Performance of deep learning models for predicting preinvasive, minimally invasive, or invasive adenocarcinoma was improved by combining binary and ternary classification models for predicting invasiveness and adjudication of discordant classification.
Summary: Background: Pulmonary cryptococcosis (PC) is not considered an rare, opportunistic infection anymore. The immunocompetent population accounts for an increasing proportion of the morbidity.Objective: This study investigated the clinical characteristics of PC patients spanning 20 years, in a referral centre of China.Patients/Methods: We retrospectively investigated the clinical data of 99 patients with PC who were diagnosed at Peking Union Medical College Hospital (PUMCH) from January 1998 to December 2017.Results: Pulmonary cryptococcosis incidence in PUMCH has seen sharp increase in two decades. There were 40.4% (40/99), 17.2% (17/99) and 42.4% (42/99) immunocompetent, mildly immunocompromised and severe immunocompromised patients, respectively. Significantly higher (P = .035) male predominance in immunocompetent and mildly immunocompromised groups (68.4%, 39/57) compared with severe immunocompromised group (45.2%, 19/42) was found. Overall, 27.5% (11/40) immunocompetent patients reported a significant difference (P = .02) in history of more than weekly drinking, higher than mildly or severe immunocompromised. No significant difference occurred in symptoms and radiographic characteristics among the groups. In pulmonary computerised tomography findings, the non‐air pathway feature was the dominant distribution characteristics in all patients with PC (P = .002). The gap in body dissemination frequency between immunocompetent combined with mildly immunocompromised (5.26%, 3/57) and severe immunocompromised (19.0%, 8/42) was marginally significant (P = .05).Conclusions: Gender and alcohol drinking could be PC risk factors of concern in patients without severe immunodeficiency. No significant difference occurred in symptoms or radiographic characteristics between patients with different levels of immune status. The unique radiographic non‐air pathway distribution in the lung may be the feature of Cryptococcus invasion that may enhance accurate diagnosis.
To compare the image quality and pulmonary nodule detectability and measurement accuracy between deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) of chest ultra-low-dose CT (ULDCT). Participants who underwent chest standard-dose CT (SDCT) followed by ULDCT from October 2020 to January 2022 were prospectively included. ULDCT images reconstructed with HIR and DLR were compared with SDCT images to evaluate image quality, nodule detection rate, and measurement accuracy using a commercially available deep learning–based nodule evaluation system. Wilcoxon signed-rank test was used to evaluate the percentage errors of nodule size and nodule volume between HIR and DLR images. Eighty-four participants (54 ± 13 years; 26 men) were finally enrolled. The effective radiation doses of ULDCT and SDCT were 0.16 ± 0.02 mSv and 1.77 ± 0.67 mSv, respectively (P < 0.001). The mean ± standard deviation of the lung tissue noises was 61.4 ± 3.0 HU for SDCT, 61.5 ± 2.8 HU and 55.1 ± 3.4 HU for ULDCT reconstructed with HIR-Strong setting (HIR-Str) and DLR-Strong setting (DLR-Str), respectively (P < 0.001). A total of 535 nodules were detected. The nodule detection rates of ULDCT HIR-Str and ULDCT DLR-Str were 74.0% and 83.4%, respectively (P < 0.001). The absolute percentage error in nodule volume from that of SDCT was 19.5% in ULDCT HIR-Str versus 17.9% in ULDCT DLR-Str (P < 0.001). Compared with HIR, DLR reduced image noise, increased nodule detection rate, and improved measurement accuracy of nodule volume at chest ULDCT. Not applicable.