Korfiatis, Panagiotis

Significance Statement Segmentation of multiple structures in cross-sectional imaging is time-consuming and impractical to perform manually, especially if the end goal is clinical implementation. In this study, we developed, validated, and demonstrated the capability of a deep learning algorithm to segment individual medullary pyramids in a rapid, accurate, and reproducible manner. The results demonstrate that cortex volume, medullary volume, number of pyramids, and mean pyramid volume is associated with patient clinical characteristics and microstructural findings and provide insights into the mechanisms that may lead to CKD. Background The kidney is a lobulated organ, but little is known regarding the clinical importance of the number and size of individual kidney lobes. Methods After applying a previously validated algorithm to segment the cortex and medulla, a deep-learning algorithm was developed and validated to segment and count individual medullary pyramids on contrast-enhanced computed tomography images of living kidney donors before donation. The association of cortex volume, medullary volume, number of pyramids, and mean pyramid volume with concurrent clinical characteristics (kidney function and CKD risk factors), kidney biopsy morphology (nephron number, glomerular volume, and nephrosclerosis), and short- and long-term GFR <60 or <45 ml/min per 1.73 m 2 was assessed. Results Among 2876 living kidney donors, 1132 had short-term follow-up at a median of 3.8 months and 638 had long-term follow-up at a median of 10.0 years. Larger cortex volume was associated with younger age, male sex, larger body size, higher GFR, albuminuria, more nephrons, larger glomeruli, less nephrosclerosis, and lower risk of low GFR at follow-up. Larger pyramids were associated with older age, female sex, larger body size, higher GFR, more nephrons, larger glomerular volume, more nephrosclerosis, and higher risk of low GFR at follow-up. More pyramids were associated with younger age, male sex, greater height, no hypertension, higher GFR, lower uric acid, more nephrons, less nephrosclerosis, and a lower risk of low GFR at follow-up. Conclusions Cortex volume and medullary pyramid volume and count reflect underlying variation in nephron number and nephron size as well as merging of pyramids because of age-related nephrosclerosis, with loss of detectable cortical columns separating pyramids.

Abstract Background: Sarcopenia, characterized by the loss of muscle mass, has emerged as a negative prognostic factor in cancer patients. It has been associated with poorer outcomes and increased treatment-related morbidity. Post-mastectomy breast radiation therapy (RT) increases the likelihood of reconstructive complication, with up to 20% of reconstructed women requiring implant removal. The factors that lead to these complications are poorly understood and likely multifaceted. We investigated the relationship between pre-radiation therapy sarcopenia and post-mastectomy reconstruction outcomes. Methods: Chart review was performed to determine demographic, medical, and treatment variables, including reconstruction complication events and failures in breasts treated with mastectomy, immediate reconstruction, and RT. Reconstruction failure was defined as tissue expander or implant removal, resulting in no final reconstruction or autologous reconstruction only. Reconstruction complications included surgical site infection, late infection (1 year post-RT), seroma development, flap necrosis, nipple necrosis, wound dehiscence, capsular contracture, hematoma, extrusion, leak, venous congestion, and unplanned reoperation. An axial slice at the L2 or L3 vertebral body from the radiation therapy planning CT scan was analyzed for skeletal muscle area using a previously validated algorithm, with manual review and adjustment as indicated. Sarcopenia was defined by skeletal muscle index (SMI, skeletal muscle area in cm2 divided by patient’s height squared) below 34.4 cm2/m2. Chi-square, Kaplan Meier, and univariate Cox regression tests were used for analysis. Results: Ninety-nine women with breast cancer who underwent mastectomy, reconstruction, and RT were included in this study. All women had immediate reconstruction: 93 women had tissue expander placement while six women had permanent implant placement. Mean age was 47.5 years (SD 10.6) at diagnosis and median BMI was 24.8. Seventy-six percent were non-smokers, 24% were former smokers, and only 16 (16.2%) and 3 (3.0%) had hypertension or diabetes, respectively. Median follow-up was 2.7 years. Median SMI was 38 cm2/m2 and 18 (18%) met criteria for sarcopenia (SMI &lt; 34.4 cm2/m2). Mastectomy was bilateral in 79 women, skin-sparing in 61, and nipple sparing in 31. Bilateral mastectomy was less frequent amongst women with sarcopenia (61%) compared to 84% of those without sarcopenia (p=0.03). After RT, twenty-three women required unplanned reoperation. Within these 23 women, there were 45 total complications. Complications included surgical site infection (n=18), capsular contracture (n=12), seroma (n=4), wound dehiscence (n=3), and others (n=8). However, only 8 women had reconstructive failure and none were sarcopenic at the time of the RT planning scan. Any complication or failure after RT occurred in similar proportions of patients with and without sarcopenia: 38% and 30%, respectively. Kaplan-Meier curves and univariate Cox regression models showed no significant difference in time to failure (p = 0.380) or time to any event (complication or failure) (p=0.53), between sarcopenic and non-sarcopenic patients. Conclusion: Sarcopenia, using SMI &lt; 34.4 cm2/m2 on pre-radiotherapy planning scans, was not associated with an increased risk of post-radiotherapy reconstructive complication or failure in this selected cohort of non-smokers. Few women had sarcopenia at the time of operation, and results should be validated in a larger series. Citation Format: Yasamin Sharifzadeh, Robert Gao, William S. Harmsen, Jason Klug, Panagiotis Korfiatis, Kimberly Gergelis, Dean A. Shumway, Robert Mutter, Kimberly Corbin. Sarcopenia and Post-Mastectomy Breast Reconstruction Outcomes after Radiation Therapy [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P3-05-52.

