Transformers for colorectal cancer segmentation in CT imaging.

PURPOSE: Most recently transformer models became the state of the art in various medical image segmentation tasks and challenges, outperforming most of the conventional deep learning approaches. Picking up on that trend, this study aims at applying various transformer models to the highly challenging task of colorectal cancer (CRC) segmentation in CT imaging and assessing how they hold up to the current state-of-the-art convolutional neural network (CNN), the nnUnet. Furthermore, we wanted to investigate the impact of the network size on the resulting accuracies, since transformer models tend to be significantly larger than conventional network architectures. METHODS: For this purpose, six different transformer models, with specific architectural advancements and network sizes were implemented alongside the aforementioned nnUnet and were applied to the CRC segmentation task of the medical segmentation decathlon. RESULTS: The best results were achieved with the Swin-UNETR, D-Former, and VT-Unet, each transformer models, with a Dice similarity coefficient (DSC) of 0.60, 0.59 and 0.59, respectively. Therefore, the current state-of-the-art CNN, the nnUnet could be outperformed by transformer architectures regarding this task. Furthermore, a comparison with the inter-observer variability (IOV) of approx. 0.64 DSC indicates almost expert-level accuracy. The comparatively low IOV emphasizes the complexity and challenge of CRC segmentation, as well as indicating limitations regarding the achievable segmentation accuracy. CONCLUSION: As a result of this study, transformer models underline their current upward trend in producing state-of-the-art results also for the challenging task of CRC segmentation. However, with ever smaller advances in total accuracies, as demonstrated in this study by the on par performances of multiple network variants, other advantages like efficiency, low computation demands, or ease of adaption to new tasks become more and more relevant.

Joint liver and hepatic lesion segmentation in MRI using a hybrid CNN with transformer layers.

Backgound and Objective: Deep learning-based segmentation of the liver and hepatic lesions therein steadily gains relevance in clinical practice due to the increasing incidence of liver cancer each year. Whereas various network variants with overall promising results in the field of medical image segmentation have been successfully developed over the last years, almost all of them struggle with the challenge of accurately segmenting hepatic lesions in magnetic resonance imaging (MRI). This led to the idea of combining elements of convolutional and transformer-based architectures to overcome the existing limitations. METHODS: This work presents a hybrid network called SWTR-Unet, consisting of a pretrained ResNet, transformer blocks as well as a common Unet-style decoder path. This network was primarily applied to single-modality non-contrast-enhanced liver MRI and additionally to the publicly available computed tomography (CT) data of the liver tumor segmentation (LiTS) challenge to verify the applicability on other modalities. For a broader evaluation, multiple state-of-the-art networks were implemented and applied, ensuring direct comparability. Furthermore, correlation analysis and an ablation study were carried out, to investigate various influencing factors on the segmentation accuracy of the presented method. RESULTS: With Dice similarity scores of averaged 98±2% for liver and 81±28% lesion segmentation on the MRI dataset and 97±2% and 79±25%, respectively on the CT dataset, the proposed SWTR-Unet proved to be a precise approach for liver and hepatic lesion segmentation with state-of-the-art results for MRI and competing accuracy in CT imaging. CONCLUSION: The achieved segmentation accuracy was found to be on par with manually performed expert segmentations as indicated by inter-observer variabilities for liver lesion segmentation. In conclusion, the presented method could save valuable time and resources in clinical practice.

StRegA: Unsupervised anomaly detection in brain MRIs using a compact context-encoding variational autoencoder.

Expert interpretation of anatomical images of the human brain is the central part of neuroradiology. Several machine learning-based techniques have been proposed to assist in the analysis process. However, the ML models typically need to be trained to perform a specific task, e.g., brain tumour segmentation or classification. Not only do the corresponding training data require laborious manual annotations, but a wide variety of abnormalities can be present in a human brain MRI - even more than one simultaneously, which renders a representation of all possible anomalies very challenging. Hence, a possible solution is an unsupervised anomaly detection (UAD) system that can learn a data distribution from an unlabelled dataset of healthy subjects and then be applied to detect out-of-distribution samples. Such a technique can then be used to detect anomalies - lesions or abnormalities, for example, brain tumours, without explicitly training the model for that specific pathology. Several Variational Autoencoder (VAE) based techniques have been proposed in the past for this task. Even though they perform very well on controlled artificially simulated anomalies, many of them perform poorly while detecting anomalies in clinical data. This research proposes a compact version of the "context-encoding" VAE (ceVAE) model, combined with pre and post-processing steps, creating a UAD pipeline (StRegA), which is more robust on clinical data and shows its applicability in detecting anomalies such as tumours in brain MRIs. The proposed pipeline achieved a Dice score of 0.642 ± 0.101 while detecting tumours in T2w images of the BraTS dataset and 0.859 ± 0.112 while detecting artificially induced anomalies, while the best performing baseline achieved 0.522 ± 0.135 and 0.783 ± 0.111, respectively.

