Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm.

BACKGROUND AND AIMS: Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance. METHODS: A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 board-certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. RESULTS: External validation of the AI algorithm yielded values of 90%, 76%, and 84% for sensitivity, specificity, and accuracy, respectively. Fellows scored corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable. CONCLUSIONS: In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases.

Fatal cases after Omicron BA.1 and BA.2 infection: Results of an autopsy study.

OBJECTIVES: Omicron lineages BA.1/2 are considered to cause mild clinical courses. Nevertheless, fatal cases after those infections are recognized but little is known about risk factors. METHODS: A total of 23 full and three partial autopsies in deceased with known Omicron BA.1/2 infections have been consecutively performed. The investigations included histology, blood analyses, and molecular virus detection. RESULTS: COVID-19-associated diffuse alveolar damage was found in only eight cases (31%). This rate is significantly lower compared with previous studies, including non-Omicron variants, where rates between 69% and 92% were observed. Neither vaccination nor known risk factors were significantly associated with a direct cause of death by COVID-19. Only those patients who were admitted to the clinic because of COVID-19 but not for other reasons had a significant association with a direct COVID-19 -caused death (P >0.001). CONCLUSION: Diffuse alveolar damage still occurred in the Omicron BA.1/BA.2 era but at a considerably lower frequency than seen with previous variants of concern. None of the known risk factors discriminated the cases with COVID-19-caused death from those that died because of a different disease. Therefore, the host's genomics might play a key role in this regard. Further studies should elucidate the existence of such a genomic risk factor.

[Benign and malignant neoplasms of the adrenal glands from the perspective of pathology]. / Benigne und maligne Neoplasien der Nebenniere aus der Sicht der Pathologie.

In the case of neoplasms of the adrenal glands that are radiologically and clinically unclear, the indications for surgical resection as well as the subsequent clarification of the entity and dignity on the surgical specimen are difficult. The diagnostics of adrenal neoplasms, in particular the clear distinction between an adenoma and a carcinoma are often tricky from the point of view of a pathologist. In the following, not only the problems of classification and the possibilities of diagnostics in pathology but also an overview of the most important differential diagnoses of other benign and malignant tumors of the adrenal cortex and medulla are presented.

ALK, NUT, and TRK Do Not Play Relevant Roles in Gastric Cancer-Results of an Immunohistochemical Study in a Large Series.

ALK, NUT, and TRK are rare molecular aberrations that are pathognomonic for specific rare tumors. In low frequencies, however, they are found in a wide range of other tumor entities. This study aimed to investigate the frequency, association with clinicopathological characteristics, and prognosis of the immunohistochemical expressions of ALK, NUT, and TRK in 477 adenocarcinomas of the stomach and gastroesophageal junction. Seven cases (1.5%) showed an expression of TRK. In NGS, no NTRK fusion was confirmed. No case with ALK or NUT expression was detected. ALK, NUT, and NTRK expression does not seem to play an important role in gastric carcinomas.

Stroma AReactive Invasion Front Areas (SARIFA)-A New Easily to Determine Biomarker in Colon Cancer-Results of a Retrospective Study.

Many studies have used histomorphological features to more precisely predict the prognosis of patients with colon cancer, focusing on tumor budding, poorly differentiated clusters, and the tumor-stroma ratio. Here, we introduce SARIFA: Stroma AReactive Invasion Front Area(s). We defined SARIFA as the direct contact between a tumor gland/tumor cell cluster (≥5 cells) and inconspicuous surrounding adipose tissue in the invasion front. In this retrospective, single-center study, we classified 449 adipose-infiltrative adenocarcinomas (not otherwise specified) from two groups based on SARIFA and found 25% of all tumors to be SARIFA-positive. Kappa values between the two pathologists were good/very good: 0.77 and 0.87. Patients with SARIFA-positive tumors had a significantly shorter colon-cancer-specific survival (p = 0.008, group A), absence of metastasis, and overall survival (p < 0.001, p = 0.003, group B). SARIFA was significantly associated with adverse features such as pT4 stage, lymph node metastasis, tumor budding, and higher tumor grade. Moreover, SARIFA was confirmed as an independent prognostic indicator for colon-cancer-specific survival (p = 0.011, group A). SARIFA assessment was very quick (<1 min). Because of low interobserver variability and good prognostic significance, SARIFA seems to be a promising histomorphological prognostic indicator in adipose-infiltrative adenocarcinomas of the colon. Further studies should validate our results and also determine whether SARIFA is a universal prognostic indicator in solid cancers.

Semiautomatic analysis of tumor proportion in colon cancer: Lessons from a validation study.

The tumor stroma ratio (TSR) is a promising histopathologic prognostic biomarker, which could allow for more accurate risk stratification and improved patient management in colorectal cancer. The purpose of our research was to validate the results of a previous study, which had suggested that not only a low but also a high tumor proportion (TP) might be an independent risk factor for occurrence of distant metastasis and worse overall survival using a semiautomatic image analysis approach with the open-source software ImageJ. We investigated 253 pT3 and pT4 adenocarcinomas of no special type. The previously established thresholds (PES-cut-offs) used to classify the patients (previous 3-tiered-classification) according to the tumor proportion (TP) in a highTP (TP ≥ 54%), a mediumTP (TP < 54% ∩ TP >15%) and a lowTP (TP ≤ 15%) group did not show a significant risk stratification. Even the adjustment of these threshold revealed no significant results. Therefore, a receiver-operating characteristic (ROC) analysis was performed to establish the cut-off with the most significant predictive power and a "new 2-tiered-classification" using this cut-off (40% at MinTP) showed a significantly shorter absence of metastasis for patients with a low TP (p = 0.007). These results confirm that a low TP is associated with an adverse prognosis. This study did not confirm the previous assumption that a high TP might also be a risk factor for occurrence of metastasis. Furthermore, it demonstrates that this semiautomatic technique is not superior to the established method, so that approaches to enhance prognostic techniques should continue.

Deep Learning Prediction of Metastasis in Locally Advanced Colon Cancer Using Binary Histologic Tumor Images.

In this study, we developed the Binary ImaGe Colon Metastasis classifier (BIg-CoMet), a semi-guided approach for the stratification of colon cancer patients into two risk groups for the occurrence of distant metastasis, using an InceptionResNetV2-based deep learning model trained on binary images. We enrolled 291 colon cancer patients with pT3 and pT4 adenocarcinomas and converted one cytokeratin-stained representative tumor section per case into a binary image. Image augmentation and dropout layers were incorporated to avoid overfitting. In a validation collective (n = 128), BIg-CoMet was able to discriminate well between patients with and without metastasis (AUC: 0.842, 95% CI: 0.774-0.911). Further, the Kaplan-Meier curves of the metastasis-free survival showed a highly significant worse clinical course for the high-risk group (log-rank test: p < 0.001), and we demonstrated superiority over other established risk factors. A multivariable Cox regression analysis adjusted for confounders supported the use of risk groups as a prognostic factor for the occurrence of metastasis (hazard ratio (HR): 5.4, 95% CI: 2.5-11.7, p < 0.001). BIg-CoMet achieved good performance for both UICC subgroups, especially for UICC III (n = 53), with a positive predictive value of 80%. Our study demonstrates the ability to stratify colon cancer patients via a semi-guided process on images that primarily reflect tumor architecture.