Perineural invasion detection in pancreatic ductal adenocarcinoma using artificial intelligence.

Perineural invasion (PNI) refers to the presence of cancer cells around or within nerves, raising the risk of residual tumor. Linked to worse prognosis in pancreatic ductal adenocarcinoma (PDAC), PNI is also being explored as a therapeutic target. The purpose of this work was to build a PNI detection algorithm to enhance accuracy and efficiency in identifying PNI in PDAC specimens. Training used 260 manually segmented nerve and tumor HD images from 6 scanned PDAC cases; Analytical performance analysis used 168 additional images; clinical analysis used 59 PDAC cases. The algorithm pinpointed key areas of tumor-nerve proximity for pathologist confirmation. Analytical performance reached sensitivity of 88% and 54%, and specificity of 78% and 85% for the detection of nerve and tumor, respectively. Incorporating tumor-nerve distance in clinical evaluation raised PNI detection from 52 to 81% of all cases. Interestingly, pathologist analysis required an average of only 24 s per case. This time-efficient tool accurately identifies PNI in PDAC, even with a small training cohort, by imitating pathologist thought processes.

Transbronchial Cryobiopsy Is Superior to Forceps Biopsy for Diagnosing both Fibrotic and Non-Fibrotic Interstitial Lung Diseases.

BACKGROUND: Interstitial lung disease (ILD) evaluation often requires lung biopsy for definite diagnosis. In recent years, transbronchial cryobiopsy (TBCB) emerged as a procedure with higher diagnostic yield than transbronchial forceps biopsy (TBFB), especially for fibrotic ILDs. Nonetheless, studies comparing these modalities in non-fibrotic ILDs and for specific ILD diagnoses are scarce. OBJECTIVES: The aim of this study was to evaluate the diagnostic yield and safety of TBCB and TBFB in patients with fibrotic and non-fibrotic ILDs. METHOD: An observational retrospective multicenter study including patients with ILD diagnosis by multidisciplinary discussion that underwent TBCB or TBFB between 2017 and 2021. Chest CT scans were reviewed by a chest radiologist. Biopsy specimens were categorized as diagnostic (with specific histological pattern), nondiagnostic, or without lung parenchyma. Nondiagnostic samples were reassessed by a second lung pathologist. TBCB and TBFB diagnostic yields were analyzed by multivariate regression. Procedural complications were evaluated as well. RESULTS: 276 patients were included, 116 (42%) underwent TBCB and 160 (58%) TBFB. Fibrotic ILDs were present in 148 patients (54%). TBCB diagnostic yield was 78% and TBFB 48% (adjusted odds ratio [AOR] 4.2, 95% CI: 2.4-7.6, p < 0.01). The diagnostic yield of TBCB was higher than TBFB among patients with fibrotic ILD (AOR 3.8, p < 0.01), non-fibrotic ILD (AOR 5.8, p < 0.01), and across most ILD diagnoses. TBCB was associated with higher risk for significant bleeding (10% vs. 3%, p < 0.01), but similar risk for pneumothorax. CONCLUSIONS: Diagnostic yield of TBCB was superior to that of TBFB for both fibrotic and non-fibrotic ILDs, and across most diagnoses.

Inhaled CD24-Enriched Exosomes (EXO-CD24) as a Novel Immune Modulator in Respiratory Disease.

Acute Respiratory Distress Syndrome (ARDS) is a major health concern with urgent unmet need for treatment options. There are three million new ARDS cases annually, and the disease's mortality rate is high (35-46%). Cluster of differentiation 24 (CD24), a long-known protein with multifaceted functions, is a small, heavily glycosylated, membrane-anchored protein which functions as an immune checkpoint control. CD24 allows for immune discrimination between Damage-Associated Molecular Patterns and Pathogen-Associated Molecular Patterns derived from pathogens. Exosomes are intraluminal vesicles which play an important role in intercellular communication. Exosomes offer the advantage of targeted delivery, which improves safety and efficacy. The safety and efficacy of EXO-CD24 is promising, as was shown in >180 ARDS patients in phase 1b/2a, phase 2b, and compassionate use. CD24 binds Damage-associated molecular patterns (DAMPs) and inhibits the activation of the NF-ĸB pathway, a pivotal mediator of inflammatory responses. In contrast to anti-inflammatory therapies that are cytokine-specific or steroids that shut down the entire immune system, EXO-CD24 acts upstream, reverting the immune system back to normal activity. Herein, the safety and efficacy of mEXO-CD24 is shown in murine models of several pulmonary diseases (sepsis, allergic asthma, Chronic Obstructive Pulmonary Disease(COPD), fibrosis). EXO CD24 can suppress the hyperinflammatory response in the lungs in several pulmonary diseases with a significant unmet need for treatment options.

Automatic ganglion cell detection for improving the efficiency and accuracy of hirschprung disease diagnosis.

Histopathologic diagnosis of Hirschsprung's disease (HSCR) is time consuming and requires expertise. The use of artificial intelligence (AI) in digital pathology is actively researched and may improve the diagnosis of HSCR. The purpose of this research was to develop an algorithm capable of identifying ganglion cells in digital pathology slides and implement it as an assisting tool for the pathologist in the diagnosis of HSCR. Ninety five digital pathology slides were used for the construction and training of the algorithm. Fifty cases suspected for HSCR (727 slides) were used as a validation cohort. Image sets suspected to contain ganglion cells were chosen by the algorithm and then reviewed and scored by five pathologists, one HSCR expert and 4 non-experts. The algorithm was able to identify ganglion cells with 96% sensitivity and 99% specificity (in normal colon) as well as to correctly identify a case previously misdiagnosed as non-HSCR. The expert was able to achieve perfectly accurate diagnoses based solely on the images suggested by the algorithm, with over 95% time saved. Non-experts would require expert consultation in 20-58% of the cases to achieve similar results. The use of AI in the diagnosis of HSCR can greatly reduce the time and effort required for diagnosis and improve accuracy.