Lacosamide efficacy and tolerability in clinical practice - Post marketing analysis from a single dedicated epilepsy center.

OBJECTIVES: Post marketing analysis of anti-epileptic drug (AED) efficacy and tolerability is of great value to the clinician since it is more representative of clinical practice than clinical trial data. We analyzed our experience with lacosamide (LCM) in patients treated after marketing. PATIENTS AND METHODS: We identified all patients who were treated with LCM during the four year period after marketing, excluding patients who were in clinical trials. We recorded demographic data and analyzed efficacy and tolerability in patients who had at least one follow up visit or telephone call 3 months after the initiation of LCM. RESULTS: A total of 165 patients met our inclusion criteria. The mean age was 41 years. The majority of the cohort had focal epilepsy (146 patients) (88.4%). The mean duration of treatment was 31.2 months. Eighty one patients (49.1%) were continuing LCM at last follow up. Adverse effects (AEs) and discontinuation were significantly more common when LCM was added to one or more Na-channel blocking agents (NCB) (p = 0.0003 and 0.17). The 50% responder rate was 26% at 3 months and increased to 49% at 36 months. Patients were more likely to continue the drug and less likely to have AEs with slower titration over >4 weeks (p = 0.02 for each). Four or more previously failed AEDs predicted poorer response rate compared to three or less AEDs (p = 0.001). CONCLUSION: LCM use in clinical practice was associated with greater rate of seizure freedom than in clinical trials. Discontinuation and occurrence of AEs were significantly more likely with faster titration and adding LCM to NCB agents.

Spinal Decerebrate-Like Posturing After Brain Death: A Case Report and Review of the Literature.

INTRODUCTION: Criteria for establishing brain death (BD) require absence of all brainstem-mediated reflexes including motor (ie, decerebrate or decorticate) posturing. A number of spinal cord automatisms may emerge after BD, but occurrence of decerebrate-like spinal reflexes may be particularly problematic; confusion of such stereotypic extension-pronation movements with brain stem reflexes may confound or delay definitive diagnosis of BD. We present a case in which we verified the noncerebral (ie, likely spinal) origin of such decerebrate-like reflexes. METHODS: Case report and systematic review of literature. RESULTS: A 63-year-old woman presented with large pontine hemorrhage and complete loss of cerebral function, including no motor response to pain. Apnea testing confirmed death by neurologic criteria. Thirty-six hours after BD declaration, during assessment for organ donation, she began to exhibit spontaneous and stimulus-induced stereotypic extension-pronation of the upper extremities. The similarity of these movements to decerebrate posturing prompted concern for retained brain stem function, but repeat neurological examination of cranial nerves and apnea testing did not reveal any cerebral responses. Electrocerebral silence on electroencephalogram and absent perfusion on nuclear medicine brain imaging further confirmed BD. Review of PubMed yielded 5 additional case reports and 4 cohorts describing cases of decerebrate-like extension-pronation movements presenting in a delayed fashion after BD. CONCLUSION: Extension-pronation movements that mimic decerebrate posturing may be seen in a delayed fashion after BD. Verification of lack of any brain activity (by both examination and multiple ancillary tests) in this case and others prompts us to attribute these movements as spinal cord reflexes and propose they be recognized within the rubric of accepted post-BD automatisms that should not delay diagnosis or necessitate confirmatory testing.

Dramatic Survival Benefit Related to R0 Resection of Pancreatic Adenocarcinoma in Patients With Tumor ≤25 mm in Size and ≤1 Involved Lymph Nodes.