BackgroundSarcopenia increases with age and is associated with poor survival outcomes in patients with cancer. By using a deep learning–based segmentation approach, clinical computed tomography (CT) images of the abdomen of patients with newly diagnosed multiple myeloma (NDMM) were reviewed to determine whether the presence of sarcopenia had any prognostic value.MethodsSarcopenia was detected by accurate segmentation and measurement of the skeletal muscle components present at the level of the L3 vertebrae. These skeletal muscle measurements were further normalized by the height of the patient to obtain the skeletal muscle index for each patient to classify them as sarcopenic or not.ResultsThe study cohort consisted of 322 patients of which 67 (28%) were categorized as having high risk (HR) fluorescence in situ hybridization (FISH) cytogenetics. A total of 171 (53%) patients were sarcopenic based on their peri‐diagnosis standard‐dose CT scan. The median overall survival (OS) and 2‐year mortality rate for sarcopenic patients was 44 months and 40% compared to 90 months and 18% for those not sarcopenic, respectively (p < .0001 for both comparisons). In a multivariable model, the adverse prognostic impact of sarcopenia was independent of International Staging System stage, age, and HR FISH cytogenetics.ConclusionsSarcopenia identified by a machine learning–based convolutional neural network algorithm significantly affects OS in patients with NDMM. Future studies using this machine learning–based methodology of assessing sarcopenia in larger prospective clinical trials are required to validate these findings.

Purpose This study aimed to compare accuracy and efficiency of a convolutional neural network (CNN)–enhanced workflow for pancreas segmentation versus radiologists in the context of interreader reliability. Methods Volumetric pancreas segmentations on a data set of 294 portal venous computed tomographies were performed by 3 radiologists (R1, R2, and R3) and by a CNN. Convolutional neural network segmentations were reviewed and, if needed, corrected (“corrected CNN [c-CNN]” segmentations) by radiologists. Ground truth was obtained from radiologists' manual segmentations using simultaneous truth and performance level estimation algorithm. Interreader reliability and model's accuracy were evaluated with Dice-Sorenson coefficient (DSC) and Jaccard coefficient (JC). Equivalence was determined using a two 1-sided test. Convolutional neural network segmentations below the 25th percentile DSC were reviewed to evaluate segmentation errors. Time for manual segmentation and c-CNN was compared. Results Pancreas volumes from 3 sets of segmentations (manual, CNN, and c-CNN) were noninferior to simultaneous truth and performance level estimation–derived volumes [76.6 cm3 (20.2 cm3), P < 0.05]. Interreader reliability was high (mean [SD] DSC between R2-R1, 0.87 [0.04]; R3-R1, 0.90 [0.05]; R2-R3, 0.87 [0.04]). Convolutional neural network segmentations were highly accurate (DSC, 0.88 [0.05]; JC, 0.79 [0.07]) and required minimal-to-no corrections (c-CNN: DSC, 0.89 [0.04]; JC, 0.81 [0.06]; equivalence, P < 0.05). Undersegmentation (n = 47 [64%]) was common in the 73 CNN segmentations below 25th percentile DSC, but there were no major errors. Total inference time (minutes) for CNN was 1.2 (0.3). Average time (minutes) taken by radiologists for c-CNN (0.6 [0.97]) was substantially lower compared with manual segmentation (3.37 [1.47]; savings of 77.9%–87% [P < 0.0001]). Conclusions Convolutional neural network–enhanced workflow provides high accuracy and efficiency for volumetric pancreas segmentation on computed tomography.

