Differences in lung attenuation gradients between supine and standing positions in healthy participants on conventional/supine and upright computed tomography.

The effect of gravity on the lungs has been evaluated using computed tomography (CT) in the supine and prone positions but not the standing position. However, as humans spend most of the daytime in the standing position, we aimed to compare lung attenuation gradients between the supine and standing positions, and to assess the correlations between the lung attenuation gradients and participant characteristics, including pulmonary function test results. Overall, 100 healthy participants underwent conventional/supine and upright CT, and lung attenuation gradients were measured. Lung attenuation gradients in anteroposterior direction were greater in the supine position than in standing position (all p values < 0.0001) in both upper lobes at the level of the aortic arch (right: standing/supine, -0.02 ± 0.19/0.53 ± 0.21; left: standing/supine, -0.06 ± 0.20/0.51 ± 0.21); in the right middle (standing/supine, -0.26 ± 0.41/0.53 ± 0.39), left upper (standing/supine, -0.35 ± 0.50/0.66 ± 0.54), and lower lobes at the level of the inferior pulmonary vein (right: standing/supine, -0.22 ± 0.30/0.65 ± 0.41; left: standing/supine, -0.16 ± 0.25/0.73 ± 0.54); and in both lower lobes just above the diaphragm (right: standing/supine, -0.13 ± 0.22/0.52 ± 0.32; left: standing/supine, -0.30 ± 0.57/0.55 ± 0.37). Craniocaudal gradients were greater in the standing position (right: standing/supine, 0.41 ± 0.30/0.00 ± 0.16; left: standing/supine, 0.35 ± 0.30/-0.02 ± 0.16, all p values < 0.0001). No moderate to very high correlations were observed between age, sex, height, weight, body index mass, or pulmonary function test results and each lung attenuation gradient. Lung attenuation gradients in anteroposterior direction, which was observed in the supine position, disappeared in the standing position. However, the craniocaudal lung attenuation gradient, which was not present in the supine position, appeared in the standing position.

A comparison of conventional 3.0-Tesla nonenhanced magnetic resonance imaging and arthroscopic findings of the anteroinferior capsulolabral complex in patients with traumatic anterior shoulder instability.

Background: This study aimed to evaluate the association between specific, reproducible findings of an anteroinferior capsulolabral complex obtained using conventional 3.0-Tesla nonenhanced magnetic resonance imaging (MRI) and pathologic arthroscopic findings and to assess the confidence level of the findings. Methods: Of 125 cases of traumatic anterior instability surgery from January 2017 to November 2019, 66 patients (52 men, 14 women; 23.5 ± 7.9 year old) who underwent conventional 3.0-Tesla MRI at our hospital were reviewed. The following anteroinferior capsulolabral complex features were observed on the T2-star axial image: size difference of the labrum (swelling, diminished), difference in marginal and internal signals (irregularity), and capsule edema image (capsular thickening). We also reviewed fraying, flattening, cracking, and capsular hypertrophy as pathologic arthroscopic findings of the capsulolabral complex. These findings allowed for the simultaneous description of the MRI and arthroscopic evaluations. Three orthopedic surgeons and one radiologist measured the interobserver reliability. We investigated the correlation between the MRI and arthroscopic findings. Results: The interobserver reliability of MRI irregularities was low (κ = -0.16), whereas reliability was moderate (κ = 0.554-0.595) for swelling in 22 cases (33%), diminished in 34 cases (52%), and capsular thickness in 40 cases (59%). Labral detachment was found in 26 patients (39%) and fluid collection in 24 patients (36%). The agreement of MRI findings with arthroscopic findings was κ = 0.46 (95% confidence interval [CI]: 0.268-0.654) for swelling to fraying; κ = 0.42 (95% CI: 0.202-0.638) for swelling to capsular hypertrophy; and 0.46 (95% CI: 0.268-0.654) for flattening to diminished. Conclusion: The swelling and diminished findings of the anteroinferior capsulolabral complex on conventional MRI were moderately related to pathologic arthroscopic findings in patients with traumatic anterior shoulder instability. These findings contribute to achieving an accurate clinical diagnosis.

