Separating overlapped nuclei is a major challenge in histopathology image analysis. Recently published approaches have achieved promising overall performance on nuclei segmentation; however, their performance on separating overlapped nuclei is quite limited. To address the issue, we propose a novel multitask learning network with a bending loss regularizer to separate overlapped nuclei accurately. The newly proposed multitask learning architecture enhances the generalization by learning shared representation from three tasks: instance segmentation, nuclei distance map prediction, and overlapped nuclei distance map prediction. The proposed bending loss defines high penalties to concave contour points with large curvatures, and applies small penalties to convex contour points with small curvatures. Minimizing the bending loss avoids generating contours that encompass multiple nuclei. In addition, two new quantitative metrics, Aggregated Jaccard Index of overlapped nuclei (AJIO) and Accuracy of overlapped nuclei (ACCO), are designed for the evaluation of overlapped nuclei segmentation. We validate the proposed approach on the CoNSeP and MoNuSegv1 datasets using seven quantitative metrics: Aggregate Jaccard Index, Dice, Segmentation Quality, Recognition Quality, Panoptic Quality, AJIO, and ACCO. Extensive experiments demonstrate that the proposed Bend-Net outperforms eight state-of-the-art approaches.
翻译:新提出的多任务学习架构通过从三个任务中学习共同表述来增强总体化:例分法、核心距离地图预测和重叠核心距离地图预测。拟议的弯曲损失定义了与大弯曲的螺旋轮接合点的高度惩罚,对小弯曲的螺旋轮接合点也适用了小额惩罚。为了解决这个问题,我们提议建立一个新的多任务学习网络,其中含有弯曲式损失校正处理器,以精确地分离核圈。新提议的多任务学习结构通过学习从三个任务(例分解、核心距离地图预测和重叠核心距离地图预测)中共同表述来增强总体化。拟议的弯曲损失定义了与大弯曲的螺旋轮接点的高度惩罚,对小弯曲的螺旋接合点适用了少量惩罚。 尽量减少弯曲式损失避免产生包含多个核圈的轮廓。 此外,两个新的定量指标,即重叠核心部分的复合纸牌指数(AJIO)和重叠核心线路段方法(ACCO)的精度。我们为评估了重叠的内分级的内质量、内核的内核分析方法,我们提议的内核部分校标准进行了核实。我们为:C-C-C-C-C-C-C-C-C-C-C-C-IAL-C-IAL-IAL-C-C-C-IAL-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-