Kristie L. Kahl

Researchers at the 2020 Society of Urologic Oncology Annual Meeting shared initial data for their novel deep-learning algorithm intended to facilitate the detection and grading of clinically significant prostate cancer.

Their findings showed that the algorithm appeared to accurately identify cancer on whole mount prostate pathology, potentially alerting pathologists to suspicious areas of cancer burden prior to clinical assessment.

“Accurate Gleason Grade grouping determination at time of prostate cancer diagnosis is vital for patients’ decision making to pursue either surveillance, definite treatment, or adjuvant therapy. However, intercarrier variability in the grading of pathologic specimens remains a significant issue,” Nitin K. Yerram, MD, a urologic oncology fellow at the National Cancer Institute, said during a virtual presentation.

“Given that deep learning algorithms are being developed to help augment and standardize detection and grading for prostate cancer, our group has utilized AI algorithms to provide a solution to similar problems in bladder cancer pathology and prostate cancer imaging,” he added.

The researchers used previous studies to create a novel algorithm that was developed to help identify and grade prostate cancer on whole mount pathology slides.

The algorithm was previously trained for detection and grading of prostate cancer using publicly available datasets, totaling over 9000 biopsies, tissue microarrays, and surgical sections. Additionally, a small number of segmented whole mount prostatectomy slides were utilized for detection task only.

“The algorithm was designed to be agnostic of tissue source operating on patches abstracted from each image,” Yerram explained. “Each patch is representing 100 microns by 100 microns, or 200 by 200 pixels at 20x. Each patch is then run through our algorithm. These patches are spatially recreated to produce a probability map where each patch is assigned either a value of zero or 1, 1 being the highest likelihood of cancer.”

Burden of each foci within each slide were marked by ink under microscope and mapped digitally for quantitative comparison.

 area were considered positive for deep learning-based detection.

“At the NCI, we sought to evaluate the congruence of the AI algorithm with pathologist annotated regions from routine clinical practice,” Yerram said, adding that the researchers then chose to convert the probability map into a detection mask, “which identifies high risk areas defined as congruent areas of high probability in a set pixel size.”

For statistical analysis, they then compared the detection rate to pathologist annotation. A true positive was called as any detection within a prospect annotation. Once the detected areas of probability that are considered cancer were found, they ran it through the grading algorithm. Each patient is given a prediction: either Gleason Grade 3, 4, or 5. Similarly, with the detection map, the researchers were able to visually look at probability maps for each one of these Gleason scores.

The algorithm was applied to 50 patients who underwent radical prostatectomy between 2008 and 2018 with available digitized whole-mount pathology and foci-level annotations of disease burden. In total, 24 patients had Gleason Grade 1 or 2 and 26 had Gleason Grade 3, 4, or 5 on surgical pathology.

Patient level detection accuracy of cancer or no cancer was 96%, with 2 patients classified as negative for cancer. However, these 2 patients had Grade 1 and 2 disease, indicating that no high-grade disease was missed, Yerram noted.

On annotated foci identification, the algorithm showed a 77.6% sensitivity, with a median rate of 1 false-positive per patient (range, 0-20). Positive predictive value was 38.4%.

“Our program performed quite well in the grading of cancer. Overall, a higher percent of the tumor grade and burden was detected in patients with Grade 3-5 disease versus patients with Grade 1-2 disease,” Yerram concluded.

“Our algorithm demonstrated excellent accuracy in identifying cancer on whole mount pathology,” he added. “Now, there is room for improvement in the first level accuracy, and our positive predictive value needs to be improved, but that will continue to be improved upon with further refinement. Systems such as this, we envision, can be used to alert pathologists to suspicious areas of cancer burden prior to clinical assessment. And lastly, spatial assessment of grade distribution can be achieved with further refinement of our algorithm.”

1. Yerram N, Harmon S, O'Connor L, et al. Application of Deep Learning Detection and Grading System for Identification of Clinically Significant Prostate Cancer on Whole Mount Pathology. Presented at: Society of Urologic Oncology 21st Annual Meeting; December 3, 2020. Abstract 3.

Articles

The algorithm was applied to 50 patients who underwent radical prostatectomy between 2008 and 2018.

Deep-learning algorithm for prostate cancer detection demonstrates early potential

Ten-year follow-up data from a retrospective study showed an overall survival (OS) rate of 97.7% and a recurrence-free survival (RFS) rate of 93.0% with Mohs surgery in patients with localized penile cancer.

The data, which were shared during the 2020 Society of Urologic Oncology Annual Meeting, support the Mohs procedure as a feasible approach for long-term local control in this patient population.

“Penile carcinoma is a rare malignancy with an annual incidence of 0.1 to 0.7 per 100,000 men, accounting for fewer than 1% of male cancers in the United States. Treatment is associated with continual mutilation changes to the quality of life for these patients,” Nicolas E. Alcalá, a fourth-year medical student at the University of North Carolina, said during a virtual presentation. “Therefore, organ-sparing approaches have been on the rise.”