Recent trends in AI applications for pelvic MRI: a comprehensive review.

Magnetic resonance imaging (MRI) is an essential tool for evaluating pelvic disorders affecting the prostate, bladder, uterus, ovaries, and/or rectum. Since the diagnostic pathway of pelvic MRI can involve various complex procedures depending on the affected organ, the Reporting and Data System (RADS) is used to standardize image acquisition and interpretation. Artificial intelligence (AI), which encompasses machine learning and deep learning algorithms, has been integrated into both pelvic MRI and the RADS, particularly for prostate MRI. This review outlines recent developments in the use of AI in various stages of the pelvic MRI diagnostic pathway, including image acquisition, image reconstruction, organ and lesion segmentation, lesion detection and classification, and risk stratification, with special emphasis on recent trends in multi-center studies, which can help to improve the generalizability of AI.

Bone marrow edema detection for diagnostic support of axial spondyloarthritis using MRI.

PURPOSE: This study proposes a process for detecting slices with bone marrow edema (BME), a typical finding of axSpA, using MRI scans as the input. This process does not require manual input of ROIs and provides the results of the judgment of the presence or absence of BME on a slice and the location of edema as the rationale for the judgment. METHODS: First, the signal intensity of the MRI scans of the sacroiliac joint was normalized to reduce the variation in signal values between scans. Next, slices containing synovial joints were extracted using a slice selection network. Finally, the BME slice detection network determines the presence or absence of the BME in each slice and outputs the location of the BME. RESULTS: The proposed method was applied to 86 MRI scans collected from 15 hospitals in Japan. The results showed that the average absolute error of the slice selection process was 1.49 slices for the misalignment between the upper and lower slices of the synovial joint range. The accuracy, sensitivity, and specificity of the BME slice detection network were 0.905, 0.532, and 0.974, respectively. CONCLUSION: This paper proposes a process to detect the slice with BME and its location as the rationale of the judgment from an MRI scan and shows its effectiveness using 86 MRI scans. In the future, we plan to develop a process for detecting other findings such as bone erosion from MR scans, followed by the development of a diagnostic support system.

Childhood interstitial lung diseases: current understanding of the classification and imaging findings.

Childhood interstitial lung diseases (chILDs) encompass a diverse group of disorders with a high mortality rate and severe respiratory morbidities. Recent investigations have revealed that the classification of adult ILDs is not valid for chILDs, particularly for ILDs of early onset. Therefore, Children's Interstitial Lung Disease Research Cooperative of North America proposed a new classification of chILDs for affected children under 2 years of age, and later another classification for affected individuals between 2 and 18 years of age. In this review, we provide an overview of the imaging findings of chILDs by classification. Most infantile ILDs have unique clinical, radiological, and molecular findings, while the manifestation of pediatric ILDs overlaps with that of adult ILDs.

Evaluation of glenoid morphology and bony Bankart lesion in shoulders with traumatic anterior instability using zero echo time magnetic resonance imaging.

