Improvement in plan quality after Implementation of clinical goals in a large network of cancer centers

Pilot study of radiation oncology peer review in low middle income country (LMIC) through cloud-based platform

PURPOSE

Peer review is an essential step in clinical quality assurance for radiation therapy. There are very little data on peer reviews from low-middle-income countries (LMIC). With increasing access to advanced technologies in LMIC also, peer review is becoming more important to ensure quality and standard of care. We evaluated cloud-based e-Peer review in our network of cancer centers in India with an aim to study its feasibility and impact on care.

MATERIALS AND METHODS

Four out of 13 cancer centers across India were selected for this pilot study. All team members were trained on the e-Peer review platform before the initiation of the study. A lead dosimetrist from a centralized planning site was selected to share new cases every week. Cases treated with only definitive intent were selected. The link to the cases was sent through an email to reviewing physicians. The following aspects were reviewed for each case. 1) Work up and staging. 2) Treatment intent and prescription. 3) Target contours. 4) Normal organ at risk contours. 5) Dose-volume-histogram (DVH) with clinical goals attached. Cases were marked as "Not Appropriate," "Appropriate," "Appropriate with minor finding," and "Represent with major revisions" as per volume and plan review.

RESULTS

Over a period of 3 months, 100 cases underwent peer review before the start of treatment. Median turnover time was 48 (interquartile range: 24-96) hours. The median time for review was 8 min with time to review cases requiring major and minor changes being 12 and 6 min, respectively (P < 0.001). Of all the cases reviewed, no changes, minor changes, and major changes were suggested for 36%, 48%, and 16% of cases, respectively. The most frequent reason for major changes was contouring corrections (15%). Also, 31.3% of major changes underwent recontouring and replanning before initiation of treatment.

CONCLUSION

Peer review was feasible in our setting through this cloud-based peer review system, with median turnover time and time taken for review being 48 h and 8 min, respectively. Like published data from the Western world, peer review led to changes that could impact patient care delivery and outcome. We plan to implement this across the remaining centers in our network.

Evaluation of a deep image-to-image network (DI2IN) auto-segmentation algorithm across a network of cancer centers

PURPOSE/OBJECTIVE S

Due to manual OAR contouring challenges, various automatic contouring solutions have been introduced. Historically, common clinical auto-segmentation algorithms used were atlas-based, which required maintaining a library of self-made contours. Searching the collection was computationally intensive and could take several minutes to complete. Deep learning approaches have shown significant benefits compared to atlas-based methods in improving segmentation accuracy and efficiency in auto-segmentation algorithms. This work represents the first multi-institutional study to describe and evaluate an AI algorithm for the auto-segmentation of organs at risk (OARs) based on a deep image-to-image network (DI2IN).

MATERIALS/METHODS

The AI-Rad Companion Organs RT (AIRC) algorithm (Siemens Healthineers, Erlangen, Germany) uses a two-step approach for segmentation. In the first step, the target organ region in the optimal input image is extracted using a trained deep reinforcement learning network (DRL), which is then used as input to create the contours in the second step based on DI2IN. The study was initially designed as a prospective single-center evaluation. The automated contours generated by AIRC were evaluated by three experienced board-certified radiation oncologists using a four-point scale where 4 is clinically usable and 1 requires re-contouring. After seeing favorable results in a single-center pilot study, we decided to expand the study to six additional institutions, encompassing eight additional evaluators for a total of 11 physician evaluators across seven institutions.

RESULTS

One hundred and fifty-six patients and 1366 contours were prospectively evaluated. The five most commonly contoured organs were the lung (136 contours, average rating = 4.0), spinal cord (106 contours, average rating = 3.1), eye globe (80 contours, average rating = 3.9), lens (77 contours, average rating = 3.9), and optic nerve (75 contours, average rating = 4.0). The average rating per evaluator per contour was 3.6. On average, 124 contours were evaluated by each evaluator. 65% of the contours were rated as 4, and 31% were rated as 3. Only 4% of contours were rated as 1 or 2. Thirty-three organs were evaluated in the study, with 19 structures having a 3.5 or above average rating (ribs, abdominopelvic cavity, skeleton, larynx, lung, aorta, brachial plexus, lens, eye globe, glottis, heart, parotid glands, bladder, kidneys, supraglottic larynx, submandibular glands, esophagus, optic nerve, oral cavity) and the remaining organs having a rating of 3.0 or greater (female breast, proximal femur, seminal vesicles, rectum, sternum, brainstem, prostate, brain, lips, mandible, liver, optic chiasm, spinal cord, spleen). No organ had an average rating below 3.

CONCLUSION

AIRC performed well with greater than 95% of contours accepted by treating physicians with no or minor edits. It supported a fully automated workflow with the potential for time savings and increased standardization with the use of AI-powered algorithms for high-quality OAR contouring.

Multicenter Study of Pelvic Nodal Autosegmentation Algorithm of Siemens Healthineers: Comparison of Male Versus Female Pelvis

Purpose

The autosegmentation algorithm of Siemens Healthineers version VA 30 (AASH) (Siemens Healthineers, Erlangen, Germany) was trained and developed in the male pelvis, with no published data on its usability in the female pelvis. This is the first multi-institutional study to describe and evaluate an artificial intelligence algorithm for autosegmentation of the pelvic nodal region by gender.

Methods and Materials

We retrospectively evaluated AASH pelvic nodal autosegmentation in both male and female patients treated at our network of institutions. The automated pelvic nodal contours generated by AASH were evaluated by 1 board-certified radiation oncologist. A 4-point scale was used for each nodal region contour: a score of 4 is clinically usable with minimal edits; a score of 3 requires minor edits (missing nodal contour region, cutting through vessels, or including bowel loops) in 3 or fewer computed tomography slices; a score of 2 requires major edits, as previously defined but in 4 or more computed tomography slices; and a score of 1 requires complete recontouring of the region. Pelvic nodal regions included the right and left side of the common iliac, external iliac, internal iliac, obturator, and midline presacral nodes. In addition, patients were graded based on their lowest nodal contour score. Statistical analysis was performed using Fisher exact tests and Yates-corrected χ2 tests.

Results

Fifty-two female and 51 male patients were included in the study, representing a total of 468 and 447 pelvic nodal regions, respectively. Ninety-six percent and 99% of contours required minor edits at most (score of 3 or 4) for female and male patients, respectively (P = .004 using Fisher exact test; P = .007 using Yates correction). No nodal regions had a statistically significant difference in scores between female and male patients. The percentage of patients requiring no more than minor edits was 87% (45 patients) and 92% (47 patients) for female and male patients, respectively (P = .53 using Fisher exact test; P = .55 using Yates correction).

Conclusions

AASH pelvic nodal autosegmentation performed very well in both male and female pelvic nodal regions, although with better male pelvic nodal autosegmentation. As autosegmentation becomes more widespread, it may be important to have equal representation from all sexes in training and validation of autosegmentation algorithms.