AUTHOR=Wang Xun , Shi Xin , Meng Xiangyu , Zhang Zhiyuan , Zhang Chaogang 

TITLE=A universal lesion detection method based on partially supervised learning

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2023.1084155

DOI=10.3389/fphar.2023.1084155

ISSN=1663-9812

ABSTRACT=Partial supervised learning(PSL) is urgently necessary to explore to construct an efficient universal lesion detection(ULD) segmentation model. An annotated dataset is crucial but hardly to acquire because of too many CT images and lack of professionals in computer-aided detection/diagnosis(CADe/CADx). To address this problem, we propose a novel loss function to reduce the proportion of negative anchors which extremely likely classify the lesion area(positive samples) as a negative bounding box, further lead to an unexpected performance. Before calculating loss, we generate a mask to intentional choose less negative anchors which will backward wrongful loss to the network. During the process of loss calculation, we set a parameter to reduce the proportion of negative samples, and it significantly reduces the adverse effect of misclassification to the model. Our experiments are implemented in a 3D framework by feeding a partially annotated dataset named Deeplesion, a large-scale public dataset for universal lesion detection from CT. We implement a lot of experiments to choose the most suitable parameter, and the result shows that the proposed method has greatly improved the performance of an ULD detector. Our code can be obtained in https://github.com/ PLuld/PLuld.