Background: Preoperative computed tomography (CT) evaluation of bone morphometry aids in determining treatment strategies for shoulder instability. The use of zero echo time (ZTE) sequence in magnetic resonance imaging (MRI), a new bone cortex imaging technique, may help reduce radiation exposure and medical costs. Therefore, this study aimed to evaluate the glenoid morphology and detect the presence of bony Bankart lesion using ZTE MRI in shoulders with anterior instability and compare its diagnostic accuracy with that of CT. Methods: Thirty-six patients (36 shoulders) with anterior instability who underwent preoperative CT and MRI examinations between April 2019 and October 2021 were retrospectively analyzed. The percentages of glenoid bone defects on 3-dimensional (3D) CT and ZTE images were determined, and the correlation between these percentages was evaluated. The number of cases with bony Bankart lesion on CT and 2 types of ZTE (3D and CT-like) images was determined, and the diagnostic accuracy of ZTE for detecting bony Bankart lesion was assessed, with CT as the gold standard. Patients with bony Bankart lesion on CT images were divided into 2 groups based on whether the lesion was detectable on 3D ZTE or CT-like images. The longer diameters of bony Bankart lesion were compared between the groups. Results: The median percentage of glenoid bone loss was 12.1% (range, 1.3%-45.9%) and 12.3% (range, 0%-46.6%) on 3D CT and 3D ZTE images, respectively. The Spearman's rank correlation coefficient was 0.89. Bony Bankart lesion was detected in 18, 13, and 8 shoulders of the 36 patients on CT, 3D ZTE, and CT-like images, respectively. The overall diagnostic accuracy of the CT-like and 3D ZTE images for detecting bony Bankart lesion was 86.1% and 72.2%, respectively. A significant difference was observed between the groups with and without bony Bankart lesion on CT-like images in terms of the long diameter of the bone fragments on CT (P < .01). Conclusion: ZTE MRI demonstrated high reproducibility for the evaluation of glenoid bone defect in shoulders with anterior instability. Although no significant difference in the measurement was observed compared with that on CT, the ability of ZTE MRI to delineate bone Bankart lesion remains limited.

Climate change and artificial intelligence in healthcare: Review and recommendations towards a sustainable future.

The rapid advancement of artificial intelligence (AI) in healthcare has revolutionized the industry, offering significant improvements in diagnostic accuracy, efficiency, and patient outcomes. However, the increasing adoption of AI systems also raises concerns about their environmental impact, particularly in the context of climate change. This review explores the intersection of climate change and AI in healthcare, examining the challenges posed by the energy consumption and carbon footprint of AI systems, as well as the potential solutions to mitigate their environmental impact. The review highlights the energy-intensive nature of AI model training and deployment, the contribution of data centers to greenhouse gas emissions, and the generation of electronic waste. To address these challenges, the development of energy-efficient AI models, the adoption of green computing practices, and the integration of renewable energy sources are discussed as potential solutions. The review also emphasizes the role of AI in optimizing healthcare workflows, reducing resource waste, and facilitating sustainable practices such as telemedicine. Furthermore, the importance of policy and governance frameworks, global initiatives, and collaborative efforts in promoting sustainable AI practices in healthcare is explored. The review concludes by outlining best practices for sustainable AI deployment, including eco-design, lifecycle assessment, responsible data management, and continuous monitoring and improvement. As the healthcare industry continues to embrace AI technologies, prioritizing sustainability and environmental responsibility is crucial to ensure that the benefits of AI are realized while actively contributing to the preservation of our planet.

Quantitative evaluation of natural progression of fatty infiltration and muscle atrophy in chronic rotator cuff tears without tear extension using magnetic resonance imaging.

Background: The pathology of and mechanisms underlying muscle degeneration remain unclear. We aimed to quantitatively evaluate the natural changes in fatty infiltration and muscle atrophy in patients with chronic rotator cuff tears using 3-dimensional 2-point Dixon magnetic resonance imaging. Methods: Thirty patients with nonoperatively observed rotator cuff tears without tear extension were evaluated using multiple magnetic resonance imaging examinations with a minimum interval of 2 years. The fatty infiltration ratio (%fat) and muscle volume of the rotator cuff muscles were compared between the 2 examinations in those with supraspinatus (SSP) tear <2 cm (<2 cm SSP group), SSP tear ≥2 cm (≥2 cm SSP group), and massive tear (massive group). The SSP) infraspinatus, and teres minor (ISP + TM), and subscapularis muscles were evaluated. Results: The massive group showed a significantly greater %fat than the <2 and ≥2 cm SSP groups in the SSP (P = .002) and ISP + TM muscles (P < .001). The total muscle volume did not differ among the 3 groups for all rotator cuff muscle components. The %fat values did not change in any rotator cuff components during the follow-up period in all groups. The total muscle volume in the massive group significantly decreased in the SSP (P = .018) and ISP + TM muscles (P = .013). Conclusion: The present results indicate that fatty infiltration of the torn muscle occurs in the early phase after a rotator cuff tear, whereas muscle atrophy appears to progress gradually in chronic rotator cuff tears. Early intervention before muscle degeneration should be considered if the tear involves the infraspinatus tendon.