OBJECTIVES: To evaluate i) the relative importance of R0 resection, tumor size and peripancreatic lymph node (LN) status are significant determinants of survival benefit following upfront surgery for pancreatic adenocarcinoma (PaCa), ii) whether R0 resection confers survival benefit in all patients or a patient subset with certain favorable prognostic factors. METHODS: Retrospective analysis of patients (2001-2010) who underwent planned potentially curative surgical resection without neoadjuvant therapy for PaCa. RESULTS: Among 154 patients, median survival following R0 (n=105) and R1 resections was 26.8 and 17.7 months, respectively (P=0.010). Tumor size and LN status were significant determinants of survival following R0 resection. There were no differences in survival based on tumor size and LN in patients with R1 resection. Median survival was 17.7 months following R1 resection and was 70.9 months (P<0.001) and 22.2 months (P=0.44) in patients with tumor ≤25 mm in size and ≤1 involved LN and in the remaining patients in the cohort respectively following R0 resection. CONCLUSIONS: R0 resection is associated with dramatic survival benefit over R1 resection in a subset of patients with tumor size ≤25 mm and ≤1 involved LN. These findings underscore the importance of R0 resection and careful patient selection for upfront surgery in patients with PaCa.

Patients with obstructive jaundice and biliary stricture ± mass lesion on imaging: prevalence of malignancy and potential role of EUS-FNA.

BACKGROUND: In patients with obstructive jaundice and biliary stricture, the role of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is debated for fear of missing a potentially resectable pancreatobiliary malignancy (PBM). We evaluated the prevalence of (1) PBM; (2) lesions that do not require a potentially curative cancer surgery; and (3) potentially resectable PBMs in patients with false-negative diagnosis by EUS-FNA. PATIENTS AND METHODS: This is a retrospective analysis of 342 patients who underwent EUS/EUS-FNA from 2002 to 2009 after presenting with obstructive jaundice and a biliary stricture. Of these, 170 patients had no definitive mass on computed tomography and 172 patients had definitive mass on computed tomography without evidence of unresectability. Final diagnosis was based on surgical pathology or definitive cytology and clinical follow-up of ≥ 12 months. RESULTS: The mean age of patients (176 male) was 68.0±12.5 years. A final diagnosis of malignancy was made in only 248 patients (72.5%; 95% confidence interval, 67.7, 77.2). The overall accuracy of EUS-FNA for diagnosing malignancy was 92.4% (89.0, 94.8), with 91.5% sensitivity (87.1, 94.5) and 80.9% negative predictive value (72.0, 87.5). Among 21 patients with false-negative diagnosis, 8 had cholangiocarcinoma (2 resectable), 13 had pancreatic cancer (5 resectable). EUS-FNA provided information to potentially modify surgical management in 116 patients (33.9%; 95% confidence interval, 29.1, 39.0): 89 patients diagnosed as true negatives, 24 with distant malignant lymphadenopathy, and 3 with malignant lymphoma. CONCLUSIONS: In above-defined patient subset, the risk of missing resectable tumors by EUS-FNA has been exaggerated because of artifactually low negative predictive value resulting from a high pretest probability of PBM. The actual miss rate for resectable PBM by EUS-FNA is rather small and was 2% in present cohort. Information from EUS-FNA can potentially modify surgical management in up to one third of patients.

Clinical predictors of pancreatic carcinoma causing acute pancreatitis.

OBJECTIVES: Acute pancreatitis may be the first presentation of pancreatic carcinoma (PaCa). The present study was designed to identify clinical findings suggestive of PaCa in patients with nonalcoholic nongallstone-related (NANG) acute pancreatitis and evaluate accuracy of endoscopic ultrasound for diagnosing PaCa in this setting. METHODS: This is a retrospective analysis of 332 consecutive patients who underwent endoscopic ultrasound-fine-needle aspiration after acute pancreatitis. Patients with gallstones or common bile duct stones, who were heavy or binge alcohol drinkers, or who had post-endoscopic retrograde cholangiopancreatography pancreatitis were excluded. RESULTS: Among 218 patients with NANG acute pancreatitis, 38 patients had PaCa. Age more than 50 years (P = 0.008), history of smoking (P < 0.001), weight loss of 10 lb or greater (P = 0.003), serum bilirubin levels of higher than 2 mg/dL (P = 0.035) or serum alkaline phosphatase level of higher than 165 U/mL (in patients with normal serum bilirubin levels) (P = 0.003), and radiological findings of an identifiable pancreatic mass (P = 0.001) or distal pancreatic atrophy (P = 0.006) had significant association with an underlying PaCa on multivariate analysis. Of the 38 patients with PaCa in this cohort, 37 had 2 or more of these findings. Endoscopic ultrasound-fine-needle aspiration had 99.5% accuracy (98.6, 100%) for diagnosing carcinoma in this clinical setting. CONCLUSIONS: The clinical criteria defined previously potentially can help select patients with NANG acute pancreatitis with a higher likelihood of an underlying pancreatic neoplasm for further imaging.

