Development and external validation of a transfer learning-based system for the pathological diagnosis of colorectal cancer: a large emulated prospective study.

Background: The progress in Colorectal cancer (CRC) screening and management has resulted in an unprecedented caseload for histopathological diagnosis. While artificial intelligence (AI) presents a potential solution, the predominant emphasis on slide-level aggregation performance without thorough verification of cancer in each location, impedes both explainability and transparency. Effectively addressing these challenges is crucial to ensuring the reliability and efficacy of AI in histology applications. Method: In this study, we created an innovative AI algorithm using transfer learning from a polyp segmentation model in endoscopy. The algorithm precisely localized CRC targets within 0.25 mm² grids from whole slide imaging (WSI). We assessed the CRC detection capabilities at this fine granularity and examined the influence of AI on the diagnostic behavior of pathologists. The evaluation utilized an extensive dataset comprising 858 consecutive patient cases with 1418 WSIs obtained from an external center. Results: Our results underscore a notable sensitivity of 90.25% and specificity of 96.60% at the grid level, accompanied by a commendable area under the curve (AUC) of 0.962. This translates to an impressive 99.39% sensitivity at the slide level, coupled with a negative likelihood ratio of <0.01, signifying the dependability of the AI system to preclude diagnostic considerations. The positive likelihood ratio of 26.54, surpassing 10 at the grid level, underscores the imperative for meticulous scrutiny of any AI-generated highlights. Consequently, all four participating pathologists demonstrated statistically significant diagnostic improvements with AI assistance. Conclusion: Our transfer learning approach has successfully yielded an algorithm that can be validated for CRC histological localizations in whole slide imaging. The outcome advocates for the integration of the AI system into histopathological diagnosis, serving either as a diagnostic exclusion application or a computer-aided detection (CADe) tool. This integration has the potential to alleviate the workload of pathologists and ultimately benefit patients.

Deinococcus wulumuqiensis R12 synthesized silver nanoparticles with peroxidase-like activity for synergistic antibacterial application.

The use of a combination of several antibacterial agents for therapy holds great promise in reducing the dosage and side effects of these agents, improving their efficiency, and inducing potential synergistic therapeutic effects. Herein, this study provides an innovative antibacterial treatment strategy by synergistically combining R12-AgNPs with H2O2 therapy. R12-AgNPs were simply produced with the supernatant of an ionizing radiation-tolerant bacterium Deinococcus wulumuqiensis R12 by one-step under room temperature. In comparison with chemically synthesized AgNPs, the biosynthesized AgNPs presented fascinating antibacterial activity and peroxidase-like properties, which endowed it with the capability to catalyze the decomposition of H2O2 to generate hydroxyl radical. After the combination of R12-AgNPs and H2O2, an excellent synergistic bacteriostatic activity was observed for both Escherichia coli and Staphylococcus aureus, especially at low concentrations. In addition, in vitro cytotoxicity tests showed R12-AgNPs had good biocompatibility. Thus, this work presents a novel antibacterial agent that exhibits favorable synergistic antibacterial activity and low toxicity, without the use of antibiotics or a complicated synthesis process.

Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos).

BACKGROUND AND AIMS: We developed a system for computer-assisted diagnosis (CAD) for real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinomas (ESCCs) to assist the diagnosis of esophageal cancer. METHODS: A total of 6473 narrow-band imaging (NBI) images, including precancerous lesions, early ESCCs, and noncancerous lesions, were used to train the CAD system. We validated the CAD system using both endoscopic images and video datasets. The receiver operating characteristic curve of the CAD system was generated based on image datasets. An artificial intelligence probability heat map was generated for each input of endoscopic images. The yellow color indicated high possibility of cancerous lesion, and the blue color indicated noncancerous lesions on the probability heat map. When the CAD system detected any precancerous lesion or early ESCCs, the lesion of interest was masked with color. RESULTS: The image datasets contained 1480 malignant NBI images from 59 consecutive cancerous cases (sensitivity, 98.04%) and 5191 noncancerous NBI images from 2004 cases (specificity, 95.03%). The area under curve was 0.989. The video datasets of precancerous lesions or early ESCCs included 27 nonmagnifying videos (per-frame sensitivity 60.8%, per-lesion sensitivity, 100%) and 20 magnifying videos (per-frame sensitivity 96.1%, per-lesion sensitivity, 100%). Unaltered full-range normal esophagus videos included 33 videos (per-frame specificity 99.9%, per-case specificity, 90.9%). CONCLUSIONS: A deep learning model demonstrated high sensitivity and specificity for both endoscopic images and video datasets. The real-time CAD system has a promising potential in the near future to assist endoscopists in diagnosing precancerous lesions and ESCCs.

Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy.

The detection and removal of precancerous polyps via colonoscopy is the gold standard for the prevention of colon cancer. However, the detection rate of adenomatous polyps can vary significantly among endoscopists. Here, we show that a machine-learning algorithm can detect polyps in clinical colonoscopies, in real time and with high sensitivity and specificity. We developed the deep-learning algorithm by using data from 1,290 patients, and validated it on newly collected 27,113 colonoscopy images from 1,138 patients with at least one detected polyp (per-image-sensitivity, 94.38%; per-image-specificity, 95.92%; area under the receiver operating characteristic curve, 0.984), on a public database of 612 polyp-containing images (per-image-sensitivity, 88.24%), on 138 colonoscopy videos with histologically confirmed polyps (per-image-sensitivity of 91.64%; per-polyp-sensitivity, 100%), and on 54 unaltered full-range colonoscopy videos without polyps (per-image-specificity, 95.40%). By using a multi-threaded processing system, the algorithm can process at least 25 frames per second with a latency of 76.80 ± 5.60 ms in real-time video analysis. The software may aid endoscopists while performing colonoscopies, and help assess differences in polyp and adenoma detection performance among endoscopists.