RASopathies for Radiologists.

RASopathies are a heterogeneous group of genetic syndromes caused by germline mutations in a group of genes that encode components or regulators of the Ras/mitogen-activated protein kinase (MAPK) signaling pathway. RASopathies include neurofibromatosis type 1, Legius syndrome, Noonan syndrome, Costello syndrome, cardiofaciocutaneous syndrome, central conducting lymphatic anomaly, and capillary malformation-arteriovenous malformation syndrome. These disorders are grouped together as RASopathies based on our current understanding of the Ras/MAPK pathway. Abnormal activation of the Ras/MAPK pathway plays a major role in development of RASopathies. The individual disorders of RASopathies are rare, but collectively they are the most common genetic condition (one in 1000 newborns). Activation or dysregulation of the common Ras/MAPK pathway gives rise to overlapping clinical features of RASopathies, involving the cardiovascular, lymphatic, musculoskeletal, cutaneous, and central nervous systems. At the same time, there is much phenotypic variability in this group of disorders. Benign and malignant tumors are associated with certain disorders. Recently, many institutions have established multidisciplinary RASopathy clinics to address unique therapeutic challenges for patients with RASopathies. Medications developed for Ras/MAPK pathway-related cancer treatment may also control the clinical symptoms due to an abnormal Ras/MAPK pathway in RASopathies. Therefore, radiologists need to be aware of the concept of RASopathies to participate in multidisciplinary care. As with the clinical manifestations, imaging features of RASopathies are overlapping and at the same time diverse. As an introduction to the concept of RASopathies, the authors present major representative RASopathies, with emphasis on their imaging similarities and differences. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

The impact of large language models on radiology: a guide for radiologists on the latest innovations in AI.

The advent of Deep Learning (DL) has significantly propelled the field of diagnostic radiology forward by enhancing image analysis and interpretation. The introduction of the Transformer architecture, followed by the development of Large Language Models (LLMs), has further revolutionized this domain. LLMs now possess the potential to automate and refine the radiology workflow, extending from report generation to assistance in diagnostics and patient care. The integration of multimodal technology with LLMs could potentially leapfrog these applications to unprecedented levels.However, LLMs come with unresolved challenges such as information hallucinations and biases, which can affect clinical reliability. Despite these issues, the legislative and guideline frameworks have yet to catch up with technological advancements. Radiologists must acquire a thorough understanding of these technologies to leverage LLMs' potential to the fullest while maintaining medical safety and ethics. This review aims to aid in that endeavor.

Fast abdominal magnetic resonance elastography with simultaneous encoding of three-dimensional displacements.

Three-dimensional (3D) magnetic resonance elastography (MRE) is more accurate than two-dimensional (2D) MRE; however, it requires long-term acquisition. This study aimed to reduce the acquisition time of abdominal 3D MRE using a new sample interval modulation (short-SLIM) approach that can acquire all three motions faster while reducing the prolongation of echo time and flow compensation. To this end, two types of phantom studies and an in vivo test of the liver in three healthy volunteers were performed to compare the performances of conventional spin-echo echo-planar (SE-EPI) MRE, conventional SLIM and short-SLIM. One phantom study measured the mean amplitude and shear modulus within the overall region of a homogeneous phantom by changing the mechanical vibration power to assess the robustness to the lowered phase-to-noise ratio in short-SLIM. The other measured the mean shear modulus in the stiff and background materials of a phantom with an embedded stiffer rod to assess the performance of short-SLIM for complex wave patterns with wave interference. The Spearman's rank correlation coefficient was used to assess similarity of elastograms in the rod-embedded phantom and liver between methods. The results of the phantom study changing the vibration power indicated that there was little difference between conventional MRE and short-SLIM. Moreover, the elastogram pattern and the mean shear modulus in the rod-embedded phantom in conventional SLIM and short-SLIM did not change for conventional MRE; the liver test also showed a small difference between the acquisition techniques. This study demonstrates that short-SLIM can provide MRE results comparable to those of conventional MRE. Short-SLIM can reduce the total acquisition time by a factor of 2.25 compared to conventional 3D MRE time, leading to an improvement in the accuracy of shear modulus estimation by suppressing the patient movements.

