Adaptive Region-Specific Loss for Improved Medical Image Segmentation.

Defining the loss function is an important part of neural network design and critically determines the success of deep learning modeling. A significant shortcoming of the conventional loss functions is that they weight all regions in the input image volume equally, despite the fact that the system is known to be heterogeneous (i.e., some regions can achieve high prediction performance more easily than others). Here, we introduce a region-specific loss to lift the implicit assumption of homogeneous weighting for better learning. We divide the entire volume into multiple sub-regions, each with an individualized loss constructed for optimal local performance. Effectively, this scheme imposes higher weightings on the sub-regions that are more difficult to segment, and vice versa. Furthermore, the regional false positive and false negative errors are computed for each input image during a training step and the regional penalty is adjusted accordingly to enhance the overall accuracy of the prediction. Using different public and in-house medical image datasets, we demonstrate that the proposed regionally adaptive loss paradigm outperforms conventional methods in the multi-organ segmentations, without any modification to the neural network architecture or additional data preparation.

Stratified assessment of an FDA-cleared deep learning algorithm for automated detection and contouring of metastatic brain tumors in stereotactic radiosurgery.

PURPOSE: Artificial intelligence-based tools can be leveraged to improve detection and segmentation of brain metastases for stereotactic radiosurgery (SRS). VBrain by Vysioneer Inc. is a deep learning algorithm with recent FDA clearance to assist in brain tumor contouring. We aimed to assess the performance of this tool by various demographic and clinical characteristics among patients with brain metastases treated with SRS. MATERIALS AND METHODS: We randomly selected 100 patients with brain metastases who underwent initial SRS on the CyberKnife from 2017 to 2020 at a single institution. Cases with resection cavities were excluded from the analysis. Computed tomography (CT) and axial T1-weighted post-contrast magnetic resonance (MR) image data were extracted for each patient and uploaded to VBrain. A brain metastasis was considered "detected" when the VBrain- "predicted" contours overlapped with the corresponding physician contours ("ground-truth" contours). We evaluated performance of VBrain against ground-truth contours using the following metrics: lesion-wise Dice similarity coefficient (DSC), lesion-wise average Hausdorff distance (AVD), false positive count (FP), and lesion-wise sensitivity (%). Kruskal-Wallis tests were performed to assess the relationships between patient characteristics including sex, race, primary histology, age, and size and number of brain metastases, and performance metrics such as DSC, AVD, FP, and sensitivity. RESULTS: We analyzed 100 patients with 435 intact brain metastases treated with SRS. Our cohort consisted of patients with a median number of 2 brain metastases (range: 1 to 52), median age of 69 (range: 19 to 91), and 50% male and 50% female patients. The primary site breakdown was 56% lung, 10% melanoma, 9% breast, 8% gynecological, 5% renal, 4% gastrointestinal, 2% sarcoma, and 6% other, while the race breakdown was 60% White, 18% Asian, 3% Black/African American, 2% Native Hawaiian or other Pacific Islander, and 17% other/unknown/not reported. The median tumor size was 0.112 c.c. (range: 0.010-26.475 c.c.). We found mean lesion-wise DSC to be 0.723, mean lesion-wise AVD to be 7.34% of lesion size (0.704 mm), mean FP count to be 0.72 tumors per case, and lesion-wise sensitivity to be 89.30% for all lesions. Moreover, mean sensitivity was found to be 99.07%, 97.59%, and 96.23% for lesions with diameter equal to and greater than 10 mm, 7.5 mm, and 5 mm, respectively. No other significant differences in performance metrics were observed across demographic or clinical characteristic groups. CONCLUSION: In this study, a commercial deep learning algorithm showed promising results in segmenting brain metastases, with 96.23% sensitivity for metastases with diameters of 5 mm or higher. As the software is an assistive AI, future work of VBrain integration into the clinical workflow can provide further clinical and research insights.

(Potential) Mishaps of High-Dose-Rate Vaginal Cuff Brachytherapy.