To maximize oncologic control and minimize psychologic emotional impacts of surgery, treatment for penile carcinoma include partial penectomy, local excision, topical chemotherapy, laser ablation, circumcision, glansectomy, and glans resurfacing.

However, Alcalá et al questioned whether Mohs microsurgery provided effective oncologic control and localized penile carcinoma. The researchers created REDCap database looking at patients from 2010 to 2020 with penile carcinoma at the University of North Carolina treated with Mohs microsurgery. Patients were seen in a multidisciplinary setting, including urologic oncology, dermatology, and reconstructive urology.

Patients with Ta, Tis, T1, and T2 disease were considered candidates for Mohs surgery.

Forty-three men who underwent Mohs surgery were identified using a prospectively maintained database. Clinical and pathologic data were collected for descriptive analysis.

In particular, the researchers evaluated variables including demographics, risk factors, lesion location, tumor size, grade, and stage. OS and RFS served as the primary outcomes.

Patients were a median age of 64 (range, 23-83), and the majority were white (88.4%). The main risk factors were patients who were not circumcised (23%) and those with a history of carcinoma in situ (23%).

Stage distribution was Ta in 4.7%, Tis in 58.1%, T1a in 14.0% %, T1b in 7.0%, and T2 in 16.3%. In total, 14% of patients reported with Grade 1 disease, 14% with Grade 2, 37.2% with Grade 3, and 34.9% with unknown grade disease. Lesions were predominantly located on the glans (41.9%).

No patient had a positive surgical margin after Mohs surgery. RFS was 93.0%, with 3 patients (7%) who experienced a recurrence. Of those with a recurrence, 2 patients exhibited local recurrence within 6 months, were treated with local resection, and found to be Tis, while 1 patient with T1b disease had a T1bN2 recurrence at 2 years and was treated with paclitaxel, ifosfamide, and cisplatin.

OS was 97.7%, with 1 death from non-cancer related causes.

“Mohs microsurgery provides effective local control for localized penile cancer. A multidisciplinary team involving urologic oncology, reconstructive oncology, and Mohs surgery is essential to patient management,” Alcalá concluded, adding that he and his colleagues will be finalizing outcomes looking at sexual, urinary, and overall health-related quality of life.

1. Alcalá NE, Reines KL, Merritt B, Figler B, Bjurlin M. Oncologic Outcomes of Mohs Surgery for Localized Penile Carcinoma: A 10-Year Retrospective Study. Presented at: Society of Urologic Oncology 21st Annual Meeting; December 3, 2020. Abstract 7.

Ten-year data showed high overall survival and recurrence-free survival rates with Mohs surgery in patients with localized penile cancer. 

Study suggests Mohs surgery is feasible for long-term local control of penile cancer

Telemedicine multidisciplinary urologic cancer clinics implemented by the University of Washington/Seattle Cancer Care Alliance to expand healthcare access during the COVID-19 pandemic achieved a high level of patient satisfaction.

The clinics delivered a positive patient experience by sparing substantial travel burden, while still delivering the high-quality care patients were accustomed to from their previous in-person medical visits, according to a poster presented during the 2020 Society of Urologic Oncology’s Annual Meeting.

“We rapidly implemented a telemedicine Multidisciplinary Urologic Cancer Clinic (MDUCC) at the University of Washington/Seattle Cancer Care Alliance in order to reduce the risk of COVID-19 transmission while providing multidisciplinary cancer care. We aim to report our experience and assess patient-reported outcomes from our telemedicine MDUCC,” wrote the researchers, adding that this could improve access to multidisciplinary urologic cancer care.

The telemedicine multidisciplinary clinics consist of video visits with a urologic oncologist, medical oncologist, and radiation oncologist. Video visits were conducted in the same format as in-person visits would have been prior to the pandemic. In addition, tumor boards that included radiologists and pathologists were conducted using video conferences.

Following the video visits, patients were invited to complete a survey to assess satisfaction, provider trust, travel time, and costs related to the visit. In the survey, 1 equated to strongly agree, while 7 equated to strongly disagree.

To assess patient-reported outcomes from the telemedicine MDUCC, the researchers prospectively collected patient demographic and oncological data, and estimated travel distances and times from each patient’s home to the MDUCC.

From March to June 2020, the researchers conducted 23 video visits, including 21 patients who took the visit from home and 2 who traveled to a nearby area for broadband access. Median age was 69 years. The majority of patients were male (87%) and white (61%). Patients presented with bladder (n = 18), kidney (n = 3), upper tract urothelial carcinoma (n = 1), and penile cancer (n = 1). Seventy percent of patients had stage III or IV disease.

In total, 12 patients (52%) responded to the post-visit survey.

The majority of patients reported they strongly agreed with the following questions:

I was pleased with the quality of the medical encounter (n = 9; 75%)

My visit was on-time and efficient (n = 5; 50%)

I believe that the medical encounter was conducted in a confidential manner (n = 9; 75%)

I was able to share sensitive and/or personal information provided (n = 8; 67%)

I was pleased with the quality of educational information provided (n = 7; 58%)

I was overall satisfied with my appointment (n = 9; 75%)

I believe the provider is able to do his or her job, even if they aren’t able to conduct a physical examination at every appointment (n = 5; 42%)

I have a trusting relationship with my provider (n = 4; 33%)

Considering the cost and time commitment of my appointment, I would choose to meet with my provider in this setting in the future (n = 8; 67%)

All 12 patients responded that they would be willing to have future appointments via telemedicine.

