Multi-organ segmentation of abdominal structures from non-contrast and contrast enhanced CT images.

Manually delineating upper abdominal organs at risk (OARs) is a time-consuming task. To develop a deep-learning-based tool for accurate and robust auto-segmentation of these OARs, forty pancreatic cancer patients with contrast-enhanced breath-hold computed tomographic (CT) images were selected. We trained a three-dimensional (3D) U-Net ensemble that automatically segments all organ contours concurrently with the self-configuring nnU-Net framework. Our tool's performance was assessed on a held-out test set of 30 patients quantitatively. Five radiation oncologists from three different institutions assessed the performance of the tool using a 5-point Likert scale on an additional 75 randomly selected test patients. The mean (± std. dev.) Dice similarity coefficient values between the automatic segmentation and the ground truth on contrast-enhanced CT images were 0.80 ± 0.08, 0.89 ± 0.05, 0.90 ± 0.06, 0.92 ± 0.03, 0.96 ± 0.01, 0.97 ± 0.01, 0.96 ± 0.01, and 0.96 ± 0.01 for the duodenum, small bowel, large bowel, stomach, liver, spleen, right kidney, and left kidney, respectively. 89.3% (contrast-enhanced) and 85.3% (non-contrast-enhanced) of duodenum contours were scored as a 3 or above, which required only minor edits. More than 90% of the other organs' contours were scored as a 3 or above. Our tool achieved a high level of clinical acceptability with a small training dataset and provides accurate contours for treatment planning.

Intraoperative Radiation After Pelvic Short Course Radiation-Based Total Neoadjuvant Therapy for Patients With Rectal Adenocarcinoma at High Risk for Local Recurrence.

BACKGROUND: Short course radiation-based total neoadjuvant therapy can improve disease-free survival for patients with high-risk locally advanced rectal cancer. Tumors that involve or threaten the circumferential resection margin have a particularly high risk of local recurrence. Intraoperative radiation therapy enables treatment escalation at the threatened or involved margin at the time of surgery. PATIENTS AND METHODS: Patients with rectal adenocarcinoma treated with preoperative short course radiotherapy-based total neoadjuvant therapy and intraoperative radiation at the time of surgery were identified. All patients had a threatened or involved circumferential resection margin on magnetic resonance imaging at the time of diagnosis. Treatment details, radiation toxicities, postoperative complications and oncologic outcomes were recorded. RESULTS: Ten patients received intraoperative radiation after short course radiation-based total neoadjuvant therapy. All patients had an involved or threatened circumferential resection margin, 60% had extramural venous invasion, and 60% had positive lateral pelvic lymph nodes. Seven patients had negative surgical margins (≥ 2 mm), and 3 patients had an R1 resection with radial margins < 2 mm. The median [IQR] length of hospitalization after surgery was 11 [7-14] days. Three patients required readmission and 2 patients required reoperation due to complications including anastamotic leak and abscess. With a median follow up of 19.5 months postoperatively, no patient developed a pelvic recurrence, and 6 patients developed distant recurrences. CONCLUSIONS: The use of intraoperative radiation after a short course radiotherapy-based neoadjuvant therapy is safe and feasible. Further data are needed to determine whether the addition of intraoperative radiation improves local recurrence rates over preoperative radiation alone.

Dosimetric Uncertainties Resulting From Interfractional Anatomic Variations for Patients Receiving Pancreas Stereotactic Body Radiation Therapy and Cone Beam Computed Tomography Image Guidance.

PURPOSE: To estimate the effects of interfractional anatomic changes on dose to organs at risk (OARs) and tumors, as measured with cone beam computed tomography (CBCT) image guidance for pancreatic stereotactic body radiation therapy. METHODS AND MATERIALS: We evaluated 11 patients with pancreatic cancer whom were treated with stereotactic body radiation therapy (33-40 Gy in 5 fractions) using daily CT-on-rails (CTOR) image guidance immediately before treatment with breath-hold motion management. CBCT alignment was simulated in the treatment planning software by aligning the original planning CT to each fractional CTOR image set via fiducial markers. CTOR data sets were used to calculate fractional doses after alignment by applying the rigid shift of the planning CT and CTOR image sets to the planning treatment isocenter and recalculating the fractional dose. Accumulated dose to the gross tumor volume (GTV), tumor vessel interface, duodenum, small bowel, and stomach were calculated by summing the 5 fractional absolute dose-volume histograms into a single dose-volume histogram for comparison with the original planned dose. RESULTS: Four patients had a GTV D100% of at least 1.5 Gy less than the fractional planned value in several fractions; 4 patients had fractional underestimation of duodenum dose by 1.0 Gy per fraction. The D1.0 cm3 <35 Gy constraint was violated for at least 1 OAR in 3 patients, with either the duodenum (n = 2) or small bowel (n = 1) D1.0 cm3 being higher on the accumulated dose distribution (P = .01). D100% was significantly lower according to accumulated dose GTV (P = .01) and tumor vessel interface (P = .02), with 4 and 2 patients having accumulated D100%  ≥4 Gy lower than the planned value for the GTV and tumor vessel interface, respectively. CONCLUSIONS: For some patients, CBCT image guidance based on fiducial alignment may cause large dosimetric uncertainties for OARs and target structures, according to accumulated dose.

Daily computed tomography image guidance: Dosimetric advantages outweigh low-dose radiation exposure for treatment of mediastinal lymphoma.

CT-guided treatment delivery can improve target localization in mediastinal lymphoma patients treated with "butterfly" intensity-modulated radiotherapy and deep-inspiration breath hold. Although daily CT imaging adds additional radiation exposure, its use may be justified given the greater normal tissue sparing enabled by PTV margin reduction.

New prospective 4D-CT for mitigating the effects of irregular respiratory motion.

Artifact caused by irregular respiration is a major source of error in 4D-CT imaging. We propose a new prospective 4D-CT to mitigate this source of error without new hardware, software or off-line data-processing on the GE CT scanner. We utilize the cine CT scan in the design of the new prospective 4D-CT. The cine CT scan at each position can be stopped by the operator when an irregular respiration occurs, and resumed when the respiration becomes regular. This process can be repeated at one or multiple scan positions. After the scan, a retrospective reconstruction is initiated on the CT console to reconstruct only the images corresponding to the regular respiratory cycles. The end result is a 4D-CT free of irregular respiration. To prove feasibility, we conducted a phantom and six patient studies. The artifacts associated with the irregular respiratory cycles could be removed from both the phantom and patient studies. A new prospective 4D-CT scanning and processing technique to mitigate the impact of irregular respiration in 4D-CT has been demonstrated. This technique can save radiation dose because the repeat scans are only at the scan positions where an irregular respiration occurs. Current practice is to repeat the scans at all positions. There is no cost to apply this technique because it is applicable on the GE CT scanner without new hardware, software or off-line data-processing.