Search

Machine learning-based systems have become instrumental in augmenting global efforts to combat cervical cancer. A burgeoning area of research focuses on leveraging artificial intelligence to enhance the cervical screening process, primarily through the exhaustive examination of Pap smears, traditionally reliant on the meticulous and labor-intensive analysis conducted by specialized experts. Despite the existence of some comprehensive and readily accessible datasets, the field is presently constrained by the limited volume of publicly available images and smears. As a remedy, our work unveils APACC (Annotated PAp cell images and smear slices for Cell Classification), a comprehensive dataset designed to bridge this gap. The APACC dataset features a remarkable array of images crucial for advancing research in this field. It comprises 103,675 annotated cell images, carefully extracted from 107 whole smears, which are further divided into 21,371 sub-regions for a more refined analysis. This dataset includes a vast number of cell images from conventional Pap smears and their specific locations on each smear, offering a valuable resource for in-depth investigation and study., (© 2024. The Author(s).)

Performing a minimally invasive surgery comes with a significant advantage regarding rehabilitating the patient after the operation. But it also causes difficulties, mainly for the surgeon or expert who performs the surgical intervention, since only visual information is available and they cannot use their tactile senses during keyhole surgeries. This is the case with laparoscopic hysterectomy since some organs are also difficult to distinguish based on visual information, making laparoscope-based hysterectomy challenging. In this paper, we propose a solution based on semantic segmentation, which can create pixel-accurate predictions of surgical images and differentiate the uterine arteries, ureters, and nerves. We trained three binary semantic segmentation models based on the U-Net architecture with the EfficientNet-b3 encoder; then, we developed two ensemble techniques that enhanced the segmentation performance. Our pixel-wise ensemble examines the segmentation map of the binary networks on the lowest level of pixels. The other algorithm developed is a region-based ensemble technique that takes this examination to a higher level and makes the ensemble based on every connected component detected by the binary segmentation networks. We also introduced and trained a classic multi-class semantic segmentation model as a reference and compared it to the ensemble-based approaches. We used 586 manually annotated images from 38 surgical videos for this research and published this dataset.

The classification of cells extracted from Pap-smears is in most cases done using neural network architectures. Nevertheless, the importance of features extracted with digital image processing is also discussed in many related articles. Decision support systems and automated analysis tools of Pap-smears often use these kinds of manually extracted, global features based on clinical expert opinion. In this paper, a solution is introduced where 29 different contextual features are combined with local features learned by a neural network so that it increases classification performance. The weight distribution between the features is also investigated leading to a conclusion that the numerical features are indeed forming an important part of the learning process. Furthermore, extensive testing of the presented methods is done using a dataset annotated by clinical experts. An increase of 3.2% in F1-Score value can be observed when using the combination of contextual and local features. Clinical Relevance - Analysis of images extracted from digital Pap-test using modern machine learning tools is discussed in many scientific papers. The manual classification of the cells can be time-consuming and expensive which requires a high amount of manual labor. Furthermore the result of the manual classification can also be uncertain due to interobserver variability. Considering these, any result that can lead to a more reliable highly accurate classification method is considered valuable in the field of cervical cancer screening.

The low number of annotated training images and class imbalance in the field of machine learning is a common problem that is faced in many applications. With this paper, we focus on a clinical dataset where cells were extracted in a previous research. Class imbalance can be experienced within this dataset since the normal cells are in a great majority in contrast to the abnormal ones. To address both problems, we present our idea of synthetic image generation using a custom variational autoencoder, that also enables the pretraining of the subsequent classifier network. Our method is compared with a performant solution, as well as presented with different modifications. We have experienced a performance increase of 4.52% regarding the classification of the abnormal cells.Clinical Relevance - We extract images from cervical smears, using digitized Pap test. When working with these kinds of smears, a single one can contain more than 10,000 cells. Examination of these is done manually by going over each cell individually. Our main goal is to make a system that can rank these samples by importance, thus making the process easier and more effective. The research that is described in this paper gets us a step closer to achieving our goal.

Background: The approach to managing out-of-hospital cardiac arrest (OOHCA) has generally involved either minimal on-scene resuscitation to reduce time to arrival at hospital or extended care at the scene to increase the chance of return of spontaneous circulation (ROSC) before transport. This study compared patient outcomes across EMS agencies with respect to the duration of on-scene time. We hypothesized that EMS agencies with greater average time on-scene would have more favorable outcomes., Methods: The Cardiac Arrest Registry to Enhance Survival (CARES) was used to identify OOHCA cases, including characteristics and outcomes. EMS agencies were included if they submitted at least 80 OOHCAs from 2013 to 2017. To study outcomes based upon culture of OOHCA management, outcomes were studied by EMS agency rather than by individual patient cases. Agencies in the top and bottom quartiles of on-scene time duration were categorized as high (HOSTAs) and low on-scene time agencies (LOSTAs), respectively. Generalized estimating equation models compared HOSTAs and LOSTAs., Results: We classified 89 agencies as HOSTAs (24,114 patients, average ≥25 minutes on scene) and 89 agencies as LOSTAs (37,297 patients, average <18.9 minutes on-scene). Among patients transported, HOSTAs were more likely to have a shockable rhythm (28.4% vs. 22.2%, OR = 1.4, 95%CI 1.2 to 1.5), a witnessed arrest (65.1% vs. 53.6%, OR = 1.7, 95% CI 1.5 to 1.9), and receive bystander CPR (41.9% vs. 37.0%, OR = 1.3, 95% CI 1.1 to 1.5) than LOSTAs, all p < 0.001. When controlling for these and other patient characteristics, including mechanical CPR device use, HOSTAs had a higher proportion of ROSC on emergency department arrival (66.7% vs. 31.1%, OR = 4.6, 95%CI 3.5 to 6.0, p < 0.001), survival to discharge for transported patients (22.3% vs. 11.2%, OR = 2.6, 95%CI 2.0 to 3.4, p < 0.001), and good neurologic outcome among survivors (84.9% vs. 78.6%, OR = 1.3, 95%CI = 1.0 to 1.7, p = 0.04) than LOSTAs., Conclusions: This study suggests that HOSTAs have more favorable patient outcomes compared to LOSTAs. RESULTS indicate that spending more time on-scene performing resuscitation is associated with higher rates of ROSC, survival and survival with good neurologic function.