Computed tomography–based radiomics for identifying pulmonary cryptococcosis mimicking lung cancer

Abstract

Background Pulmonary cryptococcosis (PC) is an invasive pulmonary fungal disease, and nodule/mass‐type PC may mimic lung cancer (LC) in imaging appearance. Thus, an accurate diagnosis of nodule/mass‐type PC is beneficial for appropriate management. However, the differentiation of nodule/mass‐type PC from LC through computed tomography (CT) is still challenging. Purpose To develop and externally test a CT‐based radiomics model for differentiating nodule/mass‐type PC from LC. Methods In this retrospective study, patients with nodule/mass‐type PC or LC who underwent non‐enhanced chest CT were included: Institution 1 was for the training set, and institutions 2 and 3 were for the external test set. Large quantities of radiomics features were extracted. The radiomics score (Rad‐score) was calculated using the linear discriminant analysis, and a subsequent fivefold cross‐validation was performed. A combined model was developed by incorporating Rad‐score and clinical factors. Finally, the models were tested with an external test set and compared using the area under the receiver operating characteristic curve (AUC). Results A total of 168 patients (45 with PC and 123 with LC) were in the training set, and 72 (36 with PC and 36 with LC) were in the external test set. Of the 81 patients with PC, 30 were immunocompromised (37%). Rad‐score, comprising 18 features, had an AUC of 0.844 after fivefold cross‐validation, which was lower than that (AUC = 0.943, p = 0.003) of the combined model integrating Rad‐score, age, lobulation, pleural retraction, and patches. In the external test set, Rad‐score and the combined model obtained good predictive performance (AUC = 0.824 for Rad‐score, and 0.869 for the combined model). Moreover, the combined model outperformed the clinical model in the cross‐validation and external test (0.943 vs. 0.810, p <0.001; 0.869 vs. 0.769, p = 0.011). Conclusions The proposed combined model exhibits a good differential diagnostic performance between nodule/mass‐type PC and LC. The CT‐based radiomics analysis has the potential to serve as an effective tool for the differentiation of nodule/mass‐type PC from LC in clinical practice.

Supervised training models with or without manual lesion delineation outperform clinicians in distinguishing pulmonary cryptococcosis from lung adenocarcinoma on chest CT

“…Previous research has indicated that AI models utilising both CT images and clinical data exhibit superior performance compared to models relying solely on CT images or clinical features alone. 16,17,27 One notable advantage of this study is the presence of conclusive etiological evidence for all cases of PC, along with a larger sample size compared to previous relevant studies. [16][17][18]…”

“…16,17,27 One notable advantage of this study is the presence of conclusive etiological evidence for all cases of PC, along with a larger sample size compared to previous relevant studies. [16][17][18]…”

“…In order to achieve an accurate differentiation diagnosis for the majority of diseases, it is essential to conduct comprehensive assessments encompassing the patient's personal history, symptoms, signs, laboratory tests, radiological characteristics and other relevant data. Previous research has indicated that AI models utilising both CT images and clinical data exhibit superior performance compared to models relying solely on CT images or clinical features alone 16,17,27 . Consequently, our initial intention in this study was to develop an integrated model incorporating chest CT images alongside other pertinent data.…”

“…[12][13][14][15] The AI or radiomic models also demonstrated satisfactory performance in distinguishing between PC and lung tumours. [16][17][18] However, the majority of these studies primarily examined cases involving solitary pulmonary nodules, overlooking those with multiple nodules/masses or other radiological characteristics. Furthermore, previous researchers predominantly employed weakly supervised frameworks or automatic deep learning systems, rather than supervised training models incorporating manual lesion delineation.…”

“…Prior research has demonstrated the potential of AI in distinguishing between benign and malignant lung nodules 12–15 . The AI or radiomic models also demonstrated satisfactory performance in distinguishing between PC and lung tumours 16–18 . However, the majority of these studies primarily examined cases involving solitary pulmonary nodules, overlooking those with multiple nodules/masses or other radiological characteristics.…”