Lung cancer is one of the most common causes of cancer-related mortality, and since the majority of cases are diagnosed when the tumor is in an advanced stage, the 5-year survival rate is dismally low. Nevertheless, the chances of survival can increase if the tumor is identified early on, which can be achieved through screening with computed tomography (CT). The clinical evaluation of CT images is a very time-consuming task and computed-aided diagnosis systems can help reduce this burden. The segmentation of the lungs is usually the first step taken in image analysis automatic models of the thorax. However, this task is very challenging since the lungs present high variability in shape and size. Moreover, the co-occurrence of other respiratory comorbidities alongside lung cancer is frequent, and each pathology can present its own scope of CT imaging appearances. This work investigated the development of a deep learning model, whose architecture consists of the combination of two structures, a U-Net and a ResNet34. The proposed model was designed on a cross-cohort dataset and it achieved a mean dice similarity coefficient (DSC) higher than 0.93 for the 4 different cohorts tested. The segmentation masks were qualitatively evaluated by two experienced radiologists to identify the main limitations of the developed model, despite the good overall performance obtained. The performance per pathology was assessed, and the results confirmed a small degradation for consolidation and pneumocystis pneumonia cases, with a DSC of 0.9015 ± 0.2140 and 0.8750 ± 0.1290, respectively. This work represents a relevant assessment of the lung segmentation model, taking into consideration the pathological cases that can be found in the clinical routine, since a global assessment could not detail the fragilities of the model.

“Watch and wait” is becoming a common treatment option for patients with locally advanced rectal cancer (LARC) submitted to neoadjuvant treatment. However, currently, no clinical modality has an acceptable accuracy for predicting pathological complete response (pCR). The aim of this study was to assess the clinical utility of circulating tumor DNA (ctDNA) in predicting the response and prognosis in these patients. We prospectively enrolled a cohort of three Iberian centers between January 2020 and December 2021 and performed an analysis on the association of ctDNA with the main response outcomes and disease-free survival (DFS). The rate of pCR in the total sample was 15.3%. A total of 24 plasma samples from 18 patients were analyzed by next-generation sequencing. At baseline, mutations were detected in 38.9%, with the most common being TP53 and KRAS. Combination of either positive magnetic resonance imaging (MRI) extramural venous invasion (mrEMVI) and ctDNA increased the risk of poor response (p = 0.021). Also, patients with two mutations vs. those with fewer than two mutations had a worse DFS (p = 0.005). Although these results should be read carefully due to sample size, this study suggests that baseline ctDNA combined with mrEMVI could potentially help to predict the response and baseline ctDNA number of mutations might allow the discrimination of groups with different DFS. Further studies are needed to clarify the role of ctDNA as an independent tool in the selection and management of LARC patients.

Intermediate- to high-grade non-muscle invasive bladder cancer is preferably treated with transurethral resection followed by adjuvant intravesical immunotherapy with Bacillus Calmette-Guérin (BCG). BCG acts as an immune stimulator, inducing a complex inflammatory response that selectively targets tumoral cells. Mild side effects of BCG instillation, such as fever, malaise, and bladder irritation are frequent, while severe treatment-associated complications of the genito-urinary tract are rare. “Distant” complications are even rarer and, since BCG is able to disseminate hematogenously, virtually all organs and systems can be involved, with the lungs, liver and musculoskeletal system being most commonly affected. Vascular complications of BCG immunotherapy are exceedingly rare and difficult to diagnose, because they can mimic other vascular infections and may occur several years after treatment. Knowledge of previous BCG immunotherapy and awareness about treatment-related complications is essential to avoid misdiagnosis, and to guide appropriate treatment.

Teaching Point: Intestinal pneumatosis associated with pneumoperitoneum, pneumomediastinum, and subcutaneous emphysema is an extremely rare complication of leukemia; even though its imaging appearance can be alarming, a benign treatment-associated etiology should always be considered in this subset of patients so that unnecessary interventions can be avoided.