p-value = 0.008) and accuracy (6.49 percent, significant at p-value = 0.01) among residents in the detection of cancer on mammograms after simulation training. CONCLUSION: Our study shows the value of simulation training in diagnostic radiology and explores the potential of generative AI to enable such simulation training. CLINICAL RELEVANCE STATEMENT: Using generative artificial intelligence, simulation training modules can be developed that can help residents in training by providing them with a visual impression of a variety of different cases. KEY POINTS: Generative networks can produce diagnostic imaging with specific characteristics, potentially useful for training residents. Training with generating images improved residents' mammographic diagnostic abilities. Development of a game-like interface that exploits these networks can result in improvement in performance over a short training period.

Chronic pulmonary aspergillosis incidence in newly detected pulmonary tuberculosis cases during follow-up.

BACKGROUND: Chronic pulmonary aspergillosis (CPA) is known to complicate patients with post-tubercular lung disease. However, some evidence suggests that CPA might co-exist in patients with newly-diagnosed pulmonary tuberculosis (P.TB) at diagnosis and also develop during therapy. The objective of this study was to confirm the presence of CPA in newly diagnosed P.TB at baseline and at the end-of-TB-therapy. MATERIALS AND METHODS: This prospective longitudinal study included newly diagnosed P.TB patients, followed up at third month and end-of-TB-therapy with symptom assessment, anti-Aspergillus IgG antibody and imaging of chest for diagnosing CPA. RESULTS: We recruited 255 patients at baseline out of which 158 (62%) completed their follow-up. Anti-Aspergillus IgG was positive in 11.1% at baseline and 27.8% at end-of-TB-therapy. Overall, proven CPA was diagnosed in 7% at baseline and 14.5% at the end-of-TB-therapy. Around 6% patients had evidence of aspergilloma in CT chest at the end-of-TB-therapy. CONCLUSIONS: CPA can be present in newly diagnosed P.TB patients at diagnosis and also develop during anti-tubercular treatment. Patients with persistent symptoms or developing new symptoms during treatment for P.TB should be evaluated for CPA. Whether patients with concomitant P.TB and CPA, while receiving antitubercular therapy, need additional antifungal therapy, needs to be evaluated in future studies.

Effect of volume of instillate on the diagnostic utility of bronchoalveolar lavage galactomannan in patients with suspected chronic pulmonary aspergillosis-A pilot study.

BACKGROUND: Bronchoalveolar lavage (BAL) galactomannan (GM) is commonly used to diagnose Aspergillus-related lung diseases. However, unlike serum GM, which is measured in undiluted blood, BAL-GM is estimated using variable aliquots and cumulative volume of instillates during bronchoscopy. OBJECTIVE: Since different studies have reported varying diagnostic accuracy and cut-offs for BAL-GM in CPA, we hypothesized that the total volume of instillate and 'order/label' of aliquots significantly affects the BAL-GM values, which was evaluated as part of this study. PATIENTS & METHODS: We obtained 250 BAL samples from 50 patients (five from each) with suspected chronic pulmonary aspergillosis. BAL fluid was collected after instilling sequential volumes of 40 mL of normal saline each for the first four labels and a fifth label was prepared by mixing 1 mL from each of the previous labels. The GM level of each label was measured by PLATELIA™ ASPERGILLUS Ag enzyme immunoassay. This study measured the discordance, level of agreement, diagnostic characteristics (sensitivity, specificity and AUROC) and best cut-offs for BAL-GM in the different aliquots of lavage fluid. RESULTS: The study population, classified into CPA (28%) and non-CPA (72%) groups, based on ERS/ESCMID criteria (excluding BAL-GM) were not different with respect to clinico-radiological characteristics. The discordance of BAL-GM positivity (using a cut-off of >1) between the serial labels for the same patient ranged between 10% and 22%, while the discordance between classification using BAL-GM positivity (using a cut-off of ≥1) and clinic-radio-microbiological classification ranged between 18% and 30%. The level of agreement for serial labels was at best fair (<0.6 for all except one 'label'). The AUROC for the serial samples ranged between 0.595 and 0.702, with the '40 mL and the 'mix' samples performing the best. The best BAL-GM cut-off also showed significant variation between serial labels of varying dilutions (Range:1.01 - 4.26). INTERPRETATION: This study highlights the variation in BAL-GM measured and the 'positivity' between different 'labels' of aliquots of BAL, with the first aliquot and the mixed sample showing the best performances for diagnosis of CPA. Future studies should attempt to 'standardise' the instilled volume for BAL-GM estimation to standardise the diagnostic yield.

Exploring the Labyrinth: Imaging in Systemic Vasculitis.