Dilation of both pancreatic duct and the common bile duct on computed tomography and magnetic resonance imaging scans in patients with or without obstructive jaundice.

OBJECTIVES: "Double-duct sign" (strictures in both common bile duct [CBD] and pancreatic duct [PD] with proximal dilation) on endoscopic retrograde cholangiopancreatography is considered suggestive of pancreatic malignancy. Dilation of CBD and PD is frequently noted on computed tomography/magnetic resonance imaging scans, sometimes found incidentally in patients without jaundice. The prevalence of malignancy in these patients is not established. METHODS: In this retrospective analysis, consecutive patients who underwent endoscopic ultrasound (EUS) at a tertiary care hospital from 2002 to 2006 for suspected pancreatic malignancy and had double-duct sign on imaging were included. We evaluated (1) prevalence of malignancy in patients with or without obstructive jaundice and (2) performance characteristics of EUS-fine-needle aspiration (FNA) in diagnosing malignancy in this setting. RESULTS: A final diagnosis of pancreatic malignancy was made in 142 (85.5%) of 166 patients with and 4 (5.9%) of 68 without obstructive jaundice (P < 0.005). The accuracy of EUS-FNA for diagnosing malignancy in patients with or without obstructive jaundice was 92.8% versus 98.5%. CONCLUSIONS: Dilation of both PD and CBD on computed tomography/magnetic resonance imaging scans is suggestive of pancreatic malignancy. The prevalence of malignancy, however, is markedly lower in patients without obstructive jaundice but is clinically significant and merits further diagnostic evaluation. Endoscopic ultrasound-FNA is highly accurate for diagnosing malignancy in this setting.

Small and potentially resectable focal pancreatic lesions noted on CT/MRI scans in nonjaundiced patients: likelihood of neoplasia and utility of EUS.

BACKGROUND: Management of small and potentially resectable "mass" lesions encountered on CT/MRI scans in patients without obstructive jaundice (ObJ) is rather empirical since there is scant data on likelihood of neoplasm to formulate treatment strategies. We evaluated (1) the prevalence of neoplasm and (2) performance characteristics of EUS-FNA for diagnosing neoplasm in above-mentioned subset of patients. PATIENTS: This is a retrospective analysis of 232 patients (without ObJ) with a focal pancreatic lesion, ≤ 25 mm and potentially resectable on CT/MRI who underwent EUS-FNA from 2002 to 2009. RESULTS: Seventy-five patients (32.3%, 95% CI 26.6, 38.6) were finally diagnosed to have a neoplasm. Four of 92 (4.3%) lesions ≤ 15 mm, 13 of 57(22.8%) lesions 16-20 mm, and 35 of 83 (42.1%) lesions 21-25 mm had an adenocarcinoma. Larger lesion size, older patient age, and h/o recent weight loss significantly increased the likelihood of adenocarcinoma. EUS-FNA had 98.2% overall accuracy and 98.1% NPV with no significant differences based on lesion size. CONCLUSIONS: In nonjaundiced patient with a potentially resectable pancreatic lesion ≤25 mm in size noted on CT/MRI scanning, EUS-FNA can provide useful adjunctive information to optimize the use of surgery and can potentially obviate the need for "wait and watch approach" with repeat imaging in their clinical management.

Imaging of pancreatic cancer: An overview.

Pancreatic cancer (PaCa) is the fourth leading cause of cancer-related death in the United States. The median size of pancreatic adenocarcinoma at the time of diagnosis is about 31 mm and has not changed significantly in last three decades despite major advances in imaging technology that can help diagnose increasingly smaller tumors. This is largely because patients are asymptomatic till late in course of pancreatic cancer or have nonspecific symptoms. Increased awareness of pancreatic cancer amongst the clinicians and knowledge of the available imaging modalities and their optimal use in evaluation of patients suspected to have pancreatic cancer can potentially help in diagnosing more early stage tumors. Another major challenge in the management of patients with pancreatic cancer involves reliable determination of resectability. Only about 10% of pancreatic adenocarcinomas are resectable at the time of diagnosis and would potentially benefit from a R0 surgical resection. The final determination of resectability cannot be made until late during surgical resection. Failure to identify unresectable tumor pre-operatively can result in considerable morbidity and mortality due to an unnecessary surgery. In this review, we review the relative advantages and shortcomings of imaging modalities available for evaluation of patients with suspected pancreatic cancer and for preoperative determination of resectability.