Considering how commonly vaginal cuff brachytherapy is used, there is relatively little literature regarding the potential, albeit low, risk for complications. We present 3 potentially serious mishaps involving cylinder misplacement, dehiscence, and excessive normal tissue irradiation due to unique anatomy. Three patients with potentially serious treatment errors were encountered in the authors' usual clinical practice. Each patient's records were reviewed for this report. For patient 1, computed tomography (CT) simulation revealed grossly inadequate cylinder insertion, which was most obvious on the sagittal view. For patient 2, CT simulation revealed that the cylinder extended beyond the perforated vaginal cuff and was surrounded by bowel. For patient 3, CT images were used only to verify cylinder depth. A standard library plan based on cylinder diameter and active length was used. In retrospect, the images revealed an unusually thin rectovaginal septum, with the lateral and posterior vaginal wall thickness estimated to be <2 mm. This patient's fractional normal tissue doses were calculated for this report, revealing a rectal maximum dose (per fraction) of 10.8 Gy, maximum dose that 2 cc of the organ receives of 7.4 Gy, and volume of the organ that receives the prescription dose or higher of 2.8 cc. All doses were far in excess of those anticipated for a minimal 0.5-cm vaginal wall depth. Vaginal cuff high-dose-rate brachytherapy is a high-volume, routine procedure. Even in experienced hands, however, it carries a risk of improper cylinder placement, cuff dehiscence, and excessive normal tissue dose, all of which could seriously affect outcomes. These potential mishaps would be better appreciated and avoided with more extensive use of CT-based quality assurance measures.

Stereotactic Radiotherapy for Recurrent Post-Transplant Primary Central Nervous System Lymphoma.

Post-transplant primary central nervous system lymphoma (PCNSL) is a rare complication of solid organ transplantation. The optimal therapy for post-transplant PCNSL is not well established and generally includes reduction of immunosuppression and chemotherapy. Progression after front-line chemotherapy is common, and whole-brain radiotherapy (WBRT) is a standard salvage treatment as there is a concern that localized treatment fields would not prevent out-of-field recurrences. However, WBRT is associated with neurotoxicity and morbidity in these patients with inherently poor prognoses. Here, we report a patient with local recurrence of post-transplant PCNSL who was treated with fractionated stereotactic radiotherapy (SRT). He had no clinical toxicity from treatment and maintained pre-treatment neurocognition and performance status. Local control was achieved for 20 months following SRT, at which point he developed an in-field recurrence. He restarted lymphoma therapy but died one month later from fungal pneumonia. For central nervous system (CNS) lymphoma, further data are needed to optimize tumor control and toxicity outcomes and identify patients in whom localized radiotherapy fields may be beneficial, avoiding the potential toxicity of WBRT.

Impact of Radiation on Cardiovascular Outcomes in Older Resectable Esophageal Cancer Patients With Medicare.

OBJECTIVES: Preoperative radiotherapy improves outcomes for operable esophageal cancer patients, though the proximity of the heart to the esophagus puts patients at risk of radiation-induced cardiovascular disease. This study characterizes the impact of radiotherapy and different radiation techniques on cardiovascular morbidity among a cohort of esophageal cancer patients. MATERIALS AND METHODS: We identified 1125 patients aged 65 and older diagnosed between 2000 and 2011 with esophageal cancer who received surgery alone, or surgery preceded by either preoperative chemotherapy or preoperative chemoradiation from the Surveillance Epidemiology and End Results (SEER)-Medicare database. We used Medicare claims to identify severe perioperative and late cardiovascular events. Multivariable logistic regression and Fine-Gray models were used to determine the effect of presurgery treatment on the risk of perioperative and late cardiovascular disease. RESULTS: Preoperative chemotherapy or chemoradiation did not significantly increase the risk of perioperative cardiovascular complications compared with surgery alone. Patients treated with preoperative chemoradiation had a 36% increased risk of having a late cardiovascular event compared with patients treated with surgery alone (subdistribution hazard ratio [SDHR]: 1.36; P=0.035). There was no significant increase in late cardiovascular events among patients treated with preoperative chemotherapy (SDHR: 1.18; P=0.40). Among patients treated with preoperative chemoradiation, those receiving intensity modulated radiotherapy had a 68% decreased risk of having a late cardiovascular event compared with patients receiving conventional radiation (SDHR: 0.32; P=0.007). CONCLUSIONS: This study demonstrates an increased risk of cardiovascular complications among operative esophageal cancer patients treated with preoperative chemoradiation, though these risks might be reduced with more cardioprotective radiation techniques such as intensity modulated radiotherapy.

