Scientific papers

efforts to organize an effective cervical cancer screening and treatment program will require adequate financial resources, the development of infrastructure, training needed manpower, and surveillance mechanisms of the targeted women. Screening with VIA (visual inspection with acetic acid) and HPV DNA testing on self-collected samples with processing at a specific site could, for the first time, make national, large-scale population-based screening feasible in Uganda. Combining screening efforts with timely treatment of all screen positives for HPV infection can prevent progression to invasive cervical cancer. To date, this is the most effective intervention in closing the current prevention gap.

Training of health professionals, ongoing construction of new radiotherapy bunkers, and opening of regional centers are all geared towards improving cervical cancer care in Uganda. The Uganda Cancer Institute Bill establishes the Institute as a semi-autonomous agency mandated to undertake and coordinate the prevention and treatment of cancer. Its implementation will be a milestone in cervical cancer prevention and control. However, execution will require political will and an increase in domestic and international investment.
Download paper

Transfer learning involves fine-tuning a pre-trained network with optimal values of hyperparameters such as learning rate, batch size, and number of training epochs. The process of training the network identifies the relevant features for solving a specific problem. Adapting the pre-trained network to solve a different problem requires fine-tuning until relevant features are obtained. This is facilitated through the use of large number of filters present in the convolutional layers of pre-trained network.

A very few features out of these features are useful for solving the problem in a different domain, while others are irrelevant, use of which may only reduce the efficacy of the network. However, by minimizing the number of filters required to solve the problem, the efficiency of the training the network can be improved. In this study, we consider identification of relevant filters using the pre-trained networks namely AlexNet and VGG-16 net to detect cervical cancer from cervix images. This paper presents a novel hybrid transfer learning technique, in which a CNN is built and trained from scratch, with initial weights of only those filters which were identified as relevant using AlexNet and VGG-16 net. This study used 2198 cervix images with 1090 belonging to negative class and 1108 to positive class. Our experiment using hybrid transfer learning achieved an accuracy of 91.46%.
See full article

Uganda has one of the highest cervical cancer incidence rates in the world (54.8 per 100,000) as a result of limited screening access and infrastructure. The integration of a self-collected cervical cancer screening program using HPV testing within existing community-based primary health care services could increase access to screening and reduce cervical cancer rates among Ugandan women.

Results from this study will inform the national scale-up of cervical cancer screening in Uganda, aligning with the World Health Organization’s target of achieving cervical cancer elimination through the pillar of increased HPV screening coverage.
Download paper

These studies used images acquired through colposcopy or cervicography. However, colposcopy is expensive and hence is not feasible as a screening tool in resource-poor settings. Cervicography uses a digital camera to acquire cervix images which are subsequently sent to experts for evaluation. Hence, cervicography does not provide a real-time decision of whether the cervix is normal or not, during the VIA examination. In case the cervix is found to be abnormal, the patient may be referred to a hospital for further evaluation using Pap smear and/or biopsy.

An android device with an inbuilt app to acquire images and provide instant results would be an obvious choice in resource-poor settings. In this paper, we propose an algorithm for analysis of cervix images acquired using an android device, which can be used for the development of decision support system to provide instant decision during cervical cancer screening. This algorithm offers an accuracy of 97.94%, a sensitivity of 99.05% and specificity of 97.16%.
See full article