Systemic vasculitis is an immune-mediated group of disorders broadly classified based on the involved vessel type. It has myriad clinical presentations, adding to the challenge of timely diagnosis and management. Thus, imaging has taken center stage in the diagnosis of these disorders as there is a lack of definitive clinical diagnostic markers. Various available imaging modalities can be used for diagnosis and follow-up on these patients. The coronavirus disease 2019 (COVID-19) has added a new dimension to the already existing problem of vasculitis. The virus has shown great affinity for the vascular endothelium, leading to multisystem organ vasculitis. There has been a spike in vasculitis cases in the COVID-19 pandemic era, thus necessitating more research and studies in this field for a better understanding of the disease. In this review, we wish to summarize the various imaging spectrums of classical systemic vasculitis along with the new addition of COVID-19-related vasculitis to the already long list.

Case Report: Multiple Metastatic Primary Multidrug-Resistant Tubercular Abscesses.

This case report presents an atypical manifestation of tuberculosis in a 21-year-old male who presented with multiple subcutaneous swellings in the bilateral heel, left elbow, and base of the left third finger for the previous 6 months. The patient also experienced loss of appetite and unintentional weight loss. Despite initial suspicion of bacterial abscesses, antibiotics did not lead to significant improvement. Further investigations revealed an elevated erythrocyte sedimentation rate and findings suggestive of osteomyelitis on imaging. Gene Xpert testing confirmed multidrug-resistant Mycobacterium tuberculosis as the causative agent. The patient was prescribed a bedaquiline-based multidrug-resistant tuberculosis regimen, which resulted in reduction in swelling size. This report highlights the challenges in diagnosing and managing complex cases of primary multiple tubercular abscesses, especially with drug-resistant strains, emphasizing the importance of timely diagnosis and multidisciplinary management for successful outcomes.

Comparison of conventional diffusion-weighted imaging, diffusion kurtosis imaging and intravoxel incoherent motion in characterization of sonographically indeterminate adnexal masses.

PURPOSE: To evaluate the role of conventional diffusion weighted imaging, diffusion kurtosis imaging (DKI), and intravoxel incoherent motion (IVIM) in distinguishing benign from malignant adnexal masses. METHODS: 38 patients with 45 adnexal masses were enrolled in this prospective study and assessed with multiparametric MRI, including the IVIM-DKI sequence, on a 3 T MRI system. The mean apparent diffusion coefficient (ADC) from conventional DWI, the apparent diffusion coefficient derived from DKI (Dapp), the apparent kurtosis coefficient (Kapp), true diffusion coefficient (Dt), perfusion fraction (f) and pseudo-diffusion coefficient (Dp) were measured. RESULTS: The mean ADC, Dapp, and Dt were significantly higher in benign adnexal masses than in malignant adnexal masses (p < 0.001). f and Dp were also significantly higher in benign adnexal masses, with p values of 0.026 and 0.002, respectively. Kapp was higher in malignant masses (p < 0.001). Among mean ADC, Dapp, and Dt, mean ADC had the highest area under the curve (AUC) of 0.885. However, no statistically significant differences were observed between the ROCs of various diffusion parameters. CONCLUSION: The mean ADC, Dapp, and Kapp are useful parameters in discriminating between benign and malignant adnexal masses. Dt derived from IVIM also helps in distinguishing benign and malignant adnexal masses; however, no incremental role of IVIM and DKI over ADC could be identified in our study.

Evaluation of Loop-Mediated Isothermal Amplification Assay in Diagnosing Tuberculous Meningitis.

BACKGROUND: Resource-limited settings like India need a simple, quick, and temperature-independent point-of-care diagnostic test that can diagnose tuberculous meningitis (TBM) at the earliest. METHODS: A prospective study was carried out at a tertiary care center in North India wherein 50 subjects suspected of TBM were recruited and followed up for six months between January 2019 and December 2020. The aim was to evaluate the performance of loop-mediated isothermal amplification (TB-LAMP) in diagnosing TBM as compared to a composite reference standard (CRS), mycobacteria growth indicator tube 960 (MGIT 960) culture, and GeneXpert®. RESULTS: Out of 50 patients, 32 were TBM cases (64%), and 18 were non-TBM cases (36%). The sensitivity of TB-LAMP and GeneXpert® for TBM diagnosis against CRS was 53% (17/32) for both, and the specificity was 78% (14/18) and 89% (16/18), respectively. On comparing TB-LAMP against GeneXpert® for TBM diagnosis, the two methods had almost perfect agreement (Cohen's kappa=0.83) with statistical significance (p<0.001). CONCLUSION: The performance of TB-LAMP assay is comparable to GeneXpert® in diagnosing TBM, and it may be used as a substitute for CSF GeneXpert® in resource-limited settings.