Pareto Optimal Projection Search (POPS): Automated Radiation Therapy Treatment Planning by Direct Search of the Pareto Surface.

OBJECTIVE: Radiation therapy treatment planning is a time-consuming, iterative process with potentially high inter-planner variability. Fully automated treatment planning processes could reduce a planner's active treatment planning time and remove inter-planner variability, with the potential to tremendously improve patient turnover and quality of care. In developing fully automated algorithms for treatment planning, we have two main objectives: to produce plans that are 1) Pareto optimal and 2) clinically acceptable. Here, we propose the Pareto optimal projection search (POPS) algorithm, which provides a general framework for directly searching the Pareto front. METHODS: Our POPS algorithm is a novel automated planning method that combines two main search processes: 1) gradient-free search in the decision variable space and 2) projection of decision variables to the Pareto front using the bisection method. We demonstrate the performance of POPS by comparing with clinical treatment plans. As one possible quantitative measure of treatment plan quality, we construct a clinical acceptability scoring function (SF) modified from the previously developed general evaluation metric (GEM). RESULTS: On a dataset of 21 prostate cases collected as part of clinical workflow, our proposed POPS algorithm produces Pareto optimal plans that are clinically acceptable in regards to dose conformity, dose homogeneity, and sparing of organs-at-risk. CONCLUSION: Our proposed POPS algorithm provides a general framework for fully automated treatment planning that achieves clinically acceptable dosimetric quality without requiring active planning from human planners. SIGNIFICANCE: Our fully automated POPS algorithm addresses many key limitations of other automated planning approaches, and we anticipate that it will substantially improve treatment planning workflow.

Low-dose total skin electron beam therapy for refractory cutaneous CD30 positive lymphoproliferative disorders.

We describe a case of a 48-year-old woman with a refractory cutaneous CD30 positive lymphoproliferative disorder treated successfully with total skin electron beam radiotherapy (TSEBT).

Outcomes and Tolerability of Definitive and Preoperative Chemoradiation in Elderly Patients With Esophageal Cancer: A Retrospective Institutional Review.

PURPOSE: Our purpose was to report outcomes of elderly patients who underwent definitive treatment involving radiation therapy for esophageal cancer at our institution. METHODS AND MATERIALS: We performed a retrospective review of patients aged ≥75 years with esophageal cancer treated with definitive radiation therapy (≥45 Gy) at our institution from 1997 to 2019. Acute and late Radiation Therapy Oncology Group grade 3+ toxicities were recorded. Survival was estimated using the Kaplan-Meier method. RESULTS: Of the 89 patients included, median age was 80 and 78% were male. Median adjusted Charlson Comorbidity Index and Karnofsky Performance Status were 5 (3-12) and 80 (50-100), respectively. The majority of cancers were adenocarcinoma (58%), distal (67%), and stage III (62%). Fifty-eight percent underwent definitive chemoradiotherapy, and one-third underwent preoperative intent chemoradiotherapy. Median prescribed dose was 50 Gy (45-66 Gy), and intensity modulated radiation therapy was used in 76%. Eighty-five percent completed the radiation therapy course. Among these, 20% had radiation therapy breaks. For those receiving concurrent chemotherapy, 37% had a dose reduction and 39.5% had a break/cycle reduction. Acute grade 3+ toxicity was 22%, with 2% grade 5 toxicity. Twenty-one of the 29 patients (72%) treated with preoperative intent underwent surgery. There were no deaths 90 days postoperatively. For patients who underwent surgery, 1- and 2-year overall survival were 95% and 84%. For those who did not undergo surgery, 1- and 2-year overall survival were 70% and 52%. CONCLUSIONS: There is a role for aggressive radiation therapy in well-selected elderly patients with esophageal cancer. However, optimization of supportive care, chemotherapy regimens, radiation therapy dose/fractionation, and surgical indications are needed to reduce toxicity.

