Imaging in Non-neurologic Oncologic Treatment Planning of the Head and Neck

Hansen, Katherine; Kent, Michael S.

doi:10.3389/fvets.2019.00090

Cited by 7 publications

(5 citation statements)

References 123 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, nasal cavity tumors display distinctive characteristics in terms of shape and location and generally have high contrast between tumor tissue and normal tissues/background, all of which could aid auto-segmentation. GTV segmentation is also particularly relevant for this group of canine HNC patients, as RT is indicated as the primary treatment ( 4 , 13 , 14 ).…”

Section: Discussionmentioning

confidence: 99%

“…In dogs, surgery is the primary treatment for most HNCs, but RT is indicated as the primary treatment for sinonasal tumors where full surgical resection is challenging ( 4 , 13 , 14 ). Multimodal treatment with surgery, RT and chemotherapy may also be considered for canine HNC patients, particularly for cancers with significant risk of metastatic spread ( 13 ). Though veterinary RT facilities are small in size and number compared to human facilities, RT has increasingly become available for veterinary patients ( 15 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning

et al. 2023

View full text Add to dashboard Cite

BackgroundRadiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task.PurposeThe purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC.Materials and methodsContrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient (Dice), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs.ResultsCNN models trained from scratch on canine data or by using transfer learning obtained mean test set Dice scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean Dice performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set Dice scores of 0.69 for both approaches.ConclusionIn conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In the future, a revised classification should be implemented, following the example of the revised TNM classification of head and neck tumors in humans ( 47 ). However, the staging of oral tumors, and thus the assessment of a patient's clinical stage remains a shortcoming of clinical studies in this field, as there is still no consensus on how to best perform complete staging in dogs with oral tumors ( 26 , 48 ).…”

Section: Discussionmentioning

confidence: 99%

“…The two main pillars of treatment for malignant oral tumors in dogs remain surgery ( 25 ) and radiation therapy ( 26 ), but alternative treatment options (e.g., electroporation-based treatments) ( 27 ) are emerging. To date, there are no studies describing the use of MC in the treatment of oral tumors in veterinary patients.…”

Section: Introductionmentioning

confidence: 99%

Metronomic Chemotherapy for Palliative Treatment of Malignant Oral Tumors in Dogs

2022

View full text Add to dashboard Cite

The aim of this study was to evaluate the efficacy of metronomic chemotherapy in the palliative treatment of various malignant oral tumors in dogs. Our focus was to determine the effect of treatment on local disease control and to assess the tolerability and safety of the treatment in dogs with various oral malignancies. Metronomic chemotherapy with cyclophosphamide was used to treat 12 dogs and was combined with non-steroidal anti-inflammatory drugs in 6/12 (50%) of dogs. A clinical benefit was observed in 6/12 (50%) patients 1 month and in 4/12 (33%) 3 months after treatment initiation. The median survival time of the dogs was 155 days (range 21–529 days). At the end of the observation period, the disease had progressed in 10/12 (83.3%) of the patients. Sterile hemorrhagic cystitis was the most commonly reported side effect of treatment, occurring in 4/12 (33.3%) dogs. The results of our study suggest that metronomic chemotherapy with cyclophosphamide can be, in a subset of dogs, beneficial in the palliation of malignant oral tumors.

show abstract

“…By comparison, SBRT also utilizes these strategies, but higher dose treatments are delivered in 1 to 5 fractions, and normal tissues are further spared by avoidance 13 . Heart‐base tumours are attractive targets for both CFRT and SBRT because: (1) surgically‐curative options are limited; 14 (2) they have somewhat well‐defined edges, providing for a focused target region, although tumour infiltration will not always correlate with imaging, 15,16 and (3) endocrine tumours respond favourably to various fractionation schemes 17‐19 . However, lung/heart motion during treatment creates uncertainty, necessitating target‐volume expansion.…”

Section: Introductionmentioning

confidence: 99%

Long‐term outcomes with conventional fractionated and stereotactic radiotherapy for suspected heart‐base tumours in dogs

Hansen

Théon

Willcox

et al. 2020

Vet Comparative Oncology

Self Cite

View full text Add to dashboard Cite

Published radiotherapy results for suspected heart‐based tumours in dogs are limited. In this retrospective longitudinal study (3/2014‐2019), eight dogs with either clinical signs attributable to a heart‐base mass (6), or asymptomatic with a progressively larger mass on echocardiogram (2), received conventional fractionated radiotherapy (CFRT) or stereotactic body radiotherapy (SBRT). Clinical findings in symptomatic cases included one or more of the following: retching/coughing (4), exercise intolerance (2), collapse (1), pericardial effusion (2), rare ventricular premature contractions (2), abdominal effusion (1), or respiratory distress due to chylothorax (1). CFRT cases received 50 Gray (Gy) in 20 fractions and SBRT cases received 30 Gy in 5 or 24 Gy in three fractions. Two dogs received chemotherapy post‐radiation. At analysis, 7/8 dogs were deceased and one was alive 684 days post‐treatment. The estimated median overall survival (MOS) from first treatment was 785 days (95% CI 114‐868 days, [range 114‐1492 days]). Five dogs received CFRT (MOS 817 days; (95% CI 155 days‐not reached [range 155‐1492 days])). Three dogs received SBRT with one alive at analysis (MOS 414 days, (95% CI, 114 days‐not reached [range 114‐414 days])). No statistically significant difference was found between survival for CFRT and SBRT. Of the symptomatic patients, 5/6 showed improvement. Mass size reduced in 4/5 cases receiving follow‐up ultrasounds. Possible complications included asymptomatic radiation pneumonitis (4), atrial tachycardia/premature beats (4) and pericardial effusion with heart failure coincident with tumour progression (1). This study provides preliminary evidence that radiotherapy may impact clinically relevant or progressively enlarging heart‐base masses.

show abstract

Imaging in Non-neurologic Oncologic Treatment Planning of the Head and Neck

Cited by 7 publications

References 123 publications

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning

Metronomic Chemotherapy for Palliative Treatment of Malignant Oral Tumors in Dogs

Long‐term outcomes with conventional fractionated and stereotactic radiotherapy for suspected heart‐base tumours in dogs

Contact Info

Product

Resources

About