The age distribution of the patients. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

Comparison experiments. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

External validation comparison results. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

Patient characteristics. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

Comparison with baseline methods. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

The details of the channel attention module. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

Ablation experiments. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

Pathological diagnosis. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

The details of ECRNet. by Ruijie Wang (5989841)

“…On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. …”

Impact of Manganese Carbonate Precipitation on Uranium(VI) Fate in Conditions Relevant to Carbonate-Buffered Aquifers by Surya Sujathan (11355082)

“…Reactive modeling of Mn and DIC data exhibited a decrease in the surface area normalized rate constants of MnCO_3(s) precipitation from 5.9 to 3.3 × 10^–8 mol m^–2 h^–1 with an increase in initial U(VI) from 0 to 500 μM. …”

Impact of Manganese Carbonate Precipitation on Uranium(VI) Fate in Conditions Relevant to Carbonate-Buffered Aquifers by Surya Sujathan (11355082)

“…Reactive modeling of Mn and DIC data exhibited a decrease in the surface area normalized rate constants of MnCO_3(s) precipitation from 5.9 to 3.3 × 10^–8 mol m^–2 h^–1 with an increase in initial U(VI) from 0 to 500 μM. …”

Ca²⁺ supplementation <i>in vitro</i> has no impact on the production of some cytokines by mouse γδ T and B cells. by Yusuf Cem Eskiocak (10789281)

Stimulation of murine <i>i</i>NKT cells, γδ T cells, or B cells in RPMI^suppl has no negative impact on cell viability. by Yusuf Cem Eskiocak (10789281)

Optimal time points for a three-colonoscopy screening program in the US. by Viktor Zaika (18611072)

“…Selected model parameters were increased and decreased by up to 50%. Dashed lines indicate average optimal points obtained for nominal simulations. …”

Variable Conformation of Benzophenone in a Series of Resorcinarene-Based Supramolecular Frameworks by Bao-Qing Ma (2540059)

“…The resorcinarene molecule adopts a chair conformation in <b>1</b>, giving rise to a 3D stepped network. …”

Variable Conformation of Benzophenone in a Series of Resorcinarene-Based Supramolecular Frameworks by Bao-Qing Ma (2540059)

“…The resorcinarene molecule adopts a chair conformation in <b>1</b>, giving rise to a 3D stepped network. …”

Variable Conformation of Benzophenone in a Series of Resorcinarene-Based Supramolecular Frameworks by Bao-Qing Ma (2540059)

“…The resorcinarene molecule adopts a chair conformation in <b>1</b>, giving rise to a 3D stepped network. …”

Variable Conformation of Benzophenone in a Series of Resorcinarene-Based Supramolecular Frameworks by Bao-Qing Ma (2540059)

“…The resorcinarene molecule adopts a chair conformation in <b>1</b>, giving rise to a 3D stepped network. …”

Variable Conformation of Benzophenone in a Series of Resorcinarene-Based Supramolecular Frameworks by Bao-Qing Ma (2540059)

“…The resorcinarene molecule adopts a chair conformation in <b>1</b>, giving rise to a 3D stepped network. …”

Variable Conformation of Benzophenone in a Series of Resorcinarene-Based Supramolecular Frameworks by Bao-Qing Ma (2540059)

“…The resorcinarene molecule adopts a chair conformation in <b>1</b>, giving rise to a 3D stepped network. …”