Virtual Radiation Oncology Clerkship During the COVID-19 Pandemic and Beyond.

PURPOSE: We evaluated the impact of a virtual radiation oncology clerkship. METHODS AND MATERIALS: We developed a 2-week virtual radiation oncology clerkship that launched on April 27, 2020. Clerkship components included a virtual clinic with radiation oncology faculty and residents, didactic lectures, student talks, and supplemental sessions such as tumor boards and chart rounds. Medical students completed pre- and post-clerkship self-assessments. Faculty and resident participants also completed surveys on their experience with virtual lectures and clinics. Pre- and post-clerkship results were compared using a 2-sided paired t test. An analysis of variance model was used to analyze the clerkship components. RESULTS: Twenty-six medical students, including 4 visiting students, enrolled over 2 clerkship periods (4 weeks). All students completed the pre- and post-clerkship self-assessments and agreed that the clerkship improved their understanding of radiation oncology. Compared with 3 (11.5%) students who agreed that they understood the daily responsibilities of a radiation oncologist before the clerkship, 22 (84.6%) students agreed and 3 (11.5%) strongly agreed that they understood the daily responsibilities of a radiation oncologist after the clerkship (P < .0001). Although 15 students (57.7%) reported an increased interest in radiation oncology because of the clerkship, the mean level of interest in radiation oncology as a career remained the same, with pre- and post-clerkship scores of 3.0 (±0.9) and 3.0 (±1.1) on a 5-point scale, respectively (P = .7). Students found virtual clinic and didactic lectures to be the most valuable components of the clerkship. Most respondents agreed (30.8%) or strongly agreed (65.4%) to recommend the clerkship to their classmates. CONCLUSIONS: Our virtual clerkship was effective in increasing medical student interest in and knowledge about radiation oncology. These data will help optimize a new paradigm of virtual radiation oncology education for medical students during COVID-19 and beyond.

Continuing Medical Student Education During the Coronavirus Disease 2019 (COVID-19) Pandemic: Development of a Virtual Radiation Oncology Clerkship.

PURPOSE: Our institution cancelled all in-person clerkships owing to the coronavirus disease 2019 pandemic. In response, we designed a virtual radiation oncology medical student clerkship. METHODS AND MATERIALS: We convened an advisory panel to design a virtual clerkship curriculum. We implemented clerkship activities using a cloud-based learning management system, video web conferencing systems, and a telemedicine portal. Students completed assessments pre- and postclerkship to provide data to improve future versions of the clerkship. RESULTS: The virtual clerkship spans 2 weeks and is graded pass or fail. Students attend interactive didactic sessions during the first week and participate in virtual clinic and give talks to the department during the second week. Didactic sessions include lectures, case-based discussions, treatment planning seminars, and material adapted from the Radiation Oncology Education Collaborative Study Group curriculum. Students also attend virtual departmental quality assurance rounds, cancer center seminars, and multidisciplinary tumor boards. The enrollment cap was met during the first virtual clerkship period (April 27 through May 8, 2020), with a total of 12 students enrolling. CONCLUSIONS: Our virtual clerkship can increase student exposure and engagement in radiation oncology. Data on clerkship outcomes are forthcoming.

Development and Usage of eContour, a Novel, Three-Dimensional, Image-Based Web Site to Facilitate Access to Contouring Guidelines at the Point of Care.

