Israel Medical Association Journal

Background: For locally advanced rectal cancer patients a watch-and-wait strategy is an acceptable treatment option in cases of complete tumor response. Clinicians need robust methods of patient selection after neoadjuvant chemoradiation.

Objectives: To predict pathologic complete response (pCR) using computer vision. To analyze radiomic wavelet transform to predict pCR.

Methods: Neoadjuvant chemoradiation for patients with locally advanced rectal adenocarcinoma who passed computed tomography (CT)-based simulation procedures were examined. Gross tumor volume was examind on the set of CT simulation images. The volume has been analyzed using radiomics software package with wavelets feature extraction module. Statistical analysis using descriptive statistics and logistic regression was performed was used. For prediction evaluation a multilayer perceptron algorithm and Random Forest model were used.

Results: In the study 140 patients with II–III stage cancer were included. After a long course of chemoradiation and further surgery the pathology examination showed pCR in 38 (27.1%) of the patients. CT-simulation images of tumor volume were extracted with 850 parameters (119,000 total features). Logistic regression showed high value of wavelet contribution to model. A multilayer perceptron model showed high predictive importance of wavelet. We applied random forest analysis for classifying the texture and predominant features of wavelet parameters. Importance was assigned to wavelets.

Conclusions: We evaluated the feasibility of using non-diagnostic CT images as a data source for texture analysis combined with wavelets feature analysis for predicting pCR in locally advanced rectal cancer patients. The model performance showed the importance of including wavelets features in radiomics analysis.

Background: Neoadjuvant chemo-radiation therapy (CRT) dosages in locally advanced non-small cell lung cancer (NSCLC) were traditionally limited to 45 Gray (Gy).

Objectives: To retrospectively analyze outcomes of patients treated with 60 Gy CRT followed by surgery.

Methods: A retrospective chart review identified patients selected for CRT to 60 Gy followed by surgery between August 2012 and April 2016. Selection for surgery was based on the extent of disease, cardiopulmonary function, and response to treatment. Pathological response after neoadjuvant CRT was scored using the modified tumor regression grading. Local control (LC), disease free survival (DFS), and overall survival (OS) were estimated by the Kaplan–Meier method.

Results: Our cohort included 52 patients: 75% (39/52) were stage IIIA. A radiation dose of 60 Gy (range 50–62Gy) was delivered in 82.7%. Surgeries performed included: lobectomy, chest-wall resection, and pneumonectomy in 67.3%, 13.4%, and 19.2%, respectively. At median follow-up of 22.4 months, the 3 year OS was 74% (95% confidence interval [CI] 52–87%), LC was 84% (95%CI 65–93), and DFS 35% (95%CI 14–59). Grade 4–5 postoperative complications were observed in 17.3% of cases and included chest wall necrosis (5.7%), bronco-pleural fistula (7.7%), and death (3.8%). A major pathologic regression with < 10% residual tumor occurred in 68.7% of patients (36/52) and showed a trend to improved OS (P = 0.1). Pneumonectomy cases had statistically worse OS (P = 0.01).

Conclusions: Major pathologic regression was observed 68.7% with 60 Gy neoadjuvant CRT with a trend to improved survival. Pneumonectomy correlated with worse survival.