Interstitial lung disease?the new synergy between radiology and pathology

Development of an Artificial Intelligence Model for Analyzing the Relationship between Imaging Features and Glucocorticoid Sensitivity in Idiopathic Interstitial Pneumonia

High-resolution CT (HRCT) imaging features of idiopathic interstitial pneumonia (IIP) patients are related to glucocorticoid sensitivity. This study aimed to develop an artificial intelligence model to assess glucocorticoid efficacy according to the HRCT imaging features of IIP. The medical records and chest HRCT images of 150 patients with IIP were analyzed retrospectively. The U-net framework was used to create a model for recognizing different imaging features, including ground glass opacities, reticulations, honeycombing, and consolidations. Then, the area ratio of those imaging features was calculated automatically. Forty-five patients were treated with glucocorticoids, and according to the drug efficacy, they were divided into a glucocorticoid-sensitive group and a glucocorticoid-insensitive group. Models assessing the correlation between imaging features and glucocorticoid sensitivity were established using the k-nearest neighbor (KNN) algorithm. The total accuracy (ACC) and mean intersection over union (mIoU) of the U-net model were 0.9755 and 0.4296, respectively. Out of the 45 patients treated with glucocorticoids, 34 and 11 were placed in the glucocorticoid-sensitive and glucocorticoid-insensitive groups, respectively. The KNN-based model had an accuracy of 0.82. An artificial intelligence model was successfully developed for recognizing different imaging features of IIP and a preliminary model for assessing the correlation between imaging features and glucocorticoid sensitivity in IIP patients was established.

Comparisons of Prognosis between Surgically and Clinically Diagnosed Idiopathic Pulmonary Fibrosis Using Gap Model: A Korean National Cohort Study

Although a multidisciplinary approach has become an important criterion for an idiopathic pulmonary fibrosis (IPF) diagnosis, lung biopsies remain crucial. However, the prognosis of patients with surgically diagnosed IPF (sIPF) is uncertain. We aimed to investigate the prognosis of patients with clinically diagnosed IPF (cIPF) and sIPF. In this retrospective observational study, the Korean Interstitial Lung Disease Study Group conducted a national survey to evaluate the clinical, physiological, radiological, and survival characteristics of patients with IPF from January 1, 2003 to December 31, 2007. Patients were recruited from 54 universities and teaching hospitals across the Republic of Korea. IPF diagnoses were established according to the 2002 American Thoracic Society (ATS)/European Respiratory Society criteria (ERS) guideline. A total of 1685 patients with IPF (1027 cIPF and 658 sIPF) were enrolled. Patients with sIPF were significantly younger, predominantly female, and nonsmokers (all P < 0.001). sIPF group had significantly better initial pulmonary function. The proportion of computed tomography-based honeycomb findings of patients with cIPF was higher than in those with sIPF (P < 0.001). A Kaplan-Meier analysis showed that the sIPF group had a better prognosis (P = 0.001). A survival analysis showed that age, pulmonary function parameters, pulmonary oxygen tension, honeycombing change, and combined lung cancer had a significant influence on patient prognosis. However, there was no significant difference in prognosis between the cIPF and sIPF groups after adjusting for GAP (gender, age, physiology) stage. The patients with sIPF had better clinical features than those with cIPF. However, after adjusting for GAP stage, the sIPF group showed similar prognoses as the cIPF group. This study showed that after adjusting for GAP stage, the prognosis of patients with IPF is the same regardless of the diagnostic method used.

[Lung disease associated with connective tissue disease]

Connective tissue diseases are often associated with lung diseases that lead to high morbidity and mortality, including interstitial disease, airway disease, pleural lesions, and vascular disease. High resolution CT has high sensitivity for detecting parenchymal disease and potentially reversible lesions, helping to guide treatment. This article emphasizes interstitial pneumonia in association with connective tissue disease and the characteristics that differentiate this entity from idiopathic types. Likewise, we review the most common pulmonary manifestations of each connective tissue disease with the aim of providing the radiologist with a practical approach to the diagnosis and management of these diseases in daily clinical practice.

The role of histology in idiopathic pulmonary fibrosis: an update

The diagnosis of idiopathic pulmonary fibrosis (IPF) currently requires an integrated clinical-radiological-pathological approach in which the histology plays a different role from in the past. The first reason for this change is that non-invasive diagnostic procedures, particularly pulmonary function tests and high resolution computed tomography, have become increasingly competitive with biopsy in providing prognostic information. The other reason is a better appreciation of the limitations of histology: sampling error and interobserver variation. In this review we analyze the reasons for this change of perspective, provide an update on the practical role of histology in the diagnosis of IPF and discuss some of its complications.

Diagnosis of usual interstitial pneumonia and distinction from other fibrosing interstitial lung diseases

Usual interstitial pneumonia is an almost uniformly fatal form of fibrosing interstitial lung disease. It is the most common idiopathic interstitial pneumonia, and currently, there is no effective therapy. Lung biopsy is often needed for diagnosis, and pathologists must be able to recognize its features and distinguish it from other interstitial lung diseases that have a better prognosis and a more favorable response to therapy. This review is an attempt to clarify the diagnostic pathologic features of usual interstitial pneumonia and to provide guidelines for its distinction from other interstitial lung diseases that enter the differential diagnosis.

Shirt-sleeve or scanning magnification as an aid to the diagnosis of commonly encountered medical lung diseases

Shirt-sleeve magnification (holding a slide over a white sleeve) and low-power magnification serve as useful adjuncts in the general categorization of noninfectious medical lung disease. This article divides medical lung disease into chronic and acute, where the temporality is determined first by clinical circumstances and then confirmed by histopathology. The low-power patterns of various lung diseases overlap, sometimes greatly. Nevertheless, classic examples of chronic disease can be sorted as linear, lobular filling, nodular dispersed, nodular lymphangitic, or cystic patterns at shirt-sleeve or low-power magnification. Classic examples of acute disease generally produce a solidifying pattern at shirt-sleeve or low-power magnification, which can be followed by a determination as to whether alveolar filling is principally fibrotic or principally fluid or cells at higher magnification. This article gives a simple system for the categorization of medical lung disease by this approach, with an emphasis on the most common diseases to be encountered in a general surgical pathology practice. In our experience, this system also proves useful in arriving at some therapeutic decisions.

Interstitial Lung Diseases

Several noninfectious nonneoplastic interstitial lung diseases (ILDs) have been recognized in dogs and cats. Overall, these ILDs are poorly characterized in dogs and cats, although awareness of the conditions based on descriptions of clinical case series may be increasing. Lung biopsy remains crucial to the diagnosis, characterization, and classification of ILDs. Histopathologic findings can help to guide clinicians in selecting appropriate therapy and providing an accurate prognosis to pet owners. Only with definitive recognition of these pulmonary conditions can our knowledge of the clinical course and response to therapy be improved.