PURPOSE: Variation in contouring quality by radiation oncologists is common and can have significant clinical consequences. Image-based guidelines can improve contour accuracy but are underused. We sought to develop a free, online, easily accessible contouring resource that allows users to scroll through cases with 3-dimensional images and access relevant evidence-based contouring information. MATERIALS AND METHODS: eContour (http://econtour.org) was developed using modern Web technologies, primarily HTML5, Python, and JavaScript, to display JPEGs generated from DICOM files from real patient cases. The viewer has standard tools for image manipulation as well as toggling of contours and overlayed images and radiation dose distributions. Brief written content references published guidelines for contour delineation. Mixpanel software was used to collect Web page usage statistics. RESULTS: In the first 3 years of operation (March 8, 2016 to March 7, 2019), a total of 13,391 users from 128 countries registered on the Web site, including 2,358 physicians from the United States. High-frequency users were more likely to be physicians (P < .001) and from the United States (P < .001). In one 6-month period, there were 68,642 individual case page views, with head-and-neck the most commonly viewed disease site (32%). Users who accessed a head-and-neck case were more likely to be high-frequency users, and 67% of repeat users accessed the same case more than once. CONCLUSION: The large, diverse user base and steady growth in Web site traffic over the first 3 years of eContour demonstrate its strong potential to address the unmet need for dissemination and use of evidence-based contouring information at the point of care.

A Population-Based Study of Morbidity After Pancreatic Cancer Diagnosis.

BACKGROUND: Pancreatic cancer is an aggressive disease characterized by early and relentless tumor spread, thus leading healthcare providers to consider it a "distant disease." However, local pancreatic tumor progression can lead to substantial morbidity. This study defines the long-term morbidity from local and nonlocal disease progression in a large population-based cohort. METHODS: A total of 21,500 Medicare beneficiaries diagnosed with pancreatic cancer in 2000 through 2011 were identified. Hospitalizations were attributed to complications of either local disease (eg, biliary disorder, upper gastrointestinal ulcer/bleed, pain, pancreas-related, radiation toxicity) or nonlocal/distant disease (eg, thromboembolic events, cytopenia, dehydration, nausea/vomiting/motility problem, malnutrition and cachexia, ascites, pathologic fracture, and chemotherapy-related toxicity). Competing risk analyses were used to identify predictors of hospitalization. RESULTS: Of the total cohort, 9,347 patients (43.5%) were hospitalized for a local complication and 13,101 patients (60.9%) for a nonlocal complication. After adjusting for the competing risk of death, the 12-month cumulative incidence of hospitalization from local complications was highest in patients with unresectable disease (53.1%), followed by resectable (39.5%) and metastatic disease (33.7%) at diagnosis. For nonlocal complications, the 12-month cumulative incidence was highest in patients with metastatic disease (57.0%), followed by unresectable (56.8%) and resectable disease (42.8%) at diagnosis. Multivariable analysis demonstrated several predictors of hospitalization for local and nonlocal complications, including age, race/ethnicity, location of residence, disease stage, tumor size, and diagnosis year. Radiation and chemotherapy had minimal impact on the risk of hospitalization. CONCLUSIONS: Despite the widely known predilection of nonlocal/distant disease spread in pancreatic cancer, local tumor progression also leads to substantial morbidity and frequent hospitalization.

An interactive contouring module improves engagement and interest in radiation oncology among preclinical medical students: Results of a randomized trial.

PURPOSE: Studies have shown significant gaps in knowledge of radiation therapy among medical students and primary care providers. The goal of this study was to evaluate the effect of an interactive contouring module on knowledge and interest in radiation oncology among preclinical medical students. METHODS AND MATERIALS: Second-year medical students at the University of California, San Diego were randomized to participate in an interactive contouring exercise or watch a traditional didactic lecture on radiation oncology. Participants completed knowledge tests and surveys at baseline, immediately following the exercise, and 3 months later. Statistical analysis included Wilcoxon signed-rank test for pre- and posttest comparisons and Wilcoxon rank sum test for comparison between groups. RESULTS: Forty-three medical students participated in the trial (21 in the didactic group; 22 in the contouring group). Students completing the contouring module demonstrated similar overall knowledge improvement compared with the traditional didactic group (+8.6% vs +6.6%, not significant) but endorsed greater engagement on a 5-point Likert-type scale (3.10 vs 3.76, P = .02). At 3-month follow-up, there was a nonsignificant trend toward improved overall knowledge in the contouring group (43% vs 51%, P = .10), with a significance difference in a subset of questions on knowledge of the process of radiation therapy as well as side effects (51% vs 75%, P = .002). Students in the contouring group demonstrated more interest in pursuing a clinical radiation oncology rotation (2.52 vs 3.27, P = .01). CONCLUSIONS: Use of an interactive contouring module was an effective method to teach preclinical medical students about radiation oncology, with no significant difference in knowledge gained compared with a traditional didactic lecture; however, higher engagement among students completing the contouring module led to improved retention of knowledge of radiation side effects and greater interest in radiation oncology. These data suggest a potential benefit of integrating an interactive radiation oncology module into the preclinical medical school curriculum.

