Multiparametric magnetic resonance imaging (mpMRI) of the prostate aids in early diagnosis of prostate cancer, but is difficult to interpret and subject to interreader variability. Our objective is to generate probability maps, overlaid on original mpMRI images to help radiologists identify where a cancer is suspected as a computer-aided diagnostic (CAD). We optimized the holistically nested edge detection (HED) deep convolutional neural network. Our dataset contains T2, apparent diffusion coefficient, and high b-value images from 186 patients across six institutions worldwide: 92 with an endorectal coil (ERC) and 94 without. Ground-truth was based on tumor segmentations manually drawn by expert radiologists based on histologic evidence of cancer.The training set consisted of 120 patients and the validation set and test set included 19 and 47, respectively. Slice-level probability maps are evaluated at the lesion level of analysis. The best model: HED using 5 × 5 convolutional kernels, batch normalization, and optimized using Adam. This CAD performed significantly better (p < 0.001) in the peripheral zone (AUC ¼ 0.94 AE 0.01) than the transition zone. It outperforms a previous CAD from our group in a head-to-head comparison on the same ERC-only test cases (AUC ¼ 0.97 AE 0.01; p < 0.001). Our CAD establishes a state-of-the-art performance for predicting prostate cancer lesions on mpMRIs.
.This erratum corrects an error in the article, “Prostate cancer detection from multi-institution multiparametric MRIs using deep convolutional neural networks system,” by Y. Sumathipala et al.
Unusual clinical course Background:Patients with post-fasciotomy CECS recurrence can experience significant mobility issues at baseline that limit independent living. For these patients, a repeat fasciotomy is not ideal because they are older and post-surgical scar tissue will make the fasciotomy technically challenging. Therefore, post-fasciotomy patients with CECS recurrence require new, non-surgical treatment options. Recent studies show botulinum toxin injections can be effective for the initial management of chronic exertional compartment syndrome (CECS) prior to surgery, especially in young patients primarily experiencing pain on exertion with minimal lower-extremity symptoms at rest. However, the ability to treat CECS recurrence status after fasciotomy with botulinum toxin injections of the legs has not been studied.
Case Report:We present the first case where botulinum toxin was applied to this patient population. Our patient was a 60-year-old man with a 34-year history of CECS who, 8 years after his third bilateral fasciotomy, progressively developed rest pain in his calves bilaterally, paresthesias, and difficulties when walking or descending stairs, with multiple near-falls due to his toes catching on stair steps. OnabotulinumtoxinA (BTX-A) injections into the posterior and lateral compartments resolved baseline symptoms: within 2 weeks, he was able to walk, negotiate stairs symptom-free, and enjoy an overseas vacation without complications.
Conclusions:Symptoms related to recurrent CECS status after multiple fasciotomies can successfully be treated with BTX-A injections. Our patient's baseline mobility issues resolved within 2 weeks after the injection and remained that way for over 31 months. However, his exertional symptoms and rest pain recurred at 9 months, suggesting that BTX-A injections are not completely curative.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.