Robust cell nuclei segmentation using statistical modelling

Assessing the performance of four different categories of histological criteria in brain tumours grading by means of a computer‐aided diagnosis image analysis system

“…Nuclei images are characterized by a polymorph background composed of extra‐ and intracellular structures, membranes, and surrounding tissue (Mouroutis et al ., ; Spyridonos et al ., ). The most important regions within these images are nuclei that have long been recognized as significant indicators of tumours malignancy (Van De Wouwer et al ., ).…”

Assessing the performance of four different categories of histological criteria in brain tumours grading by means of a computer‐aided diagnosis image analysis system

“…Nuclei images are characterized by a polymorph background composed of extra‐ and intracellular structures, membranes, and surrounding tissue (Mouroutis et al ., ; Spyridonos et al ., ). The most important regions within these images are nuclei that have long been recognized as significant indicators of tumours malignancy (Van De Wouwer et al ., ).…”

Deep-learning based breast cancer detection for cross-staining histopathology images

“…In this study, we used nucleus instance accuracy to evaluate the performance of tumor recognition. By executing the computer vision-based nuclei positioning and counting algorithms presented in previous studies [ [27] , [28] , [29] ], the tumor nucleus instances within the tumor area delineated by pathologists for all testing images could be obtained. Then, the nucleus instances of the ground truth were compared with those of the tumor area predicted by AI models using intersection over union (IoU), and the corresponding confusion matrices with sensitivities and specificities of the proposed AI models were calculated.…”

Semi‐automated software for the three‐dimensional delineation of complex vascular networks

“…Radial searching is performed from this centre point to find likely object boundary points (Mouroutis et al ., 1998; Barber et al ., 2000) based on the response of the Sobel filters. The searching range is based on an approximate seed radius and is typically 0.75–1.5 times this value.…”

Assessing the performance of four different categories of histological criteria in brain tumours grading by means of a computer‐aided diagnosis image analysis system

“…Nuclei images are characterized by a polymorph background composed of extra‐ and intracellular structures, membranes, and surrounding tissue (Mouroutis et al ., ; Spyridonos et al ., ). The most important regions within these images are nuclei that have long been recognized as significant indicators of tumours malignancy (Van De Wouwer et al ., ).…”

Deep-learning based breast cancer detection for cross-staining histopathology images

“…In this study, we used nucleus instance accuracy to evaluate the performance of tumor recognition. By executing the computer vision-based nuclei positioning and counting algorithms presented in previous studies [ [27] , [28] , [29] ], the tumor nucleus instances within the tumor area delineated by pathologists for all testing images could be obtained. Then, the nucleus instances of the ground truth were compared with those of the tumor area predicted by AI models using intersection over union (IoU), and the corresponding confusion matrices with sensitivities and specificities of the proposed AI models were calculated.…”

Semi‐automated software for the three‐dimensional delineation of complex vascular networks

“…Radial searching is performed from this centre point to find likely object boundary points (Mouroutis et al ., 1998; Barber et al ., 2000) based on the response of the Sobel filters. The searching range is based on an approximate seed radius and is typically 0.75–1.5 times this value.…”

Assessing the performance of four different categories of histological criteria in brain tumours grading by means of a computer‐aided diagnosis image analysis system

“…Nuclei images are characterized by a polymorph background composed of extra‐ and intracellular structures, membranes, and surrounding tissue (Mouroutis et al ., ; Spyridonos et al ., ). The most important regions within these images are nuclei that have long been recognized as significant indicators of tumours malignancy (Van De Wouwer et al ., ).…”

Deep-learning based breast cancer detection for cross-staining histopathology images

“…In this study, we used nucleus instance accuracy to evaluate the performance of tumor recognition. By executing the computer vision-based nuclei positioning and counting algorithms presented in previous studies [ [27] , [28] , [29] ], the tumor nucleus instances within the tumor area delineated by pathologists for all testing images could be obtained. Then, the nucleus instances of the ground truth were compared with those of the tumor area predicted by AI models using intersection over union (IoU), and the corresponding confusion matrices with sensitivities and specificities of the proposed AI models were calculated.…”

Semi‐automated software for the three‐dimensional delineation of complex vascular networks

“…Radial searching is performed from this centre point to find likely object boundary points (Mouroutis et al ., 1998; Barber et al ., 2000) based on the response of the Sobel filters. The searching range is based on an approximate seed radius and is typically 0.75–1.5 times this value.…”