Generalized Competing Event Models Can Reduce Cost and Duration of Cancer Clinical Trials.

PURPOSE: Generalized competing event (GCE) models improve stratification of patients according to their risk of cancer events relative to competing causes of mortality. The potential impact of such methods on clinical trial power and cost, however, is uncertain. We sought to test the hypothesis that GCE models can reduce estimated clinical trial cost in elderly patients with cancer. METHODS: Patients with nonmetastatic head and neck (n = 9,677), breast (n = 22,929), or prostate cancer (n = 51,713) were sampled from the SEER-Medicare database. Using multivariable Cox proportional hazards models, we compared risk scores for all-cause mortality (ACM) and cancer-specific mortality (CSM) with GCE-based risk scores for each disease. We applied a cost function to estimate the cost and duration of clinical trials with a primary end point of overall survival in each population and in high-risk subpopulations. We conducted sensitivity analyses to examine model uncertainty. RESULTS: For the purpose of enriching subpopulations, GCE models reduced estimated clinical trial cost compared with Cox models of ACM and CSM in all disease sites. The relative cost reductions with GCE models compared with ACM and CSM models, respectively, were -68.4% and -14.4% in prostate cancer, -38.8% and -18.3% in breast cancer, and -17.1% and -4.1% in head and neck cancer. Cost savings in breast and prostate cancers were on the order of millions of dollars. The GCE model also reduced relative clinical trial duration compared with CSM and ACM models for all disease sites. The optimal risk score cutoff for clinical trial enrollment occurred near the top tertile for all disease sites. CONCLUSION: GCE models have significant potential to improve clinical trial efficiency and reduce cost, with a potentially large impact in prostate and breast cancers.

Prostate adenocarcinoma metastases to the testis and brain: case report and review of the literature.

Prostate cancer is the second most common cancer in men worldwide. While clinicians commonly see metastases to the bones and lymph nodes, it may infrequently spread to more uncommon locations. We report an unusual case of an 83-year-old patient with previously treated prostate adenocarcinoma who presents with symptomatic metastases to the testis and brain in the absence of widely disseminated disease. This case report highlights the importance of including metastatic disease in the differential for patients with a history of prostate cancer and a newly discovered mass until an evaluation of the tissue can be performed.

Multi-institutional Randomized Trial Testing the Utility of an Interactive Three-dimensional Contouring Atlas Among Radiation Oncology Residents.

PURPOSE: The delivery of safe and effective radiation therapy relies on accurate target delineation, particularly in the era of highly conformal treatment techniques. Current contouring resources are fragmented and can be cumbersome to use. The present study reports on the efficacy and usability of a web-based contouring atlas compared with those of existing contouring resources in a randomized trial. METHODS AND MATERIALS: We enrolled radiation oncology residents into a 2-phase contouring study. All residents contoured a T1N1 nasopharyngeal cancer case using the currently available resources. The participants were then randomized to recontour the case with access to existing resources or an interactive web-based contouring atlas (eContour.org). Contour analysis was performed using conformation number and simultaneous truth and performance level estimation. At completion of the second contouring session, the residents completed a multiple choice question knowledge test and a 10-item System Usability Scale. RESULTS: Twenty-four residents from 5 institutions completed the study. Compared with the residents using currently available resources, the residents using eContour had improved contour agreement with both the consensus (0.63 vs 0.52; P=.02) and the expert (0.58 vs 0.50; P=.01) contours for the high-risk clinical target volume and greater agreement with the expert contour for the contralateral parotid gland (0.44 ± 0.12 vs 0.56 ± 0.08; P=.003). The residents using eContour demonstrated greater knowledge of contour delineation and radiographic anatomy on a multiple-choice knowledge-based test (89% vs 77%; P=.03). Usability (89 vs 66; P<.0001) and satisfaction (4.1 vs 3.0; P=.002) were greater for eContour than for the existing resources. CONCLUSIONS: This study demonstrates the capacity of an interactive 3-dimensional contouring atlas to improve quality of resident target delineation in radiation oncology. Further research is needed to define the utility of easily accessible interactive educational reference tool to improve adherence to contouring-based guidelines and quality of care in routine clinical practice.

