Thoracic radiology has emerged as a primary field in which artificial intelligence (AI) is extensively researched. Recent advancements highlight the potential to enhance radiologists’ performance through AI. AI aids in detecting and classifying abnormalities, and in quantifying both normal and abnormal anatomical structures. Additionally, it facilitates prognostication by leveraging these quantitative values. This review article will discuss the recent achievements of AI in thoracic radiology, focusing primarily on deep learning, and explore the current limitations and future directions of this cutting-edge technique.

Pneumocystis jirovecii pneumonia (PJP) is a life-threatening infection commonly observed in immunocompromised patients, necessitating prompt diagnosis and treatment. This review evaluates the diagnostic performance of various tests used for PJP diagnosis through a comprehensive literature review. Additionally, we propose a diagnostic algorithm tailored to non-human immunodeficiency virus immunocompromised patients, considering the specific characteristics of current medical resources in Korea.

Thoracic radiology has emerged as a primary field in which artificial intelligence (AI) is extensively researched. Recent advancements highlight the potential to enhance radiologists’ performance through AI. AI aids in detecting and classifying abnormalities, and in quantifying both normal and abnormal anatomical structures. Additionally, it facilitates prognostication by leveraging these quantitative values. This review article will discuss the recent achievements of AI in thoracic radiology, focusing primarily on deep learning, and explore the current limitations and future directions of this cutting-edge technique.

Thoracic radiology has emerged as a primary field in which artificial intelligence (AI) is extensively researched. Recent advancements highlight the potential to enhance radiologists’ performance through AI. AI aids in detecting and classifying abnormalities, and in quantifying both normal and abnormal anatomical structures. Additionally, it facilitates prognostication by leveraging these quantitative values. This review article will discuss the recent achievements of AI in thoracic radiology, focusing primarily on deep learning, and explore the current limitations and future directions of this cutting-edge technique.

Pneumocystis jirovecii pneumonia (PJP) is a life-threatening infection commonly observed in immunocompromised patients, necessitating prompt diagnosis and treatment. This review evaluates the diagnostic performance of various tests used for PJP diagnosis through a comprehensive literature review. Additionally, we propose a diagnostic algorithm tailored to non-human immunodeficiency virus immunocompromised patients, considering the specific characteristics of current medical resources in Korea.

Thoracic radiology has emerged as a primary field in which artificial intelligence (AI) is extensively researched. Recent advancements highlight the potential to enhance radiologists’ performance through AI. AI aids in detecting and classifying abnormalities, and in quantifying both normal and abnormal anatomical structures. Additionally, it facilitates prognostication by leveraging these quantitative values. This review article will discuss the recent achievements of AI in thoracic radiology, focusing primarily on deep learning, and explore the current limitations and future directions of this cutting-edge technique.

Pneumocystis jirovecii pneumonia (PJP) is a life-threatening infection commonly observed in immunocompromised patients, necessitating prompt diagnosis and treatment. This review evaluates the diagnostic performance of various tests used for PJP diagnosis through a comprehensive literature review. Additionally, we propose a diagnostic algorithm tailored to non-human immunodeficiency virus immunocompromised patients, considering the specific characteristics of current medical resources in Korea.

Thoracic radiology has emerged as a primary field in which artificial intelligence (AI) is extensively researched. Recent advancements highlight the potential to enhance radiologists’ performance through AI. AI aids in detecting and classifying abnormalities, and in quantifying both normal and abnormal anatomical structures. Additionally, it facilitates prognostication by leveraging these quantitative values. This review article will discuss the recent achievements of AI in thoracic radiology, focusing primarily on deep learning, and explore the current limitations and future directions of this cutting-edge technique.

Intrahepatic cholangiocarcinoma (iCCA) is a heterogeneous bile duct adenocarcinoma with a rising global incidence and a poor prognosis. This review aims to present a comprehensive overview of the most recent radiological research on iCCA, focusing on its histopathologic subclassification and the use of imaging findings to predict prognosis and inform treatment decisions. Histologically, iCCA is subclassified into small duct (SD-iCCA) and large duct (LD-iCCA) types. SD-iCCA typically arises in the peripheral small bile ducts and is often associated with chronic hepatitis or cirrhosis. It presents as a mass-forming lesion with a relatively favorable prognosis. LD-iCCA originates near the hepatic hilum, is linked to chronic bile duct diseases, and exhibits more aggressive behavior and poorer outcomes.Imaging is essential for differentiating these subtypes and assessing prognostic factors like tumor size, multiplicity, vascular invasion, lymph node metastasis, enhancement patterns, and intratumoral fibrosis. Imaging-based prognostic models have demonstrated predictive accuracy comparable to traditional pathological staging systems. Furthermore, imaging findings are instrumental in guiding treatment decisions, including those regarding surgical planning, lymphadenectomy, neoadjuvant therapy, and the selection of targeted therapies based on molecular profiling. Advancements in radiological research have improved our understanding of iCCA heterogeneity, facilitating prognosis prediction and treatment personalization. Imaging findings assist in subclassifying iCCA, predicting outcomes, and informing treatment decisions, thus optimizing patient management. Incorporating imaging-based approaches into clinical practice is crucial for advancing personalized medicine in the treatment of iCCA. However, further high-level evidence from international multicenter prospective studies is required to validate these findings and increase their clinical applicability.

Intrahepatic cholangiocarcinoma (iCCA) is a heterogeneous bile duct adenocarcinoma with a rising global incidence and a poor prognosis. This review aims to present a comprehensive overview of the most recent radiological research on iCCA, focusing on its histopathologic subclassification and the use of imaging findings to predict prognosis and inform treatment decisions. Histologically, iCCA is subclassified into small duct (SD-iCCA) and large duct (LD-iCCA) types. SD-iCCA typically arises in the peripheral small bile ducts and is often associated with chronic hepatitis or cirrhosis. It presents as a mass-forming lesion with a relatively favorable prognosis. LD-iCCA originates near the hepatic hilum, is linked to chronic bile duct diseases, and exhibits more aggressive behavior and poorer outcomes.Imaging is essential for differentiating these subtypes and assessing prognostic factors like tumor size, multiplicity, vascular invasion, lymph node metastasis, enhancement patterns, and intratumoral fibrosis. Imaging-based prognostic models have demonstrated predictive accuracy comparable to traditional pathological staging systems. Furthermore, imaging findings are instrumental in guiding treatment decisions, including those regarding surgical planning, lymphadenectomy, neoadjuvant therapy, and the selection of targeted therapies based on molecular profiling. Advancements in radiological research have improved our understanding of iCCA heterogeneity, facilitating prognosis prediction and treatment personalization. Imaging findings assist in subclassifying iCCA, predicting outcomes, and informing treatment decisions, thus optimizing patient management. Incorporating imaging-based approaches into clinical practice is crucial for advancing personalized medicine in the treatment of iCCA. However, further high-level evidence from international multicenter prospective studies is required to validate these findings and increase their clinical applicability.