Gynecological Cancer Screening:
Neural Network models are being used to deliver prognoses in patients
with ovarian cancer. Ovarian cancer is a catchall for heterogeneous
neoplasm, and there is a great variation in histology and inpatient
presentation such as existing tumor stages. In a report done by Enshaei
et al. their results demonstrated that ANN was able to predict survival
with a 97% accuracy [23]. The AI systems they developed have the
potential of providing an accurate prognosis. Similarly, Norwitz et al.
have created an AI software that can predict prognosis in patients with
ovarian cancer, more precisely than current methods [18]. It can
also predict the most effective treatment according to the diagnosis of
each patient. Long term survival rates for advanced ovarian cancer are
poor, thus more targeted therapies are needed.
Researchers at Brigham and Women’s Hospital and Dana-Farber Cancer
Institute have been using AI to manipulate large amounts of micro RNA
data to develop models that can potentially diagnose early ovarian
cancer [23]. Currently, no screening for ovarian cancer exists
despite it being a common gynecological cancer. Thus, most cases are
diagnosed in advanced stages leading to a high five-year mortality rate.
The AI neural network could keep up with the complex interactions
between micro RNA and accurately identified almost 100% of
abnormalities that represented ovarian cancer; as opposed to an
ultrasound screening test that was able to identify abnormal results
less than 5% of the time. This non-invasive testing consists of
measuring micro RNAs from a serum sample, which can be paramount for the
future management of ovarian cancer.
To identify patients at risk of more aggressive tumors, a newly
developed AI system has been created to scan ovarian cancer cells; this
system can help identify irregularly shaped nuclei that correlate with
tumor aggressiveness [19,23] Scanning by an AI system can be
incorporated in routine biopsies to identify these risk factors related
to DNA instability and chose therapies accordingly. Evasion of the
immune system has been identified in the misshapen nuclei in aggressive
ovarian cells, indicating that there can be a response to immune
targeted treatments such as onco-immunotherapy.
AI has recently been incorporated into oncology through commercial
applications that use the algorithm to match patient data with current
clinical trials nationwide and respective investigational drugs per
patient [24,25,26]. Watson for Oncology uses AI in conjunction with
patient data to help guide cancer management, which has proven efficient
for breast cancer patients [27].
Furthermore, AI has outperformed human experts in interpreting cervical
pre-cancer images [26]. The current screening consists of visual
inspection of the specimen collected during PAP smear and using acetic
acid to visualize whitening in the tissue which would be indicative of
disease. Despite its convenience and low cost, it lacks accuracy. AI
deep learning algorithms can gather a large number of images related to
cervical cancer screening and appropriately identify diseased tissue.
The use of automatic visual evaluation can be utilized in everyday
devices such as the camera device of the cell phone. Thus, ensuring that
the test is convenient and of low cost unlike the current method; in
addition to that, accuracy is improved, minimal training is required,
and results are immediate, thus patients can receive treatment in the
same visit [24,25,26].