The long non-coding RNA NONHSAG026900 predicts prognosis as a favorable biomarker in patients with diffuse large B-cell lymphoma.

Long non-coding RNAs are known to be involved in cancer progression, but their biological functions and prognostic values are still largely unexplored in diffuse large B-cell lymphoma. In this study, long non-coding RNAs expression was characterized in 1,403 samples including normal and diffuse large B-cell lymphoma by repurposing 7 microarray datasets. Compared with any stage of normal B cells, NONHSAG026900 expression was significantly decreased in tumor samples. And in germinal center B-cell subtype, the significantly higher expression of NONHSAG026900 indicated it was a favorable prognosis biomarker. Then the prognostic power of NONHSAG026900 was validated with another independent dataset and NONHSAG026900 improved the predictive power of International Prognostic Index as an independent factor. Moreover, functional prediction and validation demonstrated that NONHSAG026900 could inhibit cell cycle activity to restrain tumor proliferation. These findings identified NONHSAG026900 as a novel prognostic biomarker and offered a new therapeutic target for diffuse large B-cell lymphoma patients.

Biological effects of (125)i seeds radiation on A549 lung cancer cells: G2/M arrest and enhanced cell death.

External beam radiation (EBRT) and (125)I seeds continuous low dose rate radiation (CLDR) were used to treat patients with lung cancer. We herein investigated the biological effects of EBRT and CLDR on lung cancer cells. A549 human lung cancer cell line was thus exposed to different doses of EBRT and CLDR. CLDR was more efficient to inhibit cell growth than EBRT. CLDR induced increased DNA damage as evidenced by long-lasting p-H2AX activity. The enhanced inhibitory effects of CLDR on lung cancer cell growth may be, at least in part, due to the increased Bax/Bcl2 ratio and cyclin B1-mediated G2/M arrest.

Combined effects of C225 and 125-iodine seed radiation on colorectal cancer cells.

BACKGROUND: To characterize the effect of combined treatment of the anti-epidermal growth factor receptor (EGFR) monoclonal antibody C225 and 125-iodine (125I) seed radiation in human colorectal cancer. METHODS: We treated LS180 cells with 125I continuous low dose rate radiation in the presence and absence of 100 nM C225. The clonogenic capacity, cellular proliferation, cell cycle distribution, apoptosis, and molecular pathways of the cells following the treatments were analyzed in vitro. RESULTS: The sensitizer enhancement ratio of C225 was approximately 1.4. Treatment with C225 and radiation alone produced significant inhibition of cell growth, but combination therapy produced greater inhibition than either treatment administered alone. C225 increased the radiation-induced apoptosis and the fraction of γ-H2AX foci positive cells at 48 h after treatment. The Akt phosphorylation level was lower in the cells receiving the combination treatment than in the cells treated with radiation or C225 alone. CONCLUSIONS: These findings indicate that C225 sensitizes LS180 cells to 125I seed radiation. Growth inhibition is mediated by inducing apoptosis and not cell cycle arrest. Additionally, we confirmed that C225 impairs DNA repair by reducing the cellular level of the DNA-PKcs and Ku70 proteins. Furthermore, the inhibition of Akt signaling activation may be responsible for the C225-mediated radiosensitization.

The different biological effects of single, fractionated and continuous low dose rate irradiation on CL187 colorectal cancer cells.

PURPOSE: To determine the biological effectiveness of single, fractionated and continuous low dose rate irradiation on the human colorectal cancer cell line CL187 in vitro and explore the cellular mechanisms. MATERIALS AND METHODS: The CL187 cells were exposed to radiation of 6 MV X-ray at a high dose rate of 4Gy/min and 125I seed at a low dose rate of 2.77 cGy/h. Three groups were employed: single dose radiation group (SDR), fractionated dose radiation group (FDR) by 2Gy/f and continuous low dose rate radiation group (CLDR). Four radiation doses 2, 4, 6 and 8Gy were chosen and cells without irradiation as the control. The responses of CL187 cells to distinct modes of radiation were evaluated by the colony-forming assay, cell cycle progression as well as apoptosis analysis. In addition, we detected the expression patterns of DNA-PKcs, Ku70 and Ku80 by Western blotting. RESULTS: The relative biological effect for 125I seeds compared with 6 MV X-ray was 1.42. 48 hrs after 4Gy irradiation, the difference between proportions of cells at G2/M phase of SDR and CLDR groups were statistically significant (p = 0.026), so as the FDR and CLDR groups (p = 0.005). 48 hrs after 4Gy irradiation, the early apoptotic rate of CLDR group was remarkably higher than SDR and FDR groups (CLDR vs. SDR, p = 0.001; CLDR vs. FDR, p = 0.02), whereas the late apoptotic rate of CLDR group increased significantly compared with SDR and FDR group (CLDR vs. SDR, p = 0.004; CLDR vs. FDR, p = 0.007). Moreover, DNA-PKcs and Ku70 expression levels in CLDR-treated cells decreased compared with SDR and FDR groups. CONCLUSIONS: Compared with the X-ray high dose rate irradiation, 125I seeds CLDR showed more effective induction of cell apoptosis and G2/M cell cycle arrest. Furthermore, 125I seeds CLDR could impair the DNA repair capability by down-regulating DNA-PKcs and Ku70 expression.