CERVICAL CANCER
Medroxyprogesterone Acetate Prevention of Cervical Cancer Through Progesterone Receptor in a Human Papillomavirus Transgenic Mouse Model
A new study reports that medroxyprogesterone acetate (MPA) was effective in preventing the development of cervical cancer in mice with precancerous lesions (Am J Pathol 2019; doi: 10.1016/j.ajpath.2019.08.013). The drug also decreased existing precancerous lesions. If proven effective clinically, MPA may be a boon to women who do not have access to human papillomavirus (HPV) vaccines. Similar to cervical cancer progression in women, mouse cervical neoplastic disease develops through multiple stages, starting from cervical intraepithelial neoplasia (CIN) and culminating in invasive cancer. Previously, efforts to develop a non-invasive treatment for CIN have been limited. In this study, researchers treated CIN-bearing mice with MPA. Investigators found that cervical cancer did not develop in mice receiving MPA. Further, CIN was absent in most MPA-treated mice, indicating that MPA may be "chemoprotective," not only preventing CIN from progressing to invasive cancer, but also promoting its regression. The study determined that MPA inhibited cell proliferation and promoted apoptosis in CIN lesions. In addition, the preventive effect of MPA was absent in HPV transgenic mice in which the expression of progesterone receptor (PR) was genetically prevented. These results suggest that MPA is efficient for treating PR-positive CIN lesions. PR-positivity may be a useful biomarker for selecting patients who may benefit from MPA in future clinical trials.
MYELOPROLIFERATIVE NEOPLASMS
Metabolic Effects of JAK1/2 Inhibition in Patients With Myeloproliferative Neoplasms
A popular cancer drug is associated with significant weight gain and increased systolic blood pressure. The drug, ruxolitinib, was the first and currently remains the most widely used FDA-approved mechanism-based therapy for myeloproliferative neoplasms (MPNs), blood cancers that include myelofibrosis and polycythemia vera. Ruxolitinib is a Janus kinases (JAK) 1/2 inhibitor, an enzyme-blocker that affects blood cell production (Sci Rep 2019; doi:10.1038/s41598-019-53056-x). As cancer therapies improve and patients are living longer on them, understanding the long-term consequences of these targeted therapies on metabolic health is increasingly important. The researchers studied 69 patients with MPNs who started on ruxolitinib from 2010 to 2017 at Mount Sinai. The patients' medical records had data on metabolic parameters up to 1 year prior to starting ruxolitinib and 72 weeks after starting the drug. Researchers found that more than half of patients taking this medication gained more than 5 percent in body weight. The weight gain was also associated with an increase in systolic blood pressure and liver enzymes. Patients treated with ruxolitinib had a higher systolic blood pressure, serum AST, and ALT at 72 weeks, compared with baseline (p=0.03, p=0.01, p=0.04, respectively). In mice, ruxolitinib decreased basal and GH-stimulated STAT5 phosphorylation in adipose tissue. As pharmacological JAK1/2 inhibitors are being developed and used in clinical practice, it is important to understand their long-term metabolic consequences. The study is the first step in documenting the metabolic consequences of this drug. Further studies are needed to gain a greater understanding of the changes in hormones and metabolism in those receiving treatment for this condition.
LUNG CANCER
Deep Convolutional Neural Network-Based Software Improves Radiologist Detection of Malignant Lung Nodules on Chest Radiographs
Radiologists assisted by deep-learning based software were better able to detect malignant lung cancers on chest X-rays, according to a new study (Radiology 2019; doi: 10.1148/radiol.2019182465). Researchers said the characteristics of lung lesions including size, density, and location make the detection of lung nodules on chest X-rays more challenging. However, machine learning methods, including the implementation of deep convolutional neural networks (DCNN), have helped to improve detection. In this retrospective study, radiologists randomly selected a total of 800 X-rays from four participating centers, including 200 normal chest scans and 600 with at least one malignant lung nodule confirmed by CT imaging or pathological examination (50 normal and 150 with cancer from each institution). There were 704 confirmed malignant nodules in the lung cancer X-rays (78.6% primary lung cancers and 21.4% metastases). The majority (56.1%) of the nodules were between 1 cm and 2 cm, while 43.9 percent were between 2 cm and 3 cm. A second group of radiologists, including three from each institution, interpreted the selected chest X-rays with and without cancerous nodules. The readers then re-read the same X-rays with the assistance of DCNN software, which was trained to detect lung nodules. The average sensitivity, or the ability to detect an existing cancer, improved significantly from 65.1 percent for radiologists reading alone to 70.3 percent when aided by the DCNN software. The number of false positives-incorrectly reporting that cancer is present-per X-ray declined from 0.2 for radiologists alone to 0.18 with the help of the software.
ESOPHAGEAL CANCER
Attention-Based Deep Neural Networks for Detection of Cancerous and Precancerous Esophagus Tissue on Histopathological Slides
Recently, deep learning methods have shown promising results for analyzing histological patterns in microscopy images. These approaches, however, require a laborious, high-cost, manual annotation process by pathologists called "region-of-interest annotations." A research team has addressed this shortcoming of current methods by developing a novel attention-based deep learning method that automatically learns clinically important regions on whole-slide images to classify them (JAMA Netw Open 2019; DOI: 10.1001/jamanetworkopen.2019.14645). The team tested their new approach for identifying cancerous and precancerous esophagus tissue on high-resolution microscopy images without training on region-of-interest annotations. For histopathology image analysis, the manual annotation process typically outlines the regions of interest on a high-resolution whole slide image to facilitate training the computer model. The team proposed the network for Barrett esophagus and esophageal adenocarcinoma detection and found that its performance exceeds that of the existing state-of-the-art method. The researchers said their method would facilitate a more extensive range of research on analyzing histopathology images that were previously not possible due to the lack of detailed annotations, and clinical deployment of such systems could assist pathologists in reading histopathology slides more accurately and efficiently, which is a critical task for the cancer diagnosis, predicting prognosis, and treatment of cancer patients. The research team said they are planning to validate their model further by testing it on data from other institutions and running prospective clinical trials. They also plan to apply the proposed model to histological images of other types of tumors and lesions for which training data are scarce or bounding box annotations are not available.
Have Stories Delivered Directly to You
Sign up for our free e-newsletter and receive email notifications when each issue becomes available and when other new content is posted online. New to Oncology Times? Visit the publication's website at http://www.oncology-times.com where you can get free access to archived issues, subscribe to the print magazine, and create your own personal online article collections.