Search

Lateral lymph nodes in low, locally advanced, rectal cancer have proven implications for local recurrence rates, which increase drastically in the presence of persistently enlarged lateral lymph nodes. These clinical implications warrant a thorough understanding of lateral nodal disease with awareness and knowledge from all three specialties involved – radiology, radiation oncology, and surgery – to ensure proper treatment. Relevant literature for each specialty, including all current guidelines and perspectives, were examined. Variations in definitions and treatment paradigms were evaluated. There is still no consensus for the standardized treatment of lateral nodal disease. Each discipline works according to their own available evidence, but relevant data are scarce. Current international guidelines and standard recommendations for the diagnostics and treatment of lateral lymph nodes are lacking. This results in differing perspectives and interpretations between the disciplines which can lead to challenging communication in an area where multidisciplinary collaboration is essential. This review addresses this by presenting the current evidence, perspectives and practices of each specialty and makes suggestions for each phase of the diagnostic and treatment process for patients with lateral nodal disease. By doing this, steps are taken toward achieving international consensus, and multidisciplinary collaboration.

High level Movie describing the concept of radiomics.io, and, pyradiomics in

Radiomics aims to quantify phenotypic characteristics on medical imaging through the use of automated algorithms. Radiomic artificial intelligence (AI) technology, either based on engineered hard-coded algorithms or deep learning methods, can be used to develop noninvasive imaging-based biomarkers. However, lack of standardized algorithm definitions and image processing severely hampers reproducibility and comparability of results. To address this issue, we developed PyRadiomics, a flexible open-source platform capable of extracting a large panel of engineered features from medical images. PyRadiomics is implemented in Python and can be used standalone or using 3D Slicer. Here, we discuss the workflow and architecture of PyRadiomics and demonstrate its application in characterizing lung lesions. Source code, documentation, and examples are publicly available at www.radiomics.io. With this platform, we aim to establish a reference standard for radiomic analyses, provide a tested and maintained resource, and to grow the community of radiomic developers addressing critical needs in cancer research. Cancer Res; 77(21); e104–7. ©2017 AACR.

Supplementary Material with detailed descriptions of: I) selected feature within analysis for lung lesion characterization, II) methods describing lung lesion datasets used in analysis, and radiomic feature extraction and data analysis details, III) feature definitions included in PyRadiomics, and IV) links to additional resources.

Instruction Video with details about the Radiomics.io and the use of PyRadiomics, an engineered radiomic feature extraction platform.

PURPOSE: The sigmoid take-off (STO) was recently introduced as a preferred landmark, agreed upon by expert consensus recommendation, to discern rectal from sigmoid cancer on imaging. Aim of this study was to assess the reproducibility of the STO, explore its potential treatment impact and identify its main interpretation pitfalls.METHODS: Eleven international radiologists (with varying expertise) retrospectively assessed n = 155 patients with previously clinically staged upper rectal/rectosigmoid tumours and re-classified them using the STO as completely below (rectum), straddling the STO (rectosigmoid) or completely above (sigmoid), after which scores were dichotomized as rectum (below/straddling STO) and sigmoid (above STO), being the clinically most relevant distinction. A random subset of n = 48 was assessed likewise by 6 colorectal surgeons. .RESULTS: Interobserver agreement (IOA) for the 3-category score ranged from κ0.19-0.82 (radiologists) and κ0.32-0.72 (surgeons), with highest scores for the most experienced radiologists (κ0.69-0.76). Of the 155 cases, 44 (28%) were re-classified by ≥ 80% of radiologists as sigmoid cancers; 36 of these originally received neoadjuvant treatment which in retrospect might have been omitted if the STO had been applied. Main interpretation pitfalls were related to anatomical variations, borderline cases near the STO and angulation of axial imaging planes.CONCLUSIONS: Good agreement was reached for experienced radiologists. Despite considerable variation among less-expert readers, use of the STO could have changed treatment in ±1/4 of patients in our cohort. Identified interpretation pitfalls may serve as a basis for teaching and to further optimize MR protocols.