110 Background: Sarcopenia or a loss of muscle mass increases with aging and is associated with increased overall mortality in patients with cancer. Recent advances in machine learning–based CNN algorithms have allowed for the rapid processing of digital images to produce image classifications of body composition. Since incidence of MM is highly associated with aging, we sought to determine if the presence of sarcopenia, as determined by utilizing this machine learning–based CNN algorithm on CT images, had prognostic value in patients with NDMM. Methods: We identified all patients with NDMM from January 2003 to July 2019 who had a standard-dose CT scan that included the L3 vertebral level performed within 6 months of diagnosis. Using a machine learning–based CNN-algorithm, abdominal CT images were analyzed to measure muscle area. These measurements were normalized by dividing the area values by the height of the patient squared (m2) to obtain skeletal muscle index (SMI) values. Patients were categorized as sarcopenic according to international gender-specific consensus cutoffs for SMI (male: < 55 cm2/m2 and female: < 39 cm2/m2). Patients with the following FISH cytogenetics were considered high risk (HR): t(4;14), t(14;16), t(14;20), and deletion 17p/monosomy 17 whereas the remainder were standard risk (SR). Survival analysis was performed using the Kaplan-Meier method and compared via the log-rank method. Results: The study cohort consisted of 344 patients. 68 (20%) were categorized as HR based on FISH cytogenetics.187 (54%) patients were sarcopenic based on their peri-diagnosis standard-dose CT scan. Sarcopenic patients were more likely to have ISS-3 disease (45% vs. 30%; p =.023), be male (73% vs. 48%; p <.001), and be ≥ age 75 (27% vs. 14%; p =.002) compared to non-sarcopenic patients. The median OS for patients with HR FISH and ISS 2 / 3 disease was 40 months and 57 months respectively compared to 90 months and 119 months for those with SR FISH and ISS-1 disease respectively (FISH: p <.004; ISS: p <.001). The median OS for sarcopenic patients was 44 months compared to 90 months for those not sarcopenic (p <.001). The time to next therapy (TTNT) for sarcopenic patients was 39 months compared to 45 months for those not sarcopenic (p =.05). In a multivariable model, the presence of sarcopenia (HR 1.64, 95% CI, 1.05–2.56; p =.03) retained significance in the presence of HR FISH, ISS 2 / 3 disease, and age ≥ 75. Conclusions: Gender-specific sarcopenia identified by a machine learning–based CNN algorithm significantly affects OS in patients with NDMM and is independent of age, ISS stage, and cytogenetic status. Future studies utilizing this machine learning–based methodology of assessing sarcopenia in larger prospective clinical trials are required to validate these findings.

Background In kidney transplantation, a contrast CT scan is obtained in the donor candidate to detect subclinical pathology in the kidney. Recent work from the Aging Kidney Anatomy study has characterized kidney, cortex, and medulla volumes using a manual image-processing tool. However, this technique is time consuming and impractical for clinical care, and thus, these measurements are not obtained during donor evaluations. This study proposes a fully automated segmentation approach for measuring kidney, cortex, and medulla volumes. Methods A total of 1930 contrast-enhanced CT exams with reference standard manual segmentations from one institution were used to develop the algorithm. A convolutional neural network model was trained ( n =1238) and validated ( n =306), and then evaluated in a hold-out test set of reference standard segmentations ( n =386). After the initial evaluation, the algorithm was further tested on datasets originating from two external sites ( n =1226). Results The automated model was found to perform on par with manual segmentation, with errors similar to interobserver variability with manual segmentation. Compared with the reference standard, the automated approach achieved a Dice similarity metric of 0.94 (right cortex), 0.90 (right medulla), 0.94 (left cortex), and 0.90 (left medulla) in the test set. Similar performance was observed when the algorithm was applied on the two external datasets. Conclusions A fully automated approach for measuring cortex and medullary volumes in CT images of the kidneys has been established. This method may prove useful for a wide range of clinical applications.