Deep learning assists detection of esophageal cancer and precursor lesions in a prospective, randomized controlled study.

Endoscopy is the primary modality for detecting asymptomatic esophageal squamous cell carcinoma (ESCC) and precancerous lesions. Improving detection rate remains challenging. We developed a system based on deep convolutional neural networks (CNNs) for detecting esophageal cancer and precancerous lesions [high-risk esophageal lesions (HrELs)] and validated its efficacy in improving HrEL detection rate in clinical practice (trial registration ChiCTR2100044126 at www.chictr.org.cn). Between April 2021 and March 2022, 3117 patients ≥50 years old were consecutively recruited from Taizhou Hospital, Zhejiang Province, and randomly assigned 1:1 to an experimental group (CNN-assisted endoscopy) or a control group (unassisted endoscopy) based on block randomization. The primary endpoint was the HrEL detection rate. In the intention-to-treat population, the HrEL detection rate [28 of 1556 (1.8%)] was significantly higher in the experimental group than in the control group [14 of 1561 (0.9%), P = 0.029], and the experimental group detection rate was twice that of the control group. Similar findings were observed between the experimental and control groups [28 of 1524 (1.9%) versus 13 of 1534 (0.9%), respectively; P = 0.021]. The system's sensitivity, specificity, and accuracy for detecting HrELs were 89.7, 98.5, and 98.2%, respectively. No adverse events occurred. The proposed system thus improved HrEL detection rate during endoscopy and was safe. Deep learning assistance may enhance early diagnosis and treatment of esophageal cancer and may become a useful tool for esophageal cancer screening.

Anoikis-related signature identifies tumor microenvironment landscape and predicts prognosis and drug sensitivity in colorectal cancer.

Background: Anoikis, a mechanism of programmed apoptosis, plays an important role in growth and metastasis of tumors. However, there are still few available comprehensive reports on the impact of anoikis on colorectal cancer. Method: A clustering analysis was done on 133 anoikis-related genes in GSE39582, and we compared clinical features between clusters, the tumor microenvironment was analyzed with algorithms such as "Cibersort" and "ssGSEA". We investigated risk scores of clinical feature groups and anoikis-associated gene mutations after creating a predictive model. We incorporated clinical traits to build a nomogram. Additionally, the quantitative real-time PCR was employed to investigate the mRNA expression of selected anoikis-associated genes. Result: We identified two anoikis-related clusters with distinct prognoses, clinical characteristics, and biological functions. One of the clusters was associated with anoikis resistance, which activated multiple pathways encouraging tumor metastasis. In our prognostic model, oxaliplatin may be a sensitive drug for low-risk patients. The nomogram showed good ability to predict survival time. And SIRT3, PIK3CA, ITGA3, DAPK1, and CASP3 increased in CRC group through the PCR assay. Conclusion: Our study identified two distinct modes of anoikis in colorectal cancer, with active metastasis-promoting pathways inducing an anti-anoikis subtype, which has a stronger propensity for metastasis and a worse prognosis than an anoikis-activated subtype. Massive immune cell infiltration may be an indicator of anoikis resistance. Anoikis' role in the colorectal cancer remains to be investigated.