BACKGROUND AND PURPOSE: Manual delineation of head and neck tumor contours for radiomics analyses is tedious and time consuming. This study investigates if fast or readily available tumor contours can substitute full tumor contours by an experienced observer for an MR-based radiomics model to predict locoregional control (LRC) in oropharyngeal squamous cell carcinoma (OPSCC) tumors.MATERIALS AND METHODS: Radiomic features were extracted from postcontrast T1-weighted MRIs of 177 OPSCC primary tumors using six different manual delineation strategies. LRC prediction models based on recursive feature elimination combined with logistic regression were built. Models were trained and tested on data from each separate delineation. Additionally, the model derived from segmentations from the experienced reader was tested by each of the alternative delineations. Complementary, this was repeated with removal of size and shape features. Model performance was evaluated using area under the curve (AUC).RESULTS: Prediction performance of the experienced radiologist tumor delineation (AUC: 0.74) was superior compared to all other delineations when trained and tested (AUCs: 0.41-0.56) or trained on experienced delineations and tested (AUC: 0.56-0.67) on alternative segmentations. Removal of size and shape features considerably decreases prediction performance (AUC: 0.54). Applying the model based on expert delineations to spherical or single slice delineations makes prediction worthless since these models predict one class.CONCLUSION: Fast or readily available contours cannot substitute full expert tumor delineations in radiomics models predictive of LRC in OPSCC.

158 Background: Rectal cancer is traditionally treated with total mesorectal excision (TME), with/without neoadjuvant radiotherapy (RT) and chemotherapy. This approach often leads to temporary or permanent colostomies and other long-term morbidity such as urinary and sexual dysfunction in over 60% of patients. Organ preservation is increasingly being pursued in patients with a clinical complete response (cCR) following neoadjuvant treatment, thereby aiming to avoid TME-surgery. Based on preclinical data suggesting immunomodulatory effects of RT, and the synergy of combined PD-L1/VEGF blockade in several tumor types, the TARZAN study (NCT04017455) combines these treatments aiming to increase chances of organ preservation in patients with mainly MMR proficient (pMMR) rectal cancer without the need for chemotherapy. Methods: Patients with clinical stage ≤T3ab N0-1 distal-mid rectal tumors without mesorectal fascia involvement underwent 5x5 Gy RT followed by 3 cycles of atezolizumab and bevacizumab. Response was evaluated by MRI and endoscopy. The primary endpoint was clinical complete and near-complete response (CR) rate at 12 weeks after RT. Secondary endpoints included safety, organ preservation, pathologic (near) CR in case of surgery, and relapse free survival. According to a Simon’s 2-stage design, ≥3 responders were needed in stage I (18 patients) to continue accrual into stage II. Here we report data from stage I. Results: Eighteen patients (14 male, median age 63), all with pMMR tumors, were treated. Six tumors were cN1 on MRI, 10/18 tumors were ≥4cm and for 10/18 patients abdominoperineal resection (APR) appeared necessary due to distal tumor location. At the time of response evaluation, (near-)CR was achieved in 10/18 (56%) patients according to the primary endpoint. With a median follow-up of 20 months, 9/18 (50%) patients remain without TME surgery. Of these 9 patients, 5 underwent local excision to achieve organ preservation and in 5 patients no additional intervention was needed (cCR). The remaining 9 patients underwent TME surgery (4 APR), and pathologic assessment revealed near-CR in two patients, and a pCR in one patient. Three patients developed distant recurrences, one in the organ-sparing group. Neoadjuvant treatment was well-tolerated with grade 3 study drug-related adverse events (AEs) in 1 (5%) patient. Grade 3 surgery-related AEs occurred in 5/9 (55%) patients, including 4 anastomotic leaks and 1 abscess. Conclusions: Neoadjuvant RT followed by atezolizumab and bevacizumab resulted in a promising rate of clinical (near-)CRs in 56% of patients without the need for chemotherapy, reaching the primary endpoint. Accrual is ongoing in stage II, in which an additional 20 patients will be treated. Clinical trial information: NCT04017455 .