Fairness of artificial intelligence in healthcare: review and recommendations.

In this review, we address the issue of fairness in the clinical integration of artificial intelligence (AI) in the medical field. As the clinical adoption of deep learning algorithms, a subfield of AI, progresses, concerns have arisen regarding the impact of AI biases and discrimination on patient health. This review aims to provide a comprehensive overview of concerns associated with AI fairness; discuss strategies to mitigate AI biases; and emphasize the need for cooperation among physicians, AI researchers, AI developers, policymakers, and patients to ensure equitable AI integration. First, we define and introduce the concept of fairness in AI applications in healthcare and radiology, emphasizing the benefits and challenges of incorporating AI into clinical practice. Next, we delve into concerns regarding fairness in healthcare, addressing the various causes of biases in AI and potential concerns such as misdiagnosis, unequal access to treatment, and ethical considerations. We then outline strategies for addressing fairness, such as the importance of diverse and representative data and algorithm audits. Additionally, we discuss ethical and legal considerations such as data privacy, responsibility, accountability, transparency, and explainability in AI. Finally, we present the Fairness of Artificial Intelligence Recommendations in healthcare (FAIR) statement to offer best practices. Through these efforts, we aim to provide a foundation for discussing the responsible and equitable implementation and deployment of AI in healthcare.

Revolutionizing radiation therapy: the role of AI in clinical practice.

This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist's perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.

The Prospective Natural History Study of Patients with Intractable Venous Malformation and Klippel-Trenaunay Syndrome to Guide Designing a Proof-of-Concept Clinical Trial for Novel Therapeutic Intervention.

Background: The natural history of venous malformation (VM) and Klippel-Trenaunay Syndrome (KTS) has not been quantitatively studied. To obtain benchmarks to guide designing clinical trials to assess safety and efficacy of novel drug candidates, the clinical course of the patients was followed for 6 months. Methods and Results: This is a multicenter prospective observational study evaluating the change rate in lesion volume from baseline with magnetic resonance images, as the primary endpoint. In addition, disease severities, performance status (PS), pain visual analog scale (VAS) score, quality of life (QoL), infections, and coagulation markers were also evaluated. Thirty-four patients (VM = 17, KTS = 17, 1-53 of age; median 15.9 years) with measurable lesion volume were analyzed. There was no statistically significant difference in the lesion volume between baseline and day 180, and the mean change rate (standard deviation) was 1.06 (0.28). There were no baseline characteristics that affected the change in lesion volume over 6 months. However, there were patients who showed more than 20% volume change and it was suggested that the lesion volume was largely impacted by local infection. There were no statistically significant changes in pain VAS score, severity, PS, QoL score, D-dimer, and platelet count over 6 months within all patients analyzed. Conclusion: The results showed the representative natural course of VM and KTS for a 6-month period with objective change of lesion volume and other factors, suggesting that it is scientifically reasonable to conduct a Phase 2 proof-of-concept study without a placebo arm, using the results of this study as the control. Clinical Trial Registration: NCT04285723, NCT04589650.

Quantitative Assessment of Calf Muscle Volume, Strength, and Quality After Achilles Tendon Rupture Repair: A 1-Year Prospective Follow-up Study.