Automated image-based colon cleansing for laxative-free CT colonography computer-aided polyp detection.

PURPOSE: To evaluate the performance of a computer-aided detection (CAD) system for detecting colonic polyps at noncathartic computed tomography colonography (CTC) in conjunction with an automated image-based colon cleansing algorithm. METHODS: An automated colon cleansing algorithm was designed to detect and subtract tagged-stool, accounting for heterogeneity and poor tagging, to be used in conjunction with a colon CAD system. The method is locally adaptive and combines intensity, shape, and texture analysis with probabilistic optimization. CTC data from cathartic-free bowel preparation were acquired for testing and training the parameters. Patients underwent various colonic preparations with barium or Gastroview in divided doses over 48 h before scanning. No laxatives were administered and no dietary modifications were required. Cases were selected from a polyp-enriched cohort and included scans in which at least 90% of the solid stool was visually estimated to be tagged and each colonic segment was distended in either the prone or supine view. The CAD system was run comparatively with and without the stool subtraction algorithm. RESULTS: The dataset comprised 38 CTC scans from prone and/or supine scans of 19 patients containing 44 polyps larger than 10 mm (22 unique polyps, if matched between prone and supine scans). The results are robust on fine details around folds, thin-stool linings on the colonic wall, near polyps and in large fluid/stool pools. The sensitivity of the CAD system is 70.5% per polyp at a rate of 5.75 false positives/scan without using the stool subtraction module. This detection improved significantly (p = 0.009) after automated colon cleansing on cathartic-free data to 86.4% true positive rate at 5.75 false positives/scan. CONCLUSIONS: An automated image-based colon cleansing algorithm designed to overcome the challenges of the noncathartic colon significantly improves the sensitivity of colon CAD by approximately 15%.

Deep brain stimulation that abolishes Parkinsonian activity in basal ganglia improves thalamic relay fidelity in a computational circuit.

Deep brain stimulation (DBS) of the subthalamic nucleus reduces the severity of parkinsonian motor symptoms, but the therapeutic mechanisms are not understood. We hypothesize that clinically effective high frequency DBS suppresses disordered neuronal activity in the globus pallidus internus (GPi), a primary output structure of the basal ganglia. In a computational model of the basal ganglia thalamic circuit, periodic high frequency (>100 Hz) stimulation of the subthalamic nucleus reduced the incidence of thalamic cell errors, from the high error rates seen in the parkinsonian case back to the low error rates seen in the normal-healthy case. In contrast, both low frequency (<70 Hz) DBS and high frequency aperiodic DBS failed to alleviate thalamic errors. In high error rate conditions, disordered patterns of GPi activity lead to irregular synaptic inhibition of thalamus. In low error rate conditions, ordered patterns of GPi activity lead to regular synaptic inhibition of thalamus. Linear regression revealed that the variance of the GPi synaptic output accounted for 87-97% of the changes in thalamic error rate. In contrast, the average GPi synaptic output - a measure of total GPi activity--accounted for only 25-50% of the changes in thalamic error rate. Thus, while the firing rate of GPi cells may play some minor role, regularizing the pathological patterns of GPi activity is the mechanism by which DBS treats parkinsonian motor symptoms.