Improved breast cancer screening and treatment may have saved many lives.

A study using data from the Surveillance, Epidemiology and End Results (SEER) program of the National Cancer Institute published in Cancer estimated as many as 600,000 breast cancer deaths were avoided since 1989 in women aged 40 to 84 years thanks screening and treatment advances. 

The authors report that from 1975 to 1990, female breast cancer mortality rates in the United States increased by 0.4% per year. Since 1990, breast cancer mortality rates have fallen between 1.8% and 3.4% per year, a decrease that is attributed to increased mammography screening and improvements in treatment.

The authors concluded that since 1989, between 384,000 and 614,500 breast cancer deaths have been averted because of widespread use of screening mammography and advances in the treatment of breast cancer.

Artificial intelligence Can Predict Which Patients Will Develop Breast Cancer Within a Year

A study published in Radiology found that a deep learning artificial intelligence (AI) model from IBM Research can predict the development of malignant breast cancer in patients within a year by linking health records and mammograms. 

In this retrospective study, 52,936 images were obtained in 13,234 women who underwent at least one mammogram and who had health records for at least 1 year before undergoing mammography.  The algorithm was trained on 9,611 mammograms and health records to predict biopsy malignancy and to differentiate between normal from abnormal screenings.

The AI could correctly forecasted respective development of 87 percent and 77 percent of cancerous and non-cancerous cases, and also identified breast cancer in 48 percent of patients that otherwise would have been overlooked, with accuracy comparable to radiologists therefore it has the potential to substantially reduce missed diagnoses of breast cancer.

FDA warns breast implants linked to rare form of cancer

The Food and Drug Administration (FDA) issued a letter warning health care professionals to check women with breast implants for Anaplastic Large Cell Lymphoma (BIA-ALCL) a rare cancer that usually arises in the scar tissue that forms around implants.

The FDA said at least 457 women in the United States have so far been diagnosed with anaplastic large cell lymphoma, and nine women have died from the disease. Though the number of BIA-ALCL is small compared to the estimated 1.5 million patients who receive breast implants worldwide every year, confirmed data and published information reviewed to date suggests that patients with breast implants have an increased risk of BIA-ALCL.

In most of the cases the patients were diagnosed with BIA-ALCL due to symptoms such as pain, lumps, swelling, or asymmetry that developed after their initial surgical sites were fully healed. These symptoms were due to collection of fluid, or masses surrounding the breast implant. Cytological examination of the fluid and histologic examination of the capsule surrounding the breast implant can lead to the BIA-ALCL diagnosis.

The FDA is asking health care providers to report cases of BIA-ALCL in patients with breast implants. The FDA request health care providers with questions to either email the Division of Industry and Consumer Education (DICE) at DICE@FDA.HHS.GOV, or call 1-800-638-2041 or 301-796-7100.

Artificial Intelligence is Useful in the Interpretation of Screening Mammograms

A study published in Radiology found that breast radiologists had a slight higher diagnostic performance when using artificial intelligence (AI) with no additional time required.

Screening digital mammograms from 240 women (median age, 62 years; range, 39–89 years) performed between 2013 and 2017 were analyzed in this study. The mammograms were interpreted with and without AI support.

The researchers found that the cancer detection improved for all breast densities, and was independent of lesion type, vendor image quality, when radiologists used AI and interestingly did not lengthen interpretation time. The radiologists’ detection slightly improved when using AI support, with the average area under the receiver operating characteristic curve (AUC) increasing form 0,87 to 0.89.  Sensitivity increased with AI support 86% vs. 83%, whereas specificity improved slightly 79% vs. 77%. Reading time per case was for all practical purposes identical  (unaided, 146 seconds; supported by AI, 149 seconds).

The researchers concluded that AI assisted interpreting radiologists and improved their cancer detection at mammography when using AI without adding to the interpetation time.

Artificial Intelligence Can Detect Wrist Fractures

A study published in Radiology: Artificial Intelligence found that convolutional neural networks could detect and show fractures on wrist radiographs with a high level of sensitivity and specificity.

A dataset of 7356 wrist radiographs was split into training (90%) and validation (10%) sets.  The models were tested on an unseen test set of 524 consecutive emergency wrist radiographic studies with two radiologists in consensus as the reference standard.

The model detected and correctly localized 310 (91.2%) of 340 and 236 (96.3%) of 245 of all radius and ulna fractures on the frontal and lateral views, respectively. The per-study sensitivity, specificity were 98.1%, and 72.9%, respectively.

The authors concluded that convolutional neural networks were able to detect and localize radius and ulna fractures on wrist radiographs with high sensitivity and specificity.

Low Radiation Dose CT Leads to Inferior Diagnoses

Jensen et al reported in Radiology that CT evaluation of colorectal liver metastases was not as accurate after reducing the radiation exposure by more than 50 percent. 

Their study included 52 patients with biopsy-proven colorectal cancer liver metastases and few benign lesions as well.  Each patient underwent two CT scans-a standard radiation dose (SD) contrast CT and a reduced radiation dose (RD) CT scan- during the same breast hold.

Reduced dose CT resulted in a mean dose reduction of 54% compared with standard dose. Of the 260 lesions, 233 were metastatic and 27 benign, 212 were detected with RD CT, whereas 252 were detected with SD CT.   Mean qualitative scores ranked SD images as higher quality versus RD series images.

The authors concluded that CT evaluation of colorectal liver metastases is compromised with reduced radiation dose, and the use of iterative reconstructions could not maintain observer performance.

Double Reading Improves Breast Cancer Screening

A study by Taylor-Phillips et al published in Radiology reports that double reading of mammography screening studies increases the number of cancers detected and reduces recalls. 

The authors conducted a retrospective analysis, 805 206 women who were evaluated through screening and diagnostic studies at 33 English breast centers.

The first reader recalled (4.76%; 38 295 of 805 206 women). Two readers recalled 6.19% of women in total (49 857 of 805 206 women) but arbitration of discordant readings reduced the recall rate to 4.08%. A total of 7055 cancers were detected, of which 627 or 8.89% were detected by the second reader only. These additional cancers were more likely to be ductal carcinoma in situ 30.5%; (183 of 600 vs. 22.0%; 1344 of 6114, and additional invasive cancers were smaller (mean size, 14.2 vs. 16.7 mm), had fewer involved nodes, and were likely to be lower grade.

The authors concluded that double reading with arbitration reduces recall rates and increases cancer detection compared with single reading.