The median travel costs, time, and distance reported were each 0. The researchers estimated that telemedicine saved patients a median 1-way travel distance of 52 miles (IQR, 16-127) and 1-way travel time of 71 minutes (IQR, 42-147).

“Telemedicine multidisciplinary clinics are feasible and effective in providing access to multidisciplinary urologic cancer care,” the researchers concluded. “Patient satisfaction was high and many patients were spared a substantial travel burden. Telemedicine may be leveraged during and after COVID-19 to improve access to multidisciplinary urologic cancer care.”

1. Gadzinski AJ, Sekar RR, Abarro IO, et al. Telemedicine multidisciplinary urologic cancer clinics during COVID-19. Presented at: Society of Urologic Oncology 21st Annual Meeting; December 3, 2020. Poster 10.

The vast majority of patients reported being "pleased" with their medical encounter. 

Telemedicine and urologic cancer: multidisciplinary clinics expand access and deliver positive patient experience

The FDA approved the first drug for positron emission tomography (PET) imaging of prostate-specific membrane antigen (PSMA) positive lesions in men with prostate cancer, Gallium 68 PSMA-11 (Ga 68 PSMA-11).

“Ga 68 PSMA-11 is an important tool that can aid health care providers in assessing prostate cancer,” Alex Gorovets, MD, acting deputy director of the Office of Specialty Medicine in FDA’s Center for Drug Evaluation and Research, said in press release. “With this first approval of a PSMA-targeted PET imaging drug for men with prostate cancer, providers now have a new imaging approach to detect whether or not the cancer has spread to other parts of the body.”

The FDA based its decision on the safety and efficacy of Ga 68 PSMA-11 proven in 2 prospective clinical trials with a total of 960 men with prostate cancer who each received 1 injection of the drug.

In the first trial, 325 patients who were candidates for surgical removal of the prostate gland and pelvic lymph nodes and were considered at higher risk for metastasis underwent PET/CT or PET/MRI scans performed with Ga 68 PSMA-11. Of the patients who went on to undergo surgery, Ga 68 PSMA-11 PET demonstrated a clinically important rate of metastatic cancer confirmed by surgical pathology in patients with positive readings in the pelvic lymph nodes.

“The availability of this information prior to treatment is expected to have important implications for patient care. For example, it may spare certain patients from undergoing unnecessary surgery,” the FDA states in its release.

In the second trial, 635 patients who had rising serum PSA levels after initial prostate surgery or radiotherapy, 74% had at least 1 positive lesion detected by Ga 68 PSMA-11 PET in at least 1 body region. In total, 91% of patients with positive Ga 68 PSMA-11 PET readings who had correlative tissue pathology from biopsies, who also had results from baseline or follow-up imaging by conventional methods, and serial PSA levels available for comparison, also had local recurrence or metastasis of prostate cancer confirmed.

“Thus, the second trial demonstrated that Ga 68 PSMA-11 PET can detect sites of disease in patients with biochemical evidence of recurrent prostate cancer, thereby providing important information that may impact the approach to therapy,” the agency added.

No serious adverse events (AEs) were attributed to Ga 68 PSMA-11. The most common AEs included nausea, diarrhea, and dizziness.

The FDA warned there may be a risk for misdiagnosis, “because Ga 68 PSMA-11 binding may occur in other types of cancer as well as certain non-malignant processes which may lead to image interpretation errors. There are radiation risks because Ga 68 PSMA-11 contributes to a patient’s overall long-term cumulative radiation exposure, which is associated with an increased risk for cancer.”

The drug, which is a radioactive diagnostic agent that is administered in the form of an intravenous injection, is indicated for patients with suspected prostate cancer metastasis who are potentially curable by surgery or radiation therapy and for those with suspected prostate cancer recurrence based on elevated serum prostate-specific antigen (PSA) levels. Ga 68 PSMA-11 binds to PSMA once administered and can be imaged by PET to indicate the presence of PSMA-positive prostate cancer lesions in the tissues of the body.

F 18 fluciclovine and C 11 choline are 2 additional PET drugs that are approved for prostate cancer imaging, the FDA noted; however, they are only approved for use in patients with suspected cancer recurrence.

1. FDA approves first PSMA-targeted PET imaging drug for men with prostate cancer. Press release. FDA. December 1, 2020. Accessed December 1, 2020. https://bit.ly/3fWUOcN

The agency approved the first PSMA-targeted PET imaging drug for men with prostate cancer.

Kristie L. Kahl

Articles

Deep-learning algorithm for prostate cancer detection demonstrates early potential

Study suggests Mohs surgery is feasible for long-term local control of penile cancer

Telemedicine and urologic cancer: multidisciplinary clinics expand access and deliver positive patient experience

FDA approves Gallium 68 PSMA-11 for prostate cancer