RESUMO
Recently, Computer-Aided Diagnosis (CAD) systems have emerged as indispensable tools in clinical diagnostic workflows, significantly alleviating the burden on radiologists. Nevertheless, despite their integration into clinical settings, CAD systems encounter limitations. Specifically, while CAD systems can achieve high performance in the detection of lung nodules, they face challenges in accurately predicting multiple cancer types. This limitation can be attributed to the scarcity of publicly available datasets annotated with expert-level cancer type information. This research aims to bridge this gap by providing publicly accessible datasets and reliable tools for medical diagnosis, facilitating a finer categorization of different types of lung diseases so as to offer precise treatment recommendations. To achieve this objective, we curated a diverse dataset of lung Computed Tomography (CT) images, comprising 330 annotated nodules (nodules are labeled as bounding boxes) from 95 distinct patients. The quality of the dataset was evaluated using a variety of classical classification and detection models, and these promising results demonstrate that the dataset has a feasible application and further facilitate intelligent auxiliary diagnosis.
Assuntos
Neoplasias Pulmonares , Tomografia Computadorizada por Raios X , Humanos , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/diagnóstico por imagem , Diagnóstico por Computador , Pulmão/patologia , Pulmão/diagnóstico por imagemRESUMO
The advanced oxidation process (AOPs) is playing an important role in the elimination of hazardous organic pollutants, but the development of inexpensive and highly active advanced catalysts is facing challenges. In this study, a low-cost and readily available agricultural waste resource pomelo peel-flesh (PPF) biomass was used as the basic raw material, and the uniformly dispersed small cobalt nanoparticles were effectively anchored in the biochar derived from pomelo peel-flesh (BDPPF) by impregnation adsorption/complexation combined with heat treatment. Co/BDPPF (BDPPF embedded with Co) can effectively activate peroxymonosulfate (PMS) to SO4·-, ·OH and 1O2 reactive oxygen species, and achieve nearly 100% degradation of tetracycline persistent organic pollutant. Co/BDPPF can not only degrade tetracycline efficiently in complex water environment, but also degrade most organic pollutants universally, and has long-term stability, which solves the problem of poor universality and stability of heterogeneous catalysts to a certain extent. Importantly, Co/BDPPF derived from waste biomass was also innovatively designed as the core of an integrated continuous purification device to achieve continuous purification of organic wastewater. In this study, agricultural waste resources were selected as biomass raw materials to achieve efficient capture of Co2+, and finally developed advanced AOPs catalyst with excellent performance to achieve the purification of organic wastewater. It also provides a promising solution for the preparation of simple, low-cost, large-scale production of AOPs catalysts that can be put into actual production.