BACKGROUND: A number of studies have reported that calf muscle atrophy is a common long-term problem after Achilles tendon repair; however, there is still a lack of data concerning early postoperative morphological changes in the calf muscle after surgery. PURPOSE: To investigate changes over time in calf muscle volume and fatty degeneration during 1 year after Achilles tendon repair. STUDY DESIGN: Cohort study; Level of evidence, 2. METHODS: A prospective 1-year serial magnetic resonance imaging study was carried out with 20 patients who underwent tendon repair for unilateral acute Achilles tendon rupture. The magnetic resonance imaging assessment in addition to clinical and functional evaluations was performed at 1, 3, 6, and 12 months after surgery. The muscle volume of the medial and lateral gastrocnemius, soleus, and flexor hallucis longus (FHL) and fatty degeneration of the medial and lateral gastrocnemius and soleus were measured for the calf muscles, and the relative volume and fatty degeneration changes in the affected leg compared with the healthy contralateral leg were calculated as a percentage ([injured/healthy control] × 100) to assess structural changes over time. RESULTS: Muscle volumes of the medial gastrocnemius, lateral gastrocnemius, soleus, and FHL were 92.3%, 92.8%, 84.6%, and 95.9% at 12 months after surgery, respectively. Medial and lateral gastrocnemius and FHL muscle volumes improved over time and recovered to almost equal to that of the healthy side at 12 months after surgery. The soleus muscle volume did not recover significantly over time and was statistically significantly smaller than that of the healthy side at 12 months (P = .029). Fatty degeneration rates of the medial gastrocnemius, lateral gastrocnemius, and soleus were 118.2%, 113.9% and 121.1% at 12 months after surgery, respectively. Fatty degeneration of the medial and lateral gastrocnemius did not change significantly, but there was a statistically significant increase in fatty degeneration of the soleus over time (P < .001). CONCLUSION: Within the triceps surae muscle, the soleus was the most negatively affected by injury and repair for both muscle volume and fatty degeneration. Postoperative management to recover the soleus muscle function before a return to sporting activities should be considered in the future.

Pediatric Ribs at Chest Radiography: Normal Variants and Abnormalities.

Normal variants and abnormalities of the ribs are frequently encountered on chest radiographs. Accurate identification of normal variants is crucial to avoid unnecessary investigations. A meticulous evaluation of rib abnormalities can provide valuable insights into the patient's symptoms, and even when no osseous condition is suspected, rib abnormalities may offer critical clues to underlying conditions. Rib abnormalities are associated with various conditions, including benign tumors, malignant tumors, infectious and inflammatory conditions, vascular abnormalities, metabolic disorders, nonaccidental injuries, malformation syndromes, and bone dysplasias. Abnormalities of the ribs are classified into three groups based on their radiographic patterns: focal, multifocal, and diffuse changes. Focal lesions are further subdivided into nonaggressive lesions, aggressive lesions, and infectious and inflammatory disorders. Radiologists should be aware of individual disorders of the pediatric ribs, including their imaging findings, relevant clinical information, and underlying pathogenesis. Differential diagnoses are addressed as appropriate. Since chest radiographs can suffice for diagnosis in certain cases, the authors emphasize a pattern recognition approach to radiographic interpretation. However, additional cross-sectional imaging may be necessary for focal lesions such as tumors or inflammatory conditions. Awareness of disease-specific imaging findings helps ascertain the nature of the lesion and directs appropriate management. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

From FDG and beyond: the evolving potential of nuclear medicine.

The radiopharmaceutical 2-[fluorine-18]fluoro-2-deoxy-D-glucose (FDG) has been dominantly used in positron emission tomography (PET) scans for over 20 years, and due to its vast utility its applications have expanded and are continuing to expand into oncology, neurology, cardiology, and infectious/inflammatory diseases. More recently, the addition of artificial intelligence (AI) has enhanced nuclear medicine diagnosis and imaging with FDG-PET, and new radiopharmaceuticals such as prostate-specific membrane antigen (PSMA) and fibroblast activation protein inhibitor (FAPI) have emerged. Nuclear medicine therapy using agents such as [177Lu]-dotatate surpasses conventional treatments in terms of efficacy and side effects. This article reviews recently established evidence of FDG and non-FDG drugs and anticipates the future trajectory of nuclear medicine.

New trend in artificial intelligence-based assistive technology for thoracic imaging.

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.