Abraham H. Dachman

We developed an automatic ensemble training method for fusing massive-training artificial neural network (MTANN) deep-learning modules in classification between polyps and non-polyps in CT colonography. We started from an initial MTANN module that had been trained with an initial set of polyps and non-polyps. We applied the trained initial module to polyps and non-polyps to analyze the weakness of the initial module. We arranged the output scores of the initial module to form a score scale in receiver-operating-characteristic (ROC) space, representing the “degree of difficulty” in distinction between polyps and non-polyps by the initial module. Based on the score-space, several sets of training polyps and non-polyps with different degrees of difficulties were determined. We trained several MTANN modules with the several sets of training samples so that each module became an expert at a certain level of difficulty. We then combined expert modules with a mixing module to form a “mixture of expert” MTANNs. Our database consisted of CT colonography datasets acquired from 100 patients, including 26 polyps. The mixture of expert MTANNs with the ensemble training method distinguished all polyps correctly from more than 50% of the non-polyps. We compared the effectiveness of the ensemble training with that of training with manually selected cases. The performance of the mixture of expert MTANNs with ensemble training method was superior to that of the “reference-standard” MTANNs trained with manually selected cases, which could reduce the cost of the manual selection.

This Editorial Comment discusses the following AJR article: Imaging of Bowel Ischemia: An Update, From the AJR Special Series on Emergency Radiology.

Purpose To describe the favorable procedural profile of CT colonography (CTC) during the COVID-19 pandemic. Conclusion Postponement of cancer screening due to COVID-19 has resulted in a backlog of individuals needing to undergo structural examination of the colon. The experience during the initial COVID-19 surge with urgent evaluation of the colon for transplant patients prior to transplant suggests that CTC can be done in a lower risk manner as compared to other structural examinations. The procedural profile of CTC is advantageous during this pandemic as maintaining social distancing and preserving healthcare supplies including PPE are of paramount importance. CTC is an important option to utilize in the screening armamentarium to allow effective screening of average risk asymptomatic individuals in the COVID-19 era.

Standardized recommended techniques for performing and reporting CT colonography (CTC) examinations were developed by a consensus of experts. Published reporting guidelines, known as the CT colonography reporting and data system supplemented by recently updated comprehensive recommendations were incorporated into the American College of Radiology (ACR) practice guidelines. The application of continuous quality improvement to the practice of CT was aided by the development of an ACR national data registry (NRDR) for CTC that addressed both process and outcome quality measures. These measures can be used to benchmark an institution’s CTC practice as compared to all participants. This article will discuss the best practices for reporting CTC and describe the use of NRDR to foster quality CTC performance.

Some studies have shown that low frequency stimulation (LFS, most commonly 60 Hz), compared to high frequency stimulation (HFS, most commonly 130 Hz), has beneficial effects, short-term or even long-term, on improving freezing of gait (FOG) and other axial symptoms, including speech and swallowing function, in Parkinson disease (PD) patients with bilateral subthalamic nucleus deep brain stimulation (STN DBS). However, other studies failed to confirm this. It seems not clear what determines the difference in response to LFS. Differences in study design, such as presence or absence of FOG, exact LFS used (60 Hz versus 80 Hz), study size, open label versus randomized double blind assessment, retrospective versus prospective evaluation, medication On or Off state, total electric energy delivered maintained or not with the change in frequency, and the location of active contacts could all potentially affect the results. This mini-review goes over the literature with the aforementioned factors in mind, focusing on the effect of LFS versus HFS on FOG and other axial symptoms in PD with bilateral STN DBS, in an effort to extract the essential data to guide our clinical management of axial symptoms and explore the potential underlying mechanisms as well. Overall, LFS of 60 Hz seems to be consistently effective in patients with FOG at the usual HFS in regards to improving FOG, speech, swallowing function and other axial symptoms, though LFS could reduce tremor control in some patients. Whether LFS simply addresses the axial symptoms in the context of HFS or has other beneficial effects requires further studies, along with the mechanism.

Half of the polyps surgically removed during conventional colonoscopy are benign with no malignant potential. Our purpose was to develop a CADx system for distinction between neoplastic and non-neoplastic lesions in CTC to reduce "unnecessary" colonoscopic polypectomy. Although computer aided detection (CADe) systems have been developed, less attention was given to the development of CADx systems. Our CADx system consists of shape-index-based coarse segmentation of lesions, 3D volume growing and sub-voxel refinement for fine segmentation of lesions, morphologic and texture feature analysis, Wilks' lambda-based stepwise feature selection, linear discriminant analysis for providing an integrated imaging biomarker for diagnosis of neoplastic lesions. Our database contained biopsy-confirmed 54 neoplastic lesions in 29 patients and 14 non-neoplastic lesions in 10 patients. Our CADx system integrating the selected features was able to determine an accurate likelihood of being a neoplasm and distinguish 87% (47/54) neoplastic lesions from 57% (8/14) non-neoplastic lesions correctly only using computed tomography (CT) images, achieving an area under the receiver operating characteristic curve (AUC) of 0.82. This study showed the potential of the use of CTC as a diagnostic tool beyond already accepted detection, thus, CTC with CADx would be potentially useful for reducing